Hospital medical resource optimization allocation method and device

Abstract

The invention provides a hospital medical resource optimization allocation method and device. The method comprises the following steps: receiving medical resource use data, wherein the medical resource use data comprises sickbed use rate data and medical equipment use data; determining a first confusion vector, a second confusion vector and a third confusion vector for medical resource allocation, wherein each confusion vector comprises a plurality of random numbers; based on the first confusion vector and the second confusion vector, performing confusion processing on the sickbed utilization rate data to obtain a first confusion matrix; based on the second confusion vector and the third confusion vector, performing confusion processing on the medical equipment use data to obtain a second confusion matrix; and sending the first confusion matrix and the second confusion matrix to operation processing equipment. According to the invention, on the premise that the safety of medical resource use data is protected, optimal allocation of medical resources is realized, and the medical resource use efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of medical resource management, and in particular to a method and device for optimizing the allocation of hospital medical resources. Background Art

[0002] With the rapid development of medical and health care, the demand for medical resources in hospitals is increasing. In the process of implementing this application, the inventor found that the current hospitals have the following problems in medical resource management:

[0003] The utilization efficiency of medical resources in hospitals is generally low. Take hospital beds as an example. Some departments have long-term idle beds, while other departments are short of beds and cannot meet the needs of patients. This phenomenon of unbalanced resource allocation leads to low overall utilization efficiency of medical resources.

[0004] Many hospitals still use traditional manual recording and statistics methods to record the use of medical equipment. This method not only requires a large workload, but also makes it difficult to find and solve problems in the use of equipment in a timely manner, affecting the efficiency of medical equipment use.

[0005] Finally, when processing medical resource usage data, existing medical resource allocation solutions often send the data directly to a third party for processing, which poses a risk of data leakage. This practice may not only leak hospital operating data, but also involve patient privacy information. Summary of the invention

[0006] In view of this, the present application provides a method and device for optimizing the allocation of hospital medical resources, which solves the problems of low efficiency in medical resource allocation and poor data security in the prior art.

[0007] The present application embodiment provides a method for optimizing the allocation of hospital medical resources, including:

[0008] receiving medical resource usage data, wherein the medical resource usage data includes bed usage rate data and medical equipment usage data;

[0009] Determine a first confusion vector, a second confusion vector, and a third confusion vector for medical resource allocation, each confusion vector comprising a plurality of random numbers;

[0010] Based on the first confusion vector and the second confusion vector, performing confusion processing on the bed utilization rate data to obtain a first confusion matrix;

[0011] Based on the second confusion vector and the third confusion vector, performing confusion processing on the medical device usage data to obtain a second confusion matrix;

[0012] Sending the first confusion matrix and the second confusion matrix to a processing device;

[0013] Receiving a calculation result returned by the calculation processing device;

[0014] An optimized deployment scheme is obtained based on the first confusion vector, the second confusion vector, the third confusion vector and the calculation result.

[0015] Optionally, the method further comprises:

[0016] Obtain a first permutation vector, a second permutation vector, and a third permutation vector;

[0017] Based on the first permutation vector and the second permutation vector, positionally transforming the bed utilization rate data to obtain a first intermediate matrix;

[0018] Based on the second permutation vector and the third permutation vector, positionally transform the medical device usage data to obtain a second intermediate matrix;

[0019] The step of performing confusion processing on the bed usage rate data based on the first confusion vector and the second confusion vector to obtain a first confusion matrix includes: performing confusion processing on the first intermediate matrix based on the first confusion vector and the second confusion vector to obtain a first confusion matrix;

[0020] The method of performing confusion processing on the medical device usage data based on the second confusion vector and the third confusion vector to obtain a second confusion matrix includes: performing confusion processing on the second intermediate matrix based on the second confusion vector and the third confusion vector to obtain a second confusion matrix.

[0021] Optionally, obtaining the first permutation vector, the second permutation vector and the third permutation vector comprises:

[0022] Generate a first permutation vector, the first permutation vector comprising m different data elements, each data element being an integer from 1 to m;

[0023] generating a second permutation vector, the second permutation vector comprising n different data elements, each data element being an integer from 1 to n;

[0024] generating a third permutation vector, the third permutation vector comprising s different data elements, each data element being an integer from 1 to s;

[0025] Among them, m is the number of rows of bed utilization data, n is the number of rows of medical equipment utilization data, and s is the number of columns of medical equipment utilization data.

[0026] Optionally, the method further comprises:

[0027] Selecting the maximum absolute value from the bed utilization rate data and the medical equipment utilization data;

[0028] determining a value L based on the maximum absolute value;

[0029] Determine the upper limit and lower limit of the real number range according to the value L;

[0030] The random numbers included in the first obfuscation vector, the second obfuscation vector, and the third obfuscation vector are obtained by randomly selecting from the real number range.

