A biological resource scheduling big data management method, system and medium
By constructing a dynamic scheduling grid model of biological resources and machine learning analysis, the balance of biological resources scheduling is evaluated, and the problem of unbalanced resource scheduling in emergencies is solved, and efficient resource allocation and management is achieved.
Patent Information
- Application Number
- CN202411193834.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-08-28
AI Technical Summary
In major emergencies, biological resource scheduling has problems such as slow response speed, poor timeliness and low balance. The existing technology lacks a flexible emergency response mechanism and cannot quickly adjust strategies or operating procedures.
By obtaining the geographical location information of biological resource output sites, transit sites and demand sites, building a dynamic scheduling grid model, extracting and evaluating collected data, combining machine learning models to analyze historical and real-time data, calculate effective inbound and outbound indexes, and evaluate the Scheduling balances threat value, judges scheduling level, and realizes dynamic scheduling of resources.
It improves resource preparation efficiency and emergency response accuracy, ensures effective allocation and management of resources in emergencies, and avoids resource shortages or oversupply.
Smart Images

Figure CN118710025B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of scheduling data management, and is a biological resource scheduling big data management method, system and medium. Background Art
[0002] Biological resource scheduling refers to the rational arrangement and allocation of biological resources according to actual needs in order to optimize resource utilization and meet various needs. Effective data management is crucial for biological resource scheduling, which can improve resource utilization efficiency, respond to emergencies, optimize decision support and enhance management transparency. However, in major emergencies (such as natural disasters or public health events), biological resource allocation often appears unbalanced in a short period of time. At this time, resources may not be allocated to the most needed places in time, resulting in resource shortages or surpluses. In addition, problems such as inaccurate or delayed data, difficulty in coordination, and insufficient emergency response capabilities will affect the effective management of resources. Therefore, establishing a biological resource scheduling big data management method, system and medium can help achieve efficient resource allocation in emergencies and improve emergency response capabilities.
[0003] In the existing disclosed invention technologies, for example, the patent with application publication number CN115526751A discloses a blood preparation system and a blood preparation method for blood station blood management. The alarm method divides the blood preparation risk control stage in the implementation stage of blood station blood management into several blood preparation operation process risk nodes, and then compares the operation progress parameters of each blood preparation node with the corresponding node alarm limit value when it occurs, and issues a corresponding violation alarm message when the operation progress parameters of the blood preparation node exceed the corresponding node alarm limit value; the present invention also discloses a corresponding alarm system, including a blood station blood management division module, a blood station blood management node monitoring module and a blood station blood management control module.
[0004] The design of the system in the above patent relies on fixed nodes and parameters and lacks a flexible emergency response mechanism. When faced with unpredictable emergencies, it is unable to quickly adjust strategies or operating procedures, and has the problems described in the background technology. Summary of the invention
[0005] The technical problem to be solved by the present invention is that in the prior art, after a major emergency occurs, due to the differences in medical technology and equipment possessed by various biological resource demand sites, the scheduling of biological resources by biological resource transfer sites has problems such as slow response speed, poor timeliness and low balance. A biological resource scheduling big data management method, system and medium are proposed.
[0006] In order to achieve the above-mentioned object, the technical solution of a biological resource scheduling big data management method of the present invention comprises the following steps:
[0007] S1: Obtain the geographical location information of biological resource output sites, biological resource transfer sites and biological resource demand sites, and build a visualization model of biological resource dynamic scheduling grid;
[0008] S2: extracting the biological resource collection data of each biological resource output site, and importing the biological resource collection data into the effective storage index evaluation strategy to calculate and obtain the effective storage index;
[0009] S3: Obtain historical patient admission data and historical biological resource consumption data at each biological resource demand site after a major historical accident; simultaneously obtain real-time patient admission data at each biological resource demand site after this major accident;
[0010] S4: constructing a machine learning model based on the data in S3, performing a fusion analysis on the historical patient admission data and the historical biological resource consumption data, and calculating an effective outbound index based on the real-time patient admission data;
[0011] S5: Import the effective storage-in index and the effective storage-out index into the biological resource scheduling data balance evaluation strategy, calculate and obtain the scheduling balance threat value, and judge the biological resource scheduling level based on the scheduling balance threat value.
