Method and apparatus for predicting employment period of hospital personnel

Abstract

The present invention relates to a method and apparatus for predicting an employment period of hospital personnel, and more particularly, to a method and apparatus for collecting and normalizing personal data and employment data of hospital personnel, generating an employment period prediction model using item-specific assigned weights, and deriving an expected employment period of the hospital personnel through the generated prediction model.

Description

Method and device for predicting the working period of hospital staff

[0001] The present invention relates to a method and apparatus for predicting the employment period of hospital personnel, and more specifically, to a method and apparatus for predicting the employment period of hospital personnel based on information of personnel working at the hospital or applicants who have applied for hospital employment.

[0002] In medical institutions such as hospitals, various personnel, including doctors and nurses, play crucial roles in patient care and hospital operations. However, staff stability and long-term employment are essential for maintaining operational efficiency and providing high-quality medical services to patients. In particular, staff turnover directly impacts operational efficiency and patient satisfaction, requiring hospitals to invest significant costs and resources in recruiting and training new personnel.

[0003] Currently, hospitals are making various attempts to predict the tenure of their workforce, and statistical analysis methods are generally used for this purpose. These methods primarily analyze key characteristics that can influence tenure based on existing personnel data and predict the tenure of new hires based on this analysis.

[0004] However, existing statistical methods have limitations in comprehensively reflecting various factors such as hospital size, work department, and individual characteristics. Furthermore, due to a lack of adaptability to new work environments or unpredictable factors, the accuracy of employment duration predictions may consequently decrease.

[0005] In particular, at medical institutions, the tenure of staff can vary depending on the characteristics of each department or the size of the hospital. For instance, personnel working in high-intensity departments such as emergency rooms and intensive care units may exhibit relatively higher turnover rates compared to other departments, and differences in working environments between large and small-to-medium-sized hospitals can also affect the length of employment.

[0006] Recently, machine learning technology is being effectively utilized for data-driven forecasting across various industries, and there is an increasing number of attempts by hospitals to adopt this technology to predict the tenure of their workforce. Compared to traditional statistical analysis methods, machine learning models have the advantage of being able to process multidimensional and complex data and automatically learn key characteristics that influence tenure within a structure where various factors interact. Furthermore, machine learning models have the potential to provide more accurate predictions when forecasting the tenure of new hires based on historical data.

[0007] However, existing machine learning-based methods are limited to merely extracting data patterns during the training process and often fail to subdivide the impact of each characteristic on working duration or effectively reflect the relationships between characteristics. Furthermore, there is a problem in that the model's predictive performance may degrade if the training weights are not sufficiently linked to the data distribution or statistical characteristics of each characteristic.

[0008] The method and apparatus for predicting the working period of hospital personnel according to an embodiment of the present invention are intended to predict the working period of hospital personnel.

[0009] In addition, the method and apparatus for predicting the employment period of hospital staff according to an embodiment of the present invention are intended to provide a recommended work department for newly hired personnel.

[0010] However, the technical problem that this embodiment aims to solve is not limited to the technical problem described above, and other technical problems may exist.

[0011] As a technical means for achieving the aforementioned technical task, a method for calculating the expected working period of hospital personnel according to an embodiment of the present invention is a method for calculating the expected working period of hospital personnel, comprising: a step of collecting personal data and work data of existing personnel working at the hospital; a step of preprocessing the personal data of the existing personnel and the work data of the existing personnel to generate normalized data;

[0012] The method includes the steps of: setting weights for each item included in the personal data and each item included in the work data based on the normalized data; generating a hospital staff work period prediction model trained to derive the expected work period of the hospital staff using the weights; and inputting the personal data and work history data of the hospital staff into the hospital staff work period prediction model to derive the expected work period of the hospital staff.

[0013] In addition, the step of collecting personal data and work data of existing personnel according to an embodiment of the present invention includes the step of setting the age, gender, educational background, certifications, work experience, major, and number of job changes of the existing personnel as items included in the personal data, and the step of setting the work department, working hours, work type, hospital size, hospital location, average commuting distance, and annual vacation days of the existing personnel as items included in the work data.

[0014] In addition, the step of generating normalized data according to an embodiment of the present invention includes the step of generating a distribution graph for each item included in the personal data of the existing personnel and the work data of the existing personnel, and the step of generating the normalized data by removing noise data included in the distribution graph based on the normal distribution graph.

[0015] In addition, the step of setting item-specific weights according to an embodiment of the present invention is,

[0016] The method includes the steps of: generating item-specific graphs of the personal data of the existing personnel and the work data of the existing personnel; deriving a match rate by comparing the item-specific graphs with a normal distribution graph; deriving a first weight for each item based on the match rate; deriving an item-specific slope for the loss function and deriving a second weight based on the slope; setting the average value of the first weight and the second weight as the final weight; and generating a retrained hospital personnel work period prediction model based on the final weight.

