Program, information processing apparatus, and method

Abstract

To provide a program, an information processor and a method for evaluating an economical impact when a prediction model is introduced.SOLUTION: Receiving a selection of a business process, receiving an input of a parameter used in the business process, receiving a selection of a prediction model to be used for performing a future prediction in the selected business process from among registered prediction models, the program causes the computer to execute a step of performing inference using the prediction model in the selected business process, a step of calculating an economic impact on the business process when the prediction model is used in the selected business process based on a result of the inference, and a step of presenting the calculated economic impact to a user so that the calculated economic impact can be compared with another economic impact calculated for the business process.SELECTED DRAWING: Figure 8

Description

[Technical Field]

[0001] The present disclosure relates to a program, an information processing device, and a method. [Background technology]

[0002] In recent years, with the development of AI (artificial intelligence) technology, various services that utilize AI, such as services that make various predictions about the future based on various data, have been provided.

[0003] Patent Document 1 discloses a technology for optimizing product inventory in an inventory optimization system that estimates product losses, and predicts product demand based on missed sales data, which is the estimated result, and past sales performance data, thereby optimizing product inventory. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2021-103373 Summary of the Invention [Problem to be solved by the invention]

[0005] Incidentally, future predictions using AI such as the above, such as demand forecasts, are used as decision-making information for trading, resource allocation optimization, production planning, budget planning, etc. However, with such demand forecasts, it is not possible to evaluate the impact that the forecast model used for the demand forecast has on actual business processes, and as a result, it cannot be said that the results of the forecasts are necessarily linked to decision-making regarding actual actions such as trading.

[0006] Therefore, this disclosure describes a technology that makes it possible to evaluate the economic impact of introducing a predictive model. [Means for solving the problem]

[0007] According to an embodiment of the present disclosure, there is provided a program to be executed by a computer including a processor and a memory. The memory stores data related to business processes and a predictive model used to predict future trends in the business processes. The program causes the processor to execute the following steps: accepting, through a user's input, a selection of a business process related to the user's business from among registered business processes; accepting, through the user's input, input of parameters to be used in the selected business process; accepting, through the user's input, a selection of a predictive model to be used to predict future trends in the selected business process from among registered predictive models; performing inference using the predictive model for the selected business process based on the data including the input parameters; calculating, based on the inference results, an economic impact on the business process when the predictive model is used in the selected business process; and presenting the calculated economic impact to the user so that it can be compared with other economic impacts calculated for the business process. [Effects of the Invention]

[0008] According to the present disclosure, the economic impact on a business process when the predictive model is used in the business process is calculated based on data including input parameters, thereby making it possible to evaluate the economic impact of introducing the predictive model. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a block diagram showing the overall configuration of a business improvement support system 1 according to an embodiment of the present disclosure. [Figure 2] 2 is a block diagram showing a functional configuration of the terminal device 10 of FIG. 1. FIG. [Figure 3]2 is a block diagram showing the functional configuration of the server 20 of FIG. 1. FIG. [Figure 4] FIG. 4 is a diagram illustrating an example of the data structure of a business process database 2021 in FIG. 3. [Figure 5] FIG. 4 is a diagram illustrating an example of the data structure of a parameter database 2022 in FIG. 3. [Figure 6] FIG. 4 is a diagram illustrating an example of the data structure of a prediction model database 2023 in FIG. 3. [Figure 7] FIG. 4 is a diagram showing an example of the data structure of a calculated impact database 2024 in FIG. 3. [Figure 8] 10 is a flowchart showing an example of the flow of economic impact calculation processing performed by the business improvement support system 1. [Figure 9] FIG. 10 is a diagram showing an example of a business process reception screen displayed on the terminal device 10. [Figure 10] FIG. 10 is a diagram showing an example of a screen for accepting assignments displayed on the terminal device 10. [Figure 11] 10 is a diagram showing an example of a screen for accepting input of performance data displayed on the terminal device 10. FIG. [Figure 12] FIG. 10 is a diagram showing an example of a prediction model reception screen displayed on the terminal device 10. [Figure 13] FIG. 10 is a diagram showing an example of an economic impact presentation screen displayed on the terminal device 10. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. The following description and drawings are examples for explaining the present invention, and appropriate omissions and simplifications have been made for clarity of explanation. The present invention can be implemented in various other forms. Unless otherwise specified, each component may be singular or plural. In the following description, the same components are denoted by the same reference numerals. Their names and functions are also the same. Therefore, detailed descriptions thereof will not be repeated.

[0011] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes programs stored in memory.

[0012] In this disclosure, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed herein or any hardware known to be programmed to realize or perform the described functions.

[0013] If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0014] <Summary> The business improvement support system according to the present disclosure will be described below. The business improvement support system according to the present disclosure is, for example, a system used to make future predictions for business processes related to a user's business. This business improvement support system accepts a selection input of a business process from the user, accepts performance data for making future predictions as parameters, and accepts a selection of a prediction model to be used for the prediction, and then calculates the economic impact on the business process. The business improvement support system also presents the economic impact to the user so that it can be compared with other economic impacts. The business improvement support system according to the present disclosure is a system provided as a web service, for example, via a cloud server or the like, as so-called SaaS (Software as a Service), and is configured to be accessible to users through predetermined authentication.

[0015] However, the above-mentioned AI-based future predictions have the problem that it is not possible to evaluate the impact that the predictive model used for the future predictions will have on actual business processes. Specifically, it is not possible to evaluate the economic impact of such future predictions, such as the amount of sales, the amount of losses, the amount of inventory that will be missed or discarded, and the time it will take. Therefore, the current situation is that it cannot be said that prediction results are necessarily linked to decision-making regarding actual actions such as trading.

[0016] Therefore, the business improvement support system disclosed herein is configured to accept input of a business process selection from a user, accept parameters (e.g., past performance data) for making future predictions, and accept a selection of a prediction model to be used for future predictions; then calculate the economic impact on the business process and present it to the user so that it can be compared with other economic impacts.

