System and Method for predicting operating personnel based on multi-workload calculation scheme with output unit

Abstract

A system is disclosed that utilizes multiple workload estimation models defined by reflecting the work environment at various points in time to calculate workloads according to each estimation method for an entire period, and derives staffing forecast results by comprehensively reflecting operational personnel forecasts through regression analysis based on this. The system is characterized by comprising a work management server that generates work-related data, a data acquisition unit that acquires said work-related data through a communication network, and a data processing unit that calculates said workloads through pre-set individual workload estimation methods, generates said regression analysis models for said workloads, generates said staffing forecast models that calculate said staffing forecasts based on said regression analysis models, and integrates said staffing forecasts to generate a final staffing forecast value at a specific point in time.

Description

Technology Field

[0001] The present invention relates to operational workforce forecasting technology, and more specifically, to a system and method that utilizes multiple workload estimation models defined by reflecting work environments at various points in time to calculate workload according to each estimation method for an entire period, and derives a staffing forecast result by comprehensively reflecting operational workforce forecasts obtained through regression analysis based on this. It is about. Background Technology

[0002] The current society is undergoing rapid changes in the social environment, and these changes are manifesting in various forms across multiple aspects of the industrial and business landscape. In particular, regarding corporate workforce management, it is necessary to efficiently operate the company's workforce by ensuring stable management of employees and preparing in advance for potential future changes in human resources.

[0003] Furthermore, if manpower needs are not met despite active recruitment, normal company operations become difficult, and operating with an excessive number of personnel relative to workload can lead to a waste of human resources. Therefore, for efficient workforce management, it is crucial to analyze past personnel operations by organization to identify management characteristics and, based on this analysis, predict appropriate manpower demand to plan and respond to future operations.

[0004] Therefore, for efficient corporate management, it is necessary to introduce a sustainable mid-to-long-term workforce management system to analyze the current workforce status and respond to changes in the business environment. Furthermore, by developing a mid-to-long-term workforce forecasting system, objective grounds can be presented when responding to requests for workforce increases or managing staffing levels, thereby enhancing the acceptance of workforce management plans and proposals.

[0005] Previously, workforce demand information was directly received from companies and firms for workforce management analysis and staffing forecasting. Alternatively, a method primarily utilized involved receiving workforce-related data and forecasting demand based on information from similar companies.

[0006] However, because this staffing forecasting method applies a sample of similar companies at the present time, it is difficult to estimate staffing levels based on medium- to long-term manpower demand forecasts. Furthermore, since it cannot reflect the unique workforce management characteristics of a company's organization, the accuracy of predictions when determining actual medium- to long-term staffing levels may be significantly lower.

[0007] Therefore, to achieve more effective workforce management through workforce operation analysis and future staffing forecasting that reflects the company's unique management characteristics, mid-to-long-term staffing levels can be calculated by applying workload estimation models or staffing forecasting models.

[0008] Specifically, to derive accurate staffing forecast results, it is crucial to design a workload calculation model to estimate workloads by organization, update workloads to reflect changes in the work environment and define workloads accordingly, design a forecasting model capable of calculating mid-to-long-term staffing levels by analyzing or learning from past workload and operational personnel patterns, and finally, derive various workforce management characteristics that can be referenced for future operational management plans.

[0009] In particular, since staffing calculations using staffing forecasting models are derived by reflecting the manpower required for the total workload, accurate workload estimation must precede effective operational staffing calculations and staffing forecasts.

[0010] However, when estimating workload, it is necessary to identify tasks requiring manpower and consider the weight of various work items. Furthermore, since work items and their weights fluctuate in accordance with changes in the organization and work environment, it is impossible to apply a single workload estimation method to mid-to-long-term staffing forecasts.

[0011] In particular, when designing workload and staffing prediction models using regression analysis of past workloads, there is a problem in that it is difficult to derive effective predictions because a single workload calculation method defined at a specific point in time is applied to the workload calculation for the entire period, making it difficult to reflect individual workloads at various points in time where workload recalculation and redefinition have occurred.