[0012] Specifically, in S2, the effective inventory index evaluation strategy is as follows:
[0013] S21: extracting biological resource collection data of each biological resource output site, and evaluating the loss rate of biological resources in the output process of each biological resource output site according to the biological resource collection data, wherein the calculation strategy of the loss rate is:
[0014] ;
[0015] in, Here r is a subscript, indicating the rth biological resource output site near the biological resource transfer site;
[0016] is the loss rate of biological resources during the export process of the rth biological resource export site;
[0017] Q is the total number of biological resources collected today at this biological resource output site;
[0018] They are the ineffective component loss ratio coefficient and the storage loss ratio coefficient respectively;
[0019] is the actual active ingredient content of the qth biological resource after testing and analysis;
[0020] The target active ingredient content for a single biological resource;
[0021] The actual time interval from the collection of the qth biological resource at the biological resource output site to the transfer of the biological resource transfer site;
[0022] The target time interval for a single biological resource to be transferred from the collection of the biological resource export site to the transfer site of the biological resource;
[0023] S22: Extract the loss rate of biological resources during the output process of each biological resource output site, and calculate the effective storage index RK of biological resources. The specific calculation strategy is:
[0024] ;
[0025] Where e is the natural index, is the total amount of biological resources contributed by the rth biological resource export site to the biological resource transfer site, and R is the total number of biological resource export sites.
[0026] Specifically, in S3, the historical patient admission data and the historical biological resource consumption data in each biological resource demand site, wherein the historical patient admission data includes: the initial disease diagnosis level of the patient by the doctor after the patient is admitted to the hospital, and the initial disease diagnosis level is N levels in total; the historical patient admission data also includes: the number of patients at each initial disease diagnosis level and the preset biological resource reserve for each patient The biological resource historical consumption data includes: biological resource historical scheduling data and biological resource historical actual use data.
[0027] Specifically, S4 includes the following specific steps:
[0028] S41: Build a machine learning model, including: input layer, hidden layer, 2 convolutional layers, pooling layer, fully connected layer and output layer;
[0029] S42: extracting historical patient admission data and historical biological resource consumption data of the biological resource demand site after historical major accidents as a training set for the machine learning model, performing data cleaning on the historical patient admission data and historical biological resource consumption data, and performing feature extraction training on the machine learning model through the historical patient admission data and historical biological resource consumption data after historical major accidents;
[0030] S43: The feature matrices of the historical patient admission data and the historical consumption data of biological resources output by the two convolutional layers are compressed through the sampling layer in the machine learning model, and the compressed feature matrices are output through the output layer to complete the training of the convolutional neural network;
[0031] S44: Input the real-time patient admission data after this major accident into the trained machine learning model, and predict the deviation of the actual usage of biological resources in real time.
[0032] Specifically, S4 also includes the following specific steps:
[0033] S45: Through a machine learning model, the historical patient admission data and the historical biological resource consumption data are integrated and analyzed to calculate the deviation of the actual biological resource usage. The specific calculation strategy is as follows:
[0034] ;
[0035] in, In the figure, c is a subscript, which indicates the cth biological resource demand site near the biological resource transfer site;
[0036] is the deviation degree of the actual amount of biological resources used at the cth biological resource demand site;
[0037] is the number of patients with the nth initial diagnosis level;
[0038] is the mean number of patients at all initial diagnosis levels;
[0039] They represent the maximum and minimum number of patients in all initial diagnosis levels respectively;
[0040] middle is a subscript, indicating the mth patient with the nth initial disease diagnosis level;
[0041] The historical actual usage data of biological resources for the mth patient at the nth initial disease diagnosis level;
[0042] is the total number of patients with the nth initial diagnosis level; Pre-placed biological resource reserves for patients;
[0043] The proportional coefficient of the impact of the deviation in the number of patients and the proportional coefficient of the deviation in the actual amount of biological resources used are respectively;
[0044] S46: Calculate the effective outbound index based on the deviation of real-time patient admission data and actual usage of biological resources. The specific calculation strategy is as follows:
[0045] ;
[0046] in, is the total amount of biological resources dispatched by the biological resource transfer station to the cth biological resource demand station after this major accident, and C is the total number of biological resource transfer stations.