[0017] In addition, the step of deriving a first weight according to an embodiment of the present invention includes the step of deriving the first weight using a first mathematical formula, [first mathematical formula] In the above mathematical formula 1 is an item The distribution function of the actual data for, is the normal distribution function, is the standard deviation between two distributions, in the item It means the first weight for.

[0018] In addition, the step of deriving a second weight according to an embodiment of the present invention includes the step of deriving the second weight using a second mathematical formula, [second mathematical formula] In the second mathematical formula above is the loss function of the above hospital staff employment period prediction model, Key items affecting employment period , is the relevant item It means the second weight for .

[0019] Additionally, the step of generating a learned hospital workforce employment period prediction model according to an embodiment of the present invention includes generating the hospital workforce employment period prediction model to include one or more of Large Language Models (LLM), Random Forest, Gradient Boosting, or Multilayer Perceptron.

[0020] In addition, the device for providing a service for calculating the expected working period of hospital personnel according to an embodiment of the present invention is a device for providing a service for calculating the expected working period of hospital personnel, and includes a memory for storing a program for calculating the expected working period of hospital personnel, and a processor for executing the program for calculating the expected working period of hospital personnel stored in the memory. The processor collects personal data and work data of existing personnel working at the hospital, preprocesses the personal data and work data of the existing personnel to generate normalized data, sets weights for each item included in the personal data and each item included in the work data based on the normalized data, generates a hospital personnel working period prediction model trained to derive the expected working period of hospital personnel using the weights, and inputs the personal data and work history data of the hospital personnel into the hospital personnel working period prediction model to derive the expected working period of the hospital personnel.

[0021] The method and device for predicting the working period of hospital personnel according to an embodiment of the present invention can predict the working period of hospital personnel.

[0022] In addition, the method and device for predicting the working period of hospital personnel according to an embodiment of the present invention can provide a recommended work department for newly hired personnel.

[0023] FIG. 1 is an exemplary diagram showing the communication connection of a hospital staff work period prediction device according to an embodiment of the present invention.

[0024] Figure 2 is a configuration diagram of a hospital staffing period prediction server according to an embodiment of the present invention.

[0025] FIG. 3 is a configuration diagram of a terminal according to an embodiment of the present invention.

[0026] FIG. 4 is a conceptual diagram illustrating the functions of a processor according to an embodiment of the present invention.

[0027] FIGS. 5 and 6 are flowcharts of a method for predicting the working period of hospital personnel according to an embodiment of the present invention.

[0028] Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement the invention. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals.

[0029] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are "directly connected," but also cases where they are "electrically connected" with other components interposed between them. Furthermore, when a part is described as "including" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0030] In addition, the attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification, and the technical concept disclosed in this specification is not limited by the attached drawings; it should be understood that all modifications, equivalents, and substitutions included within the concept and technical scope of the present invention are included.

[0031] Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. These terms are used solely for the purpose of distinguishing one component from another.

[0032] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

[0033] A singular expression includes a plural expression unless the context clearly indicates otherwise.

[0034] In this application, terms such as “comprising” or “having” are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0035] Hereinafter, a hospital staff employment period prediction device according to an embodiment of the present invention will be described with reference to FIG. 1.

[0036] FIG. 1 is an exemplary diagram showing the communication connection between a hospital staff work period prediction service relay server (100) and a terminal (200) according to an embodiment of the present invention.

[0037] Referring to FIG. 1, a hospital staffing period prediction service relay server (100) is connected to a terminal (300) via a communication network. At this time, the hospital staffing period prediction service relay server (100) refers to a device that performs data processing to provide a hospital staffing period prediction service, and may correspond to a computing device, a server device, etc. The terminal (200) may refer to a device that receives data from a user and transmits it to the hospital staffing period prediction service relay server (100), or displays data received from the hospital staffing period prediction service relay server (100).

[0038] The hospital staff work period prediction service relay server (100) can create an interface to provide the hospital staff work period prediction service and provide it to the terminal (200), or create a message and notification list and provide it to the terminal (200).

[0039] Accordingly, personal information data and work history data of new applicants, new hires, or existing employees can be entered using the terminal (200), and the personal information data and employee data entered through the terminal (200) are transmitted to the hospital employee work period prediction service relay server (100).

[0040] A hospital staff employment period prediction service relay server (100) can derive the expected employment period of a new applicant, an employee, or an existing employee, or the expected employment period by department based on the received personal information data and staff data, and provide the derived expected employment period data to a terminal (200).

[0041] The terminal (200) may refer to any type of handheld-based wireless communication device, such as a laptop, desktop, laptop, a wireless communication device with guaranteed portability and mobility, or a smartphone, tablet PC, etc., equipped with a web browser.