[0017] With this configuration, by using the business improvement support system according to the present disclosure, it is possible to evaluate the economic impact of introducing the prediction model, which is expected to lead to effective use of the prediction results by users in making decisions regarding actual actions such as trading.

[0018] <Embodiment> A business improvement support system 1 according to an embodiment of the present disclosure will be described below. In the following description, for example, when a terminal device 10 accesses a server 20, the server 20 responds with information for generating a screen on the terminal device 10. The terminal device 10 generates and displays a screen based on the information received from the server 20.

[0019] <1 Overall configuration of business improvement support system 1> FIG. 1 is a block diagram showing the overall configuration of a business improvement support system 1 according to an embodiment of the present disclosure. As shown in FIG. 1, the business improvement support system 1 includes a plurality of terminal devices (terminal device 10A and terminal device 10B are shown in FIG. 1; hereinafter, they may be collectively referred to as "terminal devices 10") and a server 20. The terminal devices 10 and the server 20 are connected to each other so as to be able to communicate with each other via a network 80. The network 80 is configured as a wired or wireless network. In this embodiment, the server 20 is a web server (including a cloud server) and exchanges information with the terminal device 10 via web pages. Furthermore, a web page browser for viewing web pages is installed on the terminal device 10, but a dedicated application for providing the services of the server 20 may also be installed so that the web pages can be viewed using the dedicated application.

[0020] The terminal device 10 is a device operated by each user. Here, the user is a person who uses the terminal device 10 to make future predictions related to the user's business, which is a function of the business improvement support system 1, and refers to an employee of a company that is a business operator. The terminal device 10 is realized by a desktop PC (Personal Computer), a laptop PC (notebook PC), or the like. Alternatively, the terminal device 10 may be, for example, a tablet compatible with a mobile communication system, a mobile terminal such as a smartphone, or the like.

[0021] The terminal device 10 is communicatively connected to the server 20 via a network 80. The terminal device 10 is connected to the network 80 by communicating with communication devices such as a wireless base station 81 conforming to communication standards such as 4G, 5G, and LTE (Long Term Evolution), and a wireless LAN router 82 conforming to a wireless LAN (Local Area Network) standard such as IEEE (Institute of Electrical and Electronics Engineers) 802.11. As shown as a terminal device 10B in FIG. 1 , the terminal device 10 includes a communication IF (Interface) 12, an input device 13, an output device 14, a memory 15, a storage unit 16, and a processor 19.

[0022] The communication IF 12 is an interface for inputting and outputting signals so that the terminal device 10 can communicate with external devices. The input device 13 is an input device (e.g., a keyboard, a touch panel, a touch pad, a pointing device such as a mouse, etc.) for receiving input operations from a user. The output device 14 is an output device (e.g., a display, a speaker, etc.) for presenting information to a user. The memory 15 is for temporarily storing programs and data processed by the programs, etc., and is a volatile memory such as a DRAM (Dynamic Random Access Memory). The storage unit 16 is a storage device for saving data, such as a flash memory or an HDD (Hard Disc Drive). The processor 19 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0023] The server 20 is a device that accepts a selection of a prediction model and calculates the economic impact on the business process when the prediction model is used in the business process. The server 20 accepts a business process selection input from a user, accepts performance data for future predictions as parameters, and accepts a selection of a prediction model to be used for future predictions. The server 20 calculates the economic impact on the business process when the prediction model is used in the selected business process based on the input parameters. Furthermore, the server 20 presents the calculated economic impact to the user so that it can be compared with other economic impacts.

[0024] The server 20 is a computer connected to a network 80. The server 20 includes a communication IF 22, an input / output IF 23, a memory 25, a storage 26, and a processor 29.

[0025] The communication IF 22 is an interface for inputting and outputting signals so that the server 20 can communicate with external devices. The input / output IF 23 functions as an interface with an input device for receiving input operations from a user and an output device for presenting information to the user. The memory 25 is for temporarily storing programs and data processed by the programs, etc., and is a volatile memory such as a DRAM (Dynamic Random Access Memory). The storage 26 is a storage device for saving data, such as a flash memory or an HDD (Hard Disc Drive). The processor 29 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0026] <1.1 Configuration of the terminal device 10> FIG. 2 is a block diagram showing the functional configuration of a terminal device 10 constituting the business improvement support system 1 according to the first embodiment. As shown in FIG. 2, the terminal device 10 includes a plurality of antennas (antenna 111, antenna 112), wireless communication units (first wireless communication unit 121, second wireless communication unit 122) corresponding to the respective antennas, an operation reception unit 130 (including a keyboard 131 and a mouse 132), a display 140, a storage unit 150, and a control unit 160. The terminal device 10 also has functions and configurations (e.g., a battery for storing power, a power supply circuit for controlling the supply of power from the battery to each circuit, etc.) that are not specifically shown in FIG. 2. As shown in FIG. 2, the blocks included in the terminal device 10 are electrically connected by a bus or the like.

[0027] The antenna 111 emits a signal emitted by the terminal device 10 as a radio wave. The antenna 111 also receives a radio wave from space and provides the received signal to the first radio communication unit 121.

[0028] The antenna 112 emits a signal emitted by the terminal device 10 as a radio wave. The antenna 112 also receives a radio wave from space and provides the received signal to the second radio communication unit 122.

[0029] The first wireless communication unit 121 performs modulation / demodulation processing and the like for transmitting and receiving signals via the antenna 111 so that the terminal device 10 can communicate with other wireless devices. The second wireless communication unit 122 performs modulation / demodulation processing and the like for transmitting and receiving signals via the antenna 112 so that the terminal device 10 can communicate with other wireless devices. The first wireless communication unit 121 and the second wireless communication unit 122 are communication modules including a tuner, an RSSI (Received Signal Strength Indicator) calculation circuit, a CRC (Cyclic Redundancy Check) calculation circuit, a high-frequency circuit, etc. The first wireless communication unit 121 and the second wireless communication unit 122 perform modulation / demodulation and frequency conversion of wireless signals transmitted and received by the terminal device 10, and provide the received signals to the control unit 160.

