Order forecasting device, order forecasting system, and order forecasting method

Abstract

To provide an order acceptance prediction device, an order acceptance prediction system, and an order acceptance prediction method for highly accurately performing order acceptance prediction even for a company in charge of a process before accepting an order.SOLUTION: In an order acceptance prediction system 1, an order acceptance prediction device 100 includes, at its processing unit 130, a gross profit prediction unit 134 that predicts a gross profit for each manufacturing matter by using at least a usage probability of each process of the manufacturing matter and a selection probability of a company in charge of the process selected to be in charge of the process, and an order acceptance probability prediction unit 135 that predicts an order acceptance probability of the company in charge of the process using actual result values of similar manufacturing matters inclusive of gross profits.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an order forecasting device, an order forecasting system, and an order forecasting method. [Background technology]

[0002] Patent document 1 states, "The consensus building support system is equipped with a means for generating one or more evaluation scenarios from the customer's requirements and the priority of the requirements, and a means for calculating competitiveness by using the advantages of the vendor's functions over other companies in each evaluation scenario, and a means for calculating the vendor's profit amount by using the customer's requirements and budget and the vendor's provision costs, and operates to enable evaluation of projects under negotiation from both the perspective of the customer selecting the vendor and the perspective of the profit that the vendor can secure." [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2011-100394 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology described in the above-mentioned Patent Document 1 calculates costs based on customer requirements, but cannot predict specific cost structures, and therefore cannot predict orders from companies that provide parts and services to vendors.

[0005] An object of the present invention is to perform highly accurate order forecasting for companies in charge of processes before they receive orders. [Means for solving the problem]

[0006] In order to solve the above problems, the present application employs, for example, the means described in the claims. The present invention includes a plurality of means for solving the above problems, but an example thereof is an order prediction device that includes a gross profit prediction unit that predicts gross profit for each manufacturing case using at least the usage probability of each process of the manufacturing case and the selection probability of a process-performing company that is selected to be in charge of the process, and an order probability prediction unit that predicts the order probability of a process-performing company using the performance values ​​of similar manufacturing cases, including gross profit. Effect of the Invention

[0007] According to the present invention, a technology can be provided that enables companies in charge of processes to perform highly accurate order forecasts before receiving orders.

[0008] Problems, configurations and effects other than those described above will become apparent from the following description of the embodiments. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of an order forecasting system. [Diagram 2] FIG. 13 is a diagram illustrating an example of a data structure of inquiry information. [Diagram 3] FIG. 13 is a diagram illustrating an example of a data structure of past case information. [Figure 4] FIG. 13 is a diagram illustrating an example of a data structure of past parts table information. [Diagram 5] FIG. 13 is a diagram illustrating an example of a data structure of past process chart information. [Figure 6] FIG. 13 is a diagram illustrating an example of a data structure of constituent company performance information. [Figure 7] FIG. 13 is a diagram illustrating an example of a data structure of constituent company information. [Figure 8] FIG. 13 is a diagram illustrating an example of a data structure of transportation cost information. [Figure 9] FIG. 13 is a diagram illustrating an example of a data structure of bill of materials forecast information. [Figure 10] FIG. 13 is a diagram illustrating an example of a data structure of process chart forecast information. [Figure 11]FIG. 13 is a diagram illustrating an example of a data structure of constituent company forecast information. [Figure 12] FIG. 13 is a diagram illustrating an example of a data structure of cost prediction information. [Figure 13] FIG. 13 is a diagram illustrating an example of a data structure of order probability prediction information. [Figure 14] FIG. 2 illustrates an example of a hardware configuration of an order prediction device. [Figure 15] FIG. 13 is a diagram illustrating an example of a flow of an order forecast process. [Figure 16] FIG. 13 is a diagram showing an example of a screen for order probability prediction processing. [Figure 17] FIG. 13 is a diagram illustrating an example of an output screen of the order forecast process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] In the following embodiments, for convenience, when necessary, the description will be divided into multiple sections or embodiments, but unless otherwise expressly stated, they are not unrelated to each other and one is a partial or complete variation, detail, supplementary explanation, etc. of the other.