[0031] Optionally, the method also includes: before obfuscating the bed occupancy data, replacing the data element with a value of 0 in the bed occupancy data with a first non-zero real number; before obfuscating the medical device usage data, replacing the data element with a value of 0 in the medical device usage data with a second non-zero real number.

[0032] Optionally, the method further comprises:

[0033] Dynamically deploying medical resources based on the optimized deployment plan;

[0034] Monitor the use of medical resources;

[0035] When the usage of medical resources meets the preset conditions, the medical resource optimization allocation method is re-executed.

[0036] Optionally, the preset conditions include:

[0037] The bed occupancy rate exceeds the set bed occupancy threshold; and / or,

[0038] The medical device utilization rate exceeds the set medical device utilization rate threshold; and / or,

[0039] The medical staff workload exceeds the set medical staff workload threshold; and / or,

[0040] The medical resource allocation cycle reaches a preset time threshold; and / or,

[0041] Receive instructions for optimizing the allocation of medical resources.

[0042] Optionally, the method further comprises:

[0043] Establishing heterogeneous proxy nodes, wherein the heterogeneous proxy nodes include ward proxy nodes, emergency proxy nodes, operating room proxy nodes, and intensive care unit proxy nodes;

[0044] Configure the priority rules for each heterogeneous proxy node;

[0045] Based on the priority rules of the heterogeneous proxy nodes, the optimization deployment scheme is adjusted.

[0046] Optionally, adjusting the optimization deployment scheme based on the priority rule of the heterogeneous proxy nodes includes:

[0047] Receive resource requests sent by heterogeneous proxy nodes;

[0048] Adjusting the optimization allocation scheme according to the priority of the resource request;

[0049] The adjusted optimization allocation plan is sent to the relevant heterogeneous proxy nodes.

[0050] The present application also provides a device for optimizing the allocation of hospital medical resources, including:

[0051] A receiving unit, configured to receive medical resource usage data, wherein the medical resource usage data includes bed usage rate data and medical equipment usage data;

[0052] A processing unit, configured to determine a first confusion vector, a second confusion vector, and a third confusion vector for medical resource allocation, each confusion vector comprising a plurality of random numbers; based on the first confusion vector and the second confusion vector, perform confusion processing on the bed utilization rate data to obtain a first confusion matrix; based on the second confusion vector and the third confusion vector, perform confusion processing on the medical equipment utilization data to obtain a second confusion matrix;

[0053] A sending unit, configured to send the first confusion matrix and the second confusion matrix to a processing device;

[0054] A monitoring unit, used to monitor the usage of medical resources and trigger the re-execution of optimal allocation of medical resources when the usage meets preset conditions;

[0055] The receiving unit is further used to receive the operation result returned by the operation processing device; the processing unit is further used to obtain an optimized deployment plan based on the first confusion vector, the second confusion vector, the third confusion vector and the operation result.

[0056] The embodiments of the present application have the following beneficial effects:

[0057] This application uses obfuscation to ensure data security when processing medical resource usage data. By using random obfuscation vectors to obfuscate the data, it is impossible for outsiders to obtain the original information from the obfuscated data, effectively protecting the security of the hospital's operational data.

[0058] The solution proposed in this application can dynamically allocate medical resources in real time. By continuously monitoring the use of medical resources, it automatically triggers redeployment when resource usage reaches preset conditions, ensuring that the efficiency of medical resource use is always maintained at a high level.

[0059] This application uses heterogeneous proxy nodes to achieve resource coordination between different departments. By setting proxy nodes for different types of departments and configuring priority rules, the allocation of medical resources is more flexible and reasonable, which can meet the actual needs of each department. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for describing the embodiments are briefly introduced below.

[0062] Figure 1 It is a flowchart of a method for optimizing allocation of hospital medical resources provided in an embodiment of the present application;

[0063] Figure 2 It is a schematic diagram of the architecture of the hospital medical resource optimization and allocation system provided in the embodiment of the present application;

[0064] Figure 3 This is a schematic diagram of the obfuscation process provided by an embodiment of the present application;

[0065] Figure 4 It is a schematic diagram of the structure of a heterogeneous proxy node provided in an embodiment of the present application;

[0066] Figure 5 It is a module diagram of the hospital medical resource optimization allocation device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0067] The embodiments of the present application are described below in conjunction with the drawings in the present application. It should be understood that the implementation methods described below in conjunction with the drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions of the embodiments of the present application.

[0068] It will be understood by those skilled in the art that, unless specifically stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the terms "including" and "comprising" used in the embodiments of the present application refer to that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements and / or components, but do not exclude the implementation as other features, information, data, steps, operations, elements, components and / or combinations thereof supported by the technical field. It should be understood that when an embodiment of the present invention refers to an element being "connected" or "coupled" to another element, the one element may be directly connected or coupled to the other element, or may refer to the one element and the other element establishing a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein indicates at least one of the items defined by the term, for example, "A and / or B" may be implemented as "A", or as "B", or as "A and B".