[0047] Specifically, S5 includes the following specific steps:
[0048] S51: Import the effective inbound index and effective outbound index into the biological resource scheduling data balance assessment strategy to calculate the scheduling balance threat value , the biological resource scheduling data balance evaluation strategy is specifically:
[0049] .
[0050] Specifically, S5 also includes the following specific steps:
[0051] S52: Extract the scheduling balance threat value of biological resources and preset the scheduling level threshold of biological resources , and judge the biological resource scheduling level according to the scheduling balance threat value. The specific judgment strategies include:
[0052] when When , it is judged that the scheduling of biological resources is unbalanced;
[0053] when When the biological resources are balanced, the scheduling is judged;
[0054] when , it is judged that the scheduling of biological resources is unbalanced.
[0055] In addition, the biological resource scheduling big data management system of the present invention includes the following modules:
[0056] Visual model building module, effective inventory index calculation module, AI data management chip, effective inventory index calculation module, balance evaluation module;
[0057] The visualization model building module is used to obtain the geographical location information of the biological resource output site, the biological resource transfer site and the biological resource demand site, and build a visualization model of the biological resource dynamic scheduling grid;
[0058] The effective storage index calculation module is used to extract the biological resource collection data of each biological resource output site, and import the biological resource collection data into the effective storage index evaluation strategy to calculate and obtain the effective storage index;
[0059] The AI data management chip is used to obtain and store historical patient admission data and historical biological resource consumption data in various biological resource demand sites after major historical accidents; and simultaneously obtain and store real-time patient admission data in various biological resource demand sites after this major accident;
[0060] The effective outbound index calculation module is used to construct a machine learning model, perform fusion analysis on the historical patient admission data and the historical biological resource consumption data, and calculate the effective outbound index based on the real-time patient admission data;
[0061] The balance evaluation module imports the effective storage-in index and the effective storage-out index into the biological resource scheduling data balance evaluation strategy, calculates and obtains the scheduling balance threat value, and determines the biological resource scheduling level according to the scheduling balance threat value.
[0062] A storage medium stores instructions, and when a computer reads the instructions, the computer executes the biological resource scheduling big data management method.
[0063] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned biological resource scheduling big data management method is implemented.
[0064] Compared with the prior art, the technical effects of the present invention are as follows:
[0065] 1. The present invention constructs a visualization model of the biological resource dynamic scheduling grid to display the geographical location and resource distribution of each site in real time, so that the dispatching personnel can intuitively understand the real-time status of resources and make adjustments quickly to solve the problem of unbalanced resource allocation in emergencies.
[0066] 2. The present invention extracts and evaluates biological resource collection data, calculates the effective storage index, and ensures that resources are stored and managed according to actual needs, which improves the efficiency of resource preparation and reduces problems caused by insufficient or excessive resource reserves.
[0067] 3. The present invention combines historical patient admission data and biological resource consumption data, analyzes real-time admission data, and uses machine learning models for prediction and analysis. This method can more accurately assess current resource needs, improve the accuracy of emergency response, and reduce imbalanced allocation caused by delayed or inaccurate data.
[0068] 4. The present invention can scientifically evaluate the balance of current scheduling by calculating the scheduling balance threat value and judging the scheduling level. According to the evaluation results, resource allocation can be quickly adjusted to ensure effective deployment and management of resources in major emergencies and avoid resource shortages or surpluses. BRIEF DESCRIPTION OF THE DRAWINGS
[0069] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:
[0070] Figure 1 A schematic diagram of a process of a biological resource scheduling big data management method of the present invention;
[0071] Figure 2 It is a structural schematic diagram of a biological resource scheduling big data management system of the present invention. DETAILED DESCRIPTION
[0072] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.