[0011] In addition, in the following embodiments, when referring to the number of elements (including the number, numerical values, amounts, ranges, etc.), unless specifically stated or clearly limited to a specific number in principle, the number is not limited to that specific number and may be more than or less than the specific number.

[0012] Furthermore, it goes without saying that in the following embodiments, the components (including element steps, etc.) are not necessarily essential unless specifically stated otherwise or unless they are clearly considered essential in principle.

[0013] Similarly, in the following embodiments, when referring to the shapes, positional relationships, etc. of components, etc., unless otherwise specified or considered to be obviously different in principle, it includes those that are substantially similar or similar to the shapes, etc. The same applies to the above numerical values ​​and ranges.

[0014] In addition, in all the drawings for explaining the embodiments, the same components are generally given the same reference numerals, and the repeated explanations are omitted. However, when there is a high possibility of confusion occurring if the same components share the same names as the components before the change due to an environmental change, etc., different reference numerals or names may be given to the same components. Each embodiment of the present invention will be explained below with reference to the drawings.

[0015] The present invention estimates the composition (BOM: Bill of Materials) of each product manufacturing project and predicts gross profit. It also estimates the probability of companies that will be responsible for manufacturing parts to realize the estimated composition, and predicts the order probability of each manufacturing company according to the time period. The data on which the estimation is based is past data (performance data) of similar projects.

[0016] In the following embodiments, the "input unit," "output unit," and "communication unit" may be one or more interface devices. The one or more interface devices may be at least one of the following: One or more I / O (Input / Output) interface devices. The I / O interface device is an interface device to at least one of the I / O device and a remote display computer. The I / O interface device to the display computer may be a communications interface device. The at least one I / O device may be a user interface device, e.g., either an input device such as a keyboard and a pointing device, or an output device such as a display device. One or more communication interface devices. The one or more communication interface devices may be one or more homogeneous communication interface devices (e.g., one or more NICs (Network Interface Cards)) or two or more heterogeneous communication interface devices (e.g., a NIC and an HBA (Host Bus Adapter)).

[0017] In the following description, a "memory" refers to one or more memory devices, which are an example of one or more storage devices, and may typically be a primary storage device. At least one memory device in the memory may be a volatile memory device or a non-volatile memory device.

[0018] In the following description, an "external storage device" may be one or more persistent storage devices, which are an example of one or more storage devices. The persistent storage device may typically be a non-volatile storage device (e.g., an auxiliary storage device), and more specifically, may be, for example, a hard disk drive (HDD), a solid state drive (SSD), a non-volatile memory express (NVME) drive, or a storage class memory (SCM).

[0019] In the following description, a "storage unit" or an "external storage device" may refer to either a memory or a persistent storage device, or both.

[0020] Also, in the following description, a "processing unit" or a "processor" may be one or more processor devices. The at least one processor device may typically be a microprocessor device such as a CPU (Central Processing Unit), but may also be other types of processor devices such as a GPU (Graphics Processing Unit). The at least one processor device may be a single-core or multi-core. The at least one processor device may be a processor core. The at least one processor device may also be a broader processor device such as a circuit that is a collection of gate arrays written in a hardware description language that performs part or all of the processing (e.g., a Field-Programmable Gate Array (FPGA), a Complex Programmable Logic Device (CPLD), or an Application Specific Integrated Circuit (ASIC)).

[0021] Furthermore, in the following description, the "order forecast system" may be a system made up of one or more physical computers, or may be a system (e.g., a cloud computing system) realized on a group of physical computing resources (e.g., a cloud infrastructure). When the order forecast system "displays" the display information, it may mean displaying the display information on a display device possessed by the computer, or the computer may transmit the display information to a display computer (in the latter case, the display information is displayed by the display computer).