[0069] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0070] The core of the present invention is to provide a method and system for generating intelligent software test data based on Internet public information. The present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0071] It should be understood that the terms "including" and "having" and any variations thereof used herein are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0072] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0073] In the embodiments of the present application, some terms involved in the present application are explained:

[0074] Obfuscation vector: refers to a vector containing multiple random numbers, which is used to obfuscate the original data, making it difficult to restore the obfuscated data to the original data.

[0075] Permutation vector: refers to a vector containing non-repeating integers in a certain range, which is used to change the positional relationship of data elements in the matrix.

[0076] Heterogeneous proxy nodes: refers to proxy nodes with different functions and priorities set up in different departments of the hospital, which are used to coordinate resource allocation between departments.

[0077] See also Figure 1 The method for optimizing the allocation of hospital medical resources provided in the embodiment of the present application comprises the following steps:

[0078] S1: Receive medical resource usage data

[0079] The system receives medical resource usage data reported by various departments of the hospital. These data mainly include two categories: one is bed utilization rate data, which reflects the occupancy of beds in various departments; the other is medical equipment usage data, which reflects the frequency and duration of use of various medical equipment.

[0080] It should be noted that the bed utilization rate data includes information such as the total number of beds in each department, the number of beds in use, and the number of vacant beds. The medical equipment usage data includes information such as the number of times each type of equipment is used, the duration of use, and the idle time. These data will provide a basis for subsequent resource allocation optimization.

[0081] S2: Generate confusion vector and permutation vector

[0082] After obtaining the medical resource usage data, the system needs to perform protective processing on this data to prevent data leakage during transmission and calculation.

[0083] First, the system checks whether there are data elements with a value of 0 in the bed utilization data and medical equipment utilization data. If so, these 0 values ​​are replaced with preset non-zero real numbers. The purpose of this is to prevent the distribution characteristics of the original data from being inferred through 0 values.

[0084] Then, the system generates three sets of vectors: the first confusion vector, the second confusion vector, and the third confusion vector. The length of the first confusion vector is equal to the number of rows of the bed utilization data, the length of the second confusion vector is equal to the number of rows of the medical equipment utilization data, and the length of the third confusion vector is equal to the number of columns of the medical equipment utilization data. Each element in these confusion vectors is a non-zero real number randomly selected from a predefined real number range.

[0085] At the same time, the system will also generate three sets of permutation vectors: the first permutation vector, the second permutation vector and the third permutation vector. These permutation vectors are used to change the positional relationship of the elements in the data matrix to further increase the security of the data.

[0086] The specific processing flow of the above process is as follows:

[0087] 1. Data zero value processing

[0088] First, the system processes zero values ​​in the raw data. In medical resource usage data, zero values ​​may represent that the resources are completely unused. For example:

[0089] The 0 in the bed occupancy rate data may mean that the beds in a department are completely vacant during a certain period of time.

[0090] A zero in medical device usage data may indicate that a device was not used during a certain period of time.

[0091] However, these zero values ​​will expose some distribution characteristics of the original data. To improve data security, the system will:

[0092] 1. Define the range of non-zero real numbers for replacement, usually choose a smaller non-zero real number, such as in [-2 -7 , 2 -7 ] is a non-zero real number in the range. The selection of this range needs to meet two conditions:

[0093] The value is small enough not to significantly affect the subsequent data processing results

[0094] The range is appropriate to avoid numerical overflow when restoring data

[0095] 2. Select different replacement values ​​for bed occupancy data and medical equipment usage data respectively:

[0096] Replace zero values ​​in bed occupancy data with the first non-zero real number

[0097] Replace zero values ​​in medical device usage data with a second non-zero real number

[0098] 2. Confusion Vector Generation

[0099] The system needs to generate three sets of confusion vectors, and the generation process is as follows:

[0100] 1. Determine the vector dimension:

[0101] The dimension m of the first confusion vector is equal to the number of rows of bed occupancy data;

[0102] The dimension n of the second confusion vector is equal to the number of rows of the medical device usage data;

[0103] The dimension s of the third confusion vector is equal to the number of columns of the medical device usage data;

[0104] 2. Determine the range of random numbers:

[0105] Select the maximum absolute value MAX from the original data;

[0106] Calculate the L value: when log2(MAX) is an even number, L = log2(MAX); when it is an odd number, L = log2(MAX) + 1;

[0107] Determine the range of real numbers: [-2^(L / 2), 2^(L / 2)];

[0108] 3. Generate confusion vector:

[0109] First confusion vector: randomly select m non-zero real numbers from a certain real number range;

[0110] Second confusion vector: randomly select n non-zero real numbers from a certain real number range;

