Apparatus and method for supporting reception of order
The order support device addresses the challenge of managing unordered projects by estimating order probabilities and identifying causes of variations, supporting efficient order management through case extraction and cause analysis.
Patent Information
- Application Number
- JP2023083929
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-22
- Publication Date
- 2024-12-04
AI Technical Summary
Large-scale companies face a significant burden in managing unfilled orders, leading to inappropriate actions during critical project stages due to the overwhelming amount of unordered project information, which can hinder effective order management.
An order support device that extracts cases likely to cause order acceptance issues by estimating the probability of order acceptance or loss for each project attribute, identifies the cause of variations in these probabilities over time, and displays the results to support corrective actions.
The device effectively identifies problematic cases and their causes, enabling targeted interventions to improve order management by highlighting risks and their underlying factors, thereby enhancing order acceptance processes.
Smart Images

Figure 2024167689000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an order support device and an order support method. [Background technology]
[0002] In recent years, it has become possible to manage and view various project information by accumulating information on past cases, such as winning / losing order settlement information and sales activity history information.Furthermore, various methods for predicting future order possibility, winning timing, or losing of unordered projects have been developed and are now being used for project management.
[0003] Patent document 1 states that "the aggregate information calculation means calculates aggregate information by aggregating items of past cases that indicate order receipts for each person in charge, and the point calculation means calculates evaluation points for each person in charge based on the aggregate information. The feedback point registration means registers feedback points in association with unconfirmed cases with evaluation points stored in the feedback storage means. The total point calculation means calculates total points for each person in charge by adding the evaluation points to the feedback points stored in the feedback storage means. The unconfirmed case reading means reads unconfirmed cases according to the size of the total points stored in the unconfirmed case with points storage means." [Prior art documents] [Patent documents]
[0004] [Patent Document 1] JP 2010-049353 A Summary of the Invention [Problem to be solved by the invention]
[0005] In large companies, there are huge amounts of unfilled orders, and sales representatives are burdened with managing these orders, which can lead to them taking inappropriate actions to increase orders at critical moments for important projects.
[0006] An object of the present invention is to provide a technique for efficiently extracting problematic cases and supporting the development of countermeasures to increase orders, even when a large amount of unordered case information is registered. [Means for solving the problem]
[0007] The present application includes a number of means for solving at least part of the above problems, examples of which are as follows: An order support device according to one aspect of the present invention for solving the above problems is characterized by comprising: a case extraction unit that extracts cases that meet a predetermined criterion using results of estimating the probability of winning or losing an order for unordered cases by predetermined case attributes, a cause estimation unit that estimates, as the cause, the case attributes related to cases that have a large amount of variation between the probabilities at different times when the estimation was performed, and a display unit that displays the cases extracted by the case extraction unit and the cause estimated by the cause estimation unit. Effect of the Invention
[0008] According to the present invention, it is possible to provide a technology that supports order acceptance by extracting cases that may cause problems in order acceptance and indicating the likely causes of the problems. Problems, configurations, and effects other than those described above will become apparent from the following description of the embodiment of the invention. [Brief description of the drawings]
[0009] [Figure 1] FIG. 2 is a diagram illustrating a configuration example of an order receiving support device. [Diagram 2] FIG. 2 illustrates an example of a hardware configuration of the order receiving support device. [Diagram 3] FIG. 11 is a diagram illustrating an example of a sequence of an order support process. [Figure 4] FIG. 13 is a diagram illustrating an example of a processing flow of problem case extraction processing. [Diagram 5] FIG. 13 is a diagram showing an example of detailed data of attribute-specific probability information. [Figure 6]FIG. 13 is a diagram showing an example of detailed data of attribute-specific probability history information. [Figure 7] FIG. 13 is a diagram showing an example of detailed data of prediction result information. [Figure 8] FIG. 13 is a diagram illustrating an example of detailed data of prediction result history information. [Figure 9] 13 is a diagram illustrating an example of detailed data of a case extraction condition list. FIG. [Figure 10] FIG. 13 is a diagram showing an example of detailed data of problem case information. [Figure 11] FIG. 13 is a diagram showing an example of a problem case display screen. [Figure 12] FIG. 13 is a diagram showing an example of a problem cause display screen. [Figure 13] FIG. 13 is a diagram showing an example of an attribute-specific variation amount display screen. [Figure 14] FIG. 13 is a diagram illustrating an example of detailed data of problem cause identification information. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The examples are illustrative for explaining the present invention, and are omitted and simplified as appropriate for clarity of explanation. The present invention can be implemented in various other forms. Unless otherwise specified, each component may be singular or plural.