[0030] The operation reception unit 130 has a mechanism for receiving input operations from the user. Specifically, the operation reception unit 130 includes a keyboard 131 and a mouse 132. Note that the operation reception unit 130 may be configured as a touch screen that detects the position of the user's contact on the touch panel, for example, by using a capacitive touch panel.

[0031] The keyboard 131 accepts input operations by the user of the terminal device 10. The keyboard 131 is a device for inputting characters, and outputs input character information to the control unit 160 as an input signal.

[0032] The mouse 132 accepts input operations by the user of the terminal device 10. The mouse 132 is a pointing device for selecting an object displayed on the display 140, and outputs position information of the selected object on the screen and information indicating that a button has been pressed as input signals to the control unit 160.

[0033] Display 140 displays data such as images, videos, and text under the control of control unit 160. Display 140 is realized by, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display.

[0034] Storage unit 150 is configured with memory 15, such as a flash memory, and storage unit 16, and stores data and programs used by terminal device 10. In one aspect, storage unit 150 stores user information 151.

[0035] The user information 151 is information about a user who uses the terminal device 10 to make future predictions related to the user's business, which is a function of the business improvement support system 1. The user information may include information for identifying the user (user ID), the user's name, address, and organizational information such as the company to which the user belongs.

[0036] The control unit 160 is configured by, for example, the processor 19, and controls the operation of the terminal device 10 by reading a program stored in the storage unit 150 and executing instructions included in the program. The control unit 160 is, for example, an application that is pre-installed in the terminal device 10. The control unit 160 operates in accordance with the program to fulfill the functions of an input operation reception unit 161, a transmission / reception unit 162, a data processing unit 163, and a notification control unit 164.

[0037] The input operation receiving unit 161 performs processing to receive input operations by the user via an input device such as the keyboard 131 .

[0038] The transmitting / receiving unit 162 performs processing for the terminal device 10 to transmit and receive data to and from external devices such as the server 20 in accordance with a communication protocol.

[0039] The data processing unit 163 performs a process of performing calculations on data that the terminal device 10 has received as input in accordance with a program, and outputs the calculation results to a memory or the like.

[0040] The notification control unit 164 performs processing to present information to the user. The notification control unit 164 performs processing to display a display image on the display 140, etc.

[0041] <1.2 Functional configuration of server 20> 3 is a diagram showing the functional configuration of the server 20 constituting the business improvement support system 1 of the embodiment 1. As shown in FIG. 3, the server 20 fulfills the functions of a communication unit 201, a storage unit 202, and a control unit 203.

[0042] The communication unit 201 performs processing for the server 20 to communicate with external devices.

[0043] The storage unit 202 stores data and programs used by the server 20. The storage unit 202 stores a business process database 2021, a parameter database 2022, a prediction model database 2023, a calculated impact database 2024, and the like.

[0044] The business process database 2021 is a database for registering and storing data related to business processes related to the user's business, which the user selects when making future predictions using the business improvement support system 1. Data related to business processes related to the user's business is data including issues and solutions in business processes such as manufacturing plans, sales plans, and inventory plans, for example. Details will be provided below.

[0045] The parameter database 2022 is a database for registering and holding data on parameters used in business processes related to the user's business, which are input by the user when making future predictions using the business improvement support system 1. The parameters used in the business processes are, for example, performance data of the business processes that are the targets of predictions. Details will be provided later.

[0046] The prediction model database 2023 is a database for registering and holding data on prediction models used when making future predictions in business processes using the business improvement support system 1. A prediction model is, for example, a learning model that has been trained based on performance data of a business process, and is a learning model for making future predictions for the business process using the performance data as input data. The prediction model may be, for example, any machine learning model, deep learning model, artificial intelligence model that has been trained appropriately, or a rule-based model, etc. Details will be described later.

[0047] The calculated impact database 2024 is a database for storing data on economic impacts calculated when making future predictions using the business improvement support system 1. The economic impacts are data that indicate the impacts on, for example, the amount of sales, the amount of losses, the quantity of inventory that will be missed or discarded, time, etc. in the business process that is the subject of the prediction. Details will be described later.

[0048] The control unit 203 performs the functions shown in various modules, such as a receiving control module 2031, a sending control module 2032, a business process selection reception module 2033, an actual data input reception module 2034, a predictive model generation module 2035, a predictive model selection reception module 2036, an economic impact calculation module 2037, a comparison result generation module 2038, and a presentation module 2039, by the processor 29 of the server 20 performing processing according to the program.

[0049] The reception control module 2031 controls the process by which the server 20 receives signals from external devices in accordance with a communication protocol.

[0050] The transmission control module 2032 controls the process in which the server 20 transmits signals to external devices in accordance with a communication protocol.

[0051] The business process selection receiving module 2033 controls a process for receiving, based on a user's input, a selection of a business process related to the user's business from among the registered business processes. In response to an operation by a user who uses the business improvement support system 1 to make a future prediction, such as a demand prediction, the business process selection receiving module 2033 transmits data related to business processes, such as a manufacturing plan, a sales plan, and an inventory plan, registered in the business process database 2021 to the terminal device 10 used by the user and presents the data to the user. The user who makes the prediction then operates the terminal device 10 to select a business process to be predicted from the presented business processes and transmits the selection to the server 20. The business process selection receiving module 2033 receives the business process selection information transmitted from the terminal device 10 via the communication unit 201 and accepts it.

[0052] The business process selection receiving module 2033 may receive input of issues in the selected business process through user input. When the business process selection receiving module 2033 receives the selection of a business process from the user who performs demand forecasting, it transmits data on issues in the business process, such as efficiency improvement and cost reduction, registered in the business process database 2021 to the terminal device 10 used by the user and presents the data to the user. The user who performs demand forecasting then operates the terminal device 10 to select an issue in the business process for which demand forecasting is to be performed from the presented issues and transmits the input to the server 20. The business process selection receiving module 2033 receives the information on the issues in the business process transmitted from the terminal device 10 via the communication unit 201 and accepts it.

