CN116386813A

CN116386813A - Method, device, equipment and storage medium for balancing load between operations

Info

Publication number: CN116386813A
Application number: CN202310511095.2A
Authority: CN
Inventors: 赵伯羽; 高超; 罗奇
Original assignee: Suzhou Mehdi Houstton Medicalsystem Technology Co ltd
Current assignee: Suzhou Mehdi Houstton Medicalsystem Technology Co ltd
Priority date: 2023-05-08
Filing date: 2023-05-08
Publication date: 2023-07-04

Abstract

The invention discloses a load balancing method, device and equipment for an operation room and a storage medium. The method comprises the following steps: responding to the operation load balancing instruction, and determining whether the operation load of each operation room is balanced according to the operation schedule of each operation room; if not, determining at least one scheduling scheme based on the set load scheduling strategy under the condition that at least one overload operating room exists; determining the allocated duration of each surgical room corresponding to each scheduling scheme, and determining the discrete coefficient of each surgical room according to the allocated duration of each surgical room; and scheduling the partial operation of the at least one overload operating room to at least one scheduling scheme of the at least one light-load operating room by adopting a scheduling scheme corresponding to the minimum discrete coefficient so as to obtain the latest operation schedule of each operating room. Solves the problem that the load unbalance of the operation room easily occurs in the use process of the prior operation room, and improves the load balancing degree of the operation room, thereby improving the utilization rate of each operation room.

Description

Method, device, equipment and storage medium for balancing load between operations

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for load balancing between operations.

Background

The operating room is a high-cost and high-income hospital department. For doctors, the reasonable utilization of the operating room can reduce overtime, and meanwhile, for the manager of the hospital, how to reasonably and effectively allocate the resources of the operating room in the open time of the operating room, so that the method has important significance for improving the resource utilization rate of the operating room.

In the prior art, after the operation duration is predicted, the operation duration is directly added into a relatively idle operation room, and the problem of unbalanced load of the operation room is easy to occur.

Disclosure of Invention

The invention provides a load balancing method, device and equipment for an operation room and a storage medium, which are used for solving the problem that the load unbalance of the operation room easily occurs in the use process of the existing operation room.

According to an aspect of the present invention, there is provided a method of inter-operative load balancing, the method comprising:

responding to the operation load balancing instruction, and determining whether the operation load of each operation room is balanced according to the operation schedule of each operation room;

if not, determining at least one scheduling scheme for scheduling part of the at least one overload operating room to at least one light load operating room based on a set load scheduling strategy under the condition that at least one overload operating room exists, wherein the difference between the allocated time length corresponding to the overload operating room and the allocated time length corresponding to the light load operating room is larger than the predicted time length of the scheduled operation;

Determining the allocated duration of each surgical room corresponding to each scheduling scheme, and determining the discrete coefficient of each surgical room according to the allocated duration of each surgical room;

and scheduling the partial operation of the at least one overload operating room to at least one scheduling scheme of the at least one light-load operating room by adopting a scheduling scheme corresponding to the minimum discrete coefficient so as to obtain the latest operation schedule of each operating room.

According to another aspect of the present invention, there is provided an apparatus comprising:

the balancing instruction response module is used for responding to the operation load balancing instruction and determining whether the operation loads of all the operation rooms are balanced according to the operation schedule of all the operation rooms;

a scheduling scheme determining module, configured to determine, if not, that, in a case where at least one overload operating room exists, based on a set load scheduling policy, at least one scheduling scheme for scheduling a portion of the at least one overload operating room to at least one light load operating room, a difference between an allocated duration corresponding to the overload operating room and an allocated duration corresponding to the light load operating room being greater than a predicted duration of the scheduled operation;

the balance data determining module is used for determining the allocated duration of each surgical room corresponding to each scheduling scheme and determining the discrete coefficient of each surgical room according to the allocated duration of each surgical room;

And the scheduling module is used for scheduling the partial operation of the at least one overload operation room to at least one scheduling scheme of the at least one light-load operation room by adopting a scheduling scheme corresponding to the minimum discrete coefficient so as to obtain the latest operation schedule of each operation room.

According to still another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the inter-operative load balancing method of any of the embodiments of the present invention.

According to yet another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to execute an inter-operative load balancing method according to any one of the embodiments of the present invention.

According to the technical scheme provided by the embodiment of the invention, at least one scheduling scheme for distributing the operation of the overload operation room to the light load operation room is formulated according to the set load scheduling strategy and operation time length, the at least one scheduling scheme is evaluated by using the discrete coefficient, the operation scheduling is updated according to the scheduling scheme with the minimum discrete coefficient, and the load balancing degree of the operation room and the utilization rate of each operation room are improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows. The data acquisition, storage, use, processing and the like in the technical scheme meet the relevant regulations of national laws and regulations.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1A is a flow chart of a method for load balancing between surgeries according to an embodiment of the present invention;

FIG. 1B is a flow chart for constructing a procedure length prediction model using a machine learning algorithm in artificial intelligence, according to an embodiment of the present invention;

FIG. 1C is a flowchart of XGBoost provided according to an embodiment of the present invention;

FIG. 1D is a visual interface of an intelligent surgical dispatch center provided in accordance with an embodiment of the present invention;

FIG. 1E is a schematic diagram of a model feature importance analysis result provided according to an embodiment of the present invention;

FIG. 1F is a flow chart of a specific inter-operative load balancing method provided in accordance with an embodiment of the present invention;

FIG. 2A is a flow chart of another method of intraoperative load balancing provided in accordance with embodiments of the present invention;

FIG. 2B is a schematic diagram of an auxiliary decision interface provided in accordance with an embodiment of the present invention;