[0073] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0074] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0075] Embodiment 1:
[0076] like Figure 1 As shown, a biological resource scheduling big data management method according to an embodiment of the present invention is as follows: Figure 1 As shown, the specific steps are as follows:
[0077] S1: Obtain the geographical location information of biological resource output sites, biological resource transfer sites and biological resource demand sites, and build a visualization model of biological resource dynamic scheduling grid;
[0078] S2: extracting the biological resource collection data of each biological resource output site, and importing the biological resource collection data into the effective storage index evaluation strategy to calculate and obtain the effective storage index;
[0079] In S2, the effective inventory index evaluation strategy is as follows:
[0080] S21: extracting biological resource collection data of each biological resource output site, and evaluating the loss rate of biological resources in the output process of each biological resource output site according to the biological resource collection data, wherein the calculation strategy of the loss rate is:
[0081] ;
[0082] in, Here r is a subscript, indicating the rth biological resource output site near the biological resource transfer site;
[0083] is the loss rate of biological resources during the export process of the rth biological resource export site;
[0084] Q is the total number of biological resources collected today at this biological resource output site;
[0085] They are the ineffective component loss ratio coefficient and the storage loss ratio coefficient respectively;
[0086] is the actual active ingredient content of the qth biological resource after testing and analysis;
[0087] The target active ingredient content for a single biological resource;
[0088] The actual time interval from the collection of the qth biological resource at the biological resource output site to the transfer of the biological resource transfer site;
[0089] The target time interval for a single biological resource to be transferred from the collection of the biological resource export site to the transfer site of the biological resource;
[0090] S22: Extract the loss rate of biological resources during the output process of each biological resource output site, and calculate the effective storage index RK of biological resources. The specific calculation strategy is:
[0091] ;
[0092] Where e is the natural index, is the total amount of biological resources contributed by the rth biological resource export site to the biological resource transfer site, and R is the total number of biological resource export sites.
[0093] S3: Obtain historical patient admission data and historical biological resource consumption data at each biological resource demand site after a major historical accident; simultaneously obtain real-time patient admission data at each biological resource demand site after this major accident;
[0094] In S3, the historical patient admission data and the historical biological resource consumption data in each biological resource demand site, wherein the historical patient admission data includes: the initial diagnosis level of the patient by the doctor after the patient is admitted to the hospital, and the initial diagnosis level is N levels in total; the historical patient admission data also includes: the number of patients at each initial diagnosis level and the preset biological resource reserve for each patient The biological resource historical consumption data includes: biological resource historical scheduling data and biological resource historical actual use data.
[0095] For example, in this embodiment, the patient admitted after a major accident is an emergency patient, and the biological resource is a blood resource. The doctor's initial diagnosis level of the emergency patient includes: the doctor evaluates the patient's injury and ischemia and internal circulation, and then determines the patient's preset biological resource reserve. Make an estimate.
[0096] S4: constructing a machine learning model based on the data in S3, performing a fusion analysis on the historical patient admission data and the historical biological resource consumption data, and calculating an effective outbound index based on the real-time patient admission data;
[0097] S4 includes the following specific steps:
[0098] S41: Build a machine learning model, including: input layer, hidden layer, 2 convolutional layers, pooling layer, fully connected layer and output layer;
[0099] S42: extracting historical patient admission data and historical biological resource consumption data of the biological resource demand site after historical major accidents as a training set for the machine learning model, performing data cleaning on the historical patient admission data and historical biological resource consumption data, and performing feature extraction training on the machine learning model through the historical patient admission data and historical biological resource consumption data after historical major accidents;
[0100] S43: The feature matrices of the historical patient admission data and the historical consumption data of biological resources output by the two convolutional layers are compressed through the sampling layer in the machine learning model, and the compressed feature matrices are output through the output layer to complete the training of the convolutional neural network;
[0101] S44: Input the real-time patient admission data after this major accident into the trained machine learning model, and predict the deviation of the actual usage of biological resources in real time.
