Clinical training resource intelligent distribution system and method based on big data
Through big data technology and whale algorithms, clinical training resources are intelligently allocated, the problem of resource waste in the existing technology is solved, and the rational allocation and effective utilization of resources are achieved.
Patent Information
- Application Number
- CN202411154454.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2024-12-03
AI Technical Summary
The allocation of existing clinical training resources has the problem of wasted resources because the doctor’s learning and investigation results do not match, resulting in unreasonable resource allocation.
The intelligent allocation system for clinical training resources based on big data is adopted. By collecting students' learning situation, calculating the comprehensive mastery level, clustering and grading, and using the whale algorithm to set training plans for each level to achieve intelligent allocation of resources.
The rational allocation of clinical training resources has been achieved, the accuracy and efficiency of allocation results have been improved, and the effective utilization of resources has been ensured.
Smart Images

Figure CN119069099A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of resource management, and in particular to a clinical training resource intelligent allocation system and method based on big data. Background Art
[0002] With the continuous advancement and development of microelectronics technology, ultrasound machines have been further miniaturized, making it possible for clinical physicians to screen patients for critical emergencies through ultrasound equipment. Rapid and accurate diagnostic methods can not only save the lives of critically ill patients, but also improve the subsequent management of patients. Therefore, training in this type of clinical technology has gradually been valued by people.
[0003] The existing allocation of clinical training resources is often done by doctors applying for corresponding courses in the system. After the doctors have completed all the courses, they are assessed and those who fail the assessment are re-taught, which easily leads to unnecessary waste of clinical training resources. Summary of the invention
[0004] 1. Technical issues to be resolved
[0005] In order to address the deficiencies in the background technology, the present invention proposes a clinical training resource intelligent allocation system and method based on big data. The system collects the mastery of various clinical technologies by all trainees, calculates the comprehensive mastery of clinical technologies according to the training weights of various clinical technologies, clusters the comprehensive mastery of clinical technologies of each trainee, grades each trainee according to the clustering results, and sets corresponding clinical technology training plans for each level.
[0006] (II) Technical solution
[0007] A method for intelligent allocation of clinical training resources based on big data, the method comprising the following steps:
[0008] S1. Setting a clinical technology category set and a clinical training trainee set, collecting the learning situation of each clinical training trainee in the clinical technology category set for each clinical technology in the clinical technology category set, and setting a clinical technology mastery degree data matrix according to the learning situation;
[0009] S2. According to the clinical technology category set, a corresponding clinical technology training weight set is set, and based on the clinical technology training weight set and the clinical technology mastery degree data matrix, the comprehensive clinical technology mastery degree of each clinical trainee is calculated to obtain a clinical technology comprehensive mastery degree data set;
[0010] S3, clustering the clinical technology comprehensive mastery degree data set to obtain a clinical technology training level set, dividing it according to the clinical technology training level of each clinical trainee, and obtaining a clinical trainee grading matrix;
[0011] S4. Setting corresponding clinical technology training plans for each clinical technology training level through intelligent optimization algorithm;
[0012] S5. Assign corresponding clinical technical training plans to each clinical trainee in the clinical trainee grading matrix according to the clinical technical training level.
[0013] The learning status of each clinical trainee in the clinical training center for various clinical technologies is collected to set up a clinical technology mastery data matrix, and the mastery of each trainee for various clinical technologies is accurately analyzed; the comprehensive clinical technology mastery of each clinical trainee is calculated based on the set clinical technology training weight set and the clinical technology mastery data matrix to ensure the accuracy of the calculation results and provide a data basis for subsequent operations; the comprehensive clinical technology mastery data set is clustered, and the trainees are graded according to the clustering results to ensure the accuracy of the grading results; the corresponding clinical technology training plan is set for each clinical technology training level in the clinical technology training level center through the whale algorithm, the behavior of humpback whales surrounding prey, preying with bubble nets and searching for prey is simulated, and a mathematical model is constructed to ensure the speed and accuracy of the optimization process, while improving the efficiency of the convergence process; the corresponding clinical technology training plan is assigned to each trainee according to the clinical technology training level, to achieve intelligent allocation of clinical training resources and ensure the rationality of the allocation results.