FIG. 2C is a flow chart of another specific inter-operative load balancing method provided in accordance with an embodiment of the present invention;

FIG. 2D is a schematic illustration of a surgical schedule presentation interface provided in accordance with an embodiment of the present invention;

FIG. 2E is a schematic diagram of an intraoperative utilization display interface provided in accordance with embodiments of the present invention;

fig. 3A is a block diagram of an apparatus for load balancing between operations according to an embodiment of the present invention;

fig. 3B is a block diagram of another surgical load balancing apparatus provided in accordance with an embodiment of the present invention;

FIG. 3C is a block diagram of yet another surgical load balancing apparatus provided in accordance with an embodiment of the present invention;

FIG. 3D is a block diagram of yet another surgical load balancing apparatus provided in accordance with an embodiment of the present invention;

Fig. 4 is a block diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," "third," and "fourth," etc. in the description and claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Fig. 1A is a flowchart of an operation room load balancing method according to an embodiment of the present invention, where the embodiment is applicable to a scenario of performing operation room load balancing based on a predicted operation time length, and the method may be configured in an operation room load balancing device, where the operation room load balancing device may be implemented in a form of hardware and/or software, and may also be configured in a processor of an electronic device.

As shown in fig. 1A, a method for load balancing between operations includes the steps of:

s110, responding to the operation load balancing instruction, and determining whether the operation loads of all the operation rooms are balanced according to the operation schedule of all the operation rooms.

The operation load balancing instruction can be sent to a module/device/equipment provided with an operation room load balancing method through an input device of the electronic equipment, and is used for determining whether the operation load of each operation room is balanced currently.

In a specific embodiment, the operation load balancing instruction can be automatically generated and sent under the condition of meeting the preset time; the processor responds to the operation load balancing instruction to acquire operation schedules of all the operation rooms; for each surgical suite, all of the predicted surgical durations in the surgical suite row are added as the assigned duration for that surgical suite. Further, calculating discrete coefficients of the operation rooms according to the allocated time length of all the operation rooms, setting a discrete threshold value, and when the discrete coefficients are smaller than the discrete threshold value, indicating the operation load balance of each operation room, and not processing or outputting prompt information for prompting the operation load balance; when the discrete coefficient is larger than or equal to the discrete threshold value, the operation load unbalance of each operation room is indicated, and the prompt information for prompting the operation load unbalance is output.

Further, the discrete coefficient c _v Is obtained by the formula (1):

where σ is the standard deviation of the assigned durations of all the operating rooms and μ is the average of the assigned durations of all the operating rooms.

Alternatively, the method may be deployed in a processor of a hospital information system (Hospital Information System, HIS). The hospital manager/doctor sends out an operation load balancing instruction through the man-machine interaction interface, the processor receives the instruction, the operation schedule of each operation room is obtained through the HIS, and whether the operation load of each operation room is balanced or not is further determined according to the operation schedule of each operation room.

S120, if not, determining at least one scheduling scheme for scheduling partial operations of at least one overload operating room to at least one light load operating room based on a set load scheduling strategy in the case that the at least one overload operating room exists.

Wherein the difference between the allocated time length corresponding to the overload surgery room and the allocated time length corresponding to the light load surgery room is greater than the predicted time length of the scheduled surgery.

It will be appreciated that when the discrete coefficient is greater than or equal to the discrete threshold, each surgical bay is subject to a surgical load imbalance indicating that there is at least one surgical bay with a surgical bay having a surgical load imbalance as an overloaded surgical bay, and therefore, one or more of the overloaded surgical bays need to be assigned to one or more of the other lightly loaded surgical bays, and the difference between the assigned time period corresponding to the overloaded surgical bay and the assigned time period corresponding to the lightly loaded surgical bay is greater than the predicted time period for the scheduled surgery.

Optionally, an allocation duration threshold is set for indicating a single day maximum allocated duration of the operating room. Comparing the allocated time length of each surgical room with an allocation time length threshold, and taking the surgical room as an overload surgical room when the allocated time length of the surgical room is greater than/equal to the allocation time length threshold and the surgical load of the surgical room is unbalanced; and when the allocated duration of the operation room is smaller than the threshold value of the allocated duration, the operation load of the operation room is balanced, and the operation room is taken as a light-load operation room.

Specifically, the sorting can be performed according to the allocated time length of the operating rooms, the time length exceeding the maximum allocated time length of a single day is the overload operating room, the operation of the operating room with the large allocated time length of the operating room is allocated to the operating room with the small allocated time length of the operating room, and the difference between the allocated time length corresponding to the operating room with the large allocated time length of the operating room and the allocated time length corresponding to the light load operating room is larger than the predicted time length of the scheduled operation.

In a specific embodiment, determining the predicted procedure duration of the scheduled procedure comprises:

and a1, acquiring scheduling related data of scheduled operations.

Specifically, the schedule-related data includes factors that affect the duration of the procedure.

In one embodiment, the schedule-related data includes 9-dimensional information, the 9-dimensional information including:

the operating room, which describes the operating room area in which the surgery is scheduled, may be, for example, a code of the operating room area.

The department may be a code describing the department in which the patient is scheduled for surgery.

Preoperative diagnosis, preoperative diagnostic information describing the patient scheduled for surgery, may be, for example, an international disease classification (International classification of diseases, ICD) code.

Emergency preferential identification, which describes whether the scheduled procedure is an emergency procedure or a preferential procedure, and illustratively, 1 represents an emergency procedure and 0 represents a preferential procedure.

The doctor's information describing the operator of the scheduled procedure, for example, may be described using the doctor's job number.

Job title, job title for describing the operator of the scheduled operation, including primary and secondary primary physicians, attending physicians, and inpatients, etc.