[0111] The third confusion vector: randomly select s non-zero real numbers from a certain real number range;

[0112] 3. Permutation Vector Generation

[0113] The permutation vector is used to disrupt the positional relationship of the matrix elements. The generation process is as follows:

[0114] 1. First permutation vector generation:

[0115] Create a sequence of integers from 1 to m;

[0116] Shuffle the sequence using a random permutation algorithm (such as the Fisher-Yates shuffle algorithm);

[0117] The shuffled sequence is used as the first permutation vector;

[0118] 2. Second permutation vector generation:

[0119] Create a sequence of integers from 1 to n;

[0120] Use a random permutation algorithm to shuffle the sequence;

[0121] The shuffled sequence is used as the second permutation vector;

[0122] 3. The third permutation vector is generated:

[0123] Create a sequence of integers from 1 to s;

[0124] Use a random permutation algorithm to shuffle the sequence;

[0125] The shuffled sequence is used as the third permutation vector;

[0126] For example, assuming that the bed utilization data of a department is a 3×4 matrix and the medical equipment utilization data is a 4×5 matrix, then:

[0127] 1. The dimension of the generated confusion vector is:

[0128] First confusion vector: 3 random numbers;

[0129] Second confusion vector: 4 random numbers;

[0130] The third confusion vector: 5 random numbers;

[0131] 2. The generated permutation vector is:

[0132] First permutation vector: [3, 1, 2] (a random arrangement of 1-3);

[0133] Second permutation vector: [2, 4, 1, 3] (a random arrangement of 1-4);

[0134] The third permutation vector: [3, 5, 1, 4, 2] (a random arrangement of 1-5);

[0135] This multi-level data protection mechanism can effectively prevent the original data from being inferred:

[0136] Zero-value substitution eliminates significant features of the data distribution;

[0137] The confusion vector changes the numerical relationship of the data;

[0138] The permutation vector disrupts the position correspondence of the data;

[0139] Through this triple protection, even if obfuscated data is obtained, it is difficult to restore the original medical resource usage, thus ensuring the security of the data.

[0140] S3: Obfuscate the data

[0141] See also Figure 3 ,The data obfuscation process is divided into two stages: position transformation and numerical obfuscation.

[0142] In the position transformation stage, the system first transforms the bed utilization data using the first permutation vector and the second permutation vector to generate the first intermediate matrix. Specifically, the data in the i-th row and j-th column of the original data matrix will be moved to the new position indicated by the i-th element of the first permutation vector and the j-th element of the second permutation vector. The same method is also used to process the medical equipment utilization data, using the second permutation vector and the third permutation vector to generate the second intermediate matrix.

[0143] In the numerical obfuscation stage, the system uses the first obfuscation vector and the second obfuscation vector to confuse the first intermediate matrix to obtain the first obfuscation matrix. Similarly, the second obfuscation vector and the third obfuscation vector are used to confuse the second intermediate matrix to obtain the second obfuscation matrix. This double obfuscation method can effectively prevent data from being restored.

[0144] Detailed description of the implementation process of the two stages of position transformation and numerical confusion:

[0145] 1. Position Transformation Phase

[0146] This stage mainly realizes the rearrangement of the data element positions. The present application embodiment respectively describes the processing process of the bed utilization rate data and the medical equipment utilization data:

[0147] 1. Change of location of bed occupancy rate data

[0148] Assume that the original bed utilization rate data matrix is ​​X, with a dimension of m×n. The system uses the first permutation vector A (dimension is m) and the second permutation vector B (dimension is n) to transform X to obtain the first intermediate matrix X2. The transformation process is as follows:

[0149] The calculation formula for the element in the i-th row and j-th column of the first intermediate matrix X2 is:

[0150] X2[i,j]=X[A(i),B(j)]

[0151] in:

[0152] The value range of i is 1 to m;

[0153] The value range of j is from 1 to n;

[0154] A(i) represents the value of the i-th position in the first permutation vector;

[0155] B(j) represents the value of the jth position in the second permutation vector;

[0156] For example:

[0157] Suppose there is a 3×3 bed occupancy rate data matrix X:

[0158] X=[70 85 90 65 75 80 85 95 70]

[0161] The first permutation vector A = [2, 3, 1], the second permutation vector B = [3, 1, 2]

[0162] Then the calculation process of the first intermediate matrix X2 is:

[0163] X2[1,1]=X[A(1),B(1)]=X[2,3]=80

[0164] X2[1,2]=X[A(1),B(2)]=X[2,1]=65

[0165] X2[1,3]=X[A(1),B(3)]=X[2,2]=75

[0166] ...and so on

[0167] The final first intermediate matrix X2 is:

[0168] X2=[80 65 75 70 85 95 90 85 70]