[0042] In addition, the communication network illustrated in FIG. 1 can be implemented as a wired network such as a Local Area Network (LAN), Wide Area Network (WAN), or Value Added Network (VAN), or as any type of wireless network such as a mobile radio communication network or a satellite communication network.

[0043] Hereinafter, the structure of a hospital staff work period prediction service relay server according to an embodiment of the present invention will be described with reference to FIG. 2.

[0044] FIG. 2 is a structural diagram illustrating the structure of a hospital staff work period prediction service relay server (100) according to an embodiment of the present invention.

[0045] Referring to FIG. 2, the hospital staff work period prediction service relay server (100) includes a communication module (110), memory (120), and a processor (140), and may further include a database (130). The communication module (110) performs information transmission and reception with a terminal (200). The communication module (110) may include a device including hardware and software necessary to transmit and receive signals, such as control signals or data signals, using a wired or wireless connection with another network device.

[0046] The memory (120) stores a hospital staff employment period prediction program. The name of the hospital staff employment period prediction program is set for convenience of explanation and does not limit the function of the program by the name itself. The memory (120) can store at least one of the following: information and data input to the communication module (110), information and data required for functions performed by the processor (140), and data generated by the execution of the processor (140).

[0047] The term "memory" (120) should be interpreted as a collective term for a non-volatile storage device that retains stored information even when power is not supplied, and a volatile storage device that requires power to retain stored information. Additionally, the memory (120) can perform the function of temporarily or permanently storing data processed by the processor (140). The memory (120) may include magnetic storage media or flash storage media in addition to a volatile storage device that requires power to retain stored information, but the scope of the present invention is not limited thereto.

[0048] The database (130) can store personal information data and work history data regarding personnel, as well as data related to the training of the hospital personnel employment period prediction model. The database (130) may constitute a part of the memory (120), but it is not necessarily located inside the hospital personnel employment period prediction service relay server (100), and may be connected to the outside of the hospital personnel employment period prediction service relay server (100) to perform data transmission and reception using a communication connection.

[0049] Additionally, the database (130) can be configured to store data by medical institution (hospital) unit and by work department unit.

[0050] The processor (140) is configured to execute a hospital staffing period prediction program stored in memory (120). The processor (140) may include various types of devices for controlling and processing data. The processor (140) may refer to a data processing device embedded in hardware having a physically structured circuit to perform a function expressed by code or instructions included in the program.

[0051] In one example, the processor (140) may be implemented in the form of a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc., but the scope of the invention is not limited thereto.

[0052] The processor (140) is configured to execute a hospital staffing period prediction program and perform the following functions and procedures.

[0053] The processor (140) can perform a data processing process to derive an expected period of employment or an expected period of employment by department based on personal information data and work history data of new applicants, new hires, or existing employees.

[0054] Specifically, the processor (140) collects personal data and work data of existing personnel working at the hospital, and preprocesses the personal data and work data of existing personnel to generate normalized data.

[0055] And, the processor (140) sets weights for each item included in the personal data of the existing personnel and each item included in the work data of the existing personnel based on normalized data, and creates a trained hospital personnel work period prediction model to derive the expected work period of the hospital personnel using the set weights.

[0056] Additionally, the processor (140) can derive the expected working period of the hospital staff by inputting the personal data and work history data of the hospital staff received from the terminal (200) into a learned hospital staff working period prediction model. At this time, the hospital staff may include hospital staff applicants who have applied for new employment, new employees, or existing hospital staff who wish to transfer departments.

[0057] Additionally, the processor (140) can set the age, gender, education level, certifications, career, major, and number of job changes of existing personnel as items included in personal data, and the department, working hours, type of work, hospital size, hospital location, average commute distance, and number of annual vacation days of existing personnel as items included in work data.

[0058] Additionally, the processor (140) can generate a distribution graph for each item included in the personal data and work data of the existing personnel, and generate normalized data by removing noise data included in the distribution graph based on the normal distribution graph.

[0059] Additionally, the processor (140) generates item-by-item graphs of the personal data and work data of the existing personnel, and derives a match rate by comparing the item-by-item graphs with a normal distribution graph. Then, the processor (140) derives a first weight for each item based on the derived match rate.

[0060] Additionally, the processor (140) derives an item-specific gradient for the loss function and derives a second weight based on the derived gradient. Then, the processor (140) sets the average value of the derived first weight and second weight as the final weight and generates a retrained hospital staff employment period prediction model based on the final weight.

[0061] Additionally, the processor (140) derives the first weight using the first mathematical formula, and

[0062]

[0063] In mathematical formula 1 is an item The distribution function of the actual data for, is the normal distribution function, is the standard deviation between two distributions, The item It means the first weight for .