[0012] Meanwhile, when applying a single workload estimation method, examples of factors that may impede prediction accuracy during the staffing forecasting process can be cited. To elaborate, when designing a regression model for staffing forecasting, if the definition of the workload estimation method is redefined at time Nc based on the current time N due to changes in the organization and work environment within that period, then in the case of staffing forecasting based on the existing single workload estimation method, regression analysis is possible at time N based on the workload of the past period c, defined in workload definition_2.

[0013] However, since the workload for the Na period in Nc is calculated according to the workload method defined in the previous WorkloadDefinition_1, if the workload calculated using a separate workload calculation method within the learning period is reflected using the existing method, the learning interval becomes reduced or it becomes difficult to reflect the entire learning period.

[0014] Therefore, when applied to regression analysis and learning models, a problem may arise where the accuracy of mid-to-long-term staffing forecasts decreases. Additionally, if the historical period for the redefined workload is short, the application of regression analysis may be impossible, which may make it difficult to apply regression-based forecasting models for staffing prediction.

[0015] Generally, a single workload estimation model is applied uniformly over the entire period to estimate the workload. Prior art literature

[0016] 1. Republic of Korea Registered Patent No. 10-2375744 (Registration Date: March 14, 2022) The problem to be solved

[0017] The present invention is proposed to resolve the problems associated with the background technology described above, and aims to provide a system and method that calculates the workload according to each calculation method for the entire period by utilizing multiple workload estimation models defined to reflect the work environment at various points in time, and derives a staffing forecast result by comprehensively reflecting operational personnel forecasts obtained through regression analysis based on this. means of solving the problem

[0018] To achieve the objectives presented above, the present invention provides a system that calculates the workload according to each calculation method for the entire period by utilizing multiple workload estimation models defined to reflect the work environment at various points in time, and derives a staffing forecast result by comprehensively reflecting operational personnel forecasts obtained through regression analysis based on this.

[0019] The above system is,

[0020] A business management server that generates business-related data;

[0021] A data acquisition unit that acquires data related to the above-mentioned work through a communication network;

[0022] It is characterized by including a data processing unit that calculates each workload through a pre-set individual workload calculation method, generates each regression analysis model for each workload, generates each capacity prediction model that calculates each capacity prediction value based on each regression analysis model, and integrates each capacity prediction value to generate a final capacity prediction value at a specific point in time.

[0023] In addition, the data processing unit is characterized by extracting each workload item from the work-related data and calculating each workload by applying a pre-set weight to each workload item.

[0024] In addition, the above weight is characterized by being a value based on the proportion of workload by reflecting the total workload item.

[0025] In addition, the above weighting is characterized by being reflected only for selected workload items by identifying key tasks that have a major impact on manpower requirements.

[0026] In addition, the final garden prediction output value is characterized by being generated using an average value method or a weighted sum method for each garden prediction value.

[0027] In addition, the above weighted sum method is a mathematical formula

[0028]

[0029] It is characterized by being defined as (where a is the entire past period, c is the period in which the recent workload definition was changed, and A and A' are the predicted workloads derived through regression analysis based on multiple workload definitions during period a, respectively).

[0030] In addition, the data processing unit is characterized by deriving each workload by applying each calculation method to the entire past period required for the regression analysis model according to each workload calculation method based on each workload definition.

[0031] On the other hand, another embodiment of the present invention provides a method for predicting operational personnel based on multiple workload calculation methods, characterized by comprising: (a) a step in which a work management server generates work-related data; (b) a step in which a data acquisition unit acquires the work-related data through a communication network; and (c) a step in which a data processing unit calculates each workload through a pre-set individual workload calculation method, generates each regression analysis model for each workload, generates each staffing prediction model that calculates each staffing prediction value based on each regression analysis model, and integrates each staffing prediction value to generate a final staffing prediction value at a specific point in time.

[0032] Additionally, the above step (c) is characterized by including: a step in which the data processing unit extracts each workload item from the work-related data; and a step in which the data processing unit calculates each workload by applying a pre-set weight to each workload item. Effects of the invention

[0033] According to the present invention, work gaps and management disruptions caused by workforce imbalance can be minimized through mid-to-long-term workforce management planning and effective response via a mid-to-long-term workforce forecasting system.

