Nursing personnel scheduling method and device, electronic equipment and storage medium

Abstract

The invention discloses a nursing personnel scheduling method and device, electronic equipment and a storage medium, and relates to the technical field of medical data processing. The method comprises the following steps: inputting a doctor's advice record of a current hospitalized patient into a nursing operation prediction model to obtain a predicted nursing demand of each shift of the current hospitalized patient in a preset time period, and respectively calculating a matching degree between the predicted nursing demand of the ith shift and the nursing operation record of each nurse, and sorting the matching degrees according to a sequence from large to small, taking the nursing personnel corresponding to the matching degrees ranked at the top Si as the initial on-duty personnel of the i-th shift, and optimizing the initial scheduling scheme to obtain a target scheduling scheme meeting constraint conditions. The matching between the nursing demand of the current inpatient and the experience of the nursing personnel on duty is improved, and the risk of misoperation caused by insufficient experience of the nursing personnel can be reduced.

Description

Technical Field

[0001] This application relates to the technical field of medical data processing, and particularly relates to a nursing staff scheduling method, device, electronic device, and storage medium. Background Art

[0002] In the related art, clinical nursing staff play a crucial role in medical services. The management of clinical nursing staff arranges appropriate clinical nursing staff for patients according to the professional levels and skill requirements of clinical nursing staff, as well as the personal information, medical history, treatment plans, etc. of patients, to ensure that patients receive accurate nursing services. Among them, accurately classifying clinical nursing staff helps ensure that patients receive appropriate care.

[0003] However, the nursing operations and experiences that each clinical nursing staff may have performed are different. Currently, the scheduling of nursing staff does not combine the experience of nursing staff with the situation of inpatients in the hospital, which easily leads to a mismatch between the nursing needs of patients and the experience of nurses. Therefore, there is an urgent need to develop a scheduling method that combines the experience of nursing staff with the nursing needs of inpatients in the hospital. Summary of the Invention

[0004] This application aims to at least solve one of the technical problems existing in the prior art. For this purpose, this application provides a nursing staff scheduling method, device, electronic device, and storage medium, which can schedule according to the nursing operation records of nursing staff and the nursing needs of inpatients, and can reduce the risk of improper operations caused by insufficient experience of nursing staff.

[0005] According to the nursing staff scheduling method of the first aspect embodiment of this application, it includes: Obtain a nursing staff data set and an inpatient data set; the nursing staff data set includes the number of nursing staff and the nursing operation records of each nursing staff; the inpatient data set includes the doctor's order records of each current inpatient; Input the doctor's order record into a pre-trained nursing operation prediction model to obtain the predicted nursing needs of each current inpatient for each shift within a preset time period; Based on the predicted nursing needs, determine the nursing staff quantity requirements for each shift; Calculate the matching degree between the predicted nursing needs of the i-th shift and the nursing operation records of each nursing staff respectively, sort the matching degrees in descending order, and use the nursing staff corresponding to the top Si matching degrees as the preliminary scheduled duty staff for the i-th shift; where Si is the nursing staff quantity requirement for the i-th shift; i is 1, 2,..., N, and N is the total number of shifts within the preset time period; the predicted nursing needs include multiple predicted nursing operation items; Generate an initial scheduling plan based on the initially scheduled nursing staff for the 1st shift to the Nth shift; Based on the preset constraint conditions, use a genetic algorithm to optimize the initial scheduling plan to obtain a target scheduling plan that meets the constraint conditions.

[0006] According to the nursing staff scheduling method of the embodiments of the present application, it has at least the following beneficial effects: The nursing staff scheduling method first inputs the medical order records of the current inpatients into the nursing operation prediction model to obtain the predicted nursing needs of the current inpatients for each shift in the preset time period, then calculates the number of nursing staff required for each shift, and then calculates the matching degree between the predicted nursing needs of the i-th shift and the nursing operation records of each nursing staff, sorts the matching degrees in descending order, and takes the nursing staff corresponding to the top Si matching degrees as the initially scheduled nursing staff for the i-th shift to obtain an initial scheduling plan, and then uses a genetic algorithm to optimize the initial scheduling plan to obtain a target scheduling plan that meets the constraint conditions. Since the initial scheduling plan is obtained by scheduling in combination with the nursing operation records of the nursing staff and the nursing needs of the inpatients, the matching degree between the nursing needs of the current inpatients and the experience of the on-duty nursing staff is improved, and the risk of improper operation caused by insufficient experience of the nursing staff can be reduced.

