Information processing system, information processing method, and information processing program

Abstract

This tool supports the analysis of errors in demand forecasts within the target segment. [Solution] The information processing system comprises: an indicator acquisition unit that acquires indicators for managing the accuracy of demand forecasts for a target segment that includes multiple products handled by the target company; an internal information acquisition unit that acquires internal company information regarding the target segment within the target company; an external information acquisition unit that acquires external company information regarding the target segment outside the target company; and an interpretation example generation means that uses a large-scale language model to generate sentences that include factors based on internal and external company information regarding the error in demand forecasts as examples of interpretation of the indicators.

Description

Technical Field

[0001] The present disclosure relates to an information processing system, an information processing method, and an information processing program.

Background Art

[0002] In recent years, it has become important to predict the demand for products. For example, Patent Document 1 describes a technique for predicting the demand for a component by using a model constructed based on past operation hours data and operation time data of a device having the component to be predicted and the past actual number of issued parts.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Here, demand prediction may result in an error from the actual performance due to various factors. Therefore, it is important to analyze the error in demand prediction. Also, for a user who manages segments including a plurality of products, there is a desire to analyze the error in demand prediction in the segment. However, Patent Document 1 does not describe analyzing the error in demand prediction. In addition, there is a problem that specialized knowledge is required for such analysis of the error in demand prediction. Also, even when having specialized knowledge, there are problems such as the possibility of missing information to be considered, time-consuming information collection and information arrangement, and insufficient consideration time for such analysis of the error in demand prediction. Therefore, a technique for supporting the analysis of the error in demand prediction in a segment is required.

[0005] This disclosure has been made in view of the above-mentioned issues, and one exemplary purpose is to provide a technique to assist in the analysis of errors in demand forecasting in a segment. [Means for solving the problem]

[0006] An information processing system relating to an exemplary aspect of this disclosure includes: an indicator acquisition means for acquiring an indicator for managing the accuracy of demand forecasts for a target segment that includes multiple products handled by a target company; an internal information acquisition means for acquiring internal company information concerning the target segment within the target company; an external information acquisition means for acquiring external company information concerning the target segment outside the target company; and an interpretation example generation means that uses a large-scale language model to generate sentences that include factors based on the internal company information and the external company information regarding the error in the demand forecast as examples of interpretations of the indicators.

[0007] An example of an information processing method relating to this disclosure includes: an indicator acquisition process in which at least one processor acquires an indicator for managing the accuracy of demand forecasts for a target segment including multiple products handled by a target company; an internal information acquisition process in which the at least one processor acquires internal company information regarding the target segment within the target company; an external information acquisition process in which the at least one processor acquires external company information regarding the target segment outside the target company; and an interpretation example generation process in which the at least one processor uses a large-scale language model to generate a sentence as an example of interpretation of the indicator, which includes factors based on the internal company information and the external company information regarding the error in the demand forecast.

[0008] An information processing program relating to an exemplary aspect of this disclosure causes at least one processor to execute: an indicator acquisition process for acquiring indicators for managing the accuracy of demand forecasts for a target segment including multiple products handled by the target company; an internal information acquisition process for acquiring internal company information regarding the target segment within the target company; an external information acquisition process for acquiring external company information regarding the target segment outside the target company; and an interpretation example generation process that uses a large-scale language model to generate an example of an interpretation of the indicator, which includes a sentence containing factors based on the internal company information and the external company information regarding the error in the demand forecast. [Effects of the Invention]

[0009] One exemplary effect of this disclosure is that it can provide a technology that supports the analysis of errors in demand forecasting in the target segment. [Brief explanation of the drawing]

[0010] [Figure 1] This is a block diagram showing the configuration of the information processing system related to this disclosure. [Figure 2] This is a flowchart showing the flow of the information processing method related to this disclosure. [Figure 3] This is a block diagram showing the configuration of the information processing system related to this disclosure. [Figure 4] This is a block diagram showing the configuration of the information processing device related to this disclosure. [Figure 5] This block diagram shows the configuration of the user terminal related to this disclosure. [Figure 6] This is a flowchart showing the flow of the information processing method related to this disclosure. [Figure 7] This figure shows an example of a screen related to this disclosure. [Figure 8] This block diagram shows the hardware configuration of the computers that function as each of the above devices. [Modes for carrying out the invention]

[0011] The following are examples of embodiments of the present invention. However, the present invention is not limited to the exemplary embodiments shown below, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining some or all of the technologies (things or methods) employed in each of the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, embodiments obtained by appropriately omitting some of the technologies employed in each of the exemplary embodiments shown below may also be included in the scope of the present invention. In addition, the effects mentioned in each of the exemplary embodiments shown below are examples of effects that can be expected in that exemplary embodiment and do not define the scope of the present invention. That is, embodiments that do not produce the effects mentioned in each of the exemplary embodiments shown below may also be included in the scope of the present invention.

[0012] [First Exemplary Embodiment] A first exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. This exemplary embodiment is the basic form for each of the exemplary embodiments described later. The scope of application of each technology adopted in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology adopted in this exemplary embodiment can also be adopted in other exemplary embodiments included in this disclosure, to the extent that no particular technical problems occur. Furthermore, each technology shown in the drawings referenced to explain this exemplary embodiment can also be adopted in other exemplary embodiments included in this disclosure, to the extent that no particular technical problems occur.

[0013] (Configuration of Information Processing System 1) The configuration of the information processing system 1 will be explained with reference to Figure 1. Figure 1 is a block diagram showing the configuration of the information processing system 1. As shown in Figure 1, the information processing system 1 includes an indicator acquisition unit 11, an in-company information acquisition unit 12, an out-of-company information acquisition unit 13, and an interpretation example generation unit 14. The indicator acquisition unit 11 is an example of a configuration that realizes the indicator acquisition means. The in-company information acquisition unit 12 is an example of a configuration that realizes the in-company information acquisition means. The out-of-company information acquisition unit 13 is an example of a configuration that realizes the out-of-company information acquisition means. The interpretation example generation unit 14 is an example of a configuration that realizes the interpretation example generation means. Note that the information processing system 1 may be configured by a single device or by multiple devices.