[0053] As described above, the business process selection receiving module 2033 may present the business processes or tasks registered in the business process database 2021 to the user and receive their selection. The business process selection receiving module 2033 may also receive input of a business process or task from the user in natural language and interpret the received business process or task using natural language processing.

[0054] The performance data input acceptance module 2034 controls processing for accepting, from a user, input of parameters to be used in the business process selected by the business process selection acceptance module 2033. When the performance data input acceptance module 2034 accepts the selection of a business process from a user who performs demand forecasting, it transmits a message to the terminal device 10 used by the user, prompting the user to input parameter data to be used in the business process, and presents this to the user. The user who performs demand forecasting then operates the terminal device 10 to input parameters to be used in the business process and transmits the input to the server 20, and the performance data input acceptance module 2034 accepts the parameter data transmitted from the terminal device 10 by receiving it via the communication unit 201.

[0055] The parameter data accepted by the performance data input acceptance module 2034 may be, for example, current or past performance data in a business process for performing demand forecasting. Performance data in a business process is, for example, production performance data (data on production items, production quantity, defective product rate, etc.) when the business process related to the user is a production plan, sales performance data (data on sales items, sales quantity, discount rate, etc.) when the business process related to the user is a sales plan, and inventory performance data (data on inventory items, quantity, stockout quantity, discard quantity, etc.) when the business process related to the user is an inventory plan. Furthermore, the parameter data may be accepted for each scenario described below, or may be data (performance data) defined by the scenario.

[0056] The data format of the parameter data accepted by the performance data input acceptance module 2034 may be a file created in CSV format, or a file created by spreadsheet software or the like.

[0057] The performance data input reception module 2034 registers and stores the received parameter data in, for example, the parameter database 2022.

[0058] The prediction model generation module 2035 performs learning based on the performance data received by the performance data input reception module 2034 and controls the process of generating a prediction model. The prediction model generation module 2035 performs learning based on the performance data using any machine learning algorithm, deep learning algorithm, or the like, to generate a prediction model. The prediction model generation module 2035 performs supervised machine learning using performance data such as manufacturing performance data, sales performance data, and inventory performance data as training data. The prediction model generated by the prediction model generation module 2035 does not need to be a single learning model, and may be realized by switching between multiple independent learning models for each business process and issue.

[0059] The prediction model generation module 2035 reads and acquires the performance data, for example, from the parameter database 2022, and uses it as learning data. The prediction model generation module 2035 may also use other data, such as weather data and traffic volume data, as learning data. The prediction model generation module 2035 registers and stores the generated prediction model data in, for example, the prediction model database 2023.

[0060] The prediction model selection receiving module 2036 controls a process for receiving, through user input, the selection of a prediction model to be used for making future predictions in a selected business process from among the registered prediction models. In response to an operation by a user who performs demand forecasting, the prediction model selection receiving module 2036 transmits data on prediction models, such as production plans, sales plans, and inventory plans, registered in the prediction model database 2023 to the terminal device 10 used by the user, and presents the data to the user. The user who performs demand forecasting then operates the terminal device 10 to input a selection of a prediction model to be used in the business process for which demand forecasting is performed from among the presented prediction models, and transmits the selection to the server 20. The prediction model selection receiving module 2036 receives the selection information on the prediction model transmitted from the terminal device 10 via the communication unit 201 and accepts it.

[0061] When presenting a prediction model to the user, the prediction model selection receiving module 2036 may present a prediction model generated by the prediction model generation module 2035, or may present a prediction model that has been registered in advance.

[0062] The economic impact calculation module 2037 controls the process of making inferences using the prediction model for a business process selected by the user based on parameters input by the user. The economic impact calculation module 2037 makes future predictions (inferences) using the prediction model selected by the user in the prediction model selection receiving module 2036. Therefore, calculations are made according to the granularity of the parameter data (performance data). In this case, the economic impact calculation module 2037 may make future predictions (inferences) using the prediction model selected by the user in the prediction model selection receiving module 2036, i.e., based on the accuracy of the parameter data (performance data) received by the performance data input receiving module 2034. Specific examples of future predictions made by the economic impact calculation module 2037 include, but are not limited to, predictions of the production volume of products, sales volume, and inventory status.

[0063] Furthermore, the economic impact calculation module 2037 controls the process of calculating the economic impact on a business process selected by a user when the prediction model is used in the business process based on the results of future predictions (inferences) made using the prediction model. The economic impact calculation module 2037, for example, performs a predetermined calculation on the results of the inferences to calculate the economic impact on the business process when the prediction model is used. Specific examples of future predictions made by the economic impact calculation module 2037 include, but are not limited to, the shipment volume and shipment value calculated from the predicted results of the production volume of products, etc., sales revenue and sales costs calculated from the predicted results of sales volume, the required number of personnel, labor costs, the number of inventory lots calculated from the predicted results of inventory status, inventory costs, and the number of personnel and labor costs required for inventory management.

[0064] The economic impact calculation module 2037 calculates the economic impact on the business process accepted by the business process selection acceptance module 2033. At this time, the economic impact calculation module 2037 may calculate the economic impact on the business process accepted by the business process selection acceptance module 2033, which corresponds to an issue in the business process.

[0065] The economic impact calculation module 2037 may interpret the calculated economic impact using natural language processing and generate a report of the calculated economic impact in natural language using natural language processing.

[0066] The comparison result generation module 2038 controls the process of comparing the economic impact calculated by the economic impact calculation module 2037 with other economic impacts to create a comparison result. The other economic impacts may be economic impacts calculated in the past by the economic impact calculation module 2037, economic impacts calculated using a prediction model based on different parameters (for example, performance data with different timing, conditions, etc.) accepted by the performance data input acceptance module 2034, or economic impacts calculated manually.

[0067] The comparison result generation module 2038 may interpret the comparison results using natural language processing and create a report of the economic impact comparison results in natural language using natural language processing.

[0068] The presentation module 2039 controls the process of presenting to the user the economic impact calculated by the economic impact calculation module 2037 so that it can be compared with other economic impacts calculated for the business process. The presentation module 2039 may present the calculated economic impact in parallel with the other economic impacts to enable comparison with the other economic impacts, or may present the comparison results created by the comparison result generation module 2038.