[0102] S4 also includes the following specific steps:
[0103] S45: Through a machine learning model, the historical patient admission data and the historical biological resource consumption data are integrated and analyzed to calculate the deviation of the actual biological resource usage. The specific calculation strategy is as follows:
[0104] ;
[0105] in, In the figure, c is a subscript, which indicates the cth biological resource demand site near the biological resource transfer site;
[0106] is the deviation degree of the actual amount of biological resources used at the cth biological resource demand site;
[0107] is the number of patients with the nth initial diagnosis level;
[0108] is the mean number of patients at all initial diagnosis levels;
[0109] They represent the maximum and minimum number of patients in all initial diagnosis levels respectively;
[0110] middle is a subscript, indicating the mth patient with the nth initial disease diagnosis level;
[0111] The historical actual usage data of biological resources for the mth patient at the nth initial disease diagnosis level;
[0112] is the total number of patients with the nth initial diagnosis level; Pre-placed biological resource reserves for patients;
[0113] The proportional coefficient of the impact of the deviation in the number of patients and the proportional coefficient of the deviation in the actual amount of biological resources used are respectively;
[0114] S46: Calculate the effective outbound index based on the deviation of real-time patient admission data and actual usage of biological resources. The specific calculation strategy is as follows:
[0115] ;
[0116] in, is the total amount of biological resources dispatched by the biological resource transfer station to the cth biological resource demand station after this major accident, and C is the total number of biological resource transfer stations.
[0117] S5: Import the effective storage-in index and the effective storage-out index into the biological resource scheduling data balance evaluation strategy, calculate and obtain the scheduling balance threat value, and judge the biological resource scheduling level based on the scheduling balance threat value.
[0118] S5 includes the following specific steps:
[0119] S51: Import the effective inbound index and effective outbound index into the biological resource scheduling data balance assessment strategy to calculate the scheduling balance threat value , the biological resource scheduling data balance evaluation strategy is specifically:
[0120] .
[0121] S5 also includes the following specific steps:
[0122] S52: Extract the scheduling balance threat value of biological resources and preset the scheduling level threshold of biological resources , and judge the biological resource scheduling level according to the scheduling balance threat value. The specific judgment strategies include:
[0123] when When , it is judged that the scheduling of biological resources is unbalanced;
[0124] when When the biological resources are balanced, the scheduling is judged;
[0125] when , it is judged that the scheduling of biological resources is unbalanced.
[0126] Embodiment 2:
[0127] like Figure 2 As shown, a biological resource scheduling big data management system according to an embodiment of the present invention is as follows: Figure 2 As shown, it includes the following modules:
[0128] Visual model building module, effective inventory index calculation module, AI data management chip, effective inventory index calculation module, balance evaluation module;
[0129] The visualization model building module is used to obtain the geographical location information of the biological resource output site, the biological resource transfer site and the biological resource demand site, and build a visualization model of the biological resource dynamic scheduling grid;
[0130] The effective storage index calculation module is used to extract the biological resource collection data of each biological resource output site, and import the biological resource collection data into the effective storage index evaluation strategy to calculate and obtain the effective storage index;
[0131] The AI data management chip is used to obtain and store historical patient admission data and historical biological resource consumption data in various biological resource demand sites after major historical accidents; and simultaneously obtain and store real-time patient admission data in various biological resource demand sites after this major accident;
[0132] The effective outbound index calculation module is used to construct a machine learning model, perform fusion analysis on the historical patient admission data and the historical biological resource consumption data, and calculate the effective outbound index based on the real-time patient admission data;
[0133] The balance evaluation module imports the effective storage-in index and the effective storage-out index into the biological resource scheduling data balance evaluation strategy, calculates and obtains the scheduling balance threat value, and determines the biological resource scheduling level according to the scheduling balance threat value.
[0134] Embodiment three:
[0135] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;
[0136] The processor executes the above-mentioned biological resource scheduling big data management method by calling the computer program stored in the memory.
[0137] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement a biological resource scheduling big data management method provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.
[0138] Embodiment 4:
[0139] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;
[0140] When the computer program runs on a computer device, the computer device executes the above-mentioned biological resource scheduling big data management method.
[0141] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.