[0011] In order to facilitate understanding of the invention, the position, size, shape, range, etc. of each component shown in the drawings may not represent the actual position, size, shape, range, etc. Therefore, the present invention is not necessarily limited to the position, size, shape, range, etc. disclosed in the drawings.
[0012] As examples of various information, the various information may be described using expressions such as "table", "list", and "queue", but the various information may be expressed using data structures other than these. For example, various information such as "XX table", "XX list", and "XX queue" may be expressed as "XX information". When describing identification information, expressions such as "identification information", "identifier", "name", "ID", and "number" are used, but these are mutually interchangeable. Furthermore, in the embodiments, the identification information described using these expressions is represented using symbols, numbers, natural language, or a combination thereof, but the identification information may be in a form other than these.
[0013] When there are multiple components having the same or similar functions, they may be described by using the same reference numerals with different subscripts, or when there is no need to distinguish between these multiple components, the subscripts may be omitted.
[0014] In the embodiments, a process performed by executing a program may be described. Here, a computer executes the program using a processor (e.g., CPU, GPU), and performs the process defined by the program while using a storage resource (e.g., memory) and an interface device (e.g., communication port), etc. Therefore, the subject of the process performed by executing the program may be the processor. Similarly, the subject of the process performed by executing the program may be a controller, device, system, computer, or node having a processor. The subject of the process performed by executing the program may be a calculation unit, and may include a dedicated circuit that performs specific processing. Here, the dedicated circuit is, for example, an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), or a CPLD (Complex Programmable Logic Device), etc.
[0015] The program may be installed in the computer from a program source. The program source may be, for example, a program distribution server or a computer-readable storage medium. When the program source is a program distribution server, the program distribution server may include a processor and a storage resource that stores the program to be distributed, and the processor of the program distribution server may distribute the program to be distributed to other computers. In addition, in the embodiment, two or more programs may be realized as one program, and one program may be realized as two or more programs.
[0016] Furthermore, although the present invention is typically realized by an information processing device, it may also be realized as a platform having the functions of the present invention.
[0017] 1 is a diagram showing a configuration example of an order support device. The order support device 100 is a device constituting a part of an order support system 10. The order support system 10 is configured by connecting the order support device 100, a user terminal 300, and a data management device 400 via a network 200 so as to be able to communicate with each other.
[0018] The network 200 is, for example, any one of a LAN (Local Area Network), a WAN (Wide Area Network), a VPN (Virtual Private Network), a communication network using a general public line such as the Internet in part or in whole, a mobile phone communication network, etc., or a combination of these networks. Note that the network 200 may be a wireless communication network such as Wi-Fi (registered trademark) or 5G (Generation).
[0019] The user terminal 300 is an information processing device such as a PC (Personal Computer). Using the user terminal 300, the case manager registers the case extraction condition list 125, instructs the order support device 100 to extract problem cases, and instructs the order support device 100 to identify the cause of the problem. The user terminal 300 obtains screen information including problem case information 126 and problem cause identification information 127 from the order support device 100, and displays it so that the case manager can confirm it.
[0020] The data management device 400 is, for example, a system such as SFA (Sales Force Automation) or a data management device that accumulates data equivalent thereto. The data management device 400 can be configured with a storage device that stores data and a computer that transmits and receives data. The data management device 400 reads information requested by the order support device 100 and passes it to the order support device 100.
[0021] The order support device 100 registers the case extraction condition list 125 in the data management device 400 and passes necessary information. In addition, the order support device 100 receives requested information from the data management device 400. The order support device 100 can be configured using an information processing device such as a PC or a server computer, and includes a processing unit 110, a storage unit 120, an input unit 130, and a communication unit 140.
[0022] The processing unit 110 includes a case extraction unit 111, a cause estimation unit 112, and a display unit 113. The case extraction unit 111 extracts cases that meet a predetermined criterion by using the results of estimating the probability of receiving or losing an order for each predetermined case attribute for unreceived cases. Specifically, the case extraction unit 111 extracts cases whose probability of receiving or losing an order is less than a predetermined probability. The case extraction unit 111 also extracts cases whose probability of losing an order is equal to or greater than a predetermined probability. The case extraction unit 111 may extract cases whose probability of receiving or losing an order is the highest, and which will be delayed beyond a predetermined reference date.
[0023] The cause estimation unit 112 estimates, as the cause, a case attribute related to a large amount of variation between the probability of receiving or losing an order at different estimation times. Specifically, the cause estimation unit 112 accepts two or more designations for the estimation implementation times at which the probability was estimated, and determines the amount of variation as the cumulative difference in probability between the two or more designated estimation implementation times. In this case, the cause estimation unit 112 may add up the cumulative total of the differences in the probability of receiving or losing an order for the same period over the entire fiscal year to determine the amount of variation.
