Anesthetic doctor scheduling task allocation method based on big data

Abstract

The invention discloses an anesthetist scheduling task allocation method based on big data. The anesthetist scheduling task allocation method comprises the following steps: acquiring an anesthesia operation speed sequence of each anesthetist for each operation type in a target period; according to the anesthesia operation speed sequence, calculating an anesthesia operation speed mean value of each anesthetist for each operation type, and removing abnormal data which deviates from the mean value and exceeds a threshold value; determining the historical work intensity of each anesthetist for each operation type based on the corrected rate sequence; obtaining current existing operation reservation data, and calculating the anesthesia priority of each operation type at each anesthetist; and constructing an objective function of a simulated annealing algorithm, and through iterative optimization of the simulated annealing algorithm, determining the type of the anesthetist in charge of the next anesthesia operation. In combination with the current real-time operation appointment data, the anesthesia priorities of various operations at different doctors are recalculated, and dynamic response and real-time adjustment of the scheduling scheme to actual demands are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of big data, and in particular to a method for allocating anesthesiologist scheduling tasks based on big data. Background Art

[0002] Scheduling anesthesiologists in operating rooms is a critical and complex task in modern hospital management. Traditional scheduling methods rely primarily on experience and manually formulated rules, such as assigning anesthesiologists based on their title, level, shift schedule, and estimated surgical volume. Due to a lack of systematic data analysis, scheduling results often suffer from the following deficiencies: 1. Inefficiency: During peak periods or when the number of surgeries increases suddenly, task allocation cannot be adjusted in a timely manner, resulting in some anesthesiologists being overly busy and others under-worked.

[0003] 2. Lack of fairness: Scheduling often relies on subjective judgment and cannot accurately quantify the actual work capabilities and surgical ratios of different physicians, which easily leads to uneven task distribution among physicians.

[0004] 3. Lack of dynamic adjustment capabilities: Due to the large differences in the complexity of various surgeries and the required anesthesia time, and the fact that appointment data changes at any time, the traditional static scheduling model is difficult to adapt to real-time needs.

[0005] 4. Difficulty in eliminating abnormal data interference: In the operation speed recorded in big data, there may be occasional abnormal values ​​(such as extreme operation duration, sudden interruption, etc.). If directly used for decision-making, it will affect the scheduling effect.

[0006] With the development of medical information technology and big data technology, quantitative assessments of anesthesiologists' actual performance can be achieved through analysis of historical surgical and anesthesia operation data. However, there is currently a lack of anesthesiologist scheduling methods based on big data that combine outlier filtering with dynamic optimization algorithms. How to leverage the individual physician's operating speed characteristics for different surgical types, combined with real-time appointment data, and using advanced optimization algorithms to accurately and efficiently schedule patients remains an urgent challenge in this field. Summary of the Invention

[0007] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0008] In view of the above-mentioned problems existing in the existing big data-based anesthesiologist scheduling task allocation method, the present invention is proposed.

[0009] Therefore, the purpose of the present invention is to provide an anesthesiologist scheduling task allocation method based on big data, which combines the current real-time surgery reservation data to recalculate the anesthesia priority of various types of surgeries at different physicians, thereby realizing the dynamic response and real-time adjustment of the scheduling plan to actual needs.

[0010] To solve the above technical problems, the present invention provides the following technical solution: a method for allocating anesthesiologist scheduling tasks based on big data, comprising: Obtain the anesthetic operation speed sequence of each anesthesiologist for each surgical type within the target cycle; The mean anesthesia operation rate of each anesthesiologist for each type of surgery was calculated based on the anesthesia operation speed sequence, and the anesthesia operation rate that deviated from the mean by more than the threshold was eliminated. Abnormal data is used to form a corrected rate series; The historical workload intensity of each anesthesiologist for each procedure type was determined based on the modified rate series; Obtain the current existing surgical appointment data and calculate the anesthesia priority of each surgical type for each anesthesiologist; The objective function of the simulated annealing algorithm is constructed, and the optimal scheduling vector is obtained through iterative optimization of the simulated annealing algorithm to determine the type of anesthesia surgery that the anesthesiologist will be responsible for next time.

[0011] As a preferred solution of the anesthesiologist scheduling task allocation method based on big data of the present invention, the anesthesia operation speed sequence formula is: ,in Indicates the anesthesiologist number, Indicates the operation type number, Indicates the Anesthesia operation speed; anesthesia operation speed The calculation formula is:

[0012] Type of surgery The standard duration of anesthesia, The actual anesthesia duration.