[0022] 1 is a diagram showing an example of the configuration of an order prediction system. The order prediction system 1 includes an order prediction device 100, and a user terminal 200 communicatively connected to the order prediction device 100 via a network 50. The order prediction system 1 includes a group of devices according to the usage environment, such as a display computer communicatively connected via the network 50.

[0023] The network 50 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. Note that the network may be a wireless communication network such as Wi-Fi (registered trademark) or 5G (Generation).

[0024] The order prediction device 100 is a processing device including a storage unit 110, a processing unit 130, an input unit 140, an output unit 150, and a communication unit 160. The storage unit 110 includes inquiry information 111, past case information 112, past BOM information 113, past process schedule information 114, constituent company performance information 115, constituent company information 116, transportation cost information 117, BOM forecast information 118, process schedule forecast information 119, constituent company forecast information 120, cost forecast information 121, and order probability forecast information 122.

[0025] 2 is a diagram showing an example of a data structure of inquiry information. In the inquiry information 111, candidates for manufacturing orders that have not yet been accepted are listed. In the inquiry information 111, for each order No. 111a that distinguishes a manufacturing order from other orders, the customer name 111b, who is a potential customer for the order, the customer industry 111c, the delivery area 111d, the product type 111e, the required quality 111f, the customer budget 111g, the progress state 111h until the order of the order, the probability of order 111j, the number of visits 111k, and the data update date 111m are stored in association with each other.

[0026] The customer business type 111c is information that specifies the business type of the customer, which has been pre-classified. For example, customer companies are pre-classified into one of categories such as "automobiles," "finance," and "real estate." The delivery area 111d is information that specifies the delivery destination area of ​​the pre-classified customer. For example, the delivery area is pre-classified into one of categories such as "China," "America," and "Japan." The product type 111e is information that specifies the type of product to be delivered to the customer. For example, the product type is pre-classified into one of categories such as "order (custom-made product)" and "standard (ready-made product)."

[0027] The required quality 111f is information that specifies the quality of the product that the customer requires. For example, the required quality is pre-classified into one of categories such as "high", "low", "medium", etc. The progress status 111h is information that specifies the progress of the business negotiation up to the receipt of an order for the project from the customer. For example, the progress status is pre-classified into one of categories such as "inquiry", "quote", "preliminary notice", "received order", "lost order", etc. The accuracy 111j is information that specifies the probability of the project from the customer being concluded. For example, the accuracy is pre-classified into one of categories such as ranks A (confirmed) to D (needed).

[0028] 3 is a diagram showing an example of the data structure of past case information. Past case information 112 is substantially the same information as inquiry information 111, but differs in that it is the results of past cases. In addition, gross profit 112m is associated with each case, and the gross profit expected for the case on data update date 112p is shown. Note that gross profit is roughly calculated by subtracting expected costs from sales (expected).

[0029] Specifically, in the past project information 112, for each project number 112a that distinguishes a manufacturing project from other projects, the customer name 112b of the project's customer, the customer industry 112c, delivery area 112d, product type 112e, required quality 112f, customer budget 112g, progress status 112h of the project up to order, probability of order 112j, number of visits 112k, gross profit 112m, and data update date 111p are stored in association with each other.

[0030] 4 is a diagram showing an example of the data structure of past BOM information. Past BOM information 113 is performance information of the BOM constituting the finished product for each past case. Specifically, in the past BOM information 113, for each case No. 113a that distinguishes a manufacturing case from other cases, a customer name 113b that is the customer of the case, a finished product 113c that specifies the model of the product, an intermediate product 113d that constitutes the product, and an end part 113e that constitutes the intermediate product are stored in association with each other.

[0031] It should be noted that the classification into finished products, intermediate products, and parts is a classification made for convenience, and intermediate products in particular may be divided into more or fewer hierarchical levels depending on the degree of complexity of the product configuration.