[0024] The display unit 113 displays the cases extracted by the case extraction unit 111, and also displays the causes estimated by the cause estimation unit 112. The display destination may be the screen of the user terminal 300, or the display device 15 (described later) of the order support device 100 itself.
[0025] The storage unit 120 stores attribute-specific probability information 121, attribute-specific probability history information 122, prediction result information 123, prediction result history information 124, a case extraction condition list 125, problem case information 126, and problem cause identification information 127. Details of each data will be described later.
[0026] 2 is a diagram showing an example of a hardware configuration of the order support device 100. The order support device 100 includes a CPU 11, a RAM 12, a ROM 13, an auxiliary storage device 14, a display device 15, an input device 16, a media reader 17, and a communication device 18.
[0027] The CPU 11 is a unit that executes various calculations. The CPU 11 executes various processes by executing a predetermined order receiving support program loaded from the auxiliary storage device 14 to the RAM 12. The order receiving support program is, for example, an application program that can be executed on an OS (Operating System) program. The order receiving support program may be installed in the auxiliary storage device 14 from a portable storage medium via the media reader 17. Note that the CPU 11 is not limited to a CPU, and may be any processor including a GPU (Graphics Processing Unit), FPGA, ASIC, CPLD, etc., as described above.
[0028] For example, the case extracting unit 111, the cause estimating unit 112, and the display unit 113 can be realized by loading a program stored in the auxiliary storage device 14 into the RAM 12 and executing it by the CPU 11.
[0029] The RAM 12 is a memory that stores the programs executed by the CPU 11, data necessary for executing the programs, and the like.
[0030] The ROM 13 is a memory that stores programs required for starting the order support device 100 and the like.
[0031] The auxiliary storage device 14 is, for example, a device such as a hard disk drive (HDD), or may be a solid state drive (SSD) using a flash memory or the like.
[0032] The display device 15 may be, for example, a CRT display, an LCD (Liquid Crystal Display), These devices include OLED (Electro-Luminescence) displays and organic EL (Electro-Luminescence) displays.
[0033] The input device 16 is, for example, a keyboard, a mouse, a microphone, a touch panel, or the like.
[0034] The media reader 17 is a device that reads information from a portable storage medium such as a CD-ROM or a DVD (Digital Versatile Disk).
[0035] The communication device 18 is a device that transmits and receives data to and from an external device, such as a wired LAN card, a wireless LAN card, a dial-up router, or an infrared communication device.
[0036] The storage unit 120 can be realized by the CPU 11 using the RAM 12 or the auxiliary storage device 14. The input unit 130 can be realized by the CPU 11 using the input device 16 and the communication device 18. The communication unit 140 can be realized by the CPU 11 using the communication device 18.
[0037] FIG. 3 is a diagram showing an example of the sequence of the order support process. In this example of the sequence, in response to a start command from the case manager to the order support device 100, the order support device 100 acquires, from the data management device 400, prediction result information 123 of the case acceptance / loss and acceptance / loss timing, history information of the prediction results (prediction result history information 124), attribute-specific probability information 121 including a prediction of the probability of acceptance / loss occurring when focusing on a specified attribute of the case (customer's business type, importance, number of times the expected order date changes, number of times the order amount changes, or number of times the introduction form changes, etc. In this embodiment, these may be referred to as case attributes), and attribute-specific probability history information 122 which is history information of the prediction of the probability of acceptance / loss occurring when focusing on a specified attribute of the case. Furthermore, the order support device 100 extracts problem cases according to a case extraction condition list 125 as necessary, creates problem case information 126, and presents problem cause identification information 127 which is an estimation result of the case attribute information that caused each case to become problematic. The sequence of the order support process will be described below.
[0038] The case manager uses the user terminal 300 to instruct the order support device 100 to start problem case extraction. Furthermore, the case manager uses the user terminal 300 to register a case extraction condition list 125, which is the extraction conditions for problem cases (step S01). However, if the case extraction condition list 125 already registered in the data management device 400 is to be utilized, or if it is not necessary to specify the extraction conditions for problem cases, or if the extraction conditions for problem cases are to be specified from the screen in post-processing, then it is not necessary to register the case extraction condition list 125.
[0039] When the case extraction unit 111 of the order support device 100 receives an instruction to start problem case extraction and the case extraction condition list 125, it requests the data management device 400 to transmit the prediction result information 123 and its history information, that is, the prediction result history information 124 (step S02).
[0040] When the data management device 400 receives the request from the order support device 100, the data management device 400 transmits the prediction result information 123 and the prediction result history information 124 to the order support device 100 (step S03).