[0064] Additionally, the processor (140) derives the second weight using mathematical formula 2, and

[0065]

[0066] In mathematical formula 2 is the loss function of the above hospital staff employment period prediction model, Key items affecting employment period , is the relevant item It means the second weight for .

[0067] Additionally, the processor (140) can generate the hospital staff employment period prediction model to include one or more of Large Language Models (LLM), Random Forest, Gradient Boosting, or Multilayer Perceptron.

[0068] FIG. 3 is a block diagram illustrating the configuration of a terminal (200).

[0069] Referring to FIG. 3, the terminal (200) includes a memory (220), an input / output module (230), and a processor (240), and may further include a communication module (210).

[0070] The communication module (210) can perform information transmission and reception with an external database or an external device. Here, the external device may be the hospital staff employment period prediction service relay server (100 in FIG. 1) described above. The memory (220) stores the hospital staff employment period prediction program. The name of the hospital staff employment period prediction program is set for convenience of explanation and does not limit the function of the program by the name itself. The input / output module (230) can receive information, data, etc. transmitted from the outside to the terminal (200), or output information, data, etc. held by the terminal (200) to the outside. For example, the input / output module (230) may include a display, a touchpad, etc. The processor (240) executes the hospital staff employment period prediction program stored in the memory (220). Additional descriptions of the communication module (210), memory (220), and processor (240) are replaced by the descriptions of the communication module (110 in FIG. 2), memory (120 in FIG. 2), and processor (140 in FIG. 2) described above with reference to FIG. 2.

[0071] Hereinafter, the operation and function of the processor (140) according to an embodiment of the present invention will be described in detail with reference to FIG. 4.

[0072] FIG. 4 is a conceptual diagram illustrating the functions of a hospital staff work period prediction service relay server according to an embodiment of the present invention.

[0073] Referring to FIG. 4, the processor (140) includes a personal data management module (141), a work data management module (142), a graph generation module (143), a weight setting module (144), and a hospital staff work period prediction module (145).

[0074] The personal data management module (141) collects, stores, and manages personal data related to personnel who have worked at the hospital, personnel currently working at the hospital, and newly recruited personnel to work at the hospital. The personal data management module (141) can store and manage personal data at the hospital unit, hospital size unit, or work department unit.

[0075] In addition, the personal data management module (141) can collect data related to the personal information of personnel who have worked at the hospital, personnel currently working at the hospital, and newly supported personnel from other hospital servers or personnel data management servers linked to the hospital personnel work period prediction service relay server.

[0076] The personal data management module (141) can store and manage personal information related to an individual, such as age, gender, education level, qualifications held, career, major, number of job changes, marital status, presence of children, age of children, etc., in a database (130) by category.

[0077] The work data management module (142) collects, stores, and manages data related to the work history of personnel who have worked at the hospital, personnel currently working at the hospital, and newly recruited personnel to work at the hospital. The work data management module (142) can store and manage personnel work data at the hospital unit, hospital size unit, or work department unit.

[0078] Additionally, the work data management module (142) can collect data related to the work history of personnel who have worked at the hospital, personnel currently working at the hospital, and newly supported hospital personnel from other hospital servers or personnel data management servers linked to the hospital personnel work period prediction service relay server.

[0079] The work data management module (142) can store and manage information related to the work history and conditions of current hospital staff in the database (130) by item, such as work department, work hours, work type, hospital size, hospital location, average commute distance, annual vacation days, and whether it is a three-shift system.

[0080] The graph generation module (143) receives personal data of existing personnel and work data of existing personnel stored in the database (130), and generates a data distribution graph for each item containing personal data and work data of existing personnel.

[0081] In this case, the data distribution graph can be set so that the X-axis represents the item value and the Y-axis represents the work period value.

[0082] Additionally, the graph generation module (143) can compare the generated item-specific distribution graph with the normal distribution graph to remove noise included in the distribution graph and generate item-specific normalized data based on the noise-removed distribution graph.

[0083] Specifically, the graph generation module (143) can compare the item-specific distribution graph with the normal distribution graph, set item-specific data that falls outside a preset range from the normal distribution graph as noise data, and remove the noise data to generate normalized data.

[0084] The weight setting module (144) sets weights for training the hospital staff work period prediction model generated using the hospital staff work period prediction module (145).

[0085] The weight setting module (144) derives a match rate by comparing the item-by-item graphs of the existing personnel's personal data and work data, generated using the graph generation module (143), with a normal distribution graph. Then, the weight setting module (144) sets a first weight for each item based on the derived match rate.

[0086] Specifically, the first weight can be derived using the above-described mathematical formula 1, and the first weight can have a value between 0 and 1.