[0032] Here, by considering the product as a tree structure and each element (part or intermediate product) as a convenient address (house number), similar parts / intermediate products will be located at the same house number even if they are different products if they have a similar structure, making it easier to estimate costs. Therefore, in this embodiment, the bill of materials is interpreted as a tree structure, but the present invention is not limited to this, and modeling using other structures may be adopted.

[0033] 5 is a diagram showing an example of a data structure of past process schedule information. Past process schedule information 114 is performance information of the manufacturing process of the finished product for each past case. Specifically, in the past process schedule information 114, for each case No. 114a that distinguishes the manufacturing case from other cases, a customer name 114b that is the customer of the case, an assembly 114c that specifies the final assembly process of the product, a sub-assembly 114d that is the intermediate assembly of the product, and a parts supply 114e that corresponds to the procurement process of the parts are stored in association with each other.

[0034] Note that the process divisions of assembly, sub-assembly, and parts supply are made for the sake of convenience, and sub-assembly in particular may be divided into more or fewer levels depending on the degree of complexity of the product configuration.

[0035] Here, by considering the assembly process of a product as a tree structure in which larger parts are made by combining them in sequence with other parts, and considering each element (assembly process of parts or intermediate products) as a convenient address (house number), if the processes are similar even for different products, similar processes will be located at the same house number, making it easier to estimate costs. Therefore, in this embodiment, the process chart is interpreted as a tree structure, but it is not limited to this, and modeling using other structures may be adopted.

[0036] FIG. 6 is a diagram showing an example of the data structure of constituent company performance information. Constituent company performance information 115 is performance information of companies that constitute (were in charge of) a manufacturing process for each past case. Constituent company performance information 115 stores, for each case No. 115a that distinguishes a manufacturing case from other cases, a delivery area 115b that is the delivery area of ​​the case, a process 115c that specifies the process, a selected company 115d selected to be in charge of the process, and company quality 115e that indicates the quality of the product / service provided by the selected company, all in association with each other. Company quality 115e is information that specifies the quality of the product that a company provides to customers. For example, company quality is pre-classified into one of categories such as "high", "low", and "medium".

[0037] FIG. 7 is a diagram showing an example of the data structure of constituent company information. Constituent company information 116 is detailed information on the business operations of each constituent company. Constituent company information 116 stores, in association with one another, constituent companies 116a that identify the constituent companies, business operations 116b that identify the processes for which the constituent companies are responsible, costs 116c that indicate the unit price of the processes performed by the constituent companies, locations 116d of the constituent companies, and company quality 116e that indicates the quality of the products / services (parts / processes) provided by the constituent companies. Company quality 116e is information that identifies the quality of the products that a company provides to customers. For example, company quality is pre-classified into one of categories such as "high", "low", and "average".

[0038] 8 is a diagram showing an example of the data structure of the transportation cost information. The transportation cost information 117 associates the transportation cost 117c from the transportation source (From company 117a) in charge of the previous process of the parts / intermediate products between adjacent previous and next processes to the transportation destination (To company 117b) in charge of the next process, and the customs duty 117d if a customs duty is levied at the time of transportation.

[0039] 9 is a diagram showing an example of a data structure of bill of materials forecast information. Bill of materials forecast information 118 is information including the probability that a specific prediction target part / intermediate product / finished product will be used for each address in the bill of materials for each project. Specifically, bill of materials forecast information 118 stores, for each project No. 118a that distinguishes a manufacturing project from other projects, a prediction target 118b that is the prediction target part / intermediate product / finished product, and its usage probability 118c in association with each other. The usage probability is the probability that the prediction target part / intermediate product / finished product will be used at the address in the project.

[0040] 10 is a diagram showing an example of a data structure of process schedule prediction information. Process schedule prediction information 119 is information including the probability that a specific prediction target process will be used (adopted) for each address in the process schedule for each case. Specifically, the process schedule prediction information 119 stores, for each case No. 119a that distinguishes a manufacturing case from other cases, a prediction target 119b that is the process to be predicted and its usage probability 119c in association with each other. The usage probability is the probability that the prediction target process will be adopted for the address in the case.