[0171] 2. Change of location of medical device usage data

[0172] Assume that the original medical device uses a data matrix Y with a dimension of n×s. The system uses the second permutation vector B (dimension n) and the third permutation vector C (dimension s) to transform Y to obtain the second intermediate matrix Y2. The transformation process is as follows:

[0173] The calculation formula for the element in the i-th row and j-th column of the second intermediate matrix Y2 is:

[0174] Y2[i,j]=Y[B(i),C(j)]

[0175] in:

[0176] The value range of i is 1 to n

[0177] The value range of j is 1 to s

[0178] B(i) represents the value of the i-th position in the second permutation vector

[0179] C(j) represents the value of the jth position in the third permutation vector

[0180] 2. Numerical Confusion Stage

[0181] This stage performs numerical obfuscation on the position-transformed matrix:

[0182] 1. Confusion processing of the first intermediate matrix

[0183] The first confusion matrix X2 is confused using the first confusion vector O (dimension is m) and the second confusion vector P (dimension is n) to obtain the first confusion matrix X1. The confusion process is as follows:

[0184] The calculation formula for the element in the i-th row and j-th column of the first confusion matrix X1 is:

[0185] X1[i,j]=X2[i,j]+O(i)*P(j)

[0186] in:

[0187] The value range of i is 1 to m

[0188] The value range of j is 1 to n

[0189] O(i) represents the value of the i-th position in the first confusion vector

[0190] P(j) represents the value of the jth position in the second confusion vector

[0191] Continuing with the above example:

[0192] Assume that the first obfuscation vector O = [1.5, 2.0, 1.8] and the second obfuscation vector P = [1.2, 1.6, 1.4]

[0193] Then the first element of X1 is calculated as:

[0194] X1[1,1]=80+1.5*1.2=81.8

[0195] And so on for the other elements.

[0196] 2. Confusion of the second intermediate matrix

[0197] The second intermediate matrix Y2 is confused using the second confusion vector P (dimension n) and the third confusion vector Q (dimension s) to obtain the second confusion matrix Y1. The confusion process is as follows:

[0198] The calculation formula for the element in the i-th row and j-th column of the second confusion matrix Y1 is:

[0199] Y1[i,j]=Y2[i,j]+P(i)*Q(j)

[0200] in:

[0201] The value range of i is from 1 to n;

[0202] The value range of j is from 1 to s;

[0203] P(i) represents the value of the i-th position in the second confusion vector;

[0204] Q(j) represents the value of the jth position in the third confusion vector;

[0205] This double obfuscation (position transformation + numerical obfuscation) method has the following advantages:

[0206] 1. Position transformation destroys the spatial correlation of data;

[0207] 2. Numerical confusion changes the numerical relationship of the data;

[0208] 3. Use the same second confusion vector P to connect the two confusion matrices for subsequent operations;

[0209] 4. Even if the attacker obtains the obfuscated matrix, he cannot restore the original data without the obfuscation vector and the permutation vector;

[0210] 5. The obfuscation process is reversible and the original data can be restored when needed.

[0211] In this way, the security of data processing is guaranteed while the availability of data is maintained, allowing third-party computing devices to complete necessary calculations without knowing the original data.

[0212] S4: Send obfuscated data and receive calculation results

[0213] The system sends the generated first confusion matrix and second confusion matrix to the operation processing device. The operation processing device can be a server with high-performance computing capabilities or a dedicated computing device. These devices will optimize the calculation of the obfuscated data, but because the data has been obfuscated, the specific content of the original data cannot be known.

[0214] After the computing device completes the calculation, the system receives the computing result returned by it. This result is also obfuscated, and needs to be combined with the previously used obfuscation vector to restore the real optimization solution.

[0215] Specifically, during the specific implementation process, the system sends the first confusion matrix and the second confusion matrix to the operation processing device through a secure network channel. These confusion matrices are encapsulated in a specific data format, including matrix dimension information, data accuracy requirements, and metadata such as timestamps, which are convenient for the operation processing device to parse and process. The operation processing device can be a computing server equipped with a high-performance GPU, or an FPGA device specially optimized for matrix operations. These devices have parallel computing capabilities and can efficiently process large-scale matrix operation tasks.

[0216] After receiving the confusion matrix, the computing and processing device first verifies the integrity of the data to ensure that the data has not been tampered with during transmission. Subsequently, the computing and processing device processes the obfuscated data based on a preset optimization algorithm. These optimization algorithms include but are not limited to linear programming, integer programming, heuristic algorithms, etc., which are used to calculate the optimal resource allocation plan. In particular, since the data has been obfuscated, even if the computing and processing device obtains the complete calculation process, it cannot deduce the original medical resource usage, thereby ensuring the security of the data.