[0013] As a preferred solution of the anesthesiologist scheduling task allocation method based on big data of the present invention, the average anesthesia operation rate is:

[0014] The threshold ,in is the preset scale factor and , the corrected rate sequence is expressed as .

[0015] As a preferred solution of the anesthesiologist scheduling task allocation method based on big data of the present invention, the historical work intensity formula is:

[0016] in, is the rate standard deviation, and is the weighting coefficient, and ; The historical work intensity must also meet the constraints: , then Perform truncation processing, ,in , is the preset upper limit coefficient, and .

[0017] As a preferred solution of the anesthesiologist scheduling task allocation method based on big data of the present invention, the anesthesia priority is calculated as follows:

[0018] in, Type of surgery The emergency factor, To adjust the weight; The anesthesia priority The calculation also includes the following judgments: like and , then force the setting ,in is the high emergency threshold, is the minimum density threshold; and The value satisfies , ,in , .

[0019] As a preferred solution of the anesthesiologist scheduling task allocation method based on big data of the present invention, the urgency coefficient The value of is: dynamically adjusted according to the surgical risk level and appointment waiting time to meet ,in Score the risk level. is the normalized value of waiting time, is the weight and .

[0020] As a preferred solution of the anesthesiologist scheduling task allocation method based on big data of the present invention, the objective function of the annealing algorithm is:

[0021] in: is the scheduling decision variable, The maximum workload of anesthesiologists. is the penalty coefficient.

[0022] As a preferred solution of the anesthesiologist scheduling task allocation method based on big data described in the present invention, wherein: the simulated annealing algorithm is used to iteratively optimize , when continuous The energy change of iterations is lower than the threshold or the temperature drops to the threshold Terminate when , output the optimal scheduling vector , determine the type of surgery the anesthesiologist will be responsible for next time, where the temperature reduction strategy is: , is the attenuation rate coefficient and .

[0023] As a preferred solution of the method for allocating anesthesiologists' scheduling tasks based on big data described in the present invention, the threshold and The value of ,in is the proportionality coefficient and .

[0024] As a preferred solution of the big data-based anesthesiologist scheduling task allocation method of the present invention, the output of the optimal scheduling vector must meet the global constraint conditions: The total number of shifts per anesthesiologist shall not exceed ; The anesthesia task allocation for each type of surgery is not less than its scheduled amount times, of which .

[0025] Beneficial effects of the present invention: 1. Based on big data analysis, we analyze the historical operation rates of each anesthesiologist for different surgical types to obtain objective mean indicators. We then eliminate outliers to ensure data accuracy, thereby achieving accurate quantification of the physician's actual work ability. 2. Combined with current real-time surgical appointment data, the system recalculates the anesthesia priority of various surgeries at different physicians, enabling the scheduling plan to dynamically respond to actual needs and make real-time adjustments. 3. Using the simulated annealing algorithm to construct the objective function and optimize the scheduling vector in multiple iterations can effectively escape the local optimum and obtain the global approximate optimal solution, thereby ensuring the overall efficiency and fairness of the allocation plan; 4. The combination of eliminating outliers and adopting advanced optimization algorithms makes scheduling decisions more robust and stable, reducing the risk of scheduling errors caused by data noise. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them: Figure 1 The figure is a flow chart of the method for allocating anesthesiologist scheduling tasks based on big data of the present invention. DETAILED DESCRIPTION

[0027] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0028] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0029] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0030] Furthermore, the present invention is described in detail with reference to schematic diagrams. For ease of illustration, when describing the embodiments of the present invention, cross-sectional views illustrating device structures may be partially enlarged and not to scale. Furthermore, the schematic diagrams are merely illustrative and should not limit the scope of protection of the present invention. Furthermore, in actual production, the three-dimensional dimensions of length, width, and depth should be included.

[0031] Reference Figure 1 , provides an anesthesiologist scheduling task allocation method based on big data, including: Obtain the anesthetic operation speed sequence of each anesthesiologist for each surgical type within the target cycle; The mean anesthesia operation rate of each anesthesiologist for each type of surgery was calculated based on the anesthesia operation speed sequence, and the anesthesia operation rate that deviated from the mean by more than the threshold was eliminated. Abnormal data is used to form a corrected rate series; The historical workload intensity of each anesthesiologist for each procedure type was determined based on the modified rate series; Obtain the current existing surgical appointment data and calculate the anesthesia priority of each surgical type for each anesthesiologist; The objective function of the simulated annealing algorithm is constructed, and the optimal scheduling vector is obtained through iterative optimization of the simulated annealing algorithm to determine the type of anesthesia surgery that the anesthesiologist will be responsible for next time.