[0087] Additionally, the weight setting module (144) derives an item-specific slope for the loss function and derives a second weight based on the derived slope.

[0088] Specifically, the second weight can be derived using the aforementioned mathematical formula 2 and may have a second positive or negative real value.

[0089] The weight setting module (144) can set the average value of the derived first weight and second weight as the final weight. At this time, the weight setting module (144) can perform normalization and Z-score standardization to appropriately set the range of the first weight and second weight.

[0090] The weight setting module (144) can perform normalization of the second weight using the following mathematical formula 3 to normalize the second weight to a value between 0 and 1.

[0091]

[0092] In the aforementioned mathematical formula 3 represents the second weight, and represents the normalized value of the second weight, and is the maximum value of the second weight, represents the minimum value of the second weight.

[0093] Additionally, the weight setting module (144) can perform Z-score standardization using Equation 4 so that the normalized values ​​of the first weight and the second weight have the same distribution.

[0094]

[0095] In the aforementioned mathematical formula 4 , represents the average value of the first weight and the second weight, respectively, and , represents the standard deviations of the first weight and the second weight, respectively, and and represents the first and second weights, respectively, after performing Z-score standardization.

[0096] The weight setting module (144) can consistently set the range and distribution of the first weight and the second weight as it performs Z-score standardization.

[0097] The weight setting module (144) can set the average value of the first weight and the second weight, which have undergone Z-score standardization, as the final weight and apply the final weight to the hospital staff employment period prediction model to perform training of the hospital staff employment period prediction model.

[0098] The hospital staff employment period prediction module (145) generates a learned hospital staff employment period prediction model using the personal data and employment data of existing personnel stored in the database (130), the employment period, and the final weights set using the weight setting module (144).

[0099] In addition, the hospital staff employment period prediction module (145) can derive the expected employment period of a new applicant, a new hospital worker, or an existing hospital worker who wishes to transfer department by inputting personal data and work data of a new applicant, a new hospital worker, or an existing hospital worker who wishes to transfer department, selected or entered using a terminal (200), into a learned hospital staff employment period prediction model.

[0100] That is, the hospital staff employment period prediction module (145) can derive the expected employment period of a new applicant or a hospital staff member who wishes to transfer department by using data related to personal information such as the age, gender, education level, qualifications held, career, major, number of job changes, marital status, presence of children, age of children, etc., and data related to work such as the work department, working hours, work type, hospital size, hospital location, average commute distance, annual vacation days, etc., as well as the work history, working conditions, etc., of the current hospital staff member, etc., such as whether it is a 3-shift system. At this time, the hospital staff employment period prediction module (145) can derive the predicted employment period according to the work department. Accordingly, the hospital staff employment period prediction module (145) can provide the top 5 work departments with high predicted employment periods as recommended work departments.

[0101] Additionally, the hospital staff employment period prediction module (145) can provide N personnel with the highest predicted employment period for each work department as recommended personnel when there are multiple new applicants and new hospital employees.

[0102] Additionally, the hospital staff employment period prediction module (145) can generate a hospital staff employment period prediction model using a Large Language Models (LLM), or using one or more models of Random Forest, Gradient Boosting, or Multilayer Perceptron.

[0103] In addition, when the hospital staff employment period prediction module (145) is implemented using a large-scale language model, the hospital staff employment period prediction module (145) can improve the accuracy of predicting the applicant's hospital employment period by generating a questionnaire that can be used during an interview or by providing additional feedback on the answers to the aforementioned questionnaire.

[0104] Specifically, the hospital staff employment period prediction module (145) can generate keywords related to items for which normalized data cannot be generated using the graph generation module (143) and / or items for which final weights cannot be derived using the weight setting module (144), and can generate a questionnaire containing questions regarding the generated keywords.

[0105] Specifically, the hospital staff employment period prediction module (145) generates questions that can identify the applicant's intention regarding the keyword in order to predict the employment period, such as the importance of the applicant's employment related to the keyword, and whether the applicant is positive or negative regarding the keyword.

[0106] The interviewer can conduct an interview based on a questionnaire generated using the aforementioned hospital staff employment period prediction module (145) and input the answers to the questionnaire back into the hospital staff employment period prediction module (145). Accordingly, the hospital staff employment period prediction module (145) can additionally adjust the predicted employment period based on the answers to the questionnaire.

[0107] Specifically, the hospital staff employment period prediction module (145) classifies words that have a positive or negative meaning among the words included in the answers to the questionnaire. Then, it adjusts the applicant's expected employment period based on the number of positive or negative words.

[0108] For example, if the number of positive words exceeds a preset threshold, the expected working period may be increased by a preset multiplier or period, or if the number of negative words exceeds a preset threshold, the expected working period may be shortened by a preset multiplier or period. Hereinafter, a method for predicting the working period of hospital personnel according to an embodiment of the present invention will be described in detail with reference to FIGS. 5 and 6.