[0014] Preferably, a clinical technology category set and a clinical trainee set are set, and the learning situation of each clinical trainee in the clinical training trainee set for each clinical technology in the clinical technology category set is collected. The specific steps of setting a clinical technology mastery degree data matrix according to the learning situation are as follows:
[0015] S11. Set clinical technology category set A = {a1, a2, ..., a i , …, a k}, where a i represents the i-th category of clinical technology, and k represents the total number of clinical technology categories;
[0016] S12, set the clinical training trainee set B = {b1, b2, ..., b i , …, b l}, where b i represents the ith clinical trainee, l represents the total number of clinical trainees;
[0017] S13, collect the clinical training trainee set A = {a1, a2, ..., a i , …, a k Each clinical trainee in the clinical training class has a clinical technology category set B = {b1, b2, ..., b i, …, b l}, and the clinical technology mastery degree data matrix C is set according to the learning situation as follows:
[0018]
[0019] Among them, c ij Represents the mastery level of the j-th clinical technology by the i-th clinical trainee.
[0020] Collect data on clinical training trainees’ learning status of various clinical technologies and set up a clinical technology mastery data matrix to accurately analyze each trainee’s mastery of various clinical technologies.
[0021] Preferably, the corresponding clinical technology training weight set is set according to the clinical technology category set, and the comprehensive clinical technology mastery level of each clinical trainee is calculated based on the clinical technology training weight set and the clinical technology mastery level data matrix. The specific steps for obtaining the clinical technology comprehensive mastery level data set are as follows:
[0022] S21, according to the clinical technology category set A = {a1, a2, ..., a i , …, a k} Set the corresponding clinical technology training weight set A′={a′1,a′2,…,a′ i ,…,a′ k}, where a′ i represents the training weight of the i-th clinical technology;
[0023] S22, based on the clinical technology training weight set A′={a′1,a′2,…,a′ i ,…,a′ k} and the clinical technology mastery degree data matrix C are used to calculate the comprehensive clinical technology mastery degree of each clinical training trainee; the calculation formula is as follows:
[0024] d i =a′1·c i1 +a′2·c i2 +…+a′ i ·c ij +…+a′ k ·c ik
[0025] Among them, d i It represents the comprehensive mastery of clinical technology of the i-th clinical trainee;
[0026] S23, collect the calculation results of the comprehensive mastery of clinical technology of all clinical trainees, and establish a clinical technology comprehensive mastery data set E = {e1, e2, ..., e i,…,e l}, where e i Represents the comprehensive mastery of clinical technology data of the i-th clinical training trainee.
[0027] Based on the set clinical technology training weight set and clinical technology mastery data matrix, the comprehensive clinical technology mastery level of each clinical trainee is calculated to ensure the accuracy of the calculation results and provide a data basis for subsequent operations.
[0028] Preferably, clustering the clinical technology comprehensive mastery degree data set to obtain a clinical technology training level set, dividing the clinical technology training level of each clinical trainee to obtain a clinical trainee grading matrix is performed as follows:
[0029] S31, clinical technology comprehensive mastery level data set E = {e1, e2, ..., e i ,…,e l} as a cluster, calculate the Euclidean distance between clusters, and obtain a distance matrix; find two clusters with the closest Euclidean distance from the distance matrix and merge them into a new cluster, and calculate the Euclidean distance between the new cluster and other clusters;
[0030] Repeat the above operation until the Euclidean distance between each cluster obtained after clustering is greater than the set Euclidean distance threshold, then stop clustering, and set the corresponding clinical technology training level set F = {f1, f2, ..., f i , …, f p}, where f i represents the i-th clinical technology training level, and p represents the total number of clinical technology training levels;
[0031] S32, classifying each clinical training trainee into a clinical technical training level of a clinical technical training level set, and obtaining a clinical training trainee classification matrix H as follows:
[0032]
[0033] Among them, h ij represents the jth clinical trainee in the i-th clinical technical training level, h i Represents the total number of clinical trainees in the i-th clinical technology training level.
[0034] The clinical technology comprehensive mastery data set is clustered and trainees are graded according to the clustering results to ensure the accuracy of the grading results.