[0217] After completing the optimization calculation, the computing and processing equipment will conduct a reliability assessment on the calculation results, including verifying whether the results meet the resource constraints and whether there are numerical overflows. After the assessment is passed, the computing and processing equipment will encrypt and encapsulate the results and send them back to the original system through a secure channel. It should be noted that the returned calculation results are still in an obfuscated state, which contains the composite information of the optimized resource allocation plan and the obfuscation vector.

[0218] After receiving the calculation results, the system first performs data decryption and integrity verification. Then, the system uses the first, second, and third confusion vectors saved in advance to reversely restore the calculation results. This restoration process needs to be performed in strict accordance with the generation order of the confusion matrix, including steps such as removing the influence of the confusion vector and restoring the corresponding relationship of the original data. Finally, the system obtains a real medical resource optimization allocation plan, which includes specific resource allocation suggestions, such as bed reallocation plans and medical equipment use schedules.

[0219] In order to improve the reliability of data transmission and processing, the system also implements a failure retry and result verification mechanism. When abnormal data transmission or unreasonable calculation results are detected, the system will automatically start the retry process to ensure an effective optimization solution. At the same time, the system will record key information of each data transmission and calculation process for subsequent auditing and optimization improvements.

[0220] S5: Generate optimized deployment plan

[0221] In actual operation, the resource request processing mechanism of heterogeneous proxy nodes is as follows: When a heterogeneous proxy node needs additional medical resources, it sends a resource request to the system. These requests contain elements such as the node type of the requester, specific information about the required resources (such as the number of beds, equipment type, etc.), and expected usage time. After receiving the request, the system will evaluate the request according to the pre-configured priority rules. For example, when the emergency department and the general ward request the use of CT equipment at the same time, the system will give priority to meeting the needs of the emergency department. After determining the priority of the request, the system will adjust the original optimization allocation plan accordingly, which may involve temporary allocation of resources, rescheduling of usage time, etc. Finally, the system sends the adjusted plan to the relevant heterogeneous proxy nodes, including resource suppliers and demanders, to ensure the sequential execution of resource allocation.

[0222] See also Figure 4 The system uses heterogeneous proxy nodes to achieve optimal allocation of medical resources. Specifically, different types of proxy nodes are set up in various departments of the hospital, including:

[0223] Ward agent node: responsible for bed management in general wards

[0224] Emergency agent node: responsible for the allocation of resources in the emergency ward

[0225] Operating room agent node: responsible for the scheduling of operating rooms and related equipment

[0226] Intensive Care Unit Agent Node: Responsible for the allocation of ICU resources

[0227] These proxy nodes have different priority rules. For example, the priority of the emergency proxy node is usually higher than that of the general ward proxy node, so that the needs of the emergency department can be prioritized when resources are tight.

[0228] The system generates the final optimal allocation plan for medical resources based on the calculation results and the priority rules of each proxy node. This plan will be sent to the relevant proxy nodes for execution to achieve dynamic allocation of resources.

[0229] Take the resource allocation of a Class A tertiary hospital as an example. The hospital has internal medicine wards, surgical wards, emergency departments, operating rooms, and intensive care units. At 8 o'clock on Monday morning, the system detected the following situations: the surgical operating room was fully booked, the intensive care unit utilization rate reached 85%, and many car accident victims were admitted to the emergency department, while 30% of the beds in the internal medicine ward were still vacant. At this time, the heterogeneous proxy node system will work together as follows:

[0230] First, the emergency agent node receives an urgent request for multiple car accident victims to be admitted to the hospital. Since the emergency agent node has the highest priority, the system immediately starts the emergency response process. The emergency agent node sends resource requests to other agent nodes, including: requesting 10 beds from the ward agent node, applying for emergency use rights of 2 operating rooms from the operating room agent node, and reserving 3 ICU beds from the intensive care unit agent node.

[0231] After receiving the request, the ward proxy node immediately reallocated the existing bed resources. It was found that among the 30% vacant beds in the medical ward, 15 beds could be put into use immediately. The system prioritized allocating 10 beds to support the emergency department, and the remaining 5 beds were used as mobile beds. At the same time, the ward proxy node activated the bed turnover acceleration mechanism to coordinate patients who were about to be discharged to complete discharge preparations in advance.

[0232] After receiving the emergency request, the operating room proxy node immediately evaluates the current operating room scheduling situation. It finds that the elective surgeries originally planned for operating rooms 4 and 6 can be appropriately postponed, so these two operating rooms are urgently allocated to the emergency department. At the same time, the operating room proxy node automatically notifies the relevant medical staff to stand by and coordinates the preparation of surgical instruments.

[0233] Although the current utilization rate of the intensive care unit proxy node is already high, considering the special needs of the emergency department, the emergency plan is immediately activated: two patients who are recovering well are transferred to the general ward, thus freeing up two ICU beds; at the same time, one ICU bed originally used for planned surgery is kept as a reserve to give priority to the treatment needs of the injured in the traffic accident.