[0041] FIG. 11 is a diagram showing an example of a data structure of constituent company forecast information. Constituent company forecast information 120 is information including the probability that a company constituting a specific prediction target process will be used (adopted) for each address in a process schedule for each case. Specifically, in constituent company forecast information 120, for each case No. 120a that distinguishes a manufacturing case from other cases, a prediction target 120b that is the prediction target process, its usage probability 120c, constituent companies 120d that are companies in charge of the process, and their selection probability 120e are stored in association with each other. The usage probability 120c is the probability that the prediction target process will be adopted for the address in the case. The selection probability 120e is the probability that a constituent company will be selected as the person in charge of the prediction target process.

[0042] 12 is a diagram showing an example of a data structure of cost prediction information. The cost prediction information 121 is information including the cost for each project and the predicted gross profit. Specifically, the cost prediction information 121 stores, for each project No. 121a that distinguishes a manufacturing project from other projects, a manufacturing cost 121b that is the cost required to manufacture the product, a transportation cost 121c that is the cost required to transport the product between processes, a cost 121d that is the total of the manufacturing cost and the transportation cost, and a gross profit 121e, all of which are associated with each other. The gross profit 121e is an amount calculated by subtracting the expected cost from the customer's budget.

[0043] 13 is a diagram showing an example of the data structure of order probability prediction information. The order probability prediction information 122 is information including the order time for each case, the company that will receive the order, and the probability that the company will receive the order. Specifically, the order probability prediction information 122 stores, for each case No. 122a that distinguishes a manufacturing case from other cases, a time 122b indicating a specific time, a prediction target company 122c, and an order probability 122d of the prediction target company at that time in association with each other.

[0044] Returning to the explanation of Fig. 1, the processing unit 130 includes a parts bill / process schedule prediction unit 131, a constituent company prediction unit 132, a cost prediction unit 133, a gross profit prediction unit 134, and an order probability prediction unit 135.

[0045] The BOM / Schedule Forecasting Unit 131 identifies the usage probability of each process by using the performance values ​​of manufacturing projects similar to the manufacturing project's customer industry, product type, and / or required quality. Note that the BOM / Schedule Forecasting Unit 131 predicts the BOM and usage probability of the product by using the performance values ​​of manufacturing projects similar to the manufacturing project's customer industry, product type, and / or required quality, and identifies the usage probability of each process according to the BOM.

[0046] The constituent company prediction unit 132 calculates the selection probability of a downstream process in charge of a process subsequent to the process using the performance values ​​of similar manufacturing cases, and calculates the selection probability of a process in charge of a company in charge of the downstream process according to the selection probability of the downstream process in charge.

[0047] The cost prediction unit 133 predicts the manufacturing cost and the transportation cost of the manufacturing project. Specifically, the cost prediction unit 133 calculates the process cost by adding up the probability of using each process, the probability of selecting a company in charge of the process, and the cost of the company in charge of the process among the candidate companies in charge of the process, and predicts the manufacturing cost by adding up the process costs among the processes. In addition, the cost prediction unit 133 predicts the transportation cost using the probability of using each process, the probability of selecting a company in charge of the process, the probability of using an adjacent process adjacent to a process, the probability of selecting a company in charge of the adjacent process, and the transportation cost and customs duty between the adjacent processes.

[0048] The gross profit prediction unit 134 predicts gross profit for each manufacturing job by using at least the usage probability of each process of the manufacturing job and the selection probability of a process-performing company that is selected to be in charge of the process. In addition, the gross profit prediction unit 134 causes the cost prediction unit 133 to predict manufacturing costs and transportation costs in the process of predicting gross profit.

[0049] The order probability prediction unit 135 predicts the order probability of the company in charge of the process using the performance values ​​of similar manufacturing jobs, including gross profit. The order probability prediction unit 135 identifies similar manufacturing jobs according to gross profit, attributes of the manufacturing jobs, and the business negotiation status.