[0014] The indicator acquisition unit 11 acquires indicators for managing the accuracy of demand forecasts for a target segment that includes multiple products handled by the target company. The target company is a company that handles multiple products and has introduced the information processing system 1 to manage the accuracy of demand forecasts for those multiple products. The target company may be, for example, a manufacturer that produces multiple products, a retailer that sells multiple products to consumers, or an intermediary distributor (so-called wholesaler) that mediates multiple products between manufacturers and retailers, but is not limited to these.

[0015] A segment is a classification of multiple products based on a predetermined criterion, and may include, but is not limited to, brand, distribution channel, or sales region. A target segment is the segment from which metrics are collected. A target segment may include, for example, a segment specified by the user from among multiple segments, or a predetermined segment of interest, but is not limited to these.

[0016] What needs to be predicted is to predict the demand for products. The demand prediction may be performed by a computer using any technology or manually by an expert. The accuracy of demand prediction refers to how close the demand prediction value indicating the result of demand prediction is to the demand actual value indicating the actual performance of demand. The higher the accuracy of demand prediction, the smaller the error of demand prediction. The error of demand prediction is the difference between the demand prediction value and the demand actual value.

[0017] An index for managing the accuracy of demand prediction for a target segment is an index that can be calculated based on the demand prediction value and / or the demand actual value for each product included in the target segment. The index may include, for example, an index indicating the error rate of demand prediction in the target segment, an index indicating the trend of the error of demand prediction in the target segment, an index indicating the added value of demand prediction in the target segment, etc., but is not limited thereto.

[0018] The in-company information acquisition unit 12 acquires in-company information regarding the target segment within the target company. For example, the in-company information may include information regarding the activities performed by the target company with respect to the target segment.

[0019] The out-company information acquisition unit 13 acquires out-company information regarding the target segment outside the target company. For example, the out-company information may include general information that does not depend on the target company with respect to the target segment.

[0020] The interpretation example generation unit 14 uses a large-scale language model to generate sentences that include factors based on internal company information and external company information regarding errors in demand forecasting, as examples of interpretations of the indicator. For example, "factors based on internal company information and external company information regarding errors in demand forecasting" may include internal or external company events that may be contributing to errors in demand forecasting. For example, the interpretation example generation unit 14 may generate prompts including the indicator, internal company information, and external company information and input them into the large-scale language model to output the interpretation example from the large-scale language model. Alternatively, for example, the interpretation example generation unit 14 may further train the large-scale language model using the internal company information and external company information. In this case, the interpretation example generation unit 14 may input prompts including the indicator into the further trained large-scale language model to output the interpretation example from the large-scale language model. Alternatively, for example, the interpretation example generation unit 14 may add the internal company information and external company information to the knowledge base. In this case, the interpretation example generation unit 14 may search for information about the index from the knowledge base and input the search results and a prompt containing the index to the large-scale language model, thereby causing the large-scale language model to output the interpretation example.

[0021] (Effects of Information Processing System 1) As described above, the information processing system 1 employs a configuration that includes: an indicator acquisition unit 11 that acquires indicators for managing the accuracy of demand forecasts for a target segment that includes multiple products handled by the target company; an internal information acquisition unit 12 that acquires internal company information about the target segment within the target company; an external information acquisition unit 13 that acquires external company information about the target segment outside the target company; and an interpretation example generation unit 14 that uses a large-scale language model to generate sentences that include factors based on internal and external company information regarding errors in demand forecasts as examples of indicator interpretations. Therefore, users who refer to the interpretation examples output from the information processing system 1 can learn about interpretation examples that include factors for errors in demand forecasts for the target segment, taking into account internal and external company information. As a result, the information processing system 1 can support the analysis of errors in demand forecasts for the target segment.

[0022] (Information processing method S1 flow) The flow of the information processing method S1 will be explained with reference to Figure 2. For example, if the information processing system 1 described above is equipped with at least one processor, that at least one processor may execute the information processing method S1. Figure 2 is a flowchart showing the flow of the information processing method S1. As shown in Figure 2, the information processing method S1 includes an indicator acquisition process S11, an in-company information acquisition process S12, an out-of-company information acquisition process S13, and an interpretation example generation process S14.

[0023] In the indicator acquisition process S11, at least one processor (for example, the indicator acquisition unit 11) acquires indicators for managing the accuracy of demand forecasts for a target segment that includes multiple products handled by the target company. The details of the indicator acquisition process S11 have been described as described for the indicator acquisition unit 11, so a detailed explanation will not be repeated.

[0024] In the internal company information acquisition process S12, at least one processor (for example, the internal company information acquisition unit 12) acquires internal company information concerning the target segment within the target company. The details of the internal company information acquisition process S12 have been described as described for the internal company information acquisition unit 12, so a detailed explanation will not be repeated.

[0025] In the external information acquisition process S13, at least one processor (for example, the external information acquisition unit 13) acquires external information concerning the target segment outside the target company. The details of the external information acquisition process S13 have been explained as described for the external information acquisition unit 13, so a detailed explanation will not be repeated.

[0026] In the interpretation example generation process S14, at least one processor (for example, the interpretation example generation unit 14) uses a large-scale language model to generate a text that includes factors based on internal and external company information regarding the error in demand forecasting, as an interpretation example of the indicators related to the target segment acquired by the indicator acquisition process S11. The details of the interpretation example generation process S14 have been described as described for the interpretation example generation unit 14, so a detailed explanation will not be repeated.

[0027] (Effects of information processing method S1) As described above, the information processing method S1 employs a configuration that includes: an indicator acquisition process S11 in which at least one processor acquires indicators for managing the accuracy of demand forecasts for a target segment that includes multiple products handled by the target company; an internal information acquisition process S12 in which at least one processor acquires internal company information about the target segment within the target company; an external information acquisition process S13 in which at least one processor acquires external company information about the target segment outside the target company; and an interpretation example generation process S14 in which at least one processor uses a large-scale language model to generate an example of indicator interpretation, which includes a text containing factors based on internal and external company information regarding the error in demand forecasts. Therefore, the same effects as the information processing system 1 can be obtained with the information processing method S1.