The procedure name, which describes the procedure mode performed by the scheduled procedure, may be, for example, an ICD procedure name code.

Patient gender, used to describe the gender of the patient being scheduled for surgery, is exemplified using chinese or codes to describe both men and women.

The age of the patient, which describes the age of the patient being scheduled for surgery, may be described using an age number.

Step a2, inputting the scheduling related data of the scheduled operation into a trained operation duration prediction model to obtain the predicted operation duration of the scheduled operation.

Wherein the surgical data includes schedule-related data and a surgical duration.

It can be understood that firstly, taking the schedule associated data of the preset number of operations performed in the past as a sample, and training the operation duration prediction model by taking the corresponding operation duration as a label to obtain a trained operation duration prediction model; and then, inputting the scheduling related data of the scheduled operation into a trained operation duration prediction model to obtain the predicted operation duration of the scheduled operation. In a specific embodiment, 37701 cases of surgical data are divided into 27144 cases of training set, 7541 cases of test set and 3016 cases of check set, which respectively account for 72%, 20% and 8% of the total number of samples; the training set is used for establishing a data training model; the test set is used for evaluating the model prediction result after the model is built, and testing the generalization capability of the model; the verification set is used for evaluating the parameters during training, adjusting the parameters according to the evaluation result and finally selecting a correct model. Furthermore, each feature can be analyzed in the data preparation stage, and the number and distribution of discrete values in each feature can be determined.

Further, in the training process, parameters of the model need to be adjusted according to the accuracy of prediction, and the statistical index of the prediction accuracy can be one of mean square error (Mean Square Error, MSE), root mean square error (Root Mean Squared Error, RMSE), mean absolute value error (Mean Absolute Error, MAE) or mean absolute percentage error (Mean Absolute Percentage Error, MAPE).

FIG. 1B is a flowchart of a method for constructing a model for predicting a duration of a surgery using a machine learning algorithm in artificial intelligence according to an embodiment of the present invention, as shown in FIG. 1B, the method for constructing the model includes:

and b1, determining influencing factors of the operation duration according to actual business logic and data conditions.

Optionally, each feature of the surgical data can be analyzed to determine the number and distribution of discrete values in the feature, so that parameter setting is convenient in modeling.

And b2, determining an output mode of the model about the operation duration obtained by prediction.

Illustratively, the predicted duration of the procedure is described directly using minutes in digital form, accurate to integer bits.

And b3, preprocessing the operation data to finish data preparation work.

Before training, the data of the operation data is required to be cleaned, and the method has the advantages that the content of the data can be standardized, the non-compliance or invalid data can be filtered, and the accuracy of predicting the operation duration of the model can be improved by using the cleaned data to perform model training.

In a specific embodiment, data of 529484 pieces of operation information in a certain hospital in 2015-2020 are collected, a query view is established by using a structured query language (Structured Query Language, SQL) query statement, data value content is normalized, non-compliance or invalid operation information is filtered, 37749 cases of operation data are obtained through data cleaning, and 37701 cases of operation data are obtained after the operation data with operation time length less than 10 minutes and more than 1000 minutes are removed, wherein sample characteristics and statistical data of the operation data are shown in Table 1.

TABLE 1

Features (e.g. a character)	Statistics (category number)
		Operating room	9
Department of science	457
		Preoperative diagnosis	1456
Emergency/selection period	2
		Doctor with main knife	987
Job's title	23
		Surgical name	1757
Sex of patient	2
		Age of patient	Age 0-105 years old

And b4, selecting a proper algorithm to establish a surgical duration prediction model according to the characteristics and the output.

Optionally, a prediction model of the duration of the surgery is built based on a gradient lifting tree (Gradient Boosting Decision Tree, GBDT) algorithm, which is also called an iterative regression tree (Multiple Additive Regression Tree, MART) algorithm, which is an iterative decision tree algorithm. The algorithm consists of a plurality of decision trees, and the conclusions of all the trees are accumulated to obtain a final result, so that the algorithm has stronger generalization capability. The tree in GBDT is a regression tree, not a classification tree, and GBDT is mainly used for regression prediction and can be used for classification after adjustment. The principle of GBDT is to add the results of all weak classifiers to get the predicted value, and the next weak classifier fits the residual of the error function to the predicted value (the error between the predicted value and the true value). Wherein the representation of the weak classifier is a tree. GBDT will have a predicted value for each sample at each iteration of the round, as shown in equation (2):

Wherein y is _i To be a true value of the value,

is a model predictive value.

Further, a mean square error loss function is used as the loss function; the calculation method of the negative gradient is shown in the formula (3):

further, when using a mean square loss function as the loss function, the value of each fit is the residual (i.e., the true value minus the model predicted value), where the variable is y _i And solving a negative gradient for the variable to obtain a gradient lifting tree.

GBDT regression algorithmIs input as a surgical training data set and output as a surgical duration prediction gradient lifting tree. Specifically, the maximum iteration number of the gradient lifting regression algorithm is M, the loss function is L (y, f (x)), and the operation training data set is

The GBDT regression algorithm specifically comprises the following steps:

step c1, initializing a surgery duration prediction model to obtain an initial surgery duration prediction model in a formula (4):

when m=1, 2, …, M and i=1, 2, … N, r is calculated by formula (5) _mi ：

Step c2, pair r _mi Fitting the regression tree to obtain a leaf node region R of the mth tree _mj ,j＝1,2,…,J。

Step c3, when j=1, 2, …, J, calculating c according to formula (6) _mj ：

Updating the operation duration prediction model, and updating the initial operation duration prediction model by using the operation duration prediction model in the formula (7):