[0034] In addition, another advantage of the present invention is that it can provide convenience for effective workforce management and workforce status analysis by efficiently reflecting various workload calculation methods resulting from changes in the work environment and the functionalization of mid-to-long-term workforce forecasting. Brief explanation of the drawing

[0035] FIG. 1 is a block diagram of an operational workforce prediction system based on a multiple workload calculation method according to an embodiment of the present invention. FIG. 2 is a diagram showing the processing concept of a data processing unit according to an embodiment of the present invention. FIG. 3 is a conceptual diagram of a staffing level prediction through multiple workload-based regression analysis according to an embodiment of the present invention. FIG. 4 is a flowchart showing the prediction of operational personnel based on a multiple workload calculation method according to an embodiment of the present invention. FIG. 5 is an example of a workload item for calculating the total workload according to an embodiment of the present invention. FIG. 6 is a conceptual diagram showing an example of staffing estimation through the application of a multiple workload calculation method according to an embodiment of the present invention. Specific details for implementing the invention

[0036] The present invention is capable of various modifications and may have various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the invention to specific embodiments, and it should be understood that the invention includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the invention.

[0037] When describing each drawing, similar reference numerals are used for similar components.

[0038] Terms such as first, second, etc., may be used to describe various components, but said components should not be limited by said terms. Such terms are used solely for the purpose of distinguishing one component from another.

[0039] For example, without departing from the scope of the present invention, the first component may be named the second component, and similarly, the second component may be named the first component. The term "and / or" includes a combination of a plurality of related described items or any of a plurality of related described items.

[0040] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which this invention pertains.

[0041] Terms such as those defined in commonly used dictionaries should be interpreted as having meanings consistent with their meanings in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0042] Hereinafter, an operational personnel prediction system and method based on a multiple workload calculation method according to an embodiment of the present invention will be described in detail with reference to the attached drawings.

[0043] Specifically, to collect personnel management data for business units or organizations, workload items necessary for workload calculation are extracted by linking with the work management system. Weights are assigned to each work item based on the proportion of manpower required, and a workload calculation method based on the total sum of the products of these weights is applied. Unlike the existing approach that applies a single workload calculation method, this method derives and updates all workloads for various calculation methods that may have been redefined within the past period. Individual regression analysis models are then applied to generate staffing forecast models for each method. Finally, to predict staffing levels at a specific future point in time, the prediction results derived from each regression-based forecast model are integrated and reflected, ensuring that the prediction results generated by the multiple workload calculation methods are comprehensively applied and presented.

[0044] FIG. 1 is a block diagram of an operational workforce prediction system (100) based on a multiple workload calculation method according to an embodiment of the present invention. Referring to FIG. 1, the operational workforce prediction system (100) may be configured to include a work management server (110), a communication network (120), a data acquisition unit (130), a data processing unit (140), an output unit (150), etc.

[0045] The work management server (110) collects work-related data, including personnel operation data and work data of a business office or organization, stores it in a database, and performs the function of providing it upon request. To this end, the work management server (110) may be configured to include a microprocessor, a communication modem, memory, etc.

[0046] Here, the memory may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD (Secure Digital) or XD (eXtreme Digital) memory, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), PROM (Programmable Read Only Memory), magnetic memory, magnetic disk, and optical disk. Additionally, it may operate in conjunction with web storage or cloud servers that perform storage functions over the internet.

[0047] Of course, the database may be built within the business management server (110), but the database server may also be operated separately. Additionally, the business management server (110) may be connected to a computer installed at the business office via a communication network (120), or it may be connected to a server that provides personnel information.

[0048] The communication network (120) refers to a connection structure capable of exchanging information between each node, such as multiple terminals and servers, and can be a public switched telephone network (PSTN), a public switched data network (PSDN), an integrated services digital network (ISDN), a broadband integrated services digital network (BISDN), a local area network (LAN), a metropolitan area network (MAN), a wide area network (WLAN), etc.