[0069] The presentation module 2039 may present an evaluation logic for evaluating the calculated economic impact as a report of the calculated economic impact together with the economic impact calculated by the economic impact calculation module 2037. The evaluation logic for the economic impact is an evaluation in line with the business process or issue accepted by the business process selection acceptance module 2033, and specifically includes increases or decreases in inventory, costs, etc., and increases or decreases in man-hours due to efficiency improvements. The presentation module 2039 may interpret the evaluation logic using natural language processing and create evaluation logic for the economic impact in natural language using natural language processing.

[0070] The presentation module 2039 may present a scenario based on the selected prediction model as a report of the calculated economic impact along with the economic impact calculated by the economic impact calculation module 2037. The scenario based on the prediction model is the conditions of the business process or task accepted by the business process selection acceptance module 2033, and is, for example, a prediction based on a certain performance (e.g., sales volume, inventory status, etc.) if the conditions for the performance remain the same / a prediction based on a change in the conditions. Specific examples of predictions based on a change in conditions include a change in the weather, an event being held / cancelled, an increase / decrease in traffic volume due to a predetermined factor (construction, etc.), etc. The presentation module 2039 may interpret the scenario using natural language processing and create a scenario based on the prediction model in natural language using natural language processing.

[0071] The presentation module 2039 may present the granularity of the calculated economic impact along with the economic impact calculated by the economic impact calculation module 2037. The granularity of the economic impact is based on the parameters accepted by the performance data input acceptance module 2034, and specifically indicates the time unit of the time series data, the amount, the calculation unit such as time, accuracy, etc.

[0072] <2 Data Structure> Fig. 4 is a diagram showing an example of the data structure of the business process database 2021 in Fig. 3. Fig. 5 is a diagram showing an example of the data structure of the parameter database 2022 in Fig. 3. Fig. 6 is a diagram showing an example of the data structure of the prediction model database 2023 in Fig. 3. Furthermore, Fig. 7 is a diagram showing an example of the data structure of the calculated impact database 2024 in Fig. 3.

[0073] As shown in FIG. 4, each record in the business process database 2021 includes an item "business process (BP) ID," an item "business name," an item "task name," an item "task text template," and the like.

[0074] The item “Business Process (BP) ID” is information that identifies each business process registered in the business improvement support system 1.

[0075] The item "business name" is the name of a business process registered in the business improvement support system 1. The item "business name" stores names indicating business processes, such as "manufacturing plan," "sales plan," and "inventory plan."

[0076] The item "Task name" is the name of a task in a business process that is registered in the business improvement support system 1. The item "Task name" stores names that indicate tasks in a business process, such as "standardization of manufacturing planning," "improvement of product management," and "improvement of inventory costs."

[0077] The item "Problem Text Template" is text data in which a problem in a business model or business process is written in natural language and is registered in the business improvement support system 1. The item "Problem Text Template" stores, for example, text data such as "It is standardized by improving the manufacturing process..." as text data in which the stored business process or problem is written. This text data may be used as a template for natural language processing.

[0078] As shown in FIG. 5, each record of the parameter database 2022 includes an item "user ID," an item "user company and name," an item "parameter data name," an item "parameter data," and the like.

[0079] The item "user ID" is information that identifies each user who is registered in the business improvement support system 1 and who uses the business improvement support system 1 to make future predictions.

[0080] The item "user company and name" is the company to which the user who makes a prediction using the business improvement support system 1 belongs and the name of the user, which are registered in the business improvement support system 1.

[0081] The item "parameter data name" is the name of the parameter data (performance data) received from the user and registered in the business improvement support system 1. The item "parameter data name" stores names indicating the content of the parameter data, such as "manufacturing performance data" and "sales performance data by base."

[0082] The item "parameter data" is parameter data (performance data) received from a user and registered in the business improvement support system 1. The item "parameter data" stores, for example, actual parameter data corresponding to the item "parameter data name" or a link to a storage location where the parameter data is stored.

[0083] Upon receiving the parameter data, the performance data input reception module 2034 of the server 20 adds records to the items "parameter data name" and "parameter data" of the parameter database 2022.

[0084] As shown in FIG. 6, each record in the prediction model database 2023 includes an item "prediction model ID," an item "prediction model name," an item "learning data name," an item "learning data," and the like.

[0085] The item "prediction model ID" is information that identifies each prediction model that is registered in the business improvement support system 1 and that is used to make predictions.

[0086] The item "forecast model name" is the name of the forecast model used to make predictions, which is registered in the business improvement support system 1. The item "forecast model name" stores names that indicate the content of the forecast model, such as "manufacturing plan optimization model" or "customer demand forecast model."

[0087] The item "Learning data name" is the name of the parameter data (actual data) used to learn the prediction model used to make predictions, which is registered in the business improvement support system 1, and corresponds to the item "Parameter data name" in the parameter database 2022.

[0088] The item "learning data" is parameter data (actual data) registered in the business improvement support system 1 and used to learn the predictive model used to make predictions, and corresponds to the item "parameter data" in the parameter database 2022.

[0089] As shown in FIG. 7, each record of the calculated impact database 2024 includes an item "Result ID", an item "Calculation result name", an item "Scenario name", an item "Scenario data", and the like.

[0090] The item “Result ID” is information that identifies each economic impact calculated by prediction, which is registered in the business improvement support system 1.

[0091] The item "calculation result name" is the name of the economic impact calculated by the forecast, which is registered in the business improvement support system 1. The item "calculation result name" stores names indicating the content of the economic impact, such as "manufacturing plan optimization result" or "customer demand forecast result."

[0092] The item "Scenario Name" is the name of the scenario that is the condition for the economic impact calculated by the forecast, which is registered in the business improvement support system 1. The item "Scenario Name" stores names that indicate economic impact scenarios, such as "Current Status Forecast Data" and "Customer Retention Data."