Obtaining a gradient lifting tree in the formula (8):

in one embodiment, a polar gradient lifting (eXtreme Gradient Boosting, XGBoost) is selected as a framework of a surgery duration prediction model, XGBoost is a Boosting algorithm tool kit, and is excellent in parallel computing efficiency, missing value processing, fitting control and prediction generalization capability, and is an optimized distributed gradient lifting library, so that the method has the advantages of high efficiency, flexibility, portability and the like. XGBoost (see FIG. 1C) has the following advantages over machine learning algorithm GBDT: XGBoost is optimized in terms of engineering realization on the basis of an algorithm; GBDT uses the first derivative of the loss function, which is equivalent to gradient drop in the function space, XGBoost uses the second derivative of the loss function, which is equivalent to Newton's method in the function space; the XGBoost explicitly adds a regular term to control the complexity of the model, so that overfitting can be effectively prevented; XGBoost adopts a method in a random forest, and performs column random sampling before each node splitting; XGBoost uses a sparse sensing strategy to process missing values, and GBDT does not have a missing value processing strategy; the column block design of XGBoost can effectively support parallel operation, and the efficiency is better; the XGBoost algorithm uses a step-forward additive model in equation (9):

The model no longer needs to calculate a coefficient after generating the weak learner in each iteration.

In summary, the XGBoost algorithm realizes the generation of the weak learner by optimizing the structured loss function (the loss function added with the regular term can reduce the overfitting), and the XGBoost algorithm does not adopt a search method, directly utilizes the values of the first derivative and the second derivative of the loss function, and improves the performance of the algorithm through the technologies of pre-sequencing, weighted quantile and the like.

Illustratively, the GBDT is predicted for a procedure with an actual duration of 1 hour and 20 minutes using a procedure duration prediction model, and specifically includes the following steps: fitting randomly at a first weak classifier (or first tree) for a first predetermined period of time (e.g., 1 hour) to produce a first error (e.g., 20 minutes); fitting the first error with a second predetermined time period (e.g., 12 minutes) in a second weak classifier (or a second tree) to produce a second error (e.g., 8 minutes); fitting the second error with a third predetermined time period (e.g., 7 minutes) in a third weak classifier (or a third tree) to produce a third error (e.g., 1 minute); fitting a third error in a fourth weak classifier (or a fourth tree) with a fourth preset time period (e.g., 1 minute), the error being 0; the four preset durations in the four weak classifiers (or four trees) are added together to be the actual operation duration (for example, 1 hour and 20 minutes).

And c4, training the operation duration prediction model by using the preprocessed operation data to obtain a trained operation duration prediction model.

Specifically, training the operation duration prediction model by using the preprocessed operation data to obtain a trained operation duration prediction model; evaluating the trained operation duration prediction model by using data of the check set, and adjusting parameters again according to conditions; and after the integral modeling is finished, comparing and evaluating the model prediction result with the actual test set result by using the test set data, and determining the availability of the model.

And c5, after the model is built, building a corresponding data interface aiming at the model so as to facilitate the actual application of system call.

Specifically, in the practical application system, the call of the join duration prediction interface, namely, in the intelligent operation scheduling center, when a user clicks the corresponding position of join duration prediction, the system automatically calls the duration prediction interface after acquiring an operation application, and the trained operation duration prediction model is used for predicting operation duration.

Optionally, the model is continuously used to build WebApi, and is applied to an intelligent surgical dispatching center system, the intelligent surgical dispatching center is an application program of a B/S architecture, a service end of the intelligent surgical dispatching center builds an HTTP service frame based on WebApi, a client is a website, a desktop browser supporting the use of a chromaum kernel is opened for use, and the client and the service end are both deployed on a hospital intranet server to develop service application in the hospital intranet (see fig. 1D).

In this embodiment, XGBoost is used to perform model training on the data of the test set, and after training is completed, the feature importance analysis of the model is obtained (see fig. 1E). The higher the Score, the higher the importance of the feature to the model, so that the test set data is required to perform test evaluation and tuning on the model. In a specific embodiment, the number of test surgical samples involved in the test is 7541, the average surgical duration of the test set is 152.7 minutes, and the average model prediction results are 152.1 minutes; then, MAE is calculated using equation (10) to evaluate the accuracy of the model predictions:

wherein y is _i Is true, f (x _i ) Is the predicted value of the model, m is the number of predicted results, i is [1, m]Is an integer of (a). In one specific embodiment, mae=40.9 is calculated, i.e. the average prediction error for a single procedure is 40.9 minutes.

Further, determining at least one scheduling scheme for scheduling the portion of the at least one overload surgery room to the at least one light load surgery room based on setting the load scheduling policy, comprising:

step d1, determining the operation load sorting results of all schedulable operation rooms, determining the operation room with the minimum operation load according to the operation load sorting results, and taking the operation room as a target operation room.

It will be appreciated that the procedure that has been initiated on the same day and the procedure that has been delayed do not participate in the procedure scheduling, and therefore, the procedure of the schedulable surgery room cannot include only the procedure that has been initiated on the same day and the procedure that has been delayed.

In particular, all other surgical suites that do not include only the surgery that has been started the day and the surgery that has been delayed are determined as dispatchable surgical suites; calculating the utilization rate of each schedulable operation room according to the allocated time length of the schedulable operation room, taking the calculated utilization rate as the operation load of the corresponding operation room, and sequencing the calculated operation load according to the utilization rate from high to low (or from low to high), so as to obtain a sequencing result of the operation load; the operating room with the smallest operating load is used as the operating room with the smallest operating load, the operating room with the smallest operating load is used as the target operating room, and one or more operations of the overload operating room are supposed to be dispatched to the target operating room.