[0049] However, the present invention is not limited thereto and may be wireless communication networks such as CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), Wibro (Wireless Broadband), WiFi (Wireless Fidelity), DLNA (Digital Living Network Alliance), Zigbee, Z-wave, HSDPA (High Speed ​​Downlink Packet Access) networks, Bluetooth, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), Ultra-wide Band, Wireless USB (Wireless Universal Serial Bus), NFC (Near Field Communication) networks, satellite broadcasting networks, analog broadcasting networks, DMB (Digital Multimedia Broadcasting) networks, etc. Alternatively, it may be a combination of these wired communication networks and wireless communication networks.

[0050] The data acquisition unit (130) performs the function of acquiring work-related data. Specifically, it performs the function of collecting work-related data, including personnel operation data and work data, from the work management server (110) of a business office or organization. It is also possible to acquire status data using a removable storage medium such as a memory stick. To this end, the data acquisition unit (110) may be configured to include a communication modem, memory, etc.

[0051] The communication network (120) refers to a connection structure capable of exchanging information between each node, such as multiple terminals and servers, and can be a public switched telephone network (PSTN), a public switched data network (PSDN), an integrated services digital network (ISDN), a broadband integrated services digital network (BISDN), a local area network (LAN), a metropolitan area network (MAN), a wide area network (WLAN), etc.

[0052] However, the present invention is not limited thereto and may be wireless communication networks such as CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), Wibro (Wireless Broadband), WiFi (Wireless Fidelity), DLNA (Digital Living Network Alliance), Zigbee, Z-wave, HSDPA (High Speed ​​Downlink Packet Access) networks, Bluetooth, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), Ultra-wide Band, Wireless USB (Wireless Universal Serial Bus), NFC (Near Field Communication) networks, satellite broadcasting networks, analog broadcasting networks, DMB (Digital Multimedia Broadcasting) networks, etc. Alternatively, it may be a combination of these wired communication networks and wireless communication networks.

[0053] The data processing unit (140) extracts work items necessary for calculating the workload from work-related data, assigns weights to each work item according to the proportion of manpower required, and calculates the workload based on the total sum of the products of the weights for each workload. In addition, it generates a staffing prediction model for each workload calculation method by applying individual regression analysis models. Finally, to predict the staffing at a specific point in time in the future, it generates final prediction information by integrating and reflecting the prediction results derived from each regression analysis-based staffing prediction model.

[0054] The output unit (150) performs the function of displaying final prediction information in a combination of graphics, text, and voice. Of course, it also performs the function of displaying information input screens, setting screens, processing information screens, etc. To this end, the output unit (150) may be configured to include a display, a sound system, etc. The display may be configured to include an LCD (Liquid Crystal Display), an LED (Light Emitting Diode) display, a PDP (Plasma Display Panel), an OLED (Organic LED) display, a touch screen, a CRT (Cathode Ray Tube), a flexible display, a micro LED, a mini LED, etc. In the case of a touch screen, it may be used as an input means as well as an output means.

[0055] FIG. 2 is a diagram showing the processing concept of a data processing unit (140) according to an embodiment of the present invention. Referring to FIG. 2, the data processing unit (140) calculates a workload of 1 to N (210) through an individual workload calculation method (1 to N). An individual workload calculation method refers to a method redefined within the regression analysis period. Here, the calculation of the workload Y within the period is performed by reflecting weights for the importance of various work items to which actual personnel are deployed, and as the sum of the weights for each work item, Y = W_0 *(Work Item_0) + ~ +W_N It can be expressed as *(work_item_N), and the number of work items from 0 to N can be applied variably depending on the major work items applied for workload calculation.

[0056] According to each workload calculation method, the workload for the entire period is updated to generate an updated workload (220). To elaborate, the workload for the entire period is updated to calculate 1 to N workloads. Here, each workload derived according to various workload calculation methods (210) within the entire past period subject to regression analysis is collectively updated to a workload value calculated according to each workload definition for the entire past period according to the workload update (220).

[0057] 1 to N regression models are generated based on 1 to N update workloads (230). The regression models applied here can generally utilize learning algorithms that derive predictions based on learning past data, and can include Multi-Layer Perceptron (MLP) algorithms with neural network structures and Long Short-Term Memory (LSTM) based regression analysis algorithms that can apply workloads of specific periods as time series.