[0041] The case extraction unit 111 of the order support device 100 receives the prediction result information 123 and the prediction result history information 124, and performs problem case extraction processing using the case extraction condition list 125 previously registered from the user terminal 300 (step S04). The problem case extraction processing will be described in detail later.
[0042] The case extraction unit 111 targets cases included in the prediction result information 123 and the prediction result history information, extracts cases that satisfy the conditions included in the case extraction condition list 125 as problem cases, and stores problem case information 126 including the extracted problem cases in the data management device 400 (step S05).
[0043] Then, the display unit 113 creates a predetermined display screen so that the problem case information 126 can be confirmed by the case management staff, and displays it on the user terminal 300 (step S06). The display screen will be described in detail later.
[0044] Next, the case manager uses the user terminal 300 to instruct the order support device 100 to start a problem cause identification process (step S07).
[0045] When the cause estimation unit 112 of the order support device 100 receives an instruction to start the problem cause identification process, it requests the data management device 400 to transmit the attribute-specific probability information 121 and its history information, that is, the attribute-specific probability history information 122 (step S08).
[0046] When the data management device 400 receives the request from the order support device 100, the data management device 400 transmits the attribute-specific probability information 121 and the attribute-specific probability history information 122 to the order support device 100 (step S09).
[0047] Then, upon receiving the attribute-specific probability information 121 and the attribute-specific probability history information 122, the cause estimation unit 112 of the order support device 100 performs a problem cause identification process (step S10). In the problem cause identification process, first, the cause estimation unit 112 accepts, using the display screen of the user terminal 300, the designation of a case for which the case manager has determined that the problem cause needs to be identified based on the problem case extraction result. Then, the cause estimation unit 112 extracts attribute-specific probability information for the designated case from the attribute-specific probability information 121, and the display unit 113 displays it on the user terminal 300. By checking the information on the display screen, the case manager can confirm which attribute has a greater impact on the outcome of an order.
[0048] Furthermore, to perform a detailed analysis of the problem cause, the cause estimation unit 112 compares and analyzes the difference between the latest attribute-specific probability information 121 and attribute-specific probability history information 122, which is past attribute-specific probability information. At that time, for the case to be analyzed, the cause estimation unit 112 accepts the specification of one or more dates as the forecast planning date in addition to the latest date. The cause estimation unit 112 also accepts the specification of one or more dates for the specification of the attribute to be checked in detail.
[0049] Furthermore, the cause estimation unit 112 stores the result of analyzing the difference between the attribute-specific probability information 121 and the attribute-specific probability history information 122 of the specified case as problem cause identification information 127 in the data management device 400 (step S11).
[0050] Furthermore, the display unit 113 creates a predetermined display screen including problem cause identification information 127 so that the case manager can identify the attributes of the problem cause of the case designated as a problem case, and displays the screen on the user terminal 300 (step S12). The display screen will be described in detail later.
[0051] The above is an example of the sequence of the order support process. The order support process makes it possible to extract problem cases according to predetermined conditions from the huge number of registered unordered cases. It also makes it possible to show the attributes of the extracted cases that are causing the problems. Therefore, it is possible to support order acceptance by extracting cases that may cause problems in accepting orders and showing the likely causes of the problems.
[0052] 4 is a diagram showing an example of a process flow of the problem case extraction process, which is performed in step S04 of the order support process.
[0053] First, the case extraction unit 111 reads the specified case extraction condition (step S041). Specifically, if there is a specified extraction condition from a pre-stored case extraction condition list 125 (see FIG. 9), the case extraction unit 111 reads the case extraction condition list 125. If the case extraction condition list 125 is not specified, the case extraction unit 111 accepts input of a combination of a problem event, a specified date, a threshold value, and a flag as information similar to that in the case extraction condition list 125.
[0054] Here, a problem event refers to a condition that a case to be extracted as a problem case must satisfy. For example, problem events include "postponement of order date," "reduced probability of receiving order," and "measures to prevent lost orders." A specified date refers to a reference date when a reference date is one of the parameters included in a problem event. A threshold refers to a threshold of a key performance indicator (KPI) when a reference KPI is one of the parameters included in a problem event. A flag refers to information that identifies a case extraction condition used by the case extraction unit 111 from among the conditions included in the case extraction condition list 125.
[0055] For example, the problem event condition "order date postponed" is a condition for extracting cases whose predicted order date has been postponed as problem events. The extraction condition is that a case in which the date predicted as an order (forecast order date) in the prediction result history information 124 was before a specified date (for example, March 31, 2023) has a forecast order date that has been postponed to a date after the specified date in the latest prediction result information 123. Note that the case extraction unit 111 does not extract, as problem events, extraction conditions whose flag is not "1".