[0007] According to some embodiments of the first aspect of the present application, the nursing operation record includes a plurality of nursing operation items and the historical processing times of each nursing operation item; The calculating the matching degree between the predicted nursing needs of the i-th shift and the nursing operation records of each nursing staff respectively includes: Determine the target nursing operation items that match the predicted nursing needs of the i-th shift from among the multiple nursing operation items of the j-th nursing staff; Accumulate the historical processing times of each target nursing operation item corresponding to the j-th nursing staff to obtain an accumulation result, and use the accumulation result as the matching degree between the j-th nursing staff and the predicted nursing needs of the i-th shift; where j is 1, 2,..., M, and M is the total number of nursing staff.

[0008] According to some embodiments of the first aspect of the present application, the determining the number of nursing staff required for each shift based on the predicted nursing needs includes: Based on the historical average operation duration of each predicted nursing operation item in the predicted nursing needs, calculate the total operation duration of the predicted nursing needs for each shift; Based on the total operation duration, calculate the number of nursing staff required for each shift.

[0009] According to some embodiments of the first aspect of the present application, the training steps of the nursing operation prediction model include: Obtain a medical order training sample, divide the medical order training sample into a first medical order part and a second medical order part in chronological order, and extract a nursing training record from the second medical order part; wherein, the time of the first medical order part is earlier than the time of the second medical order part; Input the first medical order part into the initial nursing operation prediction model to obtain a predicted nursing operation training requirement; Based on the predicted nursing operation training requirement and the second medical order part, calculate a loss value; Based on the loss value, iteratively optimize the nursing operation prediction model to obtain a trained nursing operation prediction model.

[0010] According to some embodiments of the first aspect of the present application, the constraint condition includes a first constraint, and the first constraint is: each nurse cannot be on duty for two consecutive shifts; the expression of the first constraint is: ; Wherein, indicates that the kth nurse is on duty in the tth shift, indicates that the kth nurse is on rest in the tth shift, k is a positive integer less than or equal to the number of nurses, and t is a positive integer less than or equal to the total number of shifts.

[0011] According to some embodiments of the first aspect of the present application, the constraint condition includes a second constraint, and the second constraint is: the number of shifts of each nurse is less than a preset value; the expression of the second constraint is: ; Wherein, indicates that the kth nurse is on duty in the tth shift, indicates that the kth nurse is on rest in the tth shift, T is the total number of shifts, and A is the preset value.

[0012] According to some embodiments of the first aspect of the present application, the nurse dataset includes the levels of nurses, and the levels of nurses include junior and senior; the constraint condition includes a third constraint, and the third constraint includes: each shift must include both a junior-level nurse and a senior-level nurse on duty; the expression of the third constraint is: ; ; Wherein, indicates that the kth junior-level nurse is on duty in the tth shift, It indicates that the k-th primary-level caregiver takes a rest during the t-th shift; It indicates that the k-th senior-level caregiver is on duty during the t-th shift, It indicates that the k-th senior-level caregiver takes a rest during the t-th shift; Y1 is the total number of primary-level caregivers; Y2 is the total number of senior-level caregivers.

[0013] The second aspect embodiment of this application provides a caregiver scheduling device, including: An acquisition module, configured to acquire a caregiver dataset and an in-patient dataset; the caregiver dataset includes the number of caregivers and the care operation records of each caregiver; the in-patient dataset includes the doctor's order records of each current in-patient; An input module, configured to input the doctor's order records into a pre-trained care operation prediction model to obtain the predicted care needs of each current in-patient for each shift during a preset time period; A determination module, configured to determine the number of caregivers needed for each shift based on the predicted care needs; A calculation module, configured to calculate the matching degree between the predicted care needs of the i-th shift and the care operation records of each caregiver respectively, sort the matching degrees in descending order, and take the caregivers corresponding to the top Si matching degrees as the initially determined on-duty caregivers for the i-th shift; where Si is the number of caregivers needed for the i-th shift; i is 1, 2,..., N, and N is the total number of shifts during the preset time period; A generation module, configured to generate an initial scheduling plan based on the initially determined on-duty caregivers for the 1st shift to the Nth shift; An optimization module, configured to optimize the initial scheduling plan using a genetic algorithm based on preset constraint conditions to obtain a target scheduling plan that meets the constraint conditions.

[0014] The third aspect embodiment of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the caregiver scheduling method according to any one of the first aspect embodiments.

[0015] The fourth aspect embodiment of this application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the caregiver scheduling method according to any one of the first aspect embodiments.