[0028] [Second exemplary embodiment] A second exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same function as those described in the above-described exemplary embodiment are denoted by the same reference numerals, and their descriptions are omitted as appropriate. The scope of application of each technology adopted in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology adopted in this exemplary embodiment can also be adopted in other exemplary embodiments included in this disclosure, to the extent that no particular technical problems arise. Furthermore, each technology shown in the drawings referenced to describe this exemplary embodiment can also be adopted in other exemplary embodiments included in this disclosure, to the extent that no particular technical problems arise.

[0029] (Configuration of Information Processing System 1A) Figure 3 is a block diagram showing the configuration of information processing system 1A. Information processing system 1A is a system that supports the analysis of errors in demand forecasting. As shown in Figure 3, information processing system 1A comprises an information processing device 10 and a user terminal 20. The information processing device 10 and the user terminal 20 are connected to each other via a communication line NW. The specific configuration of the communication line NW is not limited to this embodiment, but examples of communication lines NW include wireless LAN (Local Area Network), wired LAN, WAN (Wide Area Network), public telephone network, mobile data communication network, or a combination thereof.

[0030] The information processing device 10 functions as a server that provides a service for analyzing demand forecast errors by segment within the target company. For example, the information processing device 10 may be a stationary computer, but is not limited to these. The user terminal 20 is a terminal used by users of the above service within the target company. The user terminal 20 may be, for example, a notebook personal computer, a smartphone, a tablet, etc., but is not limited to these. Furthermore, the user using the user terminal 20 may be, for example, a user who manages segments. Furthermore, such a user may have limited knowledge regarding demand forecasting. Furthermore, such a user may have knowledge regarding demand forecasting.

[0031] (Configuration of the information processing device 10) Figure 4 is a block diagram showing the configuration of the information processing device 10. As shown in Figure 4, the information processing device 10 comprises a control unit 110, a storage unit 120, and a communication unit 130. The control unit 110 controls all parts of the information processing device 10. The storage unit 120 stores various information that the control unit 110 refers to. The communication unit 130 communicates with external devices (for example, a user terminal 20, etc.) via a communication line NW. The communication unit 130 transmits data supplied from the control unit 110 to other devices and supplies data received from other devices to the control unit 110.

[0032] (Functional block included in the control unit 110) The control unit 110 includes a display control unit 15 in addition to the indicator acquisition unit 11, the in-company information acquisition unit 12, the out-of-company information acquisition unit 13, and the interpretation example generation unit 14 provided by the information processing system 1. The display control unit 15 is an example of a configuration that realizes a display control means.

[0033] The indicator acquisition unit 11 is configured in the same way as the functional block of the same name in the information processing system 1, and is configured as follows. For example, the indicator acquisition unit 11 may acquire a time series of indicators over a predetermined period in the past. Detailed specific examples of the indicators acquired by the indicator acquisition unit 11 in this exemplary embodiment will be described later.

[0034] The internal company information acquisition unit 12 and the external company information acquisition unit 13 are configured in the same way as the functional blocks of the same name provided in the information processing system 1. Detailed specific examples of the information acquired by the internal company information acquisition unit 12 and the external company information acquisition unit 13 in this exemplary embodiment will be described later.

[0035] The interpretation example generation unit 14 is configured in the same way as the interpretation example generation unit 14 provided in the information processing system 1, and is configured as follows. For example, the interpretation examples generated by the interpretation example generation unit 14 include factors based on internal and external company information regarding the error in the demand forecast, and further include either or both of the situation regarding the error in the demand forecast and suggestions for dealing with the error in the demand forecast. For example, "situation regarding the error in the demand forecast" may include information such as the magnitude of the error, the tendency of the error such as whether it is an over-forecast or under-forecast, and how these change. Also, "suggestions for dealing with the error in the demand forecast" may include examples of actions that the user can take in response to the error.

[0036] The display control unit 15 displays a screen on the display unit 250 of the user terminal 20, described later, that includes the indicators acquired by the indicator acquisition unit 11 and the interpretation examples generated by the interpretation example generation unit 14, in response to an operation to specify a target segment. For example, if the indicator acquisition unit 11 acquires a time series of indicators over a predetermined period, the display control unit 15 may display a screen on the display unit 250 that includes a graph plotting the time series of indicators and the interpretation examples. The display unit 250 of the user terminal 20 is an example of a display device to which the screen by the display control unit 15 is displayed.

[0037] (Information stored in memory unit 120) The memory unit 120 stores various types of information referenced by the control unit 110. Examples of such information include demand forecasts, actual demand values, indicators, internal company information, external company information, and large-scale language models. Some or all of this information may be stored in an external device different from the information processing device 10.

[0038] (Demand forecast value) The demand forecast values ​​represent the results of demand forecasts for each of the multiple products handled by the target company. For example, the demand forecast values ​​represent the expected demand in a future unit period, and may be the expected sales amount, the expected number of units sold, etc. If the unit period is, for example, one week, the storage unit 120 may store, for example, product identification information, a future period (for example, the second week of April 2024), and the demand forecast value for that period (for example, the expected number of units sold of 120) in association with each other. Note that the unit period is not limited to one week, but may be one day, one month, one quarter, one year, etc. Demand forecast values ​​may be added to the storage unit 120 each time a demand forecast is made for a new future period.

[0039] (Actual demand figures) The actual demand value indicates the historical demand for each of the multiple products handled by the target company. For example, the actual demand value is a value that represents the demand in a past unit period, and may be, for example, the actual sales amount, the actual number of units sold, etc. If the unit period is, for example, one week, the storage unit 120 may store, for example, product identification information, a past period (for example, the first week of April 2024), and the actual demand value for that period (for example, the actual number of units sold of 100) in association with each other. Note that the unit period is not limited to one week, but may be, for example, one day, one month, one quarter, one year, etc. The actual demand value may be added to the storage unit 120 each time an actual demand value for a new past period is obtained.