[0056] Here, the order forecast date is the date if it is included in the forecast result information 123 and the forecast result history information 124 (see Figs. 7 and 8). If not, the expected order date can be determined as the time when the period-specific probability of each case included in the forecast result information 123 and the forecast result history information 124 is the highest, or the time when the cumulative order probability when adding up the order probabilities from the forecast start date to future dates becomes 50% or more. The method of determining the order forecast date varies depending on the characteristics of the case, and can be other than the above.
[0057] For example, the condition for the problem event "decrease in order probability" is a condition for extracting cases with a decreasing order probability as a problem event. The extraction condition is that for cases in which the order probability for a specified date (e.g., March 31, 2023) in the prediction result history information 124 exceeds a threshold value (e.g., 60%), the order probability for the same specified date in the prediction result information 123 falls below the threshold value. Note that the case extraction unit 111 does not extract, as problem cases, extraction conditions whose flag is not "1".
[0058] Also, for example, the condition for a problem event, "measures against losing a contract," is a condition for extracting cases in which the probability of losing a contract exceeds a threshold as a problem event. The extraction condition is that the cumulative loss rate, which is the cumulative probability of losing a contract over time starting from the prediction start date in the prediction result information 123, exceeds a threshold (e.g., 50%). Problem cases are extracted. Note that the case extraction unit 111 does not extract, as problem cases, extraction conditions for which the flag is not "1."
[0059] Then, the case extraction unit 111 performs selection according to the specified date (step S042), selection according to a threshold value (step S043), and selection according to a flag (step S044). As described above, in the problem case extraction process, the specified date and threshold value are used differently depending on the problem phenomenon to be extracted, so the case extraction unit 111 performs extraction using the specified date, threshold value, and flag depending on the problem phenomenon.
[0060] For example, for the problem event "order date postponed", the case extraction unit 111 selects cases in which the date predicted as an order (order forecast date) in the prediction result history information 124 was before a specified date (e.g., March 31, 2023), but in the latest prediction result information 123, the order forecast date has been postponed to a date after the specified date. Furthermore, if the flag is not "1", the case extraction unit 111 does not extract the case as a problem case. Note that the case extraction unit 111 may calculate a score indicating the severity of the problem of the problem event "order date postponed". For example, the case extraction unit 111 may set the difference between the order forecast date in the prediction result information 123 and the order forecast date in the prediction result history information 124 as the score of each case.
[0061] For example, for the problem event "reduced probability of receiving orders", the case extraction unit 111 selects cases in which the order probability for a specified date (e.g., March 31, 2023) in the prediction result history information 124 exceeds a threshold (e.g., 60%) and the order probability for the same specified date in the prediction result information 123 is below the threshold. If the flag is not "1", the case extraction unit 111 does not extract the case as a problem case. Note that the case extraction unit 111 may calculate a score indicating the severity of the problem of the problem event "reduced probability of receiving orders". For example, the case extraction unit 111 may set the difference between the order probability for a predetermined period including the specified date in the prediction result history information 124 and the order probability for the same period in the prediction result information 123 as the score.
[0062] For example, the case extraction unit 111 selects cases for which the cumulative loss rate, which is the cumulative loss probability over time starting from the prediction start date of the prediction result information 123, exceeds a threshold value (e.g., 50%) for the problem event "measures against loss." If the flag is not "1," the case extraction unit 111 does not extract the case as a problem case.
[0063] The above is an example of the process flow of the problem case extraction process. According to the problem case extraction process, problem cases can be extracted according to predetermined extraction conditions.
[0064] In the problem cause identification process performed in step S10 of the order support process, in order to perform a detailed analysis of the problem cause, the cause estimation unit 112 compares and analyzes the difference between the latest attribute-specific probability information 121 and the attribute-specific probability history information 122, which is past attribute-specific probability information. This process is a process that compares the probability of acceptance or loss based on the attributes of a specified case at multiple points in time, and estimates that an attribute with a large cumulative amount of fluctuation is the cause of the problem, based on the idea that an attribute with a large cumulative amount of fluctuation in the probability of acceptance or loss has a large impact on the result.
[0065] According to the problem cause identification process, by referring to the latest attribute-specific probability information 121 and attribute-specific probability history information 122, which is past attribute-specific probability information, it is possible to estimate that an attribute with a large cumulative fluctuation in the probability of receiving or losing an order is the cause of the problem.
[0066] 5 is a diagram showing an example of detailed data of attribute-specific probability information. Attribute-specific probability information 121 is calculated in the process of calculating prediction result information 123, and is probability information of acceptance or loss of an order for a predetermined period by attribute. Attribute-specific probability information 121 includes probability information by case name, prediction planning date, attribute, prediction category, and period.