[0093] The item "Scenario Data" is data on the scenario that is the condition for the economic impact calculated by the forecast, which is registered in the business improvement support system 1. The item "Scenario Data" stores, for example, actual scenario data corresponding to the item "Scenario Name," or a link to the storage location where the scenario data is stored.

[0094] The economic impact calculation module 2037 of the server 20 adds records to the calculated impact database 2024 as it calculates the economic impact.

[0095] <3 operations> Hereinafter, with reference to FIG. 8, the economic impact calculation process (method) performed by the business improvement support system 1 according to the embodiment of the present disclosure will be described.

[0096] FIG. 8 is a flowchart showing an example of the flow of the economic impact calculation process performed by the business improvement support system 1.

[0097] In step S101, the business process selection reception module 2033 of the server 20, in response to an operation by a user who makes a future prediction using the business improvement support system 1, transmits data related to business processes, such as a manufacturing plan, a sales plan, and an inventory plan, registered in the business process database 2021 to the terminal device 10 used by the user, and displays the data on the display 140 to present to the user. Then, in step S101, the user operates the terminal device 10 to input a business process to be predicted from the presented business processes and transmits the input to the server 20, and the business process selection information transmitted from the terminal device 10 is received via the communication unit 201 and accepted.

[0098] In step S102, upon receiving the selection of a business process from the user making the prediction in step S101, the performance data input receiving module 2034 of the server 20 transmits a message to the terminal device 10 used by the user prompting the input of parameter data to be used in the business process, and displays the message on the display 140 for presentation to the user. Then, in step S102, the user operates the terminal device 10 to input parameters to be used in the business process and transmits them to the server 20, and the parameter data transmitted from the terminal device 10 is received via the communication unit 201 and accepted.

[0099] In step S103, the prediction model generation module 2035 of the server 20 performs learning based on the performance data received in step S102 and generates a prediction model. In step S103, learning is performed based on the performance data using any machine learning algorithm, deep learning algorithm, etc., and a prediction model is generated.

[0100] In step S104, the prediction model selection receiving module 2036 of the server 20, in response to an operation by the user who makes a prediction, transmits data on prediction models such as a production plan, sales plan, and inventory plan registered in the prediction model database 2023 to the terminal device 10 used by the user, and displays the data on the display 140 to present to the user. Then, in step S104, the user operates the terminal device 10 to input a selection of a prediction model to be used in the business process to be predicted from the presented prediction models, and transmits the selection to the server 20, so that the prediction model selection information is received from the terminal device 10 via the communication unit 201 and accepted.

[0101] In step S105, the economic impact calculation module 2037 of the server 20 performs a future prediction (inference) using the prediction model selected by the user in step S104. Then, based on the results of the future prediction (inference) using the prediction model, a predetermined calculation is performed to calculate the economic impact on the business process selected by the user when the prediction model is used in the business process. In step S105, the economic impact on the business process received in step S101 is calculated.

[0102] In step S106, the comparison result generation module 2038 of the server 20 compares the economic impact calculated in step S105 with other economic impacts to generate a comparison result. In step S106, for example, the comparison result is generated by comparing the other economic impacts with economic impacts calculated in the past, economic impacts calculated using a prediction model with different parameters (for example, performance data with different timing, conditions, etc.), and economic impacts calculated manually.

[0103] In step S107, the presentation module 2039 of the server 20 transmits the economic impact calculated in step S105 and other economic impacts calculated for the business process to the terminal device 10 used by the user, displays them on the display 140, and presents them to the user for comparison. In step S107, the comparison results created in step S106 may be presented, and together with the economic impact, the evaluation logic for evaluating the calculated economic impact, the scenario based on the selected prediction model, and the granularity of the calculated economic impact may also be presented.

[0104] As described above, the business improvement support system 1 accepts a business process selection input from a user, and upon accepting parameter data for future predictions (e.g., past performance data), generates a prediction model based on the accepted parameter data, and upon accepting a selection of a prediction model to be used for future predictions, calculates the economic impact on the business process and presents it to the user so that it can be compared with other economic impacts. This makes it possible to evaluate the economic impact of introducing the prediction model.

[0105] <4 Screen example> Hereinafter, examples of screens used in the economic impact calculation process by the business improvement support system 1 will be described with reference to FIGS.

[0106] Fig. 9 is a diagram showing an example of a business process reception screen displayed on the terminal device 10. The example of Fig. 9 shows an example of a screen displayed to receive the selection of a business process related to the user's business. This corresponds to step S101 in Fig. 8.

[0107] 9, a business process reception screen 1411 is displayed on the display 140 of the terminal device 10. This business process reception screen 1411 displays a business selection instruction display field 1412 as instruction information for the user. In addition, business process selection fields 1413, 1414, and 1415 are provided as options for business processes accepted by the business process selection acceptance module 2033 of the server 20. The business process selection fields 1413, 1414, and 1415 correspond to business processes registered in the business process database 2021. The user can select a business process by pressing any of the business process selection fields 1413, 1414, and 1415.

[0108] Fig. 10 is a diagram showing an example of an assignment reception screen displayed on the terminal device 10. The example of Fig. 10 shows an example of a screen displayed to receive the selection of an assignment in a business process related to the user's business. This corresponds to step S101 in Fig. 8.

[0109] As shown in FIG. 10 , an assignment acceptance screen 1421 is displayed on the display 140 of the terminal device 10. This assignment acceptance screen 1421 displays an assignment selection question display field 1422 as question information to the user. In addition, assignment selection fields 1423 and 1424 are provided as options for assignments in business processes accepted by the business process selection acceptance module 2033 of the server 20. As shown in FIG. 10 , the business process selection acceptance module 2033 may generate questions for assignments in business processes using natural language processing. The assignment selection fields 1423 and 1424 may correspond to business processes registered in the business process database 2021, or may be generated using natural language processing. The user can select a business process by pressing either of the assignment selection fields 1423 and 1424.

[0110] Fig. 11 is a diagram showing an example of a screen for accepting input of performance data displayed on the terminal device 10. The screen example in Fig. 11 shows an example of a screen displayed to prompt input of parameters (performance data) used in the business process. This corresponds to step S102 in Fig. 8.