[0234] During the resource allocation process, each agent node will also coordinate in real time. For example, when a car accident patient completes surgery and needs to be transferred to the ICU, the operating room agent node will automatically communicate with the intensive care unit agent node to ensure timely connection of beds. At the same time, the ward agent node will continue to track the bed turnover of general wards to prepare for possible subsequent bed needs.

[0235] The system will also automatically record the entire process of resource allocation, including: the reason for allocation (admission of traffic accident victims), the flow of various resources (such as the precise location of 10 beds, the specific use time of 2 operating rooms, etc.), the dispatch of relevant medical staff, etc. These records can be used for subsequent analysis and optimization, and also provide detailed reference for possible medical disputes.

[0236] Through this multi-level, dynamic resource allocation mechanism, hospitals can quickly and orderly optimize the allocation of various medical resources in emergency situations to maximize the treatment effect of patients. At the same time, this allocation method based on heterogeneous proxy nodes also fully reflects the importance of differentiated needs and priority management between different departments.

[0237] S6: Continuous monitoring and dynamic adjustment

[0238] After the optimization deployment plan is implemented, the system will continue to monitor the use of medical resources. When any of the following situations occurs, the system will trigger a reallocation:

[0239] The bed occupancy rate of a department exceeds the preset threshold

[0240] The usage rate of a certain type of medical equipment exceeds the preset threshold

[0241] The workload of medical staff exceeds the preset threshold

[0242] Reach the preset resource allocation cycle

[0243] Receive manually triggered deployment instructions

[0244] See also Figure 5 The embodiment of the present application also provides a device for optimizing and allocating medical resources in a hospital, including a receiving unit, a processing unit, a sending unit and a monitoring unit.

[0245] The receiving unit is responsible for receiving the medical resource usage data and the calculation results returned by the calculation processing device. The processing unit is responsible for generating obfuscation vectors, performing data obfuscation processing, and generating an optimized deployment plan based on the calculation results. The sending unit is responsible for sending the obfuscated data to the calculation processing device. The monitoring unit is responsible for real-time monitoring of the use of medical resources and triggering redeployment when necessary.

[0246] Among them, the specific implementation of the processing unit can use one or more processors to cooperate with the corresponding computer program instructions to perform various functions. The sending unit can use a standard network interface module to support multiple network protocols to ensure the reliability of data transmission. The monitoring unit can adopt a distributed architecture, deploy data acquisition nodes in various departments, and collect and report the use status of medical resources in real time. These functional units can adopt a modular design, which can be integrated in the same physical device or distributed on different hardware devices, and communicate and collaborate through the internal network.

[0247] The device in this embodiment can be implemented in hardware or in software functional modules. When implemented in software functional modules, the functional modules of the present application can be integrated in the same processor or in different processors.

[0248] It should be noted that the above embodiments are only examples for clearly illustrating the present application, and are not intended to limit the implementation methods. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all implementation methods here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present application should be included in the protection scope of the claims of the present application.

[0249] In the description of this application, the terms "first", "second", etc. are only used to distinguish different entities or operations, rather than indicating or implying the relative importance or implicit order of these entities or operations. Unless otherwise clearly specified and limited, "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0250] The above is only an optional embodiment of the present application, and is not intended to limit the present application. Those skilled in the art can also make various changes and modifications without departing from the spirit and scope of the present application, and these changes and modifications should fall within the scope of protection of the present application. The above is only a preferred embodiment of the present application, and is not intended to limit the scope of the patent of the present application. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application should be included in the scope of patent protection of the present application. It should be understood that although the flowchart of the embodiment of the present application indicates each operation step by arrows, the implementation order of these steps is not limited to the order indicated by the arrows. Unless clearly stated in this article, in some implementation scenarios of the embodiment of the present application, the implementation steps in each flowchart can be executed in other orders according to demand. In addition, some or all of the steps in each flowchart can include multiple sub-steps or multiple stages based on the actual implementation scenario. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage in these sub-steps or stages can also be executed at different times. In scenarios with different execution times, the execution order of these sub-steps or stages can be flexibly configured according to needs, and the embodiments of the present application are not limited to this.

[0251] The above is only an optional implementation method for some implementation scenarios of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the solution of the present application, other similar implementation methods based on the technical ideas of the present application are also within the protection scope of the embodiments of the present application.

Claims

1. A method for optimizing the allocation of hospital medical resources, characterized in that: include: receiving medical resource usage data, wherein the medical resource usage data includes bed usage rate data and medical equipment usage data; Determine a first confusion vector, a second confusion vector, and a third confusion vector for medical resource allocation, each confusion vector comprising a plurality of random numbers; Based on the first confusion vector and the second confusion vector, performing confusion processing on the bed utilization rate data to obtain a first confusion matrix; Based on the second confusion vector and the third confusion vector, performing confusion processing on the medical device usage data to obtain a second confusion matrix; Sending the first confusion matrix and the second confusion matrix to a processing device; Receiving a calculation result returned by the calculation processing device; An optimized deployment scheme is obtained based on the first confusion vector, the second confusion vector, the third confusion vector and the calculation result.