[0067] The attributes are information including, for example, the type of business, importance, the number of updates of the expected order date, the number of updates of the order amount, or the update contents included in the item of the case. This probability information may be information by time calculated using a predetermined algorithm, and in this embodiment, the result of calculation by an external device is received from the data management device 400. However, it is not limited to this, and the cause estimation unit 112 may calculate it using a predetermined algorithm.
[0068] Furthermore, this probability information is set to "1" for the entire fiscal year, and for the prediction categories "order received" and "lost" of the same attribute. In other words, for example, the probability information for the attribute "scheduled order date" of "case 1" is a value of "1" when the probability information for the prediction categories "order received" and "lost" is added together for the entire fiscal year. Similarly, the probability information for the attribute "importance" of "case 1" is also set to "1" when the probability information for the prediction categories "order received" and "lost" is added together for the entire fiscal year. In other words, attribute-specific probability information 121 can be said to include probability information by order received / lost and by time period for each attribute.
[0069] 6 is a diagram showing an example of detailed data of attribute-specific probability history information. The attribute-specific probability history information 122 is information that accumulates the history of the latest and previously calculated attribute-specific probability information 121. Therefore, like the attribute-specific probability information 121, the attribute-specific probability history information 122 includes probability information by case name, forecast planning date, attribute, forecast category, and period.
[0070] 7 is a diagram showing an example of detailed data of the forecast result information. The forecast result information 123 is probability information of acceptance or loss of an unordered case for a given period. The forecast result information 123 includes the case name, forecast planning date, forecast category, and probability information by period.
[0071] Furthermore, this probability information is set to "1" for the entire fiscal year, and for the combined prediction categories "Order received" and "Lost." In other words, for example, the probability information for "Case 1" is a value that is "1" when the probability information for the prediction categories "Order received" and "Lost" is added together for the entire fiscal year. Similarly, the probability information for "Case 2" is also set to "1" when the probability information for the prediction categories "Order received" and "Lost" is added together for the entire fiscal year. In other words, prediction result information 123 can be said to include the settlement status of orders received or lost, the timing of orders received or lost, and probability information for orders received or lost by time period.
[0072] 8 is a diagram showing an example of detailed data of the prediction result history information. The prediction result history information 124 is information that accumulates the history of the latest and previously calculated prediction result information 123. Therefore, like the prediction result information 123, the prediction result history information 124 includes the case name, the prediction planning date, the prediction category, and probability information by period.
[0073] 9 is a diagram showing an example of detailed data of the case extraction condition list. The case extraction condition list 125 is information to be input to the case extraction unit 111, and is prepared in advance as a file in the storage unit 120. However, this is not limited to this, and either a method of inputting from a screen when a user performs case extraction, or using stored data if information is already stored in the data management device 400, may be used. The case extraction condition list 125 includes problem phenomena, specified dates, thresholds, and flags.
[0074] 10 is a diagram showing an example of detailed data of problem case information. Problem case information 126 is output information from the case extraction unit 111. The problem case information 126 includes information on the case name, problem phenomenon, prediction category, specified date, threshold value, prediction planning date, and score.
[0075] 11 is a diagram showing an example of a problem case display screen. The problem case display screen 500 is an example of a screen that accepts inputs required to start a problem case extraction process and displays the output of the case extraction results. This screen includes an extraction condition input area 501, a predicted planning date selection area 502, a problem case extraction start instruction button 503 for executing the case extraction unit 111, a problem case list display 504 that displays a list of the case extraction results, and an order acceptance / loss probability distribution graph display 505.
[0076] The extraction condition input area 501 is an area that accepts input of data items of the case extraction condition list 125. Specifically, the extraction condition input area 501 accepts input of a problem event, a specified date, and a threshold value. If conditions have been registered in the case extraction condition list 125 in advance, the items of the case extraction condition list 125 are presented as selection items in the problem event column. When the user selects the content that he or she wants to extract as a problem event, the extraction condition input area 501 reads the specified date and threshold value registered in the case extraction condition list 125 in accordance with the item selected in the problem event column, and updates the screen display. The extraction condition input area 501 then accepts input of corrections to the specified date and threshold value.
[0077] The forecast planning date selection area 502 is an area that accepts a designated input of the date on which the probability of receiving or losing an order was predicted. Specifically, the forecast planning date selection area 502 displays the forecast planning dates of the forecast result information 123 and the forecast result history information 124 stored in the data management device 400 as selectable candidates, and further displays the date on which the latest prediction was made and the date on which the most recent prediction was made by default with a check mark. The forecast planning date selection area 502 accepts a designated input of the date on which the probability of receiving or losing an order was predicted. Note that if three or more forecast planning dates are checked, the case extraction unit 111 extracts cases by comparing the specified forecast planning dates with the latest prediction result in order of oldest to newest.