[0032] Among them, the anesthesia operation speed sequence formula is: ,in Indicates the anesthesiologist number, Indicates the operation type number, Indicates the Anesthesia operation speed; anesthesia operation speed The calculation formula is:

[0033] Type of surgery The standard duration of anesthesia, The actual anesthesia duration.

[0034] Specifically, the average anesthesia operation rate is:

[0035] Threshold ,in is the preset scale factor and , the corrected rate sequence is expressed as .

[0036] Furthermore, the historical work intensity formula is:

[0037] in, is the rate standard deviation, and is the weighting coefficient, and ; The historical work intensity must also meet the constraints: if , then Perform truncation processing, ,in , is the preset upper limit coefficient, and .

[0038] Among them, the anesthesia priority is calculated as:

[0039] in, Type of surgery The emergency factor, To adjust the weight; Anesthesia priority The calculation also includes the following judgments: like and , then force the setting ,in is the high emergency threshold, is the minimum density threshold; and The value satisfies , ,in , .

[0040] Specifically, the emergency factor The value of is: dynamically adjusted according to the surgical risk level and appointment waiting time to meet ,in Score the risk level. is the normalized value of waiting time, is the weight and .

[0041] Among them, the objective function of the annealing algorithm is:

[0042] in: is the scheduling decision variable, The maximum workload of anesthesiologists. is the penalty coefficient.

[0043] Furthermore, the simulated annealing algorithm is used to iteratively optimize , when continuous The energy change of iterations is lower than the threshold or the temperature drops to the threshold Terminate when , output the optimal scheduling vector , determine the type of surgery the anesthesiologist will be responsible for next time, where the temperature reduction strategy is: , is the attenuation rate coefficient and ,Specific ,threshold and The value of ,in is the proportionality coefficient and .

[0044] Furthermore, the output of the optimal schedule vector must satisfy the global constraints: The total number of shifts per anesthesiologist shall not exceed ; The anesthesia task allocation for each type of surgery is not less than its scheduled amount times, of which .

[0045] Specific embodiments are as follows: Scene background: The anesthesiology department of a hospital needs to develop an anesthesia schedule for the next day's surgery. There are currently three anesthesiologists (i=1, 2, 3) and two types of surgery (j=1, 2), where: Surgery type 1 (j=1): cardiac surgery, standard anesthesia duration Minutes, emergency factor (high risk, short appointment wait time); Surgery type 2 (j=2): Orthopedic surgery, standard anesthesia duration Minutes, emergency factor ; Maximum workload of anesthesiologists , , (Unit: Taiwan / Day) Specific implementation process: Step 1: Obtain anesthesia operation speed sequence: Historical anesthesia speed sequence of physician 1 (i=1) for surgery type 1 (j=1) (Unit: surgery / hour); Speed ​​sequence of doctor 1 for surgery type 2 (j=2) ; The data of other doctors are generated similarly (simplified here, only taking doctor 1 as an example).

[0046] Step 2: Calculate the mean rate and remove abnormal data 1. Calculate the mean: ; .

[0047] 2. Eliminate abnormal data (set ,but ): for , , the data beyond [0.88,1.32] are removed; the original sequence has no anomalies, so .

[0048] for , , the data beyond [1.62,2.43] are removed; the original series are all within the range, so .

[0049] Step 3: Determine Historical Work Intensity 1. Calculate the standard deviation : ; .

[0050] 2. Computational Intensity (set up , ): ; .

[0051] 3. Truncation processing (setting ,but ): Assuming that all doctors ,but .

[0052] , no need to truncate; , also retained; Step 4: Calculate anesthesia priority 1. Set parameters , and calculate the global density ratio: Assume that the total intensity of all doctors for surgery 1 is , then the proportion of physician 1 is ; The proportion of emergency coefficient of operation 1 . 2. Calculation priority: ; Similarly calculate other .

[0053] 3. Threshold judgment (setting , ,but , ): If a surgery And corresponding ,but .

[0054] For example, a doctor , they are prohibited from participating in high-emergency operations.

[0055] Step 5: Construct the objective function Objective function :set up ; Step 6: Simulated annealing optimization: Initialization temperature , attenuation coefficient , termination condition 10, =1; Iterative process: Randomly generate initial solutions (such as allocation schemes ); Calculation Energy ; Temperature drop: ; Output the optimal solution at termination ,satisfy And the surgical allocation volume meets the standards.

[0056] Final scheduling results: Anesthesiologist 1 was responsible for 2 cardiac surgeries (j=1); Anesthesiologist 2 is responsible for 1 cardiac surgery; Anesthesiologist 3 was responsible for 3 orthopedic surgeries (j=2).