[0040] (index) The metrics are used to manage the accuracy of demand forecasts for a target segment that includes multiple products handled by the target company. These metrics may include, for example, MAPE (Mean Absolute Percentage Error), f-Bias (forecast-Bias) rate, and some or all of FVA (Forecast Value Added). However, the metrics are not limited to these.

[0041] (MAPE) MAPE is an index that represents the error rate of demand forecasts compared to actual demand for multiple products, and is used as an index to evaluate the accuracy of demand forecasts. For example, MAPE is the average of the absolute values ​​of the difference between the forecasted demand and the actual demand for each of the multiple products, divided by the actual demand.

[0042] For example, if the target segment contains n products p_1, p_2, ... p_n (where n is a natural number greater than or equal to 1), the MAPE for that target segment can be calculated using, as an example, the following formula (1). In formula (1), y_i is the actual demand value for product p_i during the target unit period (hereinafter also referred to as the target period), and ^y_i is the forecast demand value for product p_i during the target period. Note that the expression "_i" in "p_i", "y_i", etc., represents the subscript i. Also, the expression "^y_i" represents y_i with a hat. Note that as a variation of MAPE, ^y_i (forecast demand value) may be applied instead of y_i (actual demand value) as the denominator.

number

[0043] (Weighted MAPE) Furthermore, MAPE is not limited to the above formula (1), and may also be information obtained from the error rate of the demand forecast value against the actual demand value for each product, weighted according to the actual demand value for each product. Such MAPE will be referred to as "weighted MAPE" or "WAPE" below. As an example, the weighted MAPE (WAPE) for n products p_1, p_2, ... p_n can be calculated using the following formula (2).

number

[0044] (f-Bias rate) The f-Bias rate is an indicator that represents the trend of error between the forecast value and the actual demand value. The "tendency of error" refers to the tendency for the forecast value to be higher or lower than the actual demand value. The f-Bias rate reflects the peculiarities of the logic on which the demand forecast is based or changes in the market. For example, the f-Bias rate for n products p_1, p_2, ... p_n included in the target segment can be calculated using the following formula (3). In formula (3), y_i is the actual demand value for product p_i during the target period, and ^y_i is the forecast value for product p_i during the target period. As a variation of the f-Bias rate, n time units may be applied instead of n products.

number

[0045] (FVA) FVA is an index that evaluates the added value of demand forecasting in monetary terms. FVA is information that measures whether the adopted demand forecast is creating value by comparing it with a simple demand forecast. A simple demand forecast may be, for example, a forecast that uses past demand actual values ​​(for example, the sales actual values ​​of the previous week) as the demand forecast value (for example, the demand forecast value for the following week). The FVA of n products p_1, p_2, ... p_n can be calculated as an example using the following equation (4). In equation (4), y_(i,k) is the actual demand value of product p_i in the target period k, and y_(i,kx) is the actual demand value of product p_i in any period kx (x is an integer greater than or equal to 1) prior to the target period k. ^y_(i,k) is the demand forecast value of product p_i in the target period k. u_i is the unit price of product p_i.

number

[0046] (Internal information) As mentioned above, internal company information is information obtained within the target company and may be information specific to that company. For example, internal company information may include information indicating promotions conducted within the target company for some or all of the products included in the target segment. Furthermore, internal company information may further include some or all of the product information, demand forecasts, actual demand values, and actual distribution values ​​related to some or all of the products included in the target segment.

[0047] Information indicating a promotion may include, for example, information such as activities to promote the sale of the relevant product, the period during which such activities are conducted, etc. Product information related to the target segment may also include product information for some or all of the multiple products included in the target segment. Product information for each product may include the price, attributes, etc., of the product. Demand forecasts related to the target segment may also include demand forecasts for some or all of the multiple products included in the target segment, or the demand forecast for the entire target segment (i.e., the sum of the demand forecasts for each product). Actual demand related to the target segment may also include, for example, the actual demand for some or all of the multiple products included in the target segment, or the actual demand for the entire target segment (i.e., the sum of the actual demand for each product). Demand forecasts or actual demand may also include information for retail sales, wholesale shipments, and manufacturer shipments. Actual distribution values ​​related to the target segment may also include the number of destinations (e.g., the number of stores) to which some or all of the multiple products included in the target segment were distributed. Actual distribution values ​​related to the target segment may also include actual values ​​for the entire target segment (i.e., the sum of the actual distribution values ​​for each product). However, internal company information is not limited to the examples mentioned above.

[0048] Internal company information may be updated with the latest information at predetermined intervals, or new information may be added. Furthermore, internal company information may be information in which items and values ​​representing the various types of information described above are associated, or it may be a document consisting of natural language text that may contain the various types of information described above (for example, an internal company journal).

[0049] (Non-company information) External information, as described above, is information obtained from outside the target company and may be general information not specific to the target company. For example, external information may include either or both information on economic trends related to the target segment and information on social changes in the industry related to the target segment. Furthermore, external information may also include either or both information on changes in regulations related to the industry and information indicating the external environment of the industry. For example, changes in regulations related to the industry may include price revisions. Also, for example, information indicating the external environment of the industry may include external variables such as weather information, exchange rates, and the number of foreign visitors to Japan. However, external information is not limited to the examples given above.

[0050] External company information may be updated with the latest information at predetermined intervals, or new information may be added. Furthermore, external company information may be information in which items and values ​​indicating the various types of information described above are associated, or it may be a document consisting of natural language text that may contain the various types of information described above (for example, an industry journal, a journal on the external environment, etc.).

[0051] (Large-scale language models) A large-scale language model is a deep learning model designed to perform natural language processing tasks. For example, a large-scale language model may be a pre-trained general-purpose large-scale language model, or it may be a fine-tuned version of such a general-purpose large-scale language model. For example, a large-scale language model may be a model that performs a text generation task, taking a natural language sentence as input and outputting a generated natural language sentence.