[0111] 11, an achievement data input acceptance screen 1431 is displayed on the display 140 of the terminal device 10. This achievement data input acceptance screen 1431 displays an achievement data input instruction display field 1432 as instruction information for the user. In addition, upload selection fields 1433 and 1434 are provided as options to be accepted by the achievement data input acceptance module 2034 of the server 20. The upload selection fields 1433 and 1434 ask the user whether or not to upload achievement data. When the user presses the upload selection field 1433 displaying "Yes," the upload of achievement data is started, and when the user presses the upload selection field 1434 displaying "No," the upload of achievement data is not started and a screen transition is performed, for example, returning to the previous screen.

[0112] Fig. 12 is a diagram showing an example of a forecasting model acceptance screen displayed on the terminal device 10. The example of Fig. 12 shows an example of a screen displayed to accept the selection of a forecasting model to be used for performing demand forecasting in a business process selected by the user. This corresponds to step S104 in Fig. 8.

[0113] As shown in Fig. 12, a prediction model reception screen 1441 is displayed on the display 140 of the terminal device 10. This prediction model reception screen 1441 displays a prediction model explanation display field 1442 as instruction information for the user. In addition, prediction model selection fields 1443 and 1444 are provided as options for prediction models accepted by the prediction model selection acceptance module 2036 of the server 20. As shown in Fig. 12, the prediction model selection acceptance module 2036 may generate an explanation of the prediction model by natural language processing. The user can select a prediction model by pressing either the prediction model selection field 1443 or 1444.

[0114] Fig. 13 is a diagram showing an example of an economic impact presentation screen displayed on the terminal device 10. The screen example in Fig. 13 shows an example of a screen displayed to present the economic impact on a business process related to the user's business. This corresponds to step S107 in Fig. 8.

[0115] 13, an impact presentation screen 1451 is displayed on the display 140 of the terminal device 10. An economic impact display field 1452 is displayed on this impact presentation screen 1451 as information to be presented to the user. By referring to the economic impact display field 1452, the user can understand the economic impact of introducing the prediction model.

[0116] <Summary> As described above, according to this embodiment, when a user selects a business process and receives parameter data (e.g., past performance data) for future predictions, a prediction model is generated based on the received parameter data. Then, when a selection of a prediction model to be used for future predictions is received, the economic impact on the business process is calculated and presented to the user so that it can be compared with other economic impacts. Therefore, by using the business improvement support system according to the present disclosure, it is possible to evaluate the economic impact of introducing the prediction model. This is expected to lead to user decision-making regarding actual actions such as trading, making it possible to effectively utilize the prediction results.

[0117] The system also accepts business process or issue input from users in natural language and interprets it using natural language processing. It also interprets the calculated economic impact using natural language processing and creates a report of the calculated economic impact in natural language using natural language processing. This allows users to evaluate economic impact in natural language.

[0118] Although the embodiments of the disclosure have been described above, they can be implemented in various other forms and can be implemented with various omissions, substitutions, and modifications. These embodiments, modifications, and omissions, substitutions, and modifications are included in the technical scope of the claims and their equivalents.

[0119] <Additional Notes> The matters explained in the above embodiments will be supplemented below.

[0120] (Supplementary Note 1) A program to be executed by a computer having a processor 29 and a memory 25, wherein data (2021) related to a business process and a predictive model (2023) used to make future predictions for the business process are registered in the memory 25, and the program causes the processor 29 to execute the following steps: accepting, through a user's input, a selection of a business process related to the user's business from among the registered business processes (S101); accepting, through a user's input, input of parameters to be used in the selected business process (S102); accepting, through a user's input, a selection of a predictive model to be used to make future predictions for the selected business process from among the registered predictive models (S104); performing inference using the predictive model for the selected business process based on the data including the input parameters (S105); calculating, based on the inference results, an economic impact on the business process when the predictive model is used in the selected business process (S105); and presenting the calculated economic impact to the user so that it can be compared with other economic impacts calculated for the business process (S107).

[0121] (Appendix 2) A program as described in (Appendix 1), wherein in a step of accepting parameter input, current or past performance data is accepted as parameters from a user, and the program further executes a step (S103) of performing learning based on the accepted performance data and generating a predictive model, and in a step of accepting a selection of a predictive model, the generated predictive model is presented and a selection is accepted as the predictive model to be used for making future predictions in the selected business process.

[0122] (Appendix 3) A program as described in (Appendix 1), wherein in the step of presenting the calculated economic impact to the user, an evaluation logic for evaluating the calculated economic impact is presented to the user together with the calculated economic impact as a report of the calculated economic impact.

[0123] (Appendix 4) The program further executes a step (S105) of comparing the calculated economic impact with other economic impacts to create a comparison result, and in a step of presenting the calculated economic impact to a user, presents the created comparison result to the user together with the calculated economic impact as a report of the calculated economic impact. (Appendix 1)

[0124] (Appendix 5) A program described in any of (Appendix 1) to (Appendix 4), wherein in the step of presenting the calculated economic impact to the user, a report of the calculated economic impact is created and presented in natural language using natural language processing.

[0125] (Appendix 6) The program according to (Appendix 1), wherein in the step of presenting the calculated economic impact to the user, the granularity of the calculated economic impact is presented to the user together with the calculated economic impact.

[0126] (Appendix 7) A program described in (Appendix 1), which, in the step of accepting the selection of a business process, accepts input of issues in the selected business model, and, in the step of calculating the economic impact, calculates the economic impact according to the input issues.

[0127] (Appendix 8) A program described in (Appendix 7), which, in a step of accepting a business process selection, accepts input of issues in the selected business model in natural language, interprets the issues using natural language processing, and, in a step of calculating the economic impact, calculates the economic impact based on the results of the interpretation of the input issues using natural language processing.