[0109] FIGS. 5 and 6 are flowcharts of a method for predicting the working period of hospital personnel according to an embodiment of the present invention.

[0110] Referring to FIG. 5, a method for predicting the working period of hospital staff according to an embodiment of the present invention includes a step of collecting personal data and work data (S100), a preprocessing step (S200), a weight setting step (S300), a step of learning a model for predicting the working period of hospital staff (S400), a step of inputting data of new hires (S500), and a step of deriving the expected working period of new hires (S600).

[0111] In the personal data and work data collection step (S100), the hospital staff work period prediction service relay server (100) collects, stores, and manages data related to the personal details and work history of personnel who have worked at the hospital, personnel currently working at the hospital, and new support staff.

[0112] In the personal data and work data collection step (S100), the hospital staff work period prediction service relay server (100) can store and manage personal data at the hospital unit, hospital size unit, or work department unit.

[0113] Additionally, in the personal data and work data collection step (S100), the hospital staff work period prediction service relay server (100) can store and manage personal information such as age, gender, education level, qualifications held, career, major, number of job changes, marital status, presence of children, age of children, etc., as items of personal data.

[0114] In addition, in the personal data and work data collection step (S100), the hospital staff work period prediction service relay server (100) can store and manage information related to the work history and conditions of the current hospital staff as items of work data, such as work department, work hours, work type, hospital size, hospital location, average commute distance, annual vacation days, and whether it is a three-shift system.

[0115] In the preprocessing step (S200), the hospital staff work period prediction service relay server (100) generates a data distribution graph for each item containing personal data and work data of existing personnel.

[0116] And, in the preprocessing step (S200), the hospital staff work period prediction service relay server (100) compares the generated item-specific distribution graph with the normal distribution graph to remove noise included in the distribution graph, and generates item-specific normalized data based on the noise-removed distribution graph.

[0117] Specifically, in the preprocessing step (S200), the hospital staff work period prediction service relay server (100) compares the item-specific distribution graph with the normal distribution graph, sets item-specific data that falls outside the preset range from the normal distribution graph as noise data, and removes the noise data to generate normalized data, thereby performing preprocessing on the training data.

[0118] In the weight setting step (S300), the hospital staff work period prediction service relay server (100) sets weights for training the hospital staff work period prediction model.

[0119] Specifically, in the weight setting step (S300), the hospital staff employment period prediction service relay server (100) derives a match rate by comparing the item-specific graphs of the existing staff's personal data and work data with a normal distribution graph. Then, based on the derived match rate, a first weight is set for each item. At this time, in order to derive the first weight, the hospital staff employment period prediction service relay server (100) can derive the first weight using the mathematical formula 1 described above.

[0120] Additionally, in the weight setting step (S300), the hospital staff employment period prediction service relay server (100) derives a slope for each item of the loss function and derives a second weight based on the derived slope. At this time, in order to derive the second weight, the hospital staff employment period prediction service relay server (100) can derive a 12th weight using the above-described mathematical formula 2.

[0121] And, in the weight setting step (S300), the hospital staff work period prediction service relay server (100) performs normalization of the second weight using the mathematical formula 3 described above. In the weight setting step (S300), normalization of the second weight can be performed to match the range of the first weight and the second weight.

[0122] Additionally, in the weight setting step (S300), the hospital staff work period prediction service relay server (100) can perform Z-score standardization on the first weight and the second weight that has undergone normalization processing using the above-described mathematical formula 4.

[0123] And, in the weight setting step (S300), the hospital staff work period prediction service relay server (100) can derive the average value of the first weight and the second weight derived as a result of performing Z-score standardization processing as the final weight.

[0124] In the hospital staff employment period prediction model learning step (S400), the hospital staff employment period prediction service relay server (100) generates a learned hospital staff employment period prediction model using the personal data and work data of existing personnel derived by performing the preprocessing step (S200) described above and the final weights derived by performing the weight setting step (S300).

[0125] In this case, the learned hospital staff employment duration prediction model can be generated using one or more models such as Random Forest, Gradient Boosting, or Multilayer Perceptron.

[0126] In the new employee data input step (S500), the user can input personal data and work data of a new applicant or new employee using a terminal (200), or select data corresponding to a new applicant or new employee from among the stored data.

[0127] When a user inputs or selects personal data and work data of a new applicant or new hire using a terminal (200), the hospital staff work period prediction service relay server (100) inputs the personal data and work data of the input or selected new applicant or new hire into a trained hospital staff work period prediction model and derives a predicted work period. At this time, the predicted work period may be derived by division by work department.