[0035] Preferably, the specific steps of setting a corresponding clinical technology training program for each clinical technology training level in the clinical technology training level set by using an intelligent optimization algorithm are as follows:
[0036] S41. Construct a whale population, set the population size of the whale population to Z, the dimension of the clinical technology training program search space to q, the current number of iterations to t, and the maximum number of iterations to t max ;
[0037] Initialize the initial position set X of the whale population = {x1, x2, ..., x i , …, x z}, where x i represents the initial position of the i-th whale individual;
[0038] S42. Calculate the fitness function value of each individual whale in the whale population, take the individual whale with the highest fitness function value as the current optimal solution, and record the position of the current optimal solution; the fitness function formula is as follows:
[0039]
[0040] Among them, Fit(x i ) represents the fitness function value of the i-th whale individual, x i represents the ability of the i-th whale individual to help trainees understand clinical techniques, and η represents the correction value;
[0041] S43, start iteration and calculate convergence factor Update the coefficient vectors M and N according to the calculated convergence factor; the update formula is as follows:
[0042]
[0043] Among them, rand1 and rand2 both represent random numbers between [0, 1];
[0044] S44, when |M| < 1, the individual whales in the whale population randomly select one of the two methods, shrinking and encircling and spiral swimming, to update their positions;
[0045] S441. Contraction and encirclement is to update the position of the whale by identifying the location of the prey and encircling it, and to build a mathematical model; the formula is as follows:
[0046]
[0047] Among them, P represents the distance between the current whale individual and the optimal whale individual, M and N represent coefficient vectors, and X *(t) represents the position of the current optimal solution, X(t) and X(t+1) represent the position of the individual whale in the t-th and t+1-th iterations, respectively;
[0048] S442. Spiral swimming is a mathematical model that updates the position of a whale by shrinking its encirclement while moving in a spiral upward. The formula is as follows:
[0049]
[0050] Wherein, b represents the constant coefficient defining the shape of the spiral curve, and rand3 represents a random number between (-1, 1);
[0051] S45, when |M|≥1, the individual whale randomly selects a whale individual from the whale population as the target optimal solution, and updates its position by shrinking and surrounding;
[0052] S46. When all whale individuals have completed the position update, recalculate the fitness function value of each whale in the updated whale population, take the whale individual with the highest fitness function value as the current optimal solution, and record the position of the current optimal solution;
[0053] S47, determine whether the current number of iterations t reaches the maximum number of iterations t max If it is not reached, the current iteration number t is increased by 1, and the process returns to S43; if it is reached, the current optimal solution is taken as the global optimal solution, and the clinical technology training plan corresponding to the global optimal solution is output.
[0054] The whale algorithm is used to set corresponding clinical technical training plans for each clinical technical training level, simulate the behaviors of humpback whales surrounding prey, hunting with bubble nets and searching for prey, and construct a mathematical model to ensure the speed and accuracy of the optimization process, while improving the efficiency of the convergence process.
[0055] Preferably, the specific steps of allocating corresponding clinical technology training programs to each clinical training trainee in the clinical training trainee grading matrix according to the clinical technology training level are as follows:
[0056] S51. Set a threshold g for the number of clinical technical trainees in a single clinical technical training. When allocating clinical training resources to clinical trainees at each clinical technical training level, if the number of clinical trainees at that clinical technical training level is less than or equal to the threshold g for the number of clinical technical training at a single time, then the clinical technical training plan of the corresponding clinical technical training level will be allocated to the clinical trainees at that clinical technical training level; otherwise, g clinical trainees will be randomly selected from the clinical trainees at that clinical technical training level, and the clinical technical training plan of the corresponding clinical technical training level will be allocated to all the selected clinical trainees.
[0057] Assign corresponding clinical technology training plans to each trainee according to their clinical technology training level, realize the intelligent allocation of clinical training resources and ensure the rationality of the allocation results.
[0058] The present invention also discloses a system for a clinical training resource intelligent allocation method based on big data, comprising a data acquisition module, a clinical technology comprehensive mastery degree calculation module, a clustering module, a clinical technology training program setting module, and a clinical training resource allocation module;
[0059] The data collection module sets a clinical technology mastery degree data matrix by collecting the learning status of each clinical training trainee on various clinical technologies;
[0060] The clinical technology comprehensive mastery degree calculation module calculates the clinical technology comprehensive mastery degree of each clinical training trainee based on the set clinical technology training weight set and the clinical technology mastery degree data matrix to obtain a clinical technology comprehensive mastery degree data set;
[0061] The clustering module clusters the clinical technology comprehensive mastery degree data set to obtain a clinical technology training level set, and divides the clinical training trainees according to their clinical technology training levels to obtain a clinical training trainee grading matrix;
[0062] The clinical technology training program setting module sets corresponding clinical technology training programs for each clinical technology training level in the clinical technology training level set through a whale algorithm;
[0063] The clinical training resource allocation module allocates corresponding clinical technical training plans to each clinical training trainee in the clinical training trainee grading matrix according to the clinical technical training level.