[0052] (Configuration of user terminal 20) Figure 5 is a block diagram showing the configuration of the user terminal 20. As shown in Figure 5, the user terminal 20 comprises a control unit 210, a storage unit 220, a communication unit 230, an input unit 240, and a display unit 250. The control unit 210 controls all parts of the user terminal 20. The storage unit 220 stores various information that the control unit 210 refers to. The communication unit 230 communicates with external devices (e.g., an information processing device 10, etc.) of the user terminal 20 via a communication line NW. The communication unit 230 transmits data supplied from the control unit 210 to other devices and supplies data received from other devices to the control unit 210.

[0053] The input unit 240 is configured to receive input from the user terminal 20, and may include, for example, input devices such as a keyboard, mouse, touch panel, camera, and microphone. The display unit 250 is configured to display the screen output from the user terminal 20, and may include, for example, a display. The input unit 240 and the display unit 250 may also be integrally formed as a touch panel or the like. Furthermore, one or both of the input unit 240 and the display unit 250 are not limited to being built into the user terminal 20, but may also be connected externally via an interface such as USB (Universal Serial Bus).

[0054] The control unit 210 includes a UI (User Interface) unit 21. The UI unit 21 provides a user interface for using a service that analyzes errors in demand forecasting. For example, the UI unit 21 receives user operations for using the service and transmits them to the information processing device 10. Also, when the UI unit 21 receives a screen related to the service from the information processing device 10, it displays the received screen on the display unit 250. For example, the UI unit 21 may be implemented by executing an application program for using the service, which is stored in the storage unit 220. The application program may be an application dedicated to the service. Also, if the service is implemented as a web service, the application program may be a general-purpose web browser.

[0055] (Information processing method S1A flow) The information processing system 1A, configured as described above, executes the information processing method S1A. Figure 6 is a flowchart showing the flow of the information processing method S1A. As shown in Figure 6, the information processing method S1A includes steps S101 to S107.

[0056] In step S101, the UI unit 21 of the user terminal 20 receives a user operation to specify a target segment via the input unit 240. For example, the user operation may, but is not limited to, selecting a target segment from a list of segments displayed on the display unit 250. The user operation may also further include specifying a predetermined past period (e.g., a predetermined year, a predetermined month, the start date and end date of the period, etc.) for which indicators related to the target segment should be displayed. The UI unit 21 transmits the information indicated by the received operation (e.g., information indicating the target segment, information indicating the predetermined period, etc.) to the information processing device 10.

[0057] In step S102, the indicator acquisition unit 11 of the information processing device 10 acquires MAPE, f-Bias rate, and FVA as indicators related to the target segment. For example, the indicator acquisition unit 11 may acquire the indicators by reading the time series of each indicator for a predetermined period from the storage unit 120. Alternatively, the indicator acquisition unit 11 may acquire the indicators by calculating the time series of each indicator for a predetermined period based on the demand forecast values ​​and actual demand values ​​stored in the storage unit 120. If the operation to specify a predetermined period is not accepted in step S101, a predetermined period determined in advance may be applied.

[0058] In step S103, the corporate information acquisition unit 12 acquires corporate information. For example, the corporate information acquisition unit 12 may acquire corporate information corresponding to a predetermined period by reading it from the storage unit 120.

[0059] In step S104, the external information acquisition unit 13 acquires external information. For example, the external information acquisition unit 13 may acquire external information corresponding to a predetermined period by reading it from the storage unit 120.

[0060] Steps S102 to S104 do not necessarily have to be executed in this order; they may be executed in a different order, or some or all of them may be executed in parallel.

[0061] In step S105, the interpretation example generation unit 14 generates sentences that serve as interpretation examples using a large-scale language model, referencing the time series of each indicator, internal company information, and external company information. The interpretation examples include the status of the demand forecast error, the factors related to the demand forecast error based on internal and external company information, and suggestions for addressing the demand forecast error.

[0062] For example, the interpretation example generation unit 14 may generate prompts including time series data for each indicator, internal company information, external company information, and case examples, and input them into a large-scale language model, thereby obtaining sentences output from the large-scale language model as interpretation examples. The case examples to be included in the prompts include time series examples for each indicator for any segment, examples of internal company information, examples of external company information, and examples of sentences that serve as interpretation examples. In addition, the examples of sentences that serve as interpretation examples include examples of the situation of demand forecast errors, examples of factors related to demand forecasts, and examples of proposed responses to demand forecast errors.

[0063] In step S106, the display control unit 15 generates a screen that includes the time series of each indicator and an example of its interpretation. The display control unit 15 also transmits this screen to the user terminal 20.

[0064] In step S107, the UI unit 21 of the user terminal 20 displays the received screen on the display unit 250.

[0065] (Screen example) Figure 7 shows an example of a screen displayed on the display unit 250 in step S107. As shown in Figure 7, screen example G1 is an example of a screen showing the demand forecast results for the target segment. Screen example G1 includes areas G11 to G15. Area G11 includes a graph showing the trend of MAPE for the target segment over a predetermined period. Area G12 includes a graph showing the trend of the f-Bias rate for the target segment over a predetermined period. Area G13 includes a graph showing the trend of FVA for the target segment over a predetermined period. Area G14 includes a table showing the trend of the forecast-actual difference for the target segment over a predetermined period. The forecast-actual difference is the value obtained by subtracting the actual demand value from the demand forecast value.

[0066] Area G15 includes example sentences. Among these example sentences, the phrase "Globally, there is a slight tendency towards over-forecasting (sales plans are high)" indicates the situation of forecast error (in other words, the error in demand forecasting). Such sentences indicating the situation of forecast error allow even users with limited knowledge of demand forecasting to easily grasp the situation of forecast error shown in the graphs and tables in areas G11 to G14. In addition, among the example sentences, the phrase "This may be influenced by the slowdown in the economic recovery in China. The European economy is also showing a tendency to slow down due to monetary tightening, which is also considered a downward factor in demand" indicates the cause of forecast error. Such sentences indicating the cause of forecast error allow even users with limited knowledge of demand forecasting to easily grasp the cause of forecast error shown in areas G11 to G14 based on internal and external company information. Furthermore, among the example sentences, the phrase "It would be good to confirm the economic trends of major countries at the S&OP meeting and revise the demand forecast and sales plan in the medium to long term" offers a suggestion for dealing with forecast error. By providing a document that offers suggestions for addressing such forecast errors, even users with limited knowledge can easily handle forecast errors. Furthermore, as shown in example screen G1, users with knowledge of demand forecasting can be supported in reducing omissions or errors in the information that should be considered when analyzing demand forecast errors, shortening the time spent on information gathering and organization, and increasing the time available for analysis.