[0128] In the step of deriving the expected working period of new employees (S600), the hospital staff working period prediction service relay server (100) can transmit the expected working period of new applicants and new hospital employees by department to the terminal (200) and provide it to the user.

[0129] Additionally, in the step of deriving the expected working period of new hires (S600), the hospital staff working period prediction service relay server (100) can provide the top 5 working departments with the highest predicted working periods as recommended working departments, and if there are multiple new hire applicants and new hospital hires, it can provide N personnel with the highest predicted working periods for each working department as recommended personnel.

[0130] Additionally, in the step of deriving the expected working period of a new employee (S600), if the hospital staff working period prediction service relay server (100) is implemented using a large-scale language model, the hospital staff working period prediction module (145) can improve the accuracy of predicting the applicant's hospital working period by generating a questionnaire that can be used during an interview or by providing additional feedback on the answers to the aforementioned questionnaire.

[0131] Specifically, in the step of deriving the expected working period of new employees (S600), the hospital staff working period prediction service relay server (100) can generate keywords related to items for which normalized data cannot be generated using a graph generation module (143) and / or items for which a final weight cannot be derived using a weight setting module (144), and can generate a questionnaire containing questions regarding the generated keywords.

[0132] Additionally, in the step of deriving the expected working period of new hires (S600), the hospital staff working period prediction service relay server (100) generates questions that can identify the applicant's intention regarding the keyword in order to predict the working period, such as the importance of the applicant's work related to the keyword, and whether the applicant is positive or negative regarding the keyword.

[0133] The interviewer can conduct an interview based on a questionnaire received from the hospital staff employment period prediction service relay server (100) and send the answers to the questionnaire back to the hospital staff employment period prediction service relay server (100). Accordingly, the hospital staff employment period prediction service relay server (100) can additionally adjust the employment prediction period based on the answers to the questionnaire.

[0134] Specifically, in the step of deriving the expected employment period of a new hire (S600), the hospital staff employment period prediction service relay server (100) classifies words that have a positive or negative meaning among the words included in the answers to the questionnaire. Then, the applicant's expected employment period is adjusted based on the number of positive or negative words.

[0135] For example, if the number of positive words exceeds a preset threshold, the estimated work period can be increased by a preset multiplier or period, or if the number of negative words exceeds a preset threshold, the estimated work period can be shortened by a preset multiplier or period.

[0136] Additionally, referring to FIG. 6, the method for predicting the working period of hospital staff according to an embodiment of the present invention may further include an existing staff data input step (S510) and a recommended working department display step (S610).

[0137] In the existing staff data input step (S510), the user can input personal data and work data of existing hospital staff using the terminal (200), or select data corresponding to existing hospital staff from among the stored data.

[0138] When a user inputs or selects personal data and work data of existing hospital staff using a terminal (200), the hospital staff work period prediction service relay server (100) inputs the input or selected personal data and work data of existing hospital staff into a learned hospital staff work period prediction model and derives the predicted work period by work department.

[0139] In the recommended work department display step (S610), the hospital staff work period prediction service relay server (100) can transmit the expected work period of existing hospital staff by work department to the terminal (200) and provide it to the user.

[0140] Additionally, in the recommended work department display step (S610), the hospital staff work period prediction service relay server (100) can provide the top 5 work departments with high work prediction periods as recommended work departments.

[0141] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will understand that other specific forms can be easily modified without altering the technical spirit or essential features of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single unit may be implemented in a distributed manner, and components described as distributed may likewise be implemented in a combined form.

[0142] The scope of the present invention is defined by the claims set forth below rather than by the detailed description above, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts thereof should be interpreted as being included within the scope of the present invention.

[0143] The mode for carrying out the invention is the same as the best mode for carrying out the invention described above.

[0144] The present invention relates to a method and apparatus for predicting the employment period of hospital staff, and since it can be used in industries related to medical institution operation consulting and medical personnel management, it has industrial applicability.