[0016] The additional aspects and advantages of this application will be partly given in the following description, partly become obvious from the following description, or be understood through the practice of this application. Description of the Drawings

[0017] The following further describes the present application in conjunction with the accompanying drawings and embodiments, where: Figure 1 is a schematic flow chart of the steps of the nursing staff scheduling method according to an embodiment of the present application; Figure 2 is a schematic diagram of the functional modules of the nursing staff scheduling device according to an embodiment of the present application; Figure 3 is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0018] The following details the embodiments of the present application. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions from beginning to end. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present application, and should not be construed as a limitation to the present application.

[0019] In the description of the present application, it should be understood that for the orientation description, such as the orientation or positional relationship indicated by up, down, front, back, left, right, etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present application.

[0020] In the description of the present application, the meaning of several is more than one, the meaning of multiple is more than two, greater than, less than, exceeding, etc. are understood as not including the number itself, and above, below, within, etc. are understood as including the number itself. If there is a description of first and second, it is only for the purpose of distinguishing technical features and should not be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or implicitly indicating the sequence relationship of the indicated technical features.

[0021] In the description of the present application, unless otherwise clearly defined, words such as setting, installing, connecting, etc. should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meaning of the above words in the present application in combination with the specific content of the technical solution.

[0022] In the description of the present application, the description referring to terms such as "one embodiment", "some embodiments", "schematic embodiments", "examples", "specific examples", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0023] The first aspect embodiment of the present application provides a nursing staff scheduling method. The nursing staff scheduling method provided by the embodiments of the present application relates to the field of artificial intelligence technology. The nursing staff scheduling method provided by the embodiments of the present application can be applied to a terminal, or to a server side, or can be software running on a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, or can be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application for implementing the nursing staff scheduling method, etc., but is not limited to the above forms.

[0024] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment, where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0025] It should be noted that in each specific embodiment of the present application, when it comes to performing relevant processing based on data related to the user's identity or characteristics, such as the doctor's order records of inpatients, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first. For example, when obtaining the user's stored data and the access request for the user's cache data, the user's permission or consent will be obtained first; when obtaining the data of resources, the embodiments of the present application will obtain the user's permission or consent first. Moreover, the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiments of the present application need to obtain the user's sensitive personal information, the user's separate permission or separate consent will be obtained through methods such as pop-up windows or jumping to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user-related data for the normal operation of the embodiments of the present application will be obtained.

[0026] Referring to Figure 1 , Figure 1 is a schematic flowchart of the steps of the nursing staff scheduling method according to the embodiments of the present application. The nursing staff scheduling method according to the embodiments of the present application includes, but is not limited to, steps S110 to S160.

[0027] Step S110, obtaining a nursing staff data set and an inpatient data set; the nursing staff data set includes the number of nursing staff and the nursing operation records of each nursing staff; the inpatient data set includes the doctor's order records of each current inpatient; It should be noted that the number of nursing staff refers to the total number of people who can be scheduled. For example, the number of nursing staff is the total number of nurses in the inpatient department of the hospital.

[0028] In one embodiment, the nursing staff data set and the inpatient data set can be obtained through the hospital information management system of the hospital. Specifically, through the hospital human resources database interface of the hospital information management system, the number of currently on-duty nursing staff and identity identification information (such as employee numbers, department affiliations, professional titles, etc.) are retrieved. Through mobile nursing terminal devices (such as PDAs, smart bracelets), the nursing operation records of each nursing staff are collected. And the dynamic doctor's order records of all current inpatients are extracted through the hospital electronic medical record system (EMR).

[0029] Exemplarily, the nursing operation records of the nursing staff include the nursing operation items performed by the nursing staff. The nursing operation items can be items such as intravenous injection, sputum suction, catheterization, wound dressing change, patient turning, etc.

[0030] Exemplarily, the content of the doctor's order record is the drug type, drug dosage, and medication method. The doctor's order record also includes nursing operation items. For example, the nursing operation item in a doctor's order record is intravenous injection.

[0031] Step S120: Input the doctor's order record into a pre-trained nursing operation prediction model to obtain the predicted nursing needs for each shift of the current in-patient within a preset time period. In one embodiment, a Long Short-Term Memory (LSTM) model is used as the nursing operation prediction model. LSTM is a variant of the recurrent neural network designed specifically for processing time series data. Its core lies in solving the defect that traditional RNN models are difficult to capture long-term dependencies through sophisticated "memory cells" and gating mechanisms.