[0067] (Variation 1) Instead of inputting prompts containing internal company information, external company information, and indicators into the large-scale language model, the interpretation example generation unit 14 may generate interpretation examples as follows. In this modified example, the internal company information and external company information acquired by the internal company information acquisition unit 12 and the external company information acquisition unit 13 are added to a knowledge base (not shown). This updates the knowledge base to the latest state. The knowledge base may be stored in the storage unit 120 or in an external device different from the information processing device 10. The interpretation example generation unit 14 may also search for time-series information for each indicator from the updated knowledge base and input the search results and prompts containing the time-series information for each indicator into the large-scale language model. This outputs sentences that serve as interpretation examples from the large-scale language model. For example, in this modified example, in step S103 or S104, the process of adding the acquired internal company information and external company information to the knowledge base may be performed further. Furthermore, steps S103 and S104 do not need to be performed after receiving the operation to specify the target segment (S101), but may be performed at any time (for example, periodically).

[0068] (Modification 2) Instead of inputting prompts containing internal company information, external company information, and indicators into the large-scale language model, the interpretation example generation unit 14 may generate interpretation examples as follows. In this modified example, the large-scale language model is further trained using the internal company information and external company information acquired by the internal company information acquisition unit 12 and the external company information acquisition unit 13. This updates the large-scale language model to the latest state. The interpretation example generation unit 14 may also input prompts containing time series data for each indicator into the large-scale language model, which has been updated to the latest state. This outputs sentences that serve as interpretation examples from the large-scale language model. For example, in this modified example, in step S103 or S104, further processing may be performed to further train the large-scale language model using the acquired internal company information and external company information. Furthermore, steps S103 and S104 do not need to be performed after receiving the operation to specify the target segment (S101), but may be executed at any time (for example, periodically).

[0069] (Effects of Information Processing System 1A) As described above, in the information processing system 1A, the example sentences for interpretation are structured to further include either or both the situation of the demand forecast error and / or a proposed response to the demand forecast error. Therefore, in addition to the effects achieved by the information processing system 1, the information processing system 1A provides the effect of easily understanding the situation of the demand forecast error and easily responding to the demand forecast error.

[0070] Furthermore, the information processing system 1A is configured to include a display control unit 15 that, in response to an operation to specify a target segment, displays a screen on a display device containing indicators for managing the accuracy of demand forecasts for that target segment, as well as examples of their interpretation. Therefore, in addition to the effects achieved by the information processing system 1, the information processing system 1A provides the additional benefit that, for example, a user managing a target segment can view indicators for managing the accuracy of demand forecasts for that target segment and recognize examples of their interpretation.

[0071] Furthermore, in Information Processing System 1A, the internal company information is configured to include information indicating the promotions that the target company conducts with respect to the target segment. Therefore, in addition to the effects achieved by Information Processing System 1, Information Processing System 1A can provide users with examples of interpretations that take into account the possibility that the promotions conducted by the target company may be a factor in the error of demand forecasts for the target segment.

[0072] Furthermore, in Information Processing System 1A, the external information is structured to include either or both of the following: economic trend information related to the target segment, and / or information on social changes in the industry related to the target segment. Therefore, in addition to the effects achieved by Information Processing System 1, Information Processing System 1A can provide users with interpretation examples that take into account the possibility that economic trend information related to the target segment, information on social changes in the industry related to the target segment, etc., may be related to the error in demand forecasting for the target segment.

[0073] Furthermore, in Information Processing System 1A, the internal company information is configured to include some or all of the product information, demand forecasts, actual demand values, and actual distribution values ​​related to the target segment. Therefore, in addition to the effects achieved by Information Processing System 1, Information Processing System 1A can provide users with examples of interpretations that take into account the possibility that product information, demand forecasts, actual demand values, and actual distribution values ​​related to the target segment may be factors in the error of the demand forecast for that segment.

[0074] Furthermore, in Information Processing System 1A, the external information is structured to include either or both changes in regulations in the industry related to the target segment, and information indicating the external environment of the industry. Therefore, in addition to the effects achieved by Information Processing System 1, Information Processing System 1A can provide users with examples of interpretations that take into account the possibility that changes in regulations in the industry related to the target segment, information indicating the external environment of the industry, etc., may be contributing factors to errors in demand forecasting for the target segment.

[0075] [Examples of implementation using software] Some or all of the functions of the information processing system 1, the information processing device 10, and the user terminal 20 (hereinafter also referred to as "each of the above devices") may be implemented by hardware such as integrated circuits (IC chips) or by software.

[0076] In the latter case, each of the above devices is implemented, for example, by a computer that executes instructions for a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as Computer C) is shown in the figure. Figure 8 is a block diagram showing the hardware configuration of Computer C, which functions as each of the above devices.

[0077] Computer C comprises at least one processor C1 and at least one memory C2. Memory C2 stores a program P that causes computer C to operate as each of the above-mentioned devices. In computer C, processor C1 reads program P from memory C2 and executes it, thereby realizing each of the above-mentioned devices.

[0078] For processor C1, for example, a CPU (Central Processing Unit), GPU (Graphic Processing Unit), DSP (Digital Signal Processor), MPU (Micro Processing Unit), FPU (Floating Point Number Processing Unit), PPU (Physics Processing Unit), TPU (Tensor Processing Unit), quantum processor, microcontroller, or a combination thereof can be used. For memory C2, for example, flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), or a combination thereof can be used.

[0079] Computer C may also be equipped with RAM (Random Access Memory) for loading program P at runtime and for temporarily storing various data. Furthermore, computer C may be equipped with communication interfaces for sending and receiving data with other devices. Additionally, computer C may be equipped with input / output interfaces for connecting input / output devices such as keyboards, mice, displays, and printers.