[0064] (III) Beneficial effects
[0065] The present invention provides a clinical training resource intelligent allocation system and method based on big data, which has the following beneficial effects:
[0066] 1. The present invention is provided with a data acquisition module, a clinical technology comprehensive mastery degree calculation module, a clustering module, a clinical technology training program setting module and a clinical training resource allocation module; collects the learning situation of each clinical training trainee for various clinical technologies to set a clinical technology mastery degree data matrix, and accurately analyzes the mastery degree of each trainee for various clinical technologies; calculates the clinical technology comprehensive mastery degree of each clinical training trainee based on the set clinical technology training weight set and the clinical technology mastery degree data matrix, ensures the accuracy of the calculation results, and provides a data basis for subsequent operations; clusters the clinical technology comprehensive mastery degree data set, and classifies the trainees according to the clustering results to ensure the accuracy of the classification results; allocates the corresponding clinical technology training program to each trainee according to the clinical technology training level, realizes the intelligent allocation of clinical training resources, and ensures the rationality of the allocation results;
[0067] 2. Through the whale algorithm, corresponding clinical technical training plans are set for each clinical technical training level, simulating the behavior of humpback whales surrounding prey, bubble net hunting and searching for prey, and constructing a mathematical model to ensure the speed and accuracy of the optimization process, while improving the efficiency of the convergence process. BRIEF DESCRIPTION OF THE DRAWINGS
[0068] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.
[0069] Figure 1 A flowchart of a method for intelligent allocation of clinical training resources based on big data provided by the present invention;
[0070] Figure 2 A module schematic diagram of a system for an intelligent allocation method of clinical training resources based on big data provided by the present invention. DETAILED DESCRIPTION
[0071] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0072] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.
[0073] The first embodiment of the clinical training resource intelligent allocation system and method based on big data is as follows:
[0074] See also Figure 1 , a clinical training resource intelligent allocation method based on big data, comprising the following steps:
[0075] S1. Setting a clinical technology category set and a clinical training trainee set, collecting the learning situation of each clinical training trainee in the clinical technology category set for each clinical technology in the clinical technology category set, and setting a clinical technology mastery degree data matrix according to the learning situation;
[0076] S11. Set clinical technology category set A = {a1, a2, ..., a i , …, a k}, where a i represents the i-th category of clinical technology, and k represents the total number of clinical technology categories;
[0077] S12, set the clinical training trainee set B = {b1, b2, ..., b i , …, b l}, where b i represents the ith clinical trainee, l represents the total number of clinical trainees;
[0078] S13, collect the clinical training trainee set A = {a1, a2, ..., a i , …, a k Each clinical trainee in the clinical training class has a clinical technology category set B = {b1, b2, ..., b i , …, b l}, and the clinical technology mastery degree data matrix C is set according to the learning situation as follows:
[0079]
[0080] Among them, c ij Represents the mastery level of the j-th clinical technology by the i-th clinical trainee.
[0081] S2. According to the clinical technology category set, a corresponding clinical technology training weight set is set, and based on the clinical technology training weight set and the clinical technology mastery degree data matrix, the comprehensive clinical technology mastery degree of each clinical trainee is calculated to obtain a clinical technology comprehensive mastery degree data set;
[0082] S21, according to the clinical technology category set A = {a1, a2, ..., a i , …, a k} Set the corresponding clinical technology training weight set A′={a′1,a′2,…,a′ i ,…,a′ k}, where a′ i represents the training weight of the i-th clinical technology;
[0083] S22, based on the clinical technology training weight set A′={a′1,a′2,…,a′ i ,…,a′ k} and the clinical technology mastery degree data matrix C are used to calculate the comprehensive clinical technology mastery degree of each clinical training trainee; the calculation formula is as follows:
[0084] d i =a′1·c i1 +a′2·c i2 +…+a′ i ·c ij +…+a′ k ·c ik
[0085] Among them, d i It represents the comprehensive mastery of clinical technology of the i-th clinical trainee;
[0086] S23, collect the calculation results of the comprehensive mastery of clinical technology of all clinical trainees, and establish a clinical technology comprehensive mastery data set E = {e1, e2, ..., e i ,…,e l}, where e i Represents the comprehensive mastery of clinical technology data of the i-th clinical training trainee.