[0032] It should be noted that the advantage of using the LSTM model as the nursing operation prediction model is that it can effectively capture the temporal dependencies and dynamic change patterns in the doctor's order record. Since the nursing needs of in-patients often show continuous fluctuations with the treatment stage, disease evolution, and doctor's order adjustment (such as the decreasing intensity of postoperative care over time, and the phased needs caused by chemotherapy cycles), LSTM can hierarchically remember and forget long-term and short-term temporal features through the gating mechanism, and can accurately identify the triggering nodes of nursing operations (such as the need for vital sign monitoring after specific drug use), periodic execution rules (such as daily blood glucose testing), and cross-shift task correlations (such as the connection logic between morning care and night observation) hidden in the doctor's order text. The adaptability of LSTM to variable-length sequences can be compatible with patient data of different lengths of stay. By automatically learning the non-linear mapping relationship between the intervals of doctor's order execution and the intensity of nursing operations, it realizes the end-to-end prediction from the individualized treatment path to the future multi-shift demand. This temporal modeling feature is significantly superior to the mechanical segmentation of fixed time windows by traditional statistical methods, and is especially suitable for resource demand prediction with strong temporal relevance in medical scenarios.

[0033] Step S130: Based on the predicted nursing needs, determine the nursing staff quantity requirements for each shift. Step S140: Calculate the matching degrees between the predicted nursing needs of the i-th shift and the nursing operation records of each nurse, sort the matching degrees in descending order, and take the nurses corresponding to the top Si matching degrees as the preliminary scheduled duty nurses for the i-th shift; where Si is the nursing staff quantity requirement for the i-th shift; i = 1, 2,..., N, and N is the total number of shifts within the preset time period. The predicted nursing needs include multiple predicted nursing operation items. Exemplarily, the predicted nursing needs for the 1st shift are sputum suction and urinary catheterization, and the nursing staff quantity requirement for the 1st shift is 5. Then calculate the matching degrees between the nursing operation records of each nurse and ["sputum suction", "urinary catheterization"], sort each matching degree in descending order, and select the nurses corresponding to the top 5 matching degrees as the preliminary scheduled duty nurses for the 1st shift.

[0034] In one embodiment, the preset time period is the next week of the current time, that is, the next 7 days of the current time. There are 3 shifts per day, and each shift is 8 hours, so there are a total of 21 shifts within the preset time period, that is, the total number of shifts is 21.

[0035] It should be noted that step S140 is executed N times. Each time it is executed, the preliminary scheduled duty personnel for one shift are obtained, so as to obtain the preliminary scheduled duty personnel for the 1st shift to the Nth shift.

[0036] Step S150, generate an initial scheduling plan based on the preliminary scheduled duty personnel for the 1st shift to the Nth shift; Step S160, optimize the initial scheduling plan by using a genetic algorithm based on the preset constraint conditions to obtain a target scheduling plan that meets the constraint conditions.

[0037] It should be noted that the genetic algorithm (GA) is a search and optimization technology based on the principles of natural selection and genetics. It simulates the biological evolution process. Through operations such as selection, crossover (recombination), and mutation, the quality of candidate solutions is gradually improved, so as to find the optimal or near-optimal solution in a complex search space. The core idea of the genetic algorithm is to represent the solution of the problem as a "chromosome" and put it into a population. By simulating the genetic operations in the biological evolution process, the chromosomes in the population are continuously evolved until they converge to the optimal solution. In one embodiment, the average duty duration of the nursing staff is used as the optimization objective of the genetic algorithm.

[0038] In the nursing staff scheduling method of the embodiment of the present application, through the above steps S110 to S160, first input the medical order records of the current inpatients into the nursing operation prediction model to obtain the predicted nursing needs of the current inpatients for each shift within the preset time period, then calculate the number of nursing staff required for each shift, and then calculate the matching degree between the predicted nursing needs of the ith shift and the nursing operation records of each nursing staff. Sort the matching degrees in descending order, and use the nursing staff corresponding to the top Si matching degrees as the preliminary scheduled duty personnel for the ith shift to obtain an initial scheduling plan. Then, use a genetic algorithm to optimize the initial scheduling plan to obtain a target scheduling plan that meets the constraint conditions. Since the initial scheduling plan is obtained by scheduling in combination with the nursing operation records of the nursing staff and the nursing needs of the inpatients, the matching degree between the nursing needs of the current inpatients and the experience of the on-duty nursing staff is improved, and the risk of improper operations caused by insufficient experience of the nursing staff can be reduced.

[0039] In some embodiments, the nursing operation record includes multiple nursing operation items and the historical processing times of each nursing operation item; correspondingly, in step S140, the matching degrees between the predicted nursing demands of the i-th shift and the nursing operation records of each nurse are calculated respectively, which specifically includes steps S141 to S143.