[0080] Furthermore, program P can be recorded on a non-temporary, tangible recording medium M that is readable by computer C. Such a recording medium M could be, for example, tape, disk, card, semiconductor memory, or programmable logic circuitry. Computer C can acquire program P via such a recording medium M. Program P can also be transmitted via a transmission medium. Such a transmission medium could be, for example, a communication network or broadcast waves. Computer C can also acquire program P via such a transmission medium.

[0081] Furthermore, each of the above functions of each of the above devices may be implemented by a single processor in a single computer, by multiple processors in a single computer working together, or by multiple processors in each of multiple computers working together. In addition, the programs for implementing each of the above functions in each of the above devices may be stored in a single memory in a single computer, distributed and stored in multiple memories in a single computer, or distributed and stored in multiple memories in each of multiple computers.

[0082] [Additional Note A] This disclosure includes the technologies described in the following appendices. However, the present invention is not limited to the technologies described in the following appendices, and various modifications are possible within the scope of the claims.

[0083] (Note A1) A means for obtaining indicators to manage the accuracy of demand forecasts for a target segment that includes multiple products handled by the target company, An internal information acquisition means for acquiring internal company information concerning the target segment within the target company, An external information acquisition means for acquiring external information concerning the target segment outside of the target company, An interpretation example generation means that uses a large-scale language model to generate sentences that include factors based on internal and external company information regarding the error in the demand forecast, as examples of interpretations of the indicators, An information processing system equipped with the following features.

[0084] (Appendix A2) The above interpretation examples further include either or both the circumstances of the error in the demand forecast and the proposed response to the error in the demand forecast. The information processing system described in Appendix A1.

[0085] (Note A3) The system further includes a display control means that, in response to an operation to specify the target segment, displays a screen on a display device including the indicator and the interpretation example. The information processing system described in Appendix A1 or A2.

[0086] (Note A4) The aforementioned internal company information includes information indicating the promotions that the target company conducts with respect to the target segment. The information processing system described in any one of the appendices A1 to A3.

[0087] (Note A5) The aforementioned external information includes either or both of the following: information on economic trends related to the target segment and information on social changes in the industry related to the target segment. The information processing system described in any one of the appendices A1 through A4.

[0088] (Note A6) The aforementioned internal company information includes some or all of the product information, demand forecasts, actual demand figures, and actual distribution figures related to the aforementioned target segment. The information processing system described in any one of the appendices A1 through A5.

[0089] (Note A7) The aforementioned external information includes either or both changes in regulations in the industry related to the target segment, and / or information indicating the external environment of the industry. An information processing system described in any one of the appendices A1 through A6.

[0090] [Additional Notes B] This disclosure includes the technologies described in the following appendices. However, the present invention is not limited to the technologies described in the following appendices, and various modifications are possible within the scope of the claims.

[0091] (Note B1) At least one processor performs an indicator acquisition process to obtain indicators for managing the accuracy of demand forecasts for a target segment that includes multiple products handled by the target company, The at least one processor performs an internal information acquisition process to acquire internal company information relating to the target segment within the target company, The at least one processor performs an external information acquisition process to acquire external information relating to the target segment outside the target company, The at least one processor performs an interpretation example generation process that uses a large-scale language model to generate an example of the interpretation of the indicator, which includes a sentence containing factors based on the internal and external information regarding the error in the demand forecast. Information processing methods including

[0092] (Note B2) The above interpretation examples further include either or both the circumstances of the error in the demand forecast and the proposed response to the error in the demand forecast. The information processing method described in Appendix B1.

[0093] (Note B3) The at least one processor further includes a display control process that, in response to an operation to specify the target segment, displays a screen on a display device including the index and the interpretation example. The information processing method described in Appendix B1 or B2.

[0094] (Note B4) The aforementioned internal company information includes information indicating the promotions that the target company conducts with respect to the target segment. The information processing method described in any one of the appendices B1 to B3.

[0095] (Note B5) The aforementioned external information includes either or both of the following: information on economic trends related to the target segment and information on social changes in the industry related to the target segment. The information processing method described in any one of the appendices B1 to B4.

[0096] (Note B6) The aforementioned internal company information includes some or all of the product information, demand forecasts, actual demand figures, and actual distribution figures related to the aforementioned target segment. The information processing method described in any one of the appendices B1 through B5.

[0097] (Note B7) The aforementioned external information includes either or both changes in regulations in the industry related to the target segment, and / or information indicating the external environment of the industry. The information processing method described in any one of the appendices B1 to B6.

[0098] [Additional Note C] This disclosure includes the technologies described in the following appendices. However, the present invention is not limited to the technologies described in the following appendices, and various modifications are possible within the scope of the claims.

[0099] (Note C1) A program that makes a computer function as an information processing system, The aforementioned computer, A means for obtaining indicators to manage the accuracy of demand forecasts for a target segment that includes multiple products handled by the target company, An internal information acquisition means for acquiring internal company information concerning the target segment within the target company, An external information acquisition means for acquiring external information concerning the target segment outside of the target company, An interpretation example generation means that uses a large-scale language model to generate sentences that include factors based on internal and external company information regarding the error in the demand forecast, as examples of interpretations of the indicators, An information processing program that functions as such.

[0100] (Note C2) The above interpretation examples further include either or both the circumstances of the error in the demand forecast and the proposed response to the error in the demand forecast. The information processing program described in Appendix C1.

[0101] (Note C3) The aforementioned computer, In response to the operation of specifying the target segment, the display control means further functions as a means for displaying a screen including the indicator and the interpretation example on a display device. The information processing program described in Appendix C1 or C2.

[0102] (Note C4) The aforementioned internal company information includes information indicating the promotions that the target company conducts with respect to the target segment. An information processing program described in any one of the appendices C1 to C3.

[0103] (Note C5) The aforementioned external information includes either or both of the following: information on economic trends related to the target segment and information on social changes in the industry related to the target segment. An information processing program described in any one of the appendices C1 to C4.