2. The method according to claim 1, characterized in that The method further comprises: Obtain a first permutation vector, a second permutation vector, and a third permutation vector; Based on the first permutation vector and the second permutation vector, positionally transforming the bed utilization rate data to obtain a first intermediate matrix; Based on the second permutation vector and the third permutation vector, positionally transform the medical device usage data to obtain a second intermediate matrix; The step of performing confusion processing on the bed usage rate data based on the first confusion vector and the second confusion vector to obtain a first confusion matrix includes: performing confusion processing on the first intermediate matrix based on the first confusion vector and the second confusion vector to obtain a first confusion matrix; The method of performing confusion processing on the medical device usage data based on the second confusion vector and the third confusion vector to obtain a second confusion matrix includes: performing confusion processing on the second intermediate matrix based on the second confusion vector and the third confusion vector to obtain a second confusion matrix.

3. The method according to claim 2, characterized in that The obtaining of the first permutation vector, the second permutation vector and the third permutation vector comprises: Generate a first permutation vector, the first permutation vector comprising m different data elements, each data element being an integer from 1 to m; generating a second permutation vector, the second permutation vector comprising n different data elements, each data element being an integer from 1 to n; generating a third permutation vector, the third permutation vector comprising s different data elements, each data element being an integer from 1 to s; Among them, m is the number of rows of bed utilization data, n is the number of rows of medical equipment utilization data, and s is the number of columns of medical equipment utilization data.

4. The method according to claim 1, characterized in that: The method further comprises: Selecting the maximum absolute value from the bed utilization rate data and the medical equipment utilization data; determining a value L based on the maximum absolute value; Determine the upper limit and lower limit of the real number range according to the value L; The random numbers included in the first obfuscation vector, the second obfuscation vector, and the third obfuscation vector are obtained by randomly selecting from the real number range.

5. The method according to claim 1, characterized in that The method also includes: before obfuscating the bed occupancy data, replacing the data element with a value of 0 in the bed occupancy data with a first non-zero real number; before obfuscating the medical device usage data, replacing the data element with a value of 0 in the medical device usage data with a second non-zero real number.

6. The method according to claim 1, characterized in that The method further comprises: Dynamically deploying medical resources based on the optimized deployment plan; Monitor the use of medical resources; When the usage of medical resources meets the preset conditions, the medical resource optimization allocation method is re-executed.

7. The method according to claim 6, characterized in that The preset conditions include: The bed occupancy rate exceeds the set bed occupancy threshold; and / or, The medical device utilization rate exceeds the set medical device utilization rate threshold; and / or, The medical staff workload exceeds the set medical staff workload threshold; and / or, The medical resource allocation cycle reaches a preset time threshold; and / or, Receive instructions for optimizing the allocation of medical resources.

8. The method according to claim 1, characterized in that The method further comprises: Establishing heterogeneous proxy nodes, wherein the heterogeneous proxy nodes include ward proxy nodes, emergency proxy nodes, operating room proxy nodes, and intensive care unit proxy nodes; Configure the priority rules for each heterogeneous proxy node; Based on the priority rules of the heterogeneous proxy nodes, the optimization deployment scheme is adjusted.

9. The method according to claim 8, characterized in that The adjusting the optimization deployment scheme based on the priority rule of the heterogeneous proxy nodes includes: Receive resource requests sent by heterogeneous proxy nodes; Adjusting the optimization allocation scheme according to the priority of the resource request; The adjusted optimization allocation plan is sent to the relevant heterogeneous proxy nodes.

10. A device for optimizing and allocating medical resources in a hospital, characterized in that: include: A receiving unit, configured to receive medical resource usage data, wherein the medical resource usage data includes bed usage rate data and medical equipment usage data; A processing unit, configured to determine a first confusion vector, a second confusion vector, and a third confusion vector for medical resource allocation, each confusion vector comprising a plurality of random numbers; and based on the first confusion vector and the second confusion vector, perform confusion processing on the bed utilization rate data to obtain a first confusion matrix; Based on the second confusion vector and the third confusion vector, performing confusion processing on the medical device usage data to obtain a second confusion matrix; A sending unit, configured to send the first confusion matrix and the second confusion matrix to a processing device; A monitoring unit, used to monitor the usage of medical resources and trigger the re-execution of optimal allocation of medical resources when the usage meets preset conditions; The receiving unit is further used to receive the operation result returned by the operation processing device; the processing unit is further used to obtain an optimized deployment plan based on the first confusion vector, the second confusion vector, the third confusion vector and the operation result.

Images