Claims

1. As a method for calculating the expected employment period of hospital personnel, Step of collecting personal and work data of existing personnel working at the hospital, A step of generating normalized data by preprocessing the personal data and work data of the aforementioned existing personnel, A step of setting weights for each item included in the personal data and each item included in the work data based on the normalized data above. A step of generating a hospital staff employment period prediction model trained to derive the expected employment period of hospital staff using the above weights, and A step of inputting the personal data and work history data of hospital personnel into the hospital personnel work period prediction model to derive the expected work period of the hospital personnel. A method for calculating the expected working period of hospital personnel, including 2. In Paragraph 1, The step of collecting personal data and work data of the aforementioned existing personnel is, A step of setting the age, gender, educational background, certifications, work experience, major, and number of job changes of the aforementioned existing personnel as items included in personal data, and Step of setting the work department, working hours, work type, hospital size, hospital location, average commute distance, and annual vacation days of the aforementioned existing personnel as items included in the work data A method for calculating the expected working period of hospital personnel, including 3. In Paragraph 2, The step of generating the above normalized data is, A step of generating a distribution graph for each item included in the personal data of the existing personnel and the work data of the existing personnel, A step of generating the normalized data by removing noise data included in the distribution graph based on the normal distribution graph. A method for calculating the expected working period of hospital personnel, including 4. In Paragraph 3, The step of setting weights for each of the above items is, A step of generating item-by-item graphs of the personal data of the existing personnel and the work data of the existing personnel, A step of deriving the agreement rate by comparing the above item-specific graphs with a normal distribution graph, A step of deriving a first weight for each item based on the above matching rate, A step of deriving item-specific gradients for a loss function and deriving a second weight based on the said gradients, A step of setting the average value of the first weight and the second weight as the final weight, and Step of generating a hospital workforce employment period prediction model retrained based on the above final weights A method for calculating the expected working period of hospital personnel, including 5. In Paragraph 4, The step of deriving the first weight above is, Step of deriving the first weight using the first mathematical formula Includes, [First Mathematical Formula] In the above mathematical formula 1 is an item The distribution function of the actual data for, is the normal distribution function, is the standard deviation between two distributions, The item A method for calculating the expected working period of hospital personnel, which signifies the first weighting for 6. In Paragraph 5, The step of deriving the second weight mentioned above is, Step of deriving the second weight using the second mathematical formula Includes, [Second Mathematical Formula] In the second mathematical formula above is the loss function of the above hospital staff employment period prediction model, Key items affecting employment period , is the relevant item A method for calculating the expected working period of hospital personnel, meaning a second weight for 7. In Paragraph 6, The step of generating the above-mentioned learned hospital workforce employment period prediction model is, A step of generating a hospital staff employment duration prediction model to include one or more of Large Language Models (LLM), Random Forest, Gradient Boosting, or Multilayer Perceptron. A method for calculating the expected working period of hospital personnel, including 8. A device that provides a service for calculating the expected working period of hospital personnel, Memory for storing the program to calculate the estimated working period of hospital staff, and It includes a processor that executes a program for calculating the estimated working period of hospital personnel stored in the memory above, and The above processor is, A device for providing a service for calculating the expected working period of hospital personnel, which collects personal data and work data of existing personnel working at a hospital, preprocesses the personal data and work data of the existing personnel to generate normalized data, sets weights for each item included in the personal data and each item included in the work data based on the normalized data, generates a hospital personnel working period prediction model trained to derive the expected working period of the hospital personnel using the weights, and inputs the personal data and work history data of the hospital personnel into the hospital personnel working period prediction model to derive the expected working period of the hospital personnel.

9. In Paragraph 8, The above processor is, A device for providing a service to calculate the expected working period of hospital personnel, which sets the age, gender, educational background, certifications, career, major, and number of job changes of the aforementioned existing personnel as items included in personal data, and sets the work department, working hours, work type, hospital size, hospital location, average commuting distance, and annual vacation days of the aforementioned existing personnel as items included in work data.

10. In Paragraph 9, The above processor is, A device for providing a service for calculating the expected working period of hospital personnel, which generates a distribution graph for each item included in the personal data and work data of the existing personnel, and generates the normalized data by removing noise data included in the distribution graph based on the normal distribution graph.

11. In Paragraph 10, The above processor is, A device for providing a service for calculating the expected working period of hospital personnel, comprising: generating item-specific graphs of the personal data of the existing personnel and the work data of the existing personnel; deriving a match rate by comparing the item-specific graphs with a normal distribution graph; deriving a first weight for each item based on the match rate; deriving an item-specific slope for a loss function; deriving a second weight based on the slope; setting the average value of the first weight and the second weight as the final weight; and generating a retrained hospital personnel working period prediction model based on the final weight.

12. In Paragraph 11, The above processor is, The first weight is derived using mathematical formula 1, and [Mathematical Formula 1] In the above mathematical formula 1 is an item The distribution function of the actual data for, is the normal distribution function, is the standard deviation between two distributions, The item A service providing device for calculating the expected working period of hospital personnel, representing the first weighting for 13. In Paragraph 12, The above processor is, The above second weight is derived using mathematical formula 2, and [Mathematical Formula 2] In the above mathematical formula 2 is the loss function of the above hospital staff employment period prediction model, Key items affecting employment period , is the relevant item A service providing device for calculating the expected working period of hospital personnel, signifying a second weighting factor.

14. In Paragraph 13, The above processor is, A device providing a service for calculating the expected working period of hospital personnel, which generates a hospital personnel working period prediction model including one or more of Large Language Models (LLM), Random Forest, Gradient Boosting, or Multilayer Perceptron.

Images