[0104] (Appendix C6) The aforementioned internal company information includes some or all of the product information, demand forecasts, actual demand figures, and actual distribution figures related to the aforementioned target segment. An information processing program described in any one of the appendices C1 to C5.

[0105] (Note C7) The aforementioned external information includes either or both changes in regulations in the industry related to the target segment, and / or information indicating the external environment of the industry. An information processing program described in any one of the appendices C1 to C6.

[0106] [Additional Note D] This disclosure includes the technologies described in the following appendices. However, the present invention is not limited to the technologies described in the following appendices, and various modifications are possible within the scope of the claims.

[0107] (Note D1) It comprises at least one processor, and the at least one processor is An indicator acquisition process to obtain indicators for managing the accuracy of demand forecasts for a target segment that includes multiple products handled by the target company, and An internal information acquisition process that acquires internal company information concerning the target segment within the target company, An external information acquisition process that acquires external information concerning the target segment outside of the target company, An interpretation example generation process that uses a large-scale language model to generate sentences that include factors based on internal and external company information regarding the error in the demand forecast, as examples of interpretations of the indicators, An information processing system that performs [this action].

[0108] The information processing system may also include memory. Furthermore, the memory may store programs that cause at least one processor to execute each of the aforementioned processes.

[0109] (Note D2) The above interpretation examples further include either or both the circumstances of the error in the demand forecast and the proposed response to the error in the demand forecast. The information processing system described in Appendix D1.

[0110] (Note D3) The aforementioned at least one processor, In response to the operation to specify the target segment, a display control process is further executed to display the indicator and the screen including the interpretation example on a display device. The information processing system described in Appendix D1 or D2.

[0111] (Note D4) The aforementioned internal company information includes information indicating the promotions that the target company conducts with respect to the target segment. An information processing system described in any one of the appendices D1 to D3.

[0112] (Note D5) The aforementioned external information includes either or both of the following: information on economic trends related to the target segment and information on social changes in the industry related to the target segment. An information processing system described in any one of the appendices D1 to D4.

[0113] (Note D6) The aforementioned internal company information includes some or all of the product information, demand forecasts, actual demand figures, and actual distribution figures related to the aforementioned target segment. An information processing system described in any one of the appendices D1 to D5.

[0114] (Note D7) The aforementioned external information includes either or both changes in regulations in the industry related to the target segment, and / or information indicating the external environment of the industry. An information processing system described in any one of the appendices D1 to D6.

[0115] [Additional Note E] This disclosure includes the technologies described in the following appendices. However, the present invention is not limited to the technologies described in the following appendices, and various modifications are possible within the scope of the claims.

[0116] (Note E1) A program that makes a computer function as an information processing system, To the aforementioned computer, An indicator acquisition process to obtain indicators for managing the accuracy of demand forecasts for a target segment that includes multiple products handled by the target company, and An internal information acquisition process that acquires internal company information concerning the target segment within the target company, An external information acquisition process that acquires external information concerning the target segment outside of the target company, An interpretation example generation process that uses a large-scale language model to generate sentences that include factors based on internal and external company information regarding the error in the demand forecast, as examples of interpretations of the indicators, A non-temporary recording medium that stores an information processing program that executes that program. [Explanation of Symbols]

[0117] 1. 1A Information Processing System 10 Information Processing Devices 11 Indicator acquisition part 12 Corporate Information Acquisition Department 13 External Information Acquisition Department 14. Interpretation Example Generation Unit 15 Display Control Unit 20 User Terminals 21 User Interface Section 110, 210 Control Unit 120, 220 storage section 130, 230 Communications Department 240 Input section 250 Display section C1 Processor C2 Memory

Claims

1. A means for obtaining indicators to manage the accuracy of demand forecasts for a target segment that includes multiple products handled by the target company, An internal information acquisition means for acquiring internal company information concerning the target segment within the target company, An external information acquisition means for acquiring external information concerning the target segment outside of the target company, An interpretation example generation means that uses a large-scale language model to generate sentences that include factors based on internal and external company information regarding the error in the demand forecast, as examples of interpretations of the indicators, An information processing system equipped with the following features.

2. The above interpretation examples further include either or both the circumstances of the error in the demand forecast and the proposed response to the error in the demand forecast. The information processing system according to claim 1.

3. The system further includes a display control means that, in response to an operation to specify the target segment, displays a screen on a display device that includes the indicator and the interpretation example. The information processing system according to claim 1.

4. The aforementioned internal company information includes information indicating the promotions that the target company conducts with respect to the target segment. The information processing system according to claim 1.

5. The aforementioned external information includes either or both of the following: information on economic trends related to the target segment and information on social changes in the industry related to the target segment. The information processing system according to claim 1.

6. The aforementioned internal company information includes some or all of the product information, demand forecasts, actual demand figures, and actual distribution figures related to the aforementioned target segment. The information processing system according to claim 1.

7. The aforementioned external information includes either or both changes in regulations in the industry related to the target segment, and / or information indicating the external environment of the industry. The information processing system according to claim 1.

8. At least one processor performs an indicator acquisition process to obtain indicators for managing the accuracy of demand forecasts for a target segment that includes multiple products handled by the target company, The at least one processor performs an internal information acquisition process to acquire internal company information relating to the target segment within the target company, The at least one processor performs an external information acquisition process to acquire external information relating to the target segment outside the target company, The at least one processor performs an interpretation example generation process that uses a large-scale language model to generate a sentence as an example of interpretation of the indicator, which includes factors based on the internal and external information regarding the error in the demand forecast. Information processing methods including

9. At least one processor, An indicator acquisition process to obtain indicators for managing the accuracy of demand forecasts for a target segment that includes multiple products handled by the target company, and An internal information acquisition process that acquires internal company information concerning the target segment within the target company, An external information acquisition process that acquires external information concerning the target segment outside of the target company, An interpretation example generation process that uses a large-scale language model to generate sentences that include factors based on internal and external company information regarding the error in the demand forecast, as examples of interpretations of the indicators, An information processing program that executes [something].

Images