Further, the inter-operative utilization (R) is calculated by equation (11):

wherein T is the total distribution time length of the operation room, T _max It is set that each operating room can be assigned the maximum operating time.

Step d2, determining the latest sequencing result of the surgical loads of each schedulable surgical room after the target surgery of the current surgical room is scheduled to the target surgical room for each surgical room in at least one overload surgical room based on the descending order of the surgical loads.

Wherein the target surgery is a surgery other than the surgery started on the same day and the delayed surgery in the scheduling surgery of the overload surgery room.

It will be appreciated that after the target surgery of the overloaded surgery room is dispatched to the target surgery room, the load of the target surgery room will become greater, so in order to avoid the target surgery room after dispatching the target surgery being the next overloaded surgery room, it is necessary to determine the utilization rate of each dispatchable surgery room after dispatching the target surgery to the target surgery room; and determining a ranking result from high to low (or from low to high) about the utilization rate according to the utilization rate of each schedulable operation room as a latest ranking result.

Step d3, determining whether the target surgical suite meets the set load sorting condition in the latest sorting result; if not, a descending order based on the surgical load is returned.

It will be appreciated that after an overloaded surgical room is dispatched to a target surgical room, the load on the target surgical room will also become greater, and therefore, it will also be desirable to determine whether the load on the target surgical room is less than the load on the overloaded surgical room.

Specifically, assuming that the target operation is dispatched to a target operation room, calculating a discrete coefficient added to the target operation room after the target operation, and judging whether the discrete coefficient of the target operation room is smaller than that of the overload operation room or not; if the discrete coefficient of the target operating room is greater than/equal to the discrete coefficient of the overload operating room, returning to the step d2.

Step d4, if yes, generating a scheduling scheme aiming at the target operating room, determining whether an overload operating room exists currently, and if yes, returning to the step of determining the operation load sequencing result of all the schedulable operating rooms.

Specifically, if the discrete coefficient of the target operating room is smaller than the discrete coefficient of the overload operating room, generating a scheduling scheme for scheduling the target operation of the overload operating room to the target operating room, and determining whether an operating room with the discrete coefficient being larger than/equal to a discrete threshold exists, namely the overload operating room; if so, returning to the step b1, and performing operation scheduling on the target operation in the overload operation room.

S130, determining the allocated duration of each surgical room corresponding to each scheduling scheme, and determining the discrete coefficient of each surgical room according to the allocated duration of each surgical room.

In order to select a scheduling scheme with the smallest discrete coefficient among at least one scheduling scheme, it is necessary to calculate the discrete coefficient between each surgery again. Specifically, for each scheduling scheme, it is assumed that a target operation is scheduled to a target operation room according to the scheduling scheme, for each operation room, the time lengths of all operations in each operation room are added to obtain an allocated time length of each operation room, and then according to formula (1), the discrete coefficient of each operation room is determined according to the allocated time length of each operation room.

And S140, adopting a scheduling scheme corresponding to the minimum discrete coefficient, and scheduling the partial operation of the at least one overload operating room to at least one scheduling scheme of the at least one light-load operating room so as to obtain the latest operation schedule of each operating room.

Specifically, for each scheduling scheme of the overload operating room, comparing discrete coefficients of all scheduling schemes, determining the minimum value of the discrete coefficients, performing operation scheduling according to the scheduling scheme corresponding to the minimum value, and scheduling part of the overload operating room to at least one scheduling scheme of at least one light load operating room until each operation of the overload operating room is subjected to operation scheduling once; and generating operation schedules corresponding to all the operation rooms according to the scheduled operation, and obtaining the latest operation schedule.

In a specific embodiment, fig. 1F is a flowchart of a specific method for load balancing between operations according to an embodiment of the present invention, the method comprising:

step e1, acquiring operation information such as operation schedule, maximum operation load, operation table interval and the like of each operation room.

And e2, the system acquires and screens all schedulable operation rooms, and sequences all schedulable operation rooms from large to small according to operation loads (quick sequencing), so that the operation started on the same day and the operation delayed to open are not participated in scheduling.

And e3, calculating the utilization rate and the global variance of all the operating rooms, and rapidly sequencing all the operating rooms according to the utilization rate.

And e4, screening out all overload operating rooms according to the distribution duration threshold.

And e5, sequentially scheduling the operations in the overload operation room to the operation room with the minimum load, calculating variance, and checking the factors such as the rule of entering the room, whether the operation room crosses a hospital area, the information of the class of the person to be scheduled, the mutual exclusion of the person in the same time period in different operation rooms and the like in the scheduling process until the operation room with the minimum load is moved to the middle operation room.

And e6, traversing all overload operating rooms, and repeating the operation of the step e5 until all the overload operating rooms are scheduled once.

And e7, comparing all the scheduled global variances with the original variances, selecting the minimum variances as optimal solutions, and outputting a scheduling scheme corresponding to the optimal solutions.

According to the technical scheme, the operation duration is predicted based on the scheduling related data, and operation guidance is performed according to the predicted operation duration of the scheduled operation, so that load balancing among the operations is realized, and the balancing degree of load reduction of the operations and the utilization rate of each operation room are improved.

Fig. 2A is a flowchart of another method for balancing load between operations according to an embodiment of the present invention, where the method for balancing load between operations in this embodiment is the same as the method for balancing load between operations in the above embodiment, and further describes, based on the above embodiment, whether the load between operations is balanced according to the operation schedule of each operation room in response to an operation load balancing instruction: acquiring the operation schedule of each operation room and the predicted operation time length of the operation to be scheduled; determining the allocated duration corresponding to the surgical scheduling of each surgical room, and taking the surgical room with the shortest allocated duration as a target surgical room for the surgical to be scheduled; adding the surgical schedule to the target surgical room according to the surgical schedule of the target surgical room and the predicted surgical duration of the surgical schedule to update the surgical schedule of the target surgical room; triggering an operation load balancing instruction; in response to the surgical load balancing instructions, determining whether the surgical loads of the surgical rooms are balanced according to the latest surgical schedule of the surgical rooms.