[0058] Afterwards, 1 to N staffing prediction models are created to calculate staffing prediction values ​​for each regression model based on 1 to N regression models (240). Here, each staffing prediction model is individually applied to predict future workload based on a regression model (230) designed through learning workload within a past period, and through each prediction model, a prediction value can be provided for a specific point in time and period in the future through the staffing prediction model (240).

[0059] Finally, 1 to N predicted values ​​of the number of seats are integrated to generate a final predicted value of the number of seats at a specific point in time (250). Here, the predictions derived through each predicted value of the number of seats (240) can be displayed individually for each model in the visualization section of the predicted value of the number of seats, or they can be presented in an integrated manner by reflecting the average and weighted product of each prediction. In particular, when calculating the integrated workload based on the weighted product, the time of redefining the workload within the past regression analysis period can be reflected in the weights to calculate it adaptively.

[0060] FIG. 3 is a conceptual diagram of staffing estimation through regression analysis based on multiple workloads according to an embodiment of the present invention. That is, FIG. 3 is an example of staffing estimation based on regression analysis for workloads derived through workload calculation methods from 1 to N.

[0061] Referring to FIG. 3, work-related data is obtained from the work management server (110) (310).

[0062] When work-related data is obtained, work volume is extracted by applying 1 to N work volume definitions to the work-related data (320). Here, the work volume is determined based on quantitative figures for work items that require actual time and manpower, and the work items reflected in the work volume determination are assigned weights according to the proportion of work items to reflect the organization's work environment and situation, and the work volume can be calculated in the form of the sum of weighted products of various work items. Here, as shown in the example of FIG. 6, various items can be reflected entirely or selectively.

[0063] 1 to N workload items are extracted for the extracted workload (330). An example showing the workload items is illustrated in FIG. 5. Here, the workload items can be extracted by reflecting the entire workload that requires time and manpower, or by selectively reflecting major workload items according to the proportion and importance of each workload.

[0064] Referring to FIG. 3, 1 to N weights are generated for each task (340). To elaborate, for the task items requiring manpower to calculate the workload, weights can be generated based on the proportion of the workload by reflecting the total workload items for the workload calculation method (i.e., the workload calculation model). Of course, weights can also be applied only to the selected workload items by selecting major tasks that have a significant impact on manpower requirements.

[0065] Once the weights for each task are obtained, the total workload is calculated (350). Specifically, the workload can be calculated by applying environmental variables (=workload items) that are related to the actual workload of the organization, and the workload (Y) can be derived according to the workload calculation method as follows.

[0066] (Example) Workload calculation model for the power distribution job group at a power company

[0067] Y= W0

[0068] + W1*(Power supply external line requirement, new supply, underground, 30 million won or less)

[0069] + W2*(New High Voltage Power Supply Internal Line (Case))

[0070] + W3*(Power supply internal line EVC(device))

[0071] + W4*(number of distribution operation facilities)

[0072] + ...

[0073] As shown in the example above, workload Y can be estimated through a final summation by reflecting work-related environmental variables and variably applying weights W according to the major proportions of the workload. These environmental variables and weights may be reflected differently depending on changes in the work environment at a specific point in time.

[0074] Referring to FIG. 3, a past workload regression analysis is performed for each total workload (360). In addition, when the workload according to each workload calculation method is derived, a regression analysis model for each workload is created.

[0075] Each garden prediction model is created to calculate each garden prediction value based on each regression analysis model (370).

[0076] Finally, each quotation prediction is integrated to generate a final quotation prediction output value at a specific point in time (S380). To elaborate, each quotation prediction is combined to generate a single output value. The final quotation prediction output value can be calculated using an average method or a weighted sum method for the individual predictions.

[0077] FIG. 4 is a flowchart showing the prediction of operational personnel based on a multiple workload calculation method according to an embodiment of the present invention. Referring to FIG. 4, the data acquisition unit (130) acquires work-related data from the work management server (110) through the communication network (120) (step S410).

[0078] Afterwards, the data processing unit (140) defines the workload and extracts workload items based on it (steps S420, S430).

[0079] Afterwards, the data processing unit (140) generates a weight for each workload, and calculates and updates the total workload using this weight and workload item (steps S440, S450).