[0142] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0143] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.
[0144] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0145] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0146] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0147] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0148] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0149] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0150] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0151] In summary, compared with the prior art, the technical effects of the present invention are as follows:
[0152] 1. The present invention constructs a visualization model of the biological resource dynamic scheduling grid to display the geographical location and resource distribution of each site in real time, so that the dispatching personnel can intuitively understand the real-time status of resources and make adjustments quickly to solve the problem of unbalanced resource allocation in emergencies.
[0153] 2. The present invention extracts and evaluates biological resource collection data, calculates the effective storage index, and ensures that resources are stored and managed according to actual needs, which improves the efficiency of resource preparation and reduces problems caused by insufficient or excessive resource reserves.
[0154] 3. The present invention combines historical patient admission data and biological resource consumption data, analyzes real-time admission data, and uses machine learning models for prediction and analysis. This method can more accurately assess current resource needs, improve the accuracy of emergency response, and reduce imbalanced allocation caused by delayed or inaccurate data.
[0155] 4. The present invention can scientifically evaluate the balance of current scheduling by calculating the scheduling balance threat value and judging the scheduling level. According to the evaluation results, resource allocation can be quickly adjusted to ensure effective deployment and management of resources in major emergencies and avoid resource shortages or surpluses.
[0156] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.
Claims
1. A biological resource scheduling big data management method, characterized by: The method comprises the following specific steps: S1: Obtain the geographical location information of biological resource output sites, biological resource transfer sites and biological resource demand sites, and build a visualization model of biological resource dynamic scheduling grid; S2: extracting the biological resource collection data of each biological resource output site, and importing the biological resource collection data into the effective storage index evaluation strategy to calculate and obtain the effective storage index; S3: Obtain historical patient admission data and historical biological resource consumption data at each biological resource demand site after a major historical accident; simultaneously obtain real-time patient admission data at each biological resource demand site after this major accident; S4: constructing a machine learning model based on the data in S3, performing a fusion analysis on the historical patient admission data and the historical biological resource consumption data, and calculating an effective outbound index based on the real-time patient admission data; S5: Import the effective storage-in index and the effective storage-out index into the biological resource scheduling data balance evaluation strategy, calculate and obtain the scheduling balance threat value, and judge the biological resource scheduling level according to the scheduling balance threat value; In S2, the effective inventory index evaluation strategy is as follows: S21: extracting biological resource collection data of each biological resource output site, and evaluating the loss rate of biological resources in the output process of each biological resource output site according to the biological resource collection data, wherein the calculation strategy of the loss rate is: ; in, Here r is a subscript, indicating the rth biological resource output site near the biological resource transfer site; is the loss rate of biological resources during the export process of the rth biological resource export site; Q is the total number of biological resources collected today at this biological resource output site; They are the ineffective component loss ratio coefficient and the storage loss ratio coefficient respectively; is the actual active ingredient content of the qth biological resource after testing and analysis; The target active ingredient content for a single biological resource; The actual time interval from the collection of the qth biological resource at the biological resource output site to the transfer of the biological resource transfer site; The target time interval for a single biological resource to be transferred from the collection of the biological resource export site to the transfer site of the biological resource; S22: Extract the loss rate of biological resources during the output process of each biological resource output site, And calculate the effective storage index RK of biological resources. The specific calculation strategy is: ; Where e is the natural index, is the total amount of biological resources contributed by the rth biological resource export site to the biological resource transfer site, and R is the total number of biological resource export sites; In S3, the historical patient admission data and historical biological resource consumption data of each biological resource demand site, The historical patient admission data includes: the initial diagnosis level of the patient's condition after the patient is admitted to the hospital, and the initial diagnosis level is N levels in total; the historical patient admission data also includes: the number of patients at each initial diagnosis level and the preset biological resource reserve for each patient ; The historical consumption data of biological resources include: historical scheduling data of biological resources and historical actual use data of biological resources; S4 includes the following specific steps: S41: Build a machine learning model, including: input