As shown in fig. 2A, a method for load balancing between operations includes the steps of:

s2101, acquiring operation schedule of each operation room and predicted operation duration of operation to be scheduled.

Optionally, acquiring a surgical schedule of each surgical suite in the HIS; and inputting the scheduling related data of the to-be-scheduled operation into a trained operation duration prediction model to obtain the predicted operation duration of the to-be-scheduled operation.

S2102, determining the allocated duration corresponding to the surgical scheduling of each surgical room, and taking the surgical room with the shortest allocated duration as the target surgical room for the surgical to be scheduled.

Specifically, for each surgical room, determining the duration of each surgery according to the starting time and the ending time of all the surgeries in the surgical room, and adding the duration of all the surgeries to obtain the allocated duration of the surgical queue in the surgical room; sequencing the allocated time lengths corresponding to the surgical scheduling of all the surgical rooms from small to large, and taking the surgical room with the shortest allocated time length as the target surgical room for the surgical to be scheduled.

In one embodiment, the surgical load of each surgical suite is determined based on the assigned time period corresponding to the surgical schedule of each surgical suite; the operating room with the smallest operating load is taken as the target operating room. Specifically, for each surgical room, determining the duration of each surgery according to the starting time and the ending time of all the surgeries in the surgical room, and adding the duration of all the surgeries to obtain the allocated duration of the surgical queue in the surgical room; and calculating the utilization rate of each operating room according to the allocated time length, taking the operating room with the smallest operating load as a target operating room as the operating load of the corresponding operating room.

S2103, adding the surgery to be scheduled to the surgery schedule of the target surgery room according to the surgery schedule of the target surgery room and the predicted surgery duration of the surgery to be scheduled so as to update the surgery schedule of the target surgery room.

It will be appreciated that the docking bay is provided in order to ensure that there is a preparation time for each operation. Specifically, according to the operation schedule of the target operation room and the predicted operation duration of the operation to be scheduled, on the premise that the allocated duration of each operation room does not exceed the allocated duration of a single day and the set table interval is arranged between the front operation and the back operation, the operation to be scheduled is added to the operation schedule of the target operation room, the operation schedule of the target operation room is updated, and the updated operation schedule also meets the above conditions.

S2104, triggering an operation load balancing instruction.

Optionally, a triggering condition is set, and the triggering condition is used for automatically triggering the operation load and the balancing instruction when the preset triggering condition is met; the operation load balancing instruction can be generated according to the information input by the user. The triggering condition is a set time period, and when the condition of the set time period is met, the operation load balancing instruction is triggered; the triggering condition may also be that a surgical load balancing instruction is triggered when there is at least one surgical load greater than/equal to a triggering threshold.

S2105, responding to the operation load balancing instruction, and determining whether the operation loads of all the operation rooms are balanced according to the latest operation schedule of all the operation rooms.

S220, if not, determining at least one scheduling scheme for scheduling partial operations of at least one overload operating room to at least one light load operating room based on the set load scheduling strategy in the case that the at least one overload operating room exists.

S230, determining the allocated duration of each surgical room corresponding to each scheduling scheme, and determining the discrete coefficient of each surgical room according to the allocated duration of each surgical room.

S2401, outputting a scheduling scheme corresponding to the minimum discrete coefficient.

Specifically, a window can be popped up, and a scheduling scheme corresponding to the minimum discrete coefficient is output in at least one form of characters, figures, tables and the like; the scheduling scheme can also be associated with the related information of the operation schedule of the HIS, and the scheduling scheme is output in a visual interface/voice broadcasting mode and the like.

Further, the method further includes the steps of outputting a scheduling scheme corresponding to the minimum discrete coefficient: and outputting a surgical load display result corresponding to the scheduling scheme corresponding to the minimum discrete coefficient in the visual interface. The surgical load display result comprises at least one of surgical load data of an associated operating room, discrete coefficients of the associated operating room and discrete coefficients of all the operating rooms.

The associated operating rooms are at least two operating rooms related to a scheduling scheme corresponding to the minimum discrete coefficient, and the associated operating rooms comprise an overload operating room and a light load operating room of the scheduling scheme corresponding to the minimum discrete coefficient.

Specifically, in the visual interface, not only the scheduling scheme corresponding to the minimum discrete coefficient is output, but also at least one of the operation load data before and after the scheduling scheme is executed by the associated operating room, the discrete coefficients of the associated operating room, and the discrete coefficients of all the operating rooms is output. The method has the advantages that related data are expressed more clearly and effectively through the visual chart, so that management staff can directly pay attention to key information, and management efficiency is improved.

In one embodiment, an auxiliary decision-making interface is provided for displaying a scheduling scheme corresponding to the minimum discrete coefficient and a surgical load display result corresponding to the scheme (see fig. 2B), and as shown in fig. 2B, the interface includes scheduling related data, a scheduling scheme corresponding to the minimum discrete coefficient, the utilization rate of the related operating rooms before and after scheduling, the discrete degree of the utilization rate and the change condition of the overall utilization rate of all the operating rooms, so that a user can judge whether the scheduling suggestion needs to be executed according to the visualized display result, and if the scheduling suggestion is executed, clicking for confirmation; if the schedule suggestion is not executed, cancel is clicked.