[0078] When a start instruction button 503 receives input from the extraction condition input area 501 and the forecast planning date selection area 502, it starts step S01 of the sequence of the order support process.
[0079] The problem case list display 504 reads the case number, the case name, and the score of the problem case from the problem case information 126 created in the problem case extraction process, and displays them in a list.
[0080] The order loss probability distribution graph display 505 displays the order loss probability distribution for each forecast planning date for cases with a check in the check box of the problem case list display 504. The order loss probability distribution graph display 505 also displays the probability distribution of an item selected alternatively from the radio buttons "〇: Order received 〇: Lost" of the order loss probability distribution of the order loss probability distribution graph display 505. In the example order loss probability distribution, "Order received" is selected, and when the forecast planning date is October 2022, the order probability is highest in March 2023, but when the forecast planning date is January 2023, the order probability is highest in April 2023, and it can be confirmed that case 1 is a problem case whose order forecast date was pushed back from March to April beyond the specified date of March 31, 2023.
[0081] 12 is a diagram showing an example of a problem cause display screen. The problem cause display screen 510 is an example of a screen that accepts inputs required to start a problem cause identification process and displays a graph for interpreting the attributes of the cause. The problem cause display screen 510 includes a case selection area 511, a forecast planning date selection area 512, an instruction button 513 for starting an attribute-based distribution display or attribute-based history display for executing the problem cause identification process, an attribute list display 514 for displaying a list of attributes for which probability distribution is to be displayed, and an attribute-based probability distribution graph display 515.
[0082] The case selection area 511 displays case names from the problem case information 126 as selection items and accepts the selection of the case to be displayed.
[0083] The forecast creation date selection area 512 is an area that accepts input for specifying the date on which the probability of receiving or losing an order was predicted. Specifically, the forecast creation date selection area 512 displays the forecast creation dates of the attribute-specific probability information 121 and the attribute-specific probability history information 122 stored in the data management device 400 as selectable candidates, and further displays the date on which the most recent prediction was made with a check mark by default. The forecast creation date selection area 512 accepts input for specifying the date on which the probability of receiving or losing an order was predicted.
[0084] When the start instruction button 513 receives an input, it accepts input in the case selection area 511 and the forecast planning date selection area 512, and starts step S07 of the sequence of the order support process.
[0085] The attribute list display 514 displays a selectable list of attributes of the attribute-specific probability information 121 and the attribute-specific probability history information 122. When a check is input into a check box of any attribute, the attribute list display 514 displays the order acceptance / loss probability distribution by attribute in the attribute-specific probability distribution graph display 515.
[0086] In the attribute-specific probability distribution graph display 515, the horizontal axis represents time, and the vertical axis represents the probability of winning or losing the order, and the display content can be switched by reselecting the radio button "O: Win / O: Lost" at the top of the graph. The attribute-specific probability distribution displays a probability distribution predicted based on the attributes, and the higher the probability, the greater the impact of the prediction result information on the probability of winning or losing the order. In this example, "Win" has been selected, and it is shown that there are two attributes with a high probability of winning (dashed line, two-dot chain line). Selecting one of these probability distributions will transition to the attribute-specific variation display screen 520.
[0087] 13 is a diagram showing an example of an attribute-specific variation display screen. The attribute-specific variation display screen 520 is an example of a screen that displays the variation in the probability of receiving or losing an order based on an attribute when the selection of the attribute is accepted on the problem cause display screen 510. The attribute-specific variation display screen 520 includes a case selection area 511, a forecast planning date selection area 512, an instruction button 513 for starting an attribute-specific distribution display or attribute-specific history display for executing a problem cause identification process, an attribute score list display 524 for displaying a list of the attributes for which the probability distribution is to be displayed and their scores, and an attribute-specific history graph display 525.
[0088] The attribute score list display 524 displays a selectable list of attributes in the attribute-specific probability information 121 and attribute-specific probability history information 122, and scored information indicating the degree of influence on the probability distribution based on the attribute. When a check is input into the checkbox of any attribute, the attribute score list display 524 displays the probability distribution of order acceptance and loss for each forecast preparation date by attribute overlaid on the attribute-specific history graph display 525, visualizing the amount of fluctuation between the forecast preparation dates.
[0089] For example, in the attribute score list display 524 of this example, the scores are shown in descending order of scheduled order date, order amount, implementation form, importance, and industry. Although the importance was an attribute with a high probability distribution, referring to the lower graph of the attribute-specific history graph display 525, it is shown that the importance as an attribute has a small probability change range due to the forecast planning date (almost the same level with no fluctuation range). In contrast, referring to the upper graph of the attribute-specific history graph display 525, it is shown that the probability distribution of the scheduled order date has a large probability change range due to the forecast planning date (the probability distribution for January 2023 is significantly different from the probability distribution for October 2022). This shows that the cause of the problem is the change in the scheduled order date.