[0080] Afterward, the data processing unit (140) applies individual regression analysis models to generate a staffing prediction model for each workload calculation method (step S460).

[0081] Afterwards, the data processing unit (140) derives a final garden prediction result by integrating and reflecting the prediction result values ​​derived from each regression analysis-based prediction model to predict the garden at a specific point in time (step S470).

[0082] FIG. 5 is an example of work items for calculating the total workload according to an embodiment of the present invention. Referring to FIG. 5, the example shows work items requiring manpower for workload calculation, specifically the distribution job group of a power company. For instance, the major categories are classified into power supply, distribution operation, etc.; the medium categories are classified into external line requirements, internal lines, equipment volume, construction volume, etc.; the minor categories are classified into new supply, line extension, maintenance work, etc.; and the remainder can be classified into detailed categories. Of course, it is also possible to classify them differently.

[0083] FIG. 6 is a conceptual diagram showing an example of staffing estimation through the application of a multiple workload calculation method according to an embodiment of the present invention. Generally, when the definition of workload is changed during a past period a and changes to workload definition_2 instead of the existing workload definition_1 based on time Nc (i.e., N is a specific time point), the existing single workload method uses only the workload value derived by workload definition_2 within the past period c for regression analysis.

[0084] However, in one embodiment of the invention, as shown in FIG. 6, the workload is derived by applying each calculation method to the entire past period a required for the regression analysis model according to the workload calculation method according to each workload definition (611-1, 612-1) on each regression analysis-based trend line (611, 612).

[0085] Here, staffing results can be calculated by reflecting actual operating personnel for each workload, and staffing forecast results can be provided through regression analysis on the workload. Therefore, staffing forecast results for the future period b can be provided through regression analysis for each workload.

[0086] As shown in Fig. 6, the predicted number of staff at time N+b can be presented as A and A' (620) according to each workload calculation method. To calculate the final prediction result, each workload can also be calculated in the form of a weighted sum by reflecting the average value or the time of workload redefinition.

[0087] This can be expressed as a mathematical formula as follows.

[0088]

[0089] (Here, a is the entire past period, c is the period when the recent workload definition was changed, and A and A' are the predicted workloads derived through regression analysis based on multiple workload definitions during period a, respectively)

[0090] Additionally, the steps of the method or algorithm described in connection with the embodiments disclosed herein may be implemented in the form of program instructions that can be executed through various computer means, such as a microprocessor, a processor, a CPU (Central Processing Unit), etc., and recorded on a computer-readable medium. The computer-readable medium may include program (instruction) code, data files, data structures, etc., either alone or in combination.

[0091] The program (instruction) code recorded on the above medium may be those specifically designed and configured for the present invention, or those known and available to those skilled in the art of computer software. Examples of computer-readable recording media may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs, DVDs, and Blu-rays; and semiconductor memory devices specifically configured to store and execute program (instruction) code, such as ROM (Read Only Memory), RAM (Random Access Memory), and flash memory.

[0092] Here, examples of program (instruction) code include not only machine code, such as that generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter, etc. The aforementioned hardware device may be configured to operate as one or more software modules to perform the operation of the present invention, and vice versa. Explanation of the symbols

[0093] 100: Operational Manpower Prediction System 110: Business Management Server 120: Communication network 130: Data Acquisition Unit 140: Data processing unit 150: Output section

Claims

Claim 1 A multi-workload calculation method-based operational personnel prediction system having an output unit, further comprising: a work management server (110) that generates work-related data; a data acquisition unit (130) that acquires the work-related data through a communication network (120); a data processing unit (140) that calculates each workload through a pre-set individual workload calculation method, generates each regression analysis model for each workload, generates each staffing prediction model that calculates each staffing prediction value based on each regression analysis model, and integrates each staffing prediction value to generate a final staffing prediction value at a specific point in time; wherein the data processing unit (140) extracts each workload item from the work-related data, calculates each workload by applying a pre-set weight to each workload item, and the weight is a value according to the workload proportion reflecting the total workload item, and an output unit (150) that displays the final prediction information generated by the data processing unit (140) as a combination of graphics, text, and voice.

Images