S2402, responding to the confirmation operation of the scheduling scheme corresponding to the minimum discrete coefficient, and scheduling the partial operation of the at least one overload operation room to at least one scheduling scheme of the at least one light load operation room by adopting the scheduling scheme corresponding to the minimum discrete coefficient so as to obtain the latest operation schedule of each operation room.

Specifically, the user may further determine whether to execute the scheduling scheme according to the scheduling scheme corresponding to the minimum discrete coefficient. The user can send out a confirmation operation through the input device of the processor, and the processor responds to the confirmation operation and dispatches the partial operation of the at least one overload operation room to at least one dispatching scheme of the at least one light load operation room according to the dispatching scheme corresponding to the minimum discrete coefficient so as to obtain the latest operation schedule of each operation room. The advantage of this is that the user's confirmation operation is added, further improving the accuracy.

In a specific embodiment, fig. 2C is a flowchart of a specific load balancing method between operations according to an embodiment of the present invention, as shown in fig. 2C, after outputting a scheduling scheme corresponding to a minimum discrete coefficient, a user may further determine whether to adopt the scheduling scheme according to the scheduling scheme corresponding to the minimum discrete coefficient, and if the user selects yes, perform an operation scheduling operation according to the scheduling scheme; if the user selects no, the process is finished.

In one embodiment, after completing the surgical scheduling according to the scheduling scheme, the system will display the surgical scheduling conditions of each surgical suite (see fig. 2D), as shown in fig. 2D, firstly, sequentially arranging each surgical suite on the left side, calculating the utilization rate of each surgical suite by using the predicted surgical duration of the surgical duration model, and displaying the surgical duration on the periphery of the surgical suite number in a circular ring form; the corresponding operation of each operation room is displayed on a time axis in a card form, the time axis is from 0 point to 24 points, the default display position is 8 points, and the operation room can be adjusted in the system configuration. The original width of the card represents the expected duration of the operation, the left position of the card represents the planned open time of the operation, and the right position represents the planned end time of the operation. Each surgery is marked with a surgery name and surgery necessary information, wherein the surgery necessary information comprises: the surgical team constituent personnel, by way of example, may include anesthesiologists, major doctors, tour nurses, instrument nurses, and the like.

Optionally, an operation room utilization rate board (see fig. 2E) is further provided, so that the time length and the utilization rate of each operation room are displayed in the same coordinate system in the form of a histogram and a line graph, and the advantage of this is that a user can intuitively know the utilization rate of the operation room; meanwhile, the operating room utilization rate equilibrium degree is set to be directly displayed in a text description form, and the operating room load is divided into four grades according to the utilization rate or the discrete coefficient: excellent, good, general and unbalanced, each level corresponds to a discrete coefficient range, which can be dynamically adjusted according to the actual condition of the operating room utilization.

According to the technical scheme, visual display is performed through a scheduling scheme, operation scheduling, operation load and the like, related data are more clearly and effectively expressed through a visual chart, the operation load is classified, and therefore management staff can directly pay attention to key information, and management efficiency is improved.

Fig. 3A is a block diagram of an apparatus for load balancing between operations according to an embodiment of the present invention, where the embodiment is applicable to a scenario in which load balancing between operations is performed based on a predicted operation duration, and the apparatus may be implemented in hardware and/or software, and integrated into a processor of an electronic device with an application development function.

As shown in fig. 3A, the inter-operative load balancing apparatus includes:

the balancing instruction response module 301 is configured to determine whether the surgical load of each surgical room is balanced according to the surgical schedule of each surgical room in response to the surgical load balancing instruction.

The scheduling scheme determining module 302 is configured to determine, if not, that, in a case where at least one overload surgery room exists, based on a set load scheduling policy, at least one scheduling scheme for scheduling a part of the at least one overload surgery room to at least one light load surgery room, where a difference between an allocated duration corresponding to the overload surgery room and an allocated duration corresponding to the light load surgery room is greater than a predicted duration of the scheduled surgery.

The balance data determining module 303 is configured to determine an allocated duration of each surgical suite corresponding to each scheduling scheme, and determine a discrete coefficient of each surgical suite according to the allocated duration of each surgical suite.

The scheduling module 304 is configured to schedule the partial surgery of the at least one overload surgery room to at least one scheduling scheme of the at least one light-load surgery room by using a scheduling scheme corresponding to the minimum discrete coefficient, so as to obtain a latest surgery schedule of each surgery room.

Optionally, the equalization instruction response module 301 is specifically configured to:

acquiring the operation schedule of each operation room and the predicted operation time length of the operation to be scheduled;

determining the allocated duration corresponding to the surgical scheduling of each surgical room, and taking the surgical room with the shortest allocated duration as a target surgical room for the surgical to be scheduled;

adding the surgical schedule to the target surgical room according to the surgical schedule of the target surgical room and the predicted surgical duration of the surgical schedule to update the surgical schedule of the target surgical room;

triggering an operation load balancing instruction;

in response to the surgical load balancing instructions, determining whether the surgical loads of the surgical rooms are balanced according to the latest surgical schedule of the surgical rooms.

Optionally, as shown in fig. 3B, the apparatus further includes a target operating room determination module 305, where the target operating room determination module 305 is specifically configured to:

Determining the operation load of each operation room according to the allocated time length corresponding to the operation schedule of each operation room;

the operating room with the smallest operating load is taken as the target operating room.