[0040] Step S141, calculating the matching degrees between the predicted nursing demands of the i-th shift and the nursing operation records of each nurse respectively, includes: Step S142, determining the target nursing operation items that match the predicted nursing demands of the i-th shift from the multiple nursing operation items of the j-th nurse; Step S143, accumulating the historical processing times of each target nursing operation item corresponding to the j-th nurse to obtain an accumulation result, and taking the accumulation result as the matching degree between the j-th nurse and the predicted nursing demands of the i-th shift; where j is 1, 2,..., M, and M is the total number of nurses.

[0041] Exemplarily, the j-th nurse is nurse S. The specific content of the nursing operation record of nurse S includes intravenous injection, wound dressing change, and nasal feeding. The historical processing times of intravenous injection are 100, the historical processing times of wound dressing change are 10, and the historical processing times of nasal feeding are 5. The predicted nursing demands of the i-th shift include intravenous injection and nasal feeding. Then, it can be determined that the target nursing operation items in the nursing operation record of nurse S include intravenous injection and nasal feeding. The historical processing times of intravenous injection and nasal feeding are accumulated to obtain an accumulation result, and the accumulation result is 100 + 5 = 105.

[0042] In the embodiments of the present application, through steps S141 to S143, the matching degrees between the predicted nursing demands of each shift and the nursing operation records of each nurse are calculated.

[0043] In one embodiment, before step S143, the historical processing times of the nursing operation items are normalized, specifically: Calculating the sum of the actual processing times of the first nursing operation item of all nurses to obtain the first total actual times; Dividing the actual processing times of the first nursing operation item of the first nurse by the first total actual times, and taking the obtained result as the historical processing times of the first nursing operation item of the first nurse.

[0044] It should be noted that the first nursing operation item is one of the multiple nursing operation items, and the first nurse is one of the multiple nurses.

[0045] Exemplarily, the first nursing operation item is intravenous injection. The nursing staff includes nursing staff B, nursing staff C, and nursing staff D. The nursing operation record of nursing staff B includes intravenous injection, and the actual number of times of intravenous injection handled by nursing staff B is X; the nursing operation record of nursing staff C includes intravenous injection, and the actual number of times of intravenous injection handled by nursing staff C is Y; the nursing operation record of nursing staff D includes intravenous injection, and the actual number of times of intravenous injection handled by nursing staff D is Z. Then the total sum of the first actual number of times is X + Y + Z; the historical number of times of the first nursing operation item of nursing staff B is X / (X + Y + Z).

[0046] In some embodiments, step S130, based on the predicted nursing needs, determines the nursing staff quantity requirements for each shift, including step S131 and step S132.

[0047] Step S131, based on the historical average operation duration of each predicted nursing operation item in the predicted nursing needs, calculates the total operation duration of the predicted nursing needs for each shift; Step S132, based on the total operation duration, calculates the nursing staff quantity requirements for each shift.

[0048] In one embodiment, when the nursing staff performs a nursing operation item, records the execution duration of the nursing operation item, so that the historical average operation duration of the nursing operation item can be calculated. Further, based on the historical average operation duration of each predicted nursing operation item in the predicted nursing needs, calculates the total operation duration of the predicted nursing needs for each shift. For example, the predicted nursing needs for a shift include K times of patient turning and L times of nasal feeding. The historical average operation duration of patient turning is O, and the historical average operation duration of nasal feeding is P. Then the total operation duration of this shift is K * O + L * P. After obtaining the total operation duration, obtains the shift efficiency based on each nursing staff, and calculates the average shift efficiency of the nursing staff. The shift efficiency refers to the duration actually used by the nursing staff to perform nursing operation items during the shift. For example, the duty duration of the nursing staff is 8 hours, but the actual duration used to perform nursing operation items is 6 hours. Then the shift efficiency of this nursing staff is 6. Then calculates the nursing staff quantity requirements, and the nursing staff quantity requirements = total operation duration / average shift efficiency.

[0049] In some embodiments, the training steps of the nursing operation prediction model include step S210 to step S240.

[0050] Step S210, obtains the medical order training samples, divides the medical order training samples into a first medical order part and a second medical order part in chronological order, and extracts the nursing training records from the second medical order part; wherein, the time of the first medical order part is earlier than the time of the second medical order part; It should be noted that the doctor's order training samples are divided into a first doctor's order part and a second doctor's order part in chronological order. For example, if the content recorded in the doctor's order training sample corresponds to a time period of 10 days, and since the preset time period is 7 days, the content of the first 3 days in the doctor's order training sample is used as the first doctor's order part, and the content of the last 7 days in the doctor's order training sample is used as the second doctor's order part. Moreover, the doctor's order training sample not only includes nursing operation items but also other content. To reduce the interference of other content, the nursing operation items and the execution time of the nursing operation items are extracted from the second doctor's order part as the nursing training record. The nursing training record serves as the true label for the first doctor's order part. In this way, the trained nursing operation prediction model can output the predicted nursing needs of the current in-patient for each shift within the preset time period based on the doctor's order record of the current in-patient.