layer, hidden layer, 2 convolutional layers, pooling layer, fully connected layer and output layer; S42: extracting historical patient admission data and historical biological resource consumption data of the biological resource demand site after historical major accidents as a training set for the machine learning model, performing data cleaning on the historical patient admission data and historical biological resource consumption data, and performing feature extraction training on the machine learning model through the historical patient admission data and historical biological resource consumption data after historical major accidents; S43: The feature matrices of the historical patient admission data and the historical consumption data of biological resources output by the two convolutional layers are compressed through the sampling layer in the machine learning model, and the compressed feature matrices are output through the output layer to complete the training of the convolutional neural network; S44: Input the real-time patient admission data after the major accident into the trained machine learning model, and predict the deviation of the actual usage of biological resources in real time; S4 also includes the following specific steps: S45: Through a machine learning model, the historical patient admission data and the historical biological resource consumption data are integrated and analyzed to calculate the deviation of the actual biological resource usage. The specific calculation strategy is as follows: ; in, In the figure, c is a subscript, which indicates the cth biological resource demand site near the biological resource transfer site; is the deviation degree of the actual amount of biological resources used at the cth biological resource demand site; is the number of patients with the nth initial diagnosis level; is the mean number of patients at all initial diagnosis levels; They represent the maximum and minimum number of patients in all initial diagnosis levels respectively; middle is a subscript, indicating the mth patient with the nth initial disease diagnosis level; The historical actual usage data of biological resources for the mth patient at the nth initial disease diagnosis level; is the total number of patients with the nth initial diagnosis level; Pre-placed biological resource reserves for patients; The proportional coefficient of the impact of the deviation in the number of patients and the proportional coefficient of the deviation in the actual amount of biological resources used are respectively; S46: Calculate the effective outbound index based on the deviation of real-time patient admission data and actual usage of biological resources. The specific calculation strategy is as follows: ; in, is the total amount of biological resources dispatched by the biological resource transfer station to the cth biological resource demand station after this major accident, and C is the total number of biological resource transfer stations.
2. A biological resource scheduling big data management method according to claim 1, characterized in that: S5 includes the following specific steps: S51: Import the effective inbound index and effective outbound index into the biological resource scheduling data balance assessment strategy to calculate the scheduling balance threat value , the biological resource scheduling data balance evaluation strategy is specifically: 。 3. A biological resource scheduling big data management method according to claim 2, characterized in that: S5 also includes the following specific steps: S52: Extract the scheduling balance threat value of biological resources and preset the scheduling level threshold of biological resources , and judge the biological resource scheduling level according to the scheduling balance threat value. The specific judgment strategies include: when When , it is judged that the scheduling of biological resources is unbalanced; when When the biological resources are balanced, the scheduling is judged; when , it is judged that the scheduling of biological resources is unbalanced.
4. A biological resource scheduling big data management system, which is implemented based on a biological resource scheduling big data management method according to any one of claims 1 to 3, characterized in that: The system includes the following modules: Visual model building module, effective inventory index calculation module, AI data management chip, effective inventory index calculation module, balance evaluation module; The visualization model building module is used to obtain the geographical location information of the biological resource output site, the biological resource transfer site and the biological resource demand site, and build a visualization model of the biological resource dynamic scheduling grid; The effective storage index calculation module is used to extract the biological resource collection data of each biological resource output site, and import the biological resource collection data into the effective storage index evaluation strategy to calculate and obtain the effective storage index; The AI data management chip is used to obtain and store historical patient admission data and historical biological resource consumption data in various biological resource demand sites after major historical accidents; and simultaneously obtain and store real-time patient admission data in various biological resource demand sites after this major accident; The effective outbound index calculation module is used to construct a machine learning model, perform fusion analysis on the historical patient admission data and the historical biological resource consumption data, and calculate the effective outbound index based on the real-time patient admission data; The balance evaluation module imports the effective storage-in index and the effective storage-out index into the biological resource scheduling data balance evaluation strategy, calculates and obtains the scheduling balance threat value, and determines the biological resource scheduling level according to the scheduling balance threat value.
5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, a biological resource scheduling big data management method as described in any one of claims 1-3 is implemented.