Optionally, the scheduling scheme determining module 302 is specifically configured to:

determining the surgical load sequencing results of all schedulable surgical rooms, determining the surgical room with the minimum surgical load according to the surgical load sequencing results, and taking the surgical room as a target surgical room;

determining, for each of the at least one overload operating room, a latest sequencing result of the operating loads of each schedulable operating room after scheduling the target operation of the current operating room to the target operating room based on the descending order of the operating loads;

determining whether the target operating room accords with a set load sorting condition in the latest sorting result;

if not, returning to the order of decreasing based on the surgical load;

if yes, a scheduling scheme aiming at the target operating room is generated, whether the overload operating room exists currently or not is determined, and if yes, a step of determining the operation load sequencing result of all the schedulable operating rooms is returned.

Optionally, the scheduling module 304 is specifically configured to:

outputting a scheduling scheme corresponding to the minimum discrete coefficient;

And responding to the confirmation operation of the scheduling scheme corresponding to the minimum discrete coefficient, adopting the scheduling scheme corresponding to the minimum discrete coefficient, and scheduling the partial operation of the at least one overload operating room to at least one scheduling scheme of the at least one light-load operating room so as to obtain the latest operation schedule of each operating room.

Optionally, as shown in fig. 3C, the apparatus further includes a visual display module 306, where the visual display module 306 is specifically configured to:

and outputting an operation load display result corresponding to the scheduling scheme corresponding to the minimum discrete coefficient in the visual interface, wherein the operation load display result comprises at least one of operation load data of an associated operation room, discrete coefficients of the associated operation room and discrete coefficients of all operation rooms.

Optionally, as shown in fig. 3D, the apparatus further includes a surgery duration prediction module 307, where the surgery duration prediction module 307 is specifically configured to:

acquiring scheduling related data of scheduled operations;

the scheduling related data of the scheduled surgery is input into a trained surgery duration prediction model to obtain the predicted surgery duration of the scheduled surgery.

According to the technical scheme of the embodiment, through the mutual coordination of the modules, at least one scheduling scheme for distributing the operation of the overload operation room to the light load operation room is formulated according to the set load scheduling strategy and operation time length, the at least one scheduling scheme is evaluated by using the discrete coefficient, the operation scheduling is updated according to the scheduling scheme with the minimum discrete coefficient, and the balance degree of the load of the operation room and the utilization rate of each operation room are improved.

The load balancing device for the operation room provided by the embodiment of the invention can execute the load balancing method for the operation room provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.

Fig. 4 is a block diagram of an electronic device according to an embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 4, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the inter-operative load balancing method.

In some embodiments, the inter-operative load balancing method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the inter-operative load balancing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the inter-operative load balancing method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method of load balancing between operations, comprising:

if not, determining at least one scheduling scheme for scheduling partial operations of at least one overload operating room to at least one light load operating room based on a set load scheduling strategy under the condition that at least one overload operating room exists, wherein the difference between the allocated duration corresponding to the overload operating room and the allocated duration corresponding to the light load operating room is larger than the predicted duration of the scheduled operation;

2. The method of claim 1, wherein determining whether the surgical load of each surgical suite is balanced based on the surgical schedule of each surgical suite in response to the surgical load balancing instructions comprises:

determining the allocated duration corresponding to the surgical scheduling of each surgical room, and taking the surgical room with the shortest allocated duration as the target surgical room for the surgical to be scheduled;

adding the surgery to be scheduled to the surgery schedule of the target surgery room according to the surgery schedule of the target surgery room and the predicted surgery duration of the surgery to be scheduled so as to update the surgery schedule of the target surgery room;

triggering an operation load balancing instruction;

3. The method of claim 2, wherein determining the target surgical suite for the surgical procedure to be scheduled based on the surgical schedule for the respective surgical suite comprises:

4. The method of claim 1, wherein the determining at least one scheduling scheme for scheduling the portion of the at least one overload surgery room to at least one light load surgery room based on the set load scheduling policy comprises:

determining, for each of the at least one overload operating room, a latest sequencing result of the operating loads of each schedulable operating room after scheduling a target operation of a current operating room to the target operating room based on the decreasing order of the operating loads;

determining whether the target operating room meets a set load sorting condition in the latest sorting result;

If not, returning to the order of decreasing based on the surgical load;

if yes, generating a scheduling scheme aiming at the target operating room, determining whether an overload operating room exists currently, and if yes, returning to the step of determining the operation load sequencing result of all the schedulable operating rooms.

5. The method of claim 1, wherein the scheduling the partial surgery of the at least one overload surgery room to at least one scheduling of the at least one light load surgery room using the scheduling scheme corresponding to the minimum discrete coefficient to obtain the latest surgery schedule of each surgery room, comprising:

6. The method of claim 5, wherein outputting the scheduling scheme corresponding to the minimum discrete coefficient further comprises:

And outputting an operation load display result corresponding to the scheduling scheme corresponding to the minimum discrete coefficient in a visual interface, wherein the operation load display result comprises at least one of operation load data of an associated operation room, discrete coefficients of the associated operation room and discrete coefficients of all operation rooms.

7. The method of claim 1, wherein determining the predicted procedure duration of the scheduled procedure comprises:

acquiring scheduling related data of the scheduled surgery;

and inputting the scheduling related data of the scheduled surgery into a trained surgery duration prediction model to obtain the predicted surgery duration of the scheduled surgery.

8. An intraoperative load balancing apparatus comprising:

a scheduling scheme determining module, configured to determine, if not, at least one scheduling scheme for scheduling a part of operations in at least one overload operation room to at least one light load operation room based on a set load scheduling policy in a case where at least one overload operation room exists, where a difference between an allocated time length corresponding to the overload operation room and an allocated time length corresponding to the light load operation room is greater than a predicted time length of the scheduled operation;

9. An electronic device, the electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the inter-operative load balancing method of any one of claims 1-7.

10. A computer readable storage medium storing computer instructions for causing a processor to perform the inter-operative load balancing method of any one of claims 1-7.