[0087] S3, clustering the clinical technology comprehensive mastery degree data set to obtain a clinical technology training level set, dividing it according to the clinical technology training level of each clinical trainee, and obtaining a clinical trainee grading matrix;
[0088] S31, clinical technology comprehensive mastery level data set E = {e1, e2, ..., e i ,…,e l} as a cluster, calculate the Euclidean distance between clusters, and obtain a distance matrix; find two clusters with the closest Euclidean distance from the distance matrix and merge them into a new cluster, and calculate the Euclidean distance between the new cluster and other clusters;
[0089] Repeat the above operation until the Euclidean distance between each cluster obtained after clustering is greater than the set Euclidean distance threshold, then stop clustering, and set the corresponding clinical technology training level set F = {f1, f2, ..., f i , …, f p}, where f i represents the i-th clinical technology training level, and p represents the total number of clinical technology training levels;
[0090] S32, classifying each clinical training trainee into a clinical technical training level of a clinical technical training level set, and obtaining a clinical training trainee classification matrix H as follows:
[0091]
[0092] Among them, h ij represents the jth clinical trainee in the i-th clinical technical training level, h i Represents the total number of clinical trainees in the i-th clinical technology training level.
[0093] S4. Setting corresponding clinical technology training plans for each clinical technology training level through intelligent optimization algorithm;
[0094] S41. Construct a whale population, set the population size of the whale population to Z, the dimension of the clinical technology training program search space to q, the current number of iterations to t, and the maximum number of iterations to t max ;
[0095] Initialize the initial position set X of the whale population = {x1, x2, ..., x i , …, x z}, where x i represents the initial position of the i-th whale individual;
[0096] S42. Calculate the fitness function value of each individual whale in the whale population, take the individual whale with the highest fitness function value as the current optimal solution, and record the position of the current optimal solution; the fitness function formula is as follows:
[0097]
[0098] Among them, Fit(x i ) represents the fitness function value of the i-th whale individual, xi represents the ability of the i-th whale individual to help trainees understand clinical techniques, and η represents the correction value;
[0099] S43, start iteration and calculate convergence factor Update the coefficient vectors M and N according to the calculated convergence factor; the update formula is as follows:
[0100]
[0101] Among them, rand1 and rand2 both represent random numbers between [0, 1];
[0102] S44, when |M| < 1, the individual whales in the whale population randomly select one of the two methods, shrinking and encircling and spiral swimming, to update their positions;
[0103] S441. Contraction and encirclement is to update the position of the whale by identifying the location of the prey and encircling it, and to build a mathematical model; the formula is as follows:
[0104]
[0105] Among them, P represents the distance between the current whale individual and the optimal whale individual, M and N represent coefficient vectors, and X * (t) represents the position of the current optimal solution, X(t) and X(t+1) represent the position of the individual whale in the t-th and t+1-th iterations, respectively;
[0106] S442. Spiral swimming is a mathematical model that updates the position of a whale by shrinking its encirclement while moving in a spiral upward. The formula is as follows:
[0107]
[0108] Wherein, b represents the constant coefficient defining the shape of the spiral curve, and rand3 represents a random number between (-1, 1);
[0109] S45, when |M|≥1, the individual whale randomly selects a whale individual from the whale population as the target optimal solution, and updates its position by shrinking and surrounding;
[0110] S46. When all whale individuals have completed the position update, recalculate the fitness function value of each whale in the updated whale population, take the whale individual with the highest fitness function value as the current optimal solution, and record the position of the current optimal solution;
[0111] S47. Determine whether the current number of iterations t reaches the maximum number of iterations tmax. If not, add 1 to the current number of iterations t and return to S43. If reached, take the current optimal solution as the global optimal solution and output the clinical technology training plan corresponding to the global optimal solution.
[0112] S5. Allocate corresponding clinical technology training plans to each clinical trainee in the clinical trainee grading matrix according to the clinical technology training level;
[0113] S51. Set a threshold g for the number of clinical technical trainees in a single clinical technical training. When allocating clinical training resources to clinical trainees at each clinical technical training level, if the number of clinical trainees at that clinical technical training level is less than or equal to the threshold g for the number of clinical technical training at a single time, then the clinical technical training plan of the corresponding clinical technical training level will be allocated to the clinical trainees at that clinical technical training level; otherwise, g clinical trainees will be randomly selected from the clinical trainees at that clinical technical training level, and the clinical technical training plan of the corresponding clinical technical training level will be allocated to all the selected clinical trainees.