[0051] It should be noted that when obtaining the doctor's order training sample, the permission of the patient corresponding to the doctor's order training sample needs to be obtained in advance.

[0052] Step S220: Input the first doctor's order part into the initial nursing operation prediction model to obtain the predicted nursing operation training requirements; Step S230: Calculate the loss value based on the predicted nursing operation training requirements and the nursing training record; Step S240: Iteratively optimize the nursing operation prediction model based on the loss value to obtain the trained nursing operation prediction model.

[0053] In the embodiment of the present application, through steps S210 to S240, the training of the initial nursing operation prediction model is realized. In step S240, the nursing operation prediction model is iteratively optimized based on the loss value until the number of iterations reaches the preset value to obtain the trained nursing operation prediction model. It should be noted that the loss value is calculated through a preset loss function, and the present application does not make specific limitations on the loss function, and those skilled in the art can select the loss function according to actual needs.

[0054] In some embodiments, the constraint condition includes a first constraint, and the first constraint is that each nurse cannot be on duty for two consecutive shifts; the expression of the first constraint is: ; where indicates that the kth nurse is on duty in the tth shift, indicates that the kth nurse is on rest in the tth shift, k is a positive integer less than or equal to the number of nurses, and t is a positive integer less than or equal to the total number of shifts. Through the first constraint, the situation of nurses being on duty continuously can be avoided.

[0055] In some embodiments, the constraint conditions include a second constraint, and the second constraint is that the number of shifts of each caregiver is less than a preset value; the expression of the second constraint is: ; where represents that the k-th caregiver is on duty in the t-th shift, represents that the k-th caregiver takes a rest in the t-th shift, T is the total number of shifts, and A is a preset value. Through the second constraint, the situation where caregivers have too many shifts can be avoided. Those skilled in the art can set the value of A according to the actual situation.

[0056] In some embodiments, the caregiver dataset includes the levels of caregivers, and the levels of caregivers include junior and senior; the constraint conditions include a third constraint, and the third constraint includes that the caregivers on duty in each shift must include both junior-level caregivers and senior-level caregivers; the expression of the third constraint is: ; ; where represents that the k-th junior-level caregiver is on duty in the t-th shift, represents that the k-th junior-level caregiver takes a rest in the t-th shift; represents that the k-th senior-level caregiver is on duty in the t-th shift, represents that the k-th senior-level caregiver takes a rest in the t-th shift; Y1 is the total number of junior-level caregivers; Y2 is the total number of senior-level caregivers. It should be noted that junior-level caregivers are those with less experience; while senior-level caregivers are those with more experience. Junior-level caregivers cannot be on duty independently and need the guidance of senior-level caregivers.

[0057] The second aspect of the embodiments of the present application provides a caregiver scheduling device. Referring to Figure 2 , Figure 2 is a schematic diagram of the functional modules of the caregiver scheduling device according to the embodiments of the present application. The caregiver scheduling device includes: An acquisition module 210, configured to acquire a caregiver dataset and an in-patient dataset; the caregiver dataset includes the number of caregivers and the care operation records of each caregiver; the in-patient dataset includes the medical order records of each current in-patient; An input module 220, configured to input the medical order records into a pre-trained care operation prediction model to obtain the predicted care needs of each current in-patient in each shift within a preset time period; A determination module 230, configured to determine the nursing staff quantity requirement for each shift based on the predicted nursing needs. A calculation module 240, configured to calculate the matching degree between the predicted nursing needs of the i-th shift and the nursing operation records of each nursing staff respectively, sort the matching degrees in descending order, and take the nursing staff corresponding to the top Si matching degrees as the preliminary scheduled duty staff for the i-th shift; where Si is the nursing staff quantity requirement for the i-th shift; i is 1, 2,..., N, and N is the total number of shifts within a preset time period. A generation module 250, configured to generate an initial scheduling plan based on the preliminary scheduled duty staff for the 1st shift to the N-th shift. An optimization module 260, configured to optimize the initial scheduling plan by using a genetic algorithm based on preset constraint conditions to obtain a target scheduling plan that meets the constraint conditions.