[0128] (Supplementary Note 9) An information processing device comprising a control unit 203 and a memory (storage unit 202), wherein data (2021) related to business processes and a prediction model (2023) used to make future predictions in the business processes are registered in the memory, and the control unit 203 executes the following steps: accepting, through a user's input, a selection of a business process related to the user's business from among the registered business processes (S101); accepting, through a user's input, input of parameters to be used in the selected business process (S102); accepting, through a user's input, a selection of a prediction model to be used to make future predictions in the selected business process from among the registered prediction models (S104); performing inference using the prediction model for the selected business process based on data including the input parameters (S105); calculating, based on the inference result, an economic impact on the business process when the prediction model is used in the selected business process (S105); and presenting the calculated economic impact to the user so as to be comparable with other economic impacts calculated for the business process (S107).

[0129] (Supplementary Note 10) A method to be executed by a computer including a processor 29 and a memory 25, wherein data (2021) related to a business process and a predictive model (2023) used to make future predictions for the business process are registered in the memory 25, and the method includes the steps of: receiving, by user input, a selection of a business process related to the user's business from among the registered business processes (S101); receiving, by user input, input of parameters to be used in the selected business process (S102); receiving, by user input, a selection of a predictive model to be used to make future predictions for the selected business process from among the registered predictive models (S104); performing inference using the predictive model for the selected business process based on the data including the input parameters (S105); calculating, based on the inference results, an economic impact on the business process when the predictive model is used in the selected business process (S105); and presenting the calculated economic impact to the user so as to be comparable with other economic impacts calculated for the business process (S107). [Explanation of symbols]

[0130] 1: Business improvement support system 10: Terminal device 10A: Terminal equipment 10B: Terminal device 13: Input device 14: Output device 15: Memory 16: Storage section 19: Processor 20: Server 25: Memory 26: Storage 29: Processor 80: Network 81: Wireless base station 82: Wireless LAN router 111: Antenna 112: Antenna 121: First wireless communication unit 122: Second wireless communication unit 130: Operation reception unit 131: Keyboard 132: Mouse 140: Display 150: Storage section 151: User information 160: Control unit 161: Input operation reception unit 162: Transmitter / receiver 163: Data processing section 164: Notification control section 201: Communications Department 202: Storage section 203: Control unit 2021: Business Process Database 2022: Parameter database 2023: Prediction model database 2024: Calculated Impact Database 2031: Receiving control module 2032: Transmission control module 2033: Business process selection reception module 2034: Performance data entry acceptance module 2035: Prediction model generation module 2036: Prediction model selection reception module 2037: Economic Impact Calculation Module 2038: Comparison result generation module 2039: Presentation module

Claims

1. A program to be executed by a computer having a processor and a memory, The memory stores data related to the business process and a prediction model used to make a future prediction in the business process; The program causes the processor to: receiving, through input from a user, a selection of a business process related to the user's business from among registered business processes; accepting input from the user of parameters to be used in the selected business process; receiving, through input from the user, a selection of a prediction model to be used for making a future prediction for the selected business process from among the registered prediction models; performing an inference using the predictive model on a selected business process based on data including input parameters; calculating an economic impact on the selected business process when the predictive model is used in the selected business process based on the result of the inference; and presenting the calculated economic impact to the user so that the calculated economic impact can be compared with other economic impacts calculated for the business process.

2. In the step of accepting input of parameters, current or past performance data is accepted as parameters from the user; The program further comprises: Execute a step of performing learning based on the received performance data and generating a predictive model; 2. The program according to claim 1, wherein in the step of accepting a selection of a predictive model, the generated predictive model is presented and a selection is accepted as the predictive model to be used for making future predictions in the selected business process.

3. The program of claim 1, wherein in the step of presenting the calculated economic impact to the user, an evaluation logic for evaluating the calculated economic impact is presented to the user together with the calculated economic impact as a report of the calculated economic impact.

4. The program further comprises: Executing a step of comparing the calculated economic impact with other economic impacts to generate a comparison result; 2. The program according to claim 1, wherein in the step of presenting the calculated economic impact to the user, the created comparison results are presented to the user together with the calculated economic impact as a report of the calculated economic impact.

5. 5. The program according to claim 1, wherein in the step of presenting the calculated economic impact to the user, a report of the calculated economic impact is created and presented in natural language using natural language processing.

6. 2. The program according to claim 1, wherein in the step of presenting the calculated economic impact to the user, the granularity of the calculated economic impact is presented to the user together with the calculated economic impact.

7. In the step of accepting a selection of a business process, an input of a problem in the selected business model is accepted; 2. The program according to claim 1, wherein the step of calculating an economic impact calculates an economic impact according to the input issue.

8. In the step of accepting a selection of a business process, an input of a problem in the selected business model is accepted in natural language, and the problem is interpreted by natural language processing; 8. The program according to claim 7, wherein in the step of calculating the economic impact, the economic impact is calculated according to a result of interpretation of the input issue by natural language processing.

9. An information processing device including a control unit and a memory, The memory stores data related to the business process and a prediction model used to make a future prediction in the business process; The control unit receiving, through input from a user, a selection of a business process related to the user's business from among registered business processes; accepting input from the user of parameters to be used in the selected business process; receiving, through input from the user, a selection of a prediction model to be used for making a future prediction for the selected business process from among the registered prediction models; performing an inference using the predictive model on a selected business process based on data including input parameters; calculating an economic impact on the selected business process when the predictive model is used in the selected business process based on the result of the inference; and presenting the calculated economic impact to the user so that the calculated economic impact can be compared with other economic impacts calculated for the business process.

10. 1. A method to be executed by a computer having a processor and a memory, comprising: The memory stores data related to the business process and a prediction model used to make a future prediction in the business process; The method further comprises the processor: receiving, through input from a user, a selection of a business process related to the user's business from among registered business processes; accepting input from the user of parameters to be used in the selected business process; receiving, through input from the user, a selection of a prediction model to be used for making a future prediction for the selected business process from among the registered prediction models; performing an inference using the predictive model on a selected business process based on data including input parameters; calculating an economic impact on the selected business process when the predictive model is used in the selected business process based on the result of the inference; presenting the calculated economic impact to the user so that it can be compared with other economic impacts calculated for the business process.

Images