[0114] 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 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.
[0115] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.
Claims
1. A method for intelligent allocation of clinical training resources based on big data, characterized in that: The steps include: S1. Setting a clinical technology category set and a clinical training trainee set, collecting the learning situation of each clinical training trainee in the clinical technology category set for each clinical technology in the clinical technology category set, and setting a clinical technology mastery degree data matrix according to the learning situation; S2. According to the clinical technology category set, a corresponding clinical technology training weight set is set, and based on the clinical technology training weight set and the clinical technology mastery degree data matrix, the comprehensive clinical technology mastery degree of each clinical trainee is calculated to obtain a clinical technology comprehensive mastery degree data set; S3, clustering the clinical technology comprehensive mastery degree data set to obtain a clinical technology training level set, dividing it according to the clinical technology training level of each clinical trainee, and obtaining a clinical trainee grading matrix; S4. Setting corresponding clinical technology training plans for each clinical technology training level through intelligent optimization algorithm; S5. Assign corresponding clinical technical training plans to each clinical trainee in the clinical trainee grading matrix according to the clinical technical training level.
2. According to the big data-based intelligent allocation method for clinical training resources according to claim 1, it is characterized in that: The S1 comprises the following steps: S11. Set clinical technology category set A = {a1, a2, ..., a i , …, a k }, where a i represents the i-th category of clinical technology, and k represents the total number of clinical technology categories; S12, set the clinical training trainee set B = {b1, b2, ..., b i , …, b l }, where b i represents the ith clinical trainee, l represents the total number of clinical trainees; S13, collect the clinical training trainee set A = {a1, a2, ..., a i , …, a k Each clinical trainee in the clinical training class has a clinical technology category set B = {b1, b2, ..., b i , …, b l }, and set the clinical technology mastery degree data matrix C according to the learning situation of various clinical technologies.
3. According to the big data-based intelligent allocation method for clinical training resources according to claim 2, it is characterized in that: The S2 comprises the following steps: S21, according to the clinical technology category set A = {a1, a2, ..., a i , …, a k } Set the corresponding clinical technology training weight set A′={a′1,a′2,…,a′ i ,…,a′ k }, where a′ i represents the training weight of the i-th clinical technology; S22. Calculate the comprehensive mastery of clinical skills of each clinical training trainee; S23, collect the calculation results of the comprehensive mastery of clinical technology of all clinical trainees, and establish a clinical technology comprehensive mastery data set E = {e1, e2, ..., e i ,…,e i }, where e i Represents the comprehensive mastery of clinical technology data of the i-th clinical training trainee.
4. According to the big data-based clinical training resource intelligent allocation method of claim 3, it is characterized in that: The calculation of the comprehensive mastery of clinical skills of each clinical trainee in S22 includes the following steps: Based on the clinical technology training weight set A′={a′1,a′2,…,a′ i ,…,a′ k } and the clinical technology mastery data matrix C; the calculation formula is as follows: d i =a′1·c i1 +a′2·c i2 +…+a′ i ·c ij +…+a′ k ·c ik Among them, d i Represents the comprehensive mastery of clinical technology by the i-th clinical trainee.
5. According to the big data-based intelligent allocation method for clinical training resources according to claim 4, it is characterized in that: The S3 comprises the following steps: S31, clinical technology comprehensive mastery level data set E = {e1, e2, ..., e i ,…,e i } as a cluster, calculate the Euclidean distance between clusters, and obtain a distance matrix; find two clusters with the closest Euclidean distance from the distance matrix and merge them into a new cluster, and calculate the Euclidean distance between the new cluster and other clusters; Repeat the above operation until the Euclidean distance between each cluster obtained after clustering is greater than the set Euclidean distance threshold, then stop clustering, and set the corresponding clinical technology training level set F = {f1, f2, ..., f i , …, f p }, where f i represents the i-th clinical technology training level, and p represents the total number of clinical technology training levels; S32. Classify each clinical training trainee into a clinical technical training level of a clinical technical training level set to obtain a clinical training trainee grading matrix H.