[0058] The nurse scheduling device according to the second aspect embodiment of the present application is used to execute the nurse scheduling method according to the first aspect embodiment of the present application. When executing the method, first input the doctor's order records of the current in-patient into the nursing operation prediction model to obtain the predicted nursing needs of the current in-patient for each shift within a preset time period, then calculate the nursing staff quantity requirement for each shift, and then calculate the matching degree between the predicted nursing needs of the i-th shift and the nursing operation records of each nursing staff respectively, sort the matching degrees in descending order, and take the nursing staff corresponding to the top Si matching degrees as the preliminary scheduled duty staff for the i-th shift to obtain an initial scheduling plan, and then optimize the initial scheduling plan by using a genetic algorithm to obtain a target scheduling plan that meets the constraint conditions. Since the initial scheduling plan is obtained by scheduling in combination with the nursing operation records of the nursing staff and the nursing needs of the in-patients, the matching degree between the nursing needs of the current in-patients and the experience of the on-duty nursing staff is improved, and the risk of improper operation caused by insufficient experience of the nursing staff can be reduced.

[0059] It should be noted that the specific implementation manner of this nursing staff scheduling device is basically the same as the specific embodiments of the above nursing staff scheduling method, and will not be elaborated here. On the premise of meeting the requirements of the embodiments of the present application, other functional units can also be set in the nursing staff scheduling device to implement the nursing staff scheduling method in the above embodiments.

[0060] The third aspect embodiment of the present application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the nursing staff scheduling method according to any one of the first aspect embodiments. This electronic device can be any intelligent terminal including a tablet computer, an in-vehicle computer, etc.

[0061] Reference Figure 3 , Figure 3 is a schematic structural diagram of an electronic device according to an embodiment. The electronic device includes: A processor 301, which can be implemented in ways such as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application; A memory 302, which can be implemented in forms such as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 302 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 302 and are called by the processor 301 to execute the caregiver scheduling method of the embodiments of the present application; An input / output interface 303, which is used to implement information input and output; A communication interface 304, which is used to implement communication interaction between this device and other devices, and can implement communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.); A bus 305, which transmits information between various components of the device (such as the processor 301, the memory 302, the input / output interface 303, and the communication interface 304); Among them, the processor 301, the memory 302, the input / output interface 303, and the communication interface 304 achieve communication connections with each other inside the device through the bus 305.

[0062] In the fourth aspect of the embodiments of the present application, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the caregiver scheduling method according to any one of the embodiments of the first aspect.

[0063] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory optionally includes a memory remotely disposed relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0064] The embodiments described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art will know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0065] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than those shown in the figures, or combine certain steps, or different steps.

[0066] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0067] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices can be implemented as software, firmware, hardware, and appropriate combinations thereof.

[0068] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order different from those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0069] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the mapping relationship of mapped objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Here, A and B can be singular or plural. The character " / " generally indicates an "or" relationship between the front and back mapped objects. "At least one (one)" or similar expressions below refer to any combination of these items, including any combination of single item (one) or plural items (ones). For example, at least one (one) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0070] In several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the above division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0071] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0072] In addition, the functional units in each embodiment of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0073] When an integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes: various media that can store programs, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0074] The preferred embodiments of the embodiments of this application have been described above with reference to the accompanying drawings. This does not limit the scope of the rights of the embodiments of this application. Any modifications, equivalent replacements, and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of this application shall be within the scope of the rights of the embodiments of this application.

Claims

1. A scheduling method for nursing staff, characterized in that, Including: Obtaining a dataset of nursing staff and a dataset of inpatients; The dataset of nursing staff includes the number of nursing staff and the nursing operation records of each nursing staff; The dataset of inpatients includes the doctor's order records of each current inpatient; Inputting the doctor's order records into a pre-trained nursing operation prediction model to obtain the predicted nursing needs of each shift for the current inpatients within a preset time period; Based on the predicted nursing needs, determining the number of nursing staff required for each shift; Calculating the matching degree between the predicted nursing needs of the i-th shift and the nursing operation records of each nursing staff respectively, sorting the matching degrees in descending order, and taking the nursing staff corresponding to the top Si matching degrees as the preliminary scheduled duty staff for the i-th shift; where Si is the number of nursing staff required for the i-th shift; i is 1, 2,..., N, and N is the total number of shifts within the preset time period; the predicted nursing needs include multiple predicted nursing operation items; Generating an initial scheduling plan based on the preliminary scheduled duty staff from the 1st shift to the Nth shift; Based on the preset constraint conditions, using a genetic algorithm to optimize the initial scheduling plan to obtain a target scheduling plan that meets the constraint conditions.