[0090] Fig. 14 is a diagram showing an example of detailed data of problem cause identification information. Problem cause identification information 127 is information that is one of the outputs of the problem cause identification process of the order support process, that is, information that clearly indicates the attributes that are the cause of the problem. The problem cause identification information 127 includes the case name, problem phenomenon, prediction category, specified date, threshold, predicted date, attributes, and scores. Among these, the attribute with the highest score is the attribute that is presumed to be the cause of the problem.
[0091] The above is an example of the order support system 10 according to the embodiment of the present invention. Note that the present invention is not limited to the above-mentioned embodiment, and various modified examples are included. For example, the above-mentioned embodiment has been described in detail to clearly explain the present invention, and is not necessarily limited to having all of the configurations described. It is possible to replace a part of the configuration of the embodiment with another configuration, and it is also possible to add the configuration of another embodiment to the configuration of the embodiment. It is also possible to delete a part of the configuration of the embodiment.
[0092] For example, in the above embodiment, an example was shown in which the order acceptance / loss probability distribution uses the results calculated by another system, but this is not limited to this, and it may be calculated in the order support device 100, or it can be applied to a configuration in which it is calculated in the data management device 400 or the user terminal 300.
[0093] The above-mentioned units, configurations, functions, processing units, etc. may be realized in part or in whole by hardware, for example by designing them as integrated circuits. Also, the above-mentioned units, configurations, functions, etc. may be realized in software by a processor interpreting and executing a program that realizes each function. Information such as the programs, tables, files, etc. that realize each function can be stored in a memory, a recording device such as a hard disk, or a recording medium such as an IC card, an SD card, or a DVD.
[0094] The control lines and information lines in the above-described embodiment are those considered necessary for the explanation, and do not necessarily show all the control lines and information lines in the product. In reality, it may be considered that almost all the components are connected to each other. The present invention has been described above with a focus on the embodiment. [Explanation of symbols]
[0095] 10: order support system, 100: order support device, 110: processing unit, 111: case extraction unit, 112: cause estimation unit, 113: display unit, 120: memory unit, 121: attribute-specific probability information, 122: attribute-specific probability history information, 123: prediction result information, 124: prediction result history information, 125: case extraction condition list, 126: problem case information, 127: problem cause identification information, 130: input unit, 140: communication unit.
Claims
1. a case extraction unit that extracts cases that meet a predetermined criterion by using a result of estimating a probability of winning or losing a case for each of predetermined case attributes for unordered cases; a cause estimation unit that estimates, for the case, the case attribute that has a large amount of variation among the probabilities when the estimation was performed at different times as a cause; a display unit that displays the cases extracted by the case extraction unit and the causes inferred by the cause inferring unit; An order support device comprising:
2. The order support device according to claim 1, the case extraction unit extracts the case where the probability of receiving the order is less than a predetermined probability from among the probabilities; An order support device comprising:
3. The order support device according to claim 1, The case extraction unit extracts the case in which a probability of losing the order is equal to or higher than a predetermined probability. An order support device comprising:
4. The order support device according to claim 1, the job extraction unit extracts the job for which the time when the probability of receiving the order is maximized crosses a predetermined base date and is delayed; An order support device comprising:
5. The order support device according to claim 1, The project attributes include at least one of the following: the type of business of the client of the project, the importance, the number of times the order date has changed, the number of times the order amount has changed, or the number of times the implementation form has changed; An order support device comprising:
6. The order support device according to claim 1, The cause estimation unit receives two or more designations of estimation implementation times at which the probability of receiving or losing an order is estimated, and determines the amount of variation as a cumulative sum of the difference in the probability between the two or more designated estimation implementation times. An order support device comprising:
7. The order support device according to claim 1, The probability is estimated for a predetermined time period; The cause estimation unit adds up the cumulative sum of the differences in the probabilities for the same period over the entire term to obtain the amount of fluctuation. An order support device comprising:
8. An order receiving support method using an information processing device, The information processing device includes: an order extraction step of extracting orders that meet a predetermined criterion by using a result of estimating a probability of winning or losing an order based on predetermined order attributes for an order that has not yet been received; a cause estimation step of estimating, for the cases, the case attribute related to the case with a large amount of fluctuation in the probability where the estimation was performed at different times as the cause; a display step of displaying the case extracted in the case extracting step and displaying the cause estimated in the cause estimating step; The method for supporting receiving an order is characterized by carrying out the steps described above.
Citation Information
Patent Citations
Business support device, business support method, and business support program
JP2010049353A