6. The method for intelligent allocation of clinical training resources based on big data according to claim 5, characterized in that: The S4 comprises the following steps: S41, construct a whale population, set the population size of the whale population to Z, the dimension of the clinical technology training program search space to q, the current number of iterations to t, and the maximum number of iterations to t; Initialize the initial position set X of the whale population = {x1, x2, ..., x i , …, x z }, where x i represents the initial position of the i-th whale individual; S42. Calculate the fitness function value of each individual whale in the whale population, take the individual whale with the highest fitness function value as the current optimal solution, and record the position of the current optimal solution; the fitness function formula is as follows: Among them, Fit(x i ) represents the fitness function value of the i-th whale individual, x i represents the ability of the i-th whale individual to help trainees understand clinical techniques, and η represents the correction value; S43, start iteration and calculate convergence factor Update the coefficient vectors M and N according to the calculated convergence factor; the update formula is as follows: Among them, rand1 and rand2 both represent random numbers between [0, 1]; S44, when |M| < 1, the individual whales in the whale population randomly select one of the two methods, shrinking and encircling and spiral swimming, to update their positions; S45. When |M|≥1, the individual whale randomly selects a whale from the whale population as the target optimal solution, and updates its position by shrinking and surrounding; S46. When all whale individuals have completed the position update, recalculate the fitness function value of each whale in the updated whale population, take the whale individual with the highest fitness function value as the current optimal solution, and record the position of the current optimal solution; S47. Determine whether the current number of iterations t reaches the maximum number of iterations t. If not, add 1 to the current number of iterations t and return to S43. If reached, take the current optimal solution as the global optimal solution and output the clinical technology training plan corresponding to the global optimal solution.
7. The method for intelligent allocation of clinical training resources based on big data according to claim 6, characterized in that: The S44 comprises the following steps: S441. Contraction and encirclement is to update the position of the whale by identifying the location of the prey and encircling it, and to build a mathematical model; the formula is as follows: Among them, P represents the distance between the current whale individual and the optimal whale individual, M and N represent coefficient vectors, and X * (t) represents the position of the current optimal solution, X(t) and X(t+1) represent the position of the individual whale in the t-th and t+1-th iterations, respectively; S442. Spiral swimming is a mathematical model that updates the position of a whale by shrinking its encirclement while moving in a spiral upward. The formula is as follows: Wherein, b represents a constant coefficient defining the shape of the spiral curve, and rand3 represents a random number between (-1, 1).
8. The method for intelligent allocation of clinical training resources based on big data according to claim 7, characterized in that: The S5 comprises the following steps: S51. Set a threshold g for the number of people participating in a single clinical technical training, and allocate clinical training resources to each clinical training trainee according to the clinical technical training level.
9. The method for intelligent allocation of clinical training resources based on big data according to claim 8, characterized in that: The allocation of clinical training resources to each clinical training trainee in S51 includes the following steps: If the number of clinical trainees at this clinical technical training level is less than or equal to the threshold number g of single clinical technical training, the clinical technical training plan of the corresponding clinical technical training level will be allocated to the clinical trainees at this clinical technical training level; otherwise, g clinical trainees will be randomly selected from the clinical trainees at this clinical technical training level, and the clinical technical training plan of the corresponding clinical technical training level will be allocated to all the selected clinical trainees.
10. A system for implementing the big data-based intelligent allocation method for clinical training resources as described in any one of claims 1 to 9, comprising a data acquisition module, a clinical technology comprehensive mastery degree calculation module, a clustering module, a clinical technology training program setting module, and a clinical training resource allocation module; The data collection module sets a clinical technology mastery degree data matrix by collecting the learning status of each clinical training trainee on various clinical technologies; The clinical technology comprehensive mastery degree calculation module calculates the clinical technology comprehensive mastery degree of each clinical training trainee based on the set clinical technology training weight set and the clinical technology mastery degree data matrix to obtain a clinical technology comprehensive mastery degree data set; The clustering module clusters the clinical technology comprehensive mastery degree data set to obtain a clinical technology training level set, and divides the clinical training trainees according to their clinical technology training levels to obtain a clinical training trainee grading matrix; The clinical technology training program setting module sets corresponding clinical technology training programs for each clinical technology training level in the clinical technology training level set through a whale algorithm; The clinical training resource allocation module allocates corresponding clinical technical training plans to each clinical training trainee in the clinical training trainee grading matrix according to the clinical technical training level.