2. The nursing staff scheduling method according to claim 1, wherein The nursing operation records include multiple nursing operation items and the historical processing times of each nursing operation item; The calculating the matching degree between the predicted nursing needs of the i-th shift and the nursing operation records of each nursing staff respectively includes: Determining the target nursing operation items that match the predicted nursing needs of the i-th shift from the multiple nursing operation items of the j-th nursing staff; Accumulating the historical processing times of each target nursing operation item corresponding to the j-th nursing staff to obtain an accumulation result, and taking the accumulation result as the matching degree between the j-th nursing staff and the predicted nursing needs of the i-th shift; where j is 1, 2,..., M, and M is the total number of nursing staff.

3. The nursing staff scheduling method according to claim 1, characterized in that, The determining the number of nursing staff required for each shift based on the predicted nursing needs includes: Based on the historical average operation duration of each predicted nursing operation item in the predicted nursing needs, calculating the total operation duration of the predicted nursing needs for each shift; Based on the total operation duration, calculating the number of nursing staff required for each shift.

4. The nursing staff scheduling method according to claim 1, wherein The training steps of the nursing operation prediction model include: Obtaining doctor's order training samples, dividing the doctor's order training samples into a first doctor's order part and a second doctor's order part in chronological order, and extracting nursing training records from the second doctor's order part; where the time of the first doctor's order part is earlier than the time of the second doctor's order part; Inputting the first doctor's order part into an initial nursing operation prediction model to obtain predicted nursing operation training needs; Calculating a loss value based on the predicted nursing operation training needs and the nursing training records; Based on the loss value, iteratively optimizing the nursing operation prediction model to obtain a trained nursing operation prediction model.

5. The nursing staff scheduling method according to claim 1, wherein The constraint conditions include a first constraint, and the first constraint is that each caregiver cannot be on duty for two consecutive shifts; the expression of the first constraint is: ； Among them, indicates that the k-th caregiver is on duty in the t-th shift, indicates that the k-th caregiver takes a rest in the t-th shift, where k is a positive integer less than or equal to the number of caregivers, and t is a positive integer less than or equal to the total number of shifts.

6. The nursing staff scheduling method according to claim 5, wherein The constraint conditions include a second constraint, and the second constraint is that the number of shifts of each caregiver is less than a preset value; the expression of the second constraint is: ； Among them, indicates that the k-th caregiver is on duty in the t-th shift, indicates that the k-th caregiver takes a rest in the t-th shift, T is the total number of the shifts, and A is the preset value.

7. The nursing staff scheduling method according to claim 6, wherein The caregiver dataset includes the levels of caregivers, and the levels of caregivers include junior and senior; the constraint conditions include a third constraint, and the third constraint includes that the caregivers on duty for each shift must include both junior-level caregivers and senior-level caregivers; the expression of the third constraint is: ； ； Among them, indicates that the k-th primary-level caregiver is on duty in the t-th shift, indicates that the k-th primary-level caregiver takes a rest in the t-th shift; indicates that the k-th senior-level caregiver is on duty in the t-th shift, indicates that the k-th senior-level caregiver takes a rest in the t-th shift; Y1 is the total number of primary-level caregivers; Y2 is the total number of senior-level caregivers.

8. A nursing staff scheduling device, characterized in that, including: An acquisition module, configured to acquire a caregiver dataset and an in-patient dataset; The caregiver dataset includes the number of caregivers and the nursing operation records of each caregiver; the in-patient dataset includes the medical order records of each current in-patient; An input module, configured to input the medical order records into a pre-trained nursing operation prediction model to obtain the predicted nursing needs of each shift of the current in-patient within a preset time period; A determination module, configured to determine the number of caregivers required for each shift based on the predicted nursing needs; A calculation module, configured to calculate the matching degree between the predicted nursing needs of the i-th shift and the nursing operation records of each caregiver respectively, sort the matching degrees in descending order, and use the caregivers corresponding to the top Si matching degrees as the preliminary scheduled caregivers for the i-th shift; where Si is the number of caregivers required for the i-th shift; i is 1, 2,..., N, and N is the total number of shifts within the preset time period; A generation module, configured to generate an initial scheduling plan based on the preliminary scheduled caregivers from the 1st shift to the Nth shift; An optimization module, configured to optimize the initial scheduling plan by using a genetic algorithm based on the preset constraint conditions to obtain a target scheduling plan that meets the constraint conditions.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, it implements the caregiver scheduling method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the caregiver scheduling method according to any one of claims 1 to 7.

Images