[0057] This plan prioritizes assigning high-emergency surgeries to physicians with high density, while balancing the overall workload and meeting actual needs.

[0058] The present invention analyzes the historical operation rate of each anesthesiologist for different types of surgeries based on big data to obtain an objective mean indicator, and ensures the accuracy of the data by eliminating outliers, thereby achieving accurate quantification of the physician's actual work ability; combined with the current real-time surgery appointment data, the anesthesia priority of various types of surgeries at different physicians is recalculated, realizing the dynamic response and real-time adjustment of the scheduling plan to actual needs; the simulated annealing algorithm is used to construct the objective function, and the scheduling vector is optimized in multiple iterations, which can effectively jump out of the local optimum and obtain the global approximate optimal solution, thereby ensuring the overall efficiency and fairness of the allocation plan; the combination of eliminating outliers and adopting advanced optimization algorithms makes the scheduling decision more robust and stable, and reduces the risk of scheduling errors caused by data noise.

[0059] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for allocating anesthesiologists' scheduling tasks based on big data, characterized in that: include: Obtain the anesthetic operation speed sequence of each anesthesiologist for each surgical type within the target cycle; The mean anesthesia operation rate of each anesthesiologist for each type of surgery was calculated based on the anesthesia operation speed sequence, and the anesthesia operation rate that deviated from the mean by more than the threshold was eliminated. Abnormal data is used to form a corrected rate series; The historical workload intensity of each anesthesiologist for each procedure type was determined based on the modified rate series; Obtain the current existing surgical appointment data and calculate the anesthesia priority of each surgical type for each anesthesiologist; The objective function of the simulated annealing algorithm is constructed, and the optimal scheduling vector is obtained through iterative optimization of the simulated annealing algorithm to determine the type of anesthesia surgery that the anesthesiologist will be responsible for next time.

2. The method for allocating anesthesiologist scheduling tasks based on big data according to claim 1, characterized in that: The anesthesia operation speed sequence formula is: ,in Indicates the anesthesiologist number, Indicates the operation type number, Indicates the Anesthesia operation speed; anesthesia operation speed The calculation formula is: Type of surgery The standard duration of anesthesia, The actual anesthesia duration.

3. The method for allocating anesthesiologists' scheduling tasks based on big data according to claim 2, characterized in that: The mean anesthesia operation rate is: The threshold ,in is the preset scale factor and , the corrected rate sequence is expressed as .

4. The method for allocating anesthesiologist scheduling tasks based on big data according to claim 3, characterized in that: The historical work intensity formula is: in, is the rate standard deviation, and is the weighting coefficient, and ; The historical work intensity must also meet the constraints: , then Perform truncation processing, ,in , is the preset upper limit coefficient, and .

5. The method for allocating anesthesiologists' scheduling tasks based on big data according to claim 4, characterized in that: The anesthesia priority is calculated as: in, Type of surgery The emergency factor, To adjust the weight; The anesthesia priority The calculation also includes the following judgments: like and , then force the setting ,in is the high emergency threshold, is the minimum density threshold; and The value satisfies , ,in , .

6. The method for allocating anesthesiologists' scheduling tasks based on big data according to claim 5, characterized in that: The emergency factor The value of is: dynamically adjusted according to the surgical risk level and appointment waiting time to meet ,in Score the risk level. is the normalized value of waiting time, is the weight and .

7. The method for allocating anesthesiologists' scheduling tasks based on big data according to claim 6, characterized in that: The objective function of the annealing algorithm is: in: is the scheduling decision variable, The maximum workload of anesthesiologists. is the penalty coefficient.

8. The method for allocating anesthesiologists' scheduling tasks based on big data according to claim 7, characterized in that: Iterative optimization through simulated annealing algorithm , when continuous The energy change of iterations is lower than the threshold or the temperature drops to the threshold Terminate when , output the optimal scheduling vector , determine the type of surgery the anesthesiologist will be responsible for next time, where the temperature reduction strategy is: , is the attenuation rate coefficient and .

9. The method for allocating anesthesiologists' scheduling tasks based on big data according to claim 8, characterized in that: The threshold and The value of ,in is the proportionality coefficient and .

10. The method for allocating anesthesiologists' scheduling tasks based on big data according to claim 7, characterized in that: The output of the optimal schedule vector must satisfy the global constraints: The total number of shifts per anesthesiologist shall not exceed ; The anesthesia task allocation for each type of surgery is not less than its scheduled amount times, of which .

Images