[0050] The input unit 140 receives input information that is displayed and operated on a screen, for example, and is input by operating a keyboard or a mouse.

[0051] The output unit 150 creates screen information including information to be output as a result of performing a predetermined process, for example, and outputs the screen information to a display computer.

[0052] The communication unit 160 communicates with other devices via a network. For example, the communication unit 160 is communicably connected to a user terminal 200 that is mainly used by a user.

[0053] The user terminal 200 includes a processing unit, an input unit, an output unit, and a communication unit.

[0054] Although not shown, the processing unit is provided with a web browser that is operable, and communicates with the order forecasting device 100 via the network 50 using HTTP (HyperText Transfer Protocol) or HTTPS (HyperText Transfer Protocol over Secure Socket Layer).

[0055] FIG. 14 is a diagram showing an example of a hardware configuration of the order prediction device 100. The order prediction device 100 can be realized by a general computer 900 including a processor (e.g., a CPU or a GPU) 901, a memory 902 such as a RAM (Random Access Memory), an external storage device 903 such as a hard disk drive (HDD) or SSD, a reading device 905 for reading information from a portable storage medium 904 such as a CD or a DVD, an input device 906 such as a keyboard, a mouse, a barcode reader, or a touch panel, an output device 907 such as a display, and a communication device 908 for communicating with other computers via a communication network such as a LAN or the Internet, or a network system including a plurality of such computers 900. It goes without saying that the reading device 905 may be capable of not only reading but also writing to the portable storage medium 904.

[0056] For example, the parts bill / process schedule prediction unit 131, constituent company prediction unit 132, cost prediction unit 133, gross profit prediction unit 134, and order probability prediction unit 135 included in the processing unit 130 can be realized by loading a predetermined program stored in an external storage device 903 into the memory 902 and executing it by the processor 901, the input unit 140 can be realized by the processor 901 using the input device 906, the output unit 150 can be realized by the processor 901 using the output device 907 or the communication device 908, the communication unit 160 can be realized by the processor 901 using the communication device 908, and the storage unit 110 can be realized by the processor 901 using the memory 902 or the external storage device 903.

[0057] This predetermined program may be downloaded to the external storage device 903 from the portable storage medium 904 via the reading device 905 or from the network via the communication device 908, and then loaded onto the memory 902 and executed by the processor 901. Alternatively, the program may be directly loaded onto the memory 902 from the portable storage medium 904 via the reading device 905 or from the network via the communication device 908, and executed by the processor 901. Note that the present invention is not limited to this, and the order prediction device 100 may be a wearable computer that a worker can wear, such as a headset, goggles, glasses, or an intercom.

[0058] 15 is a diagram showing an example of the flow of the order forecasting process. The order forecasting process is started when the order forecasting device 100 receives a start instruction from a user via an interface device.

[0059] First, the BOM / Schedule Forecasting Unit 131 reads inquiry case information (step S001). Specifically, the BOM / Schedule Forecasting Unit 131 loads the inquiry information 111.

[0060] Then, the BOM / process schedule prediction unit 131 performs the processes of steps S003 to S008 for each inquiry (steps S002 and S009).

[0061] Then, the BOM / Schedule Forecasting Unit 131 extracts multiple cases with similar attributes from the past case information (step S003). Specifically, the BOM / Schedule Forecasting Unit 131 loads the past case information 112 and extracts multiple cases similar to the target inquiry case. As for the criteria for determining whether cases are similar, for example, the BOM / Schedule Forecasting Unit 131 determines similarity in terms of the customer industry, product type, and required quality, but this is not limited to this. Also, the attributes of the cases may be vectorized using an existing algorithm and a determination may be made according to the distance between the vectors, or other determination algorithms may be used.

[0062] Then, the BOM / Schedule Forecasting Unit 131 specifies the past BOM and past schedule of the extracted similar case (Step S004). Specifically, the BOM / Schedule Forecasting Unit 131 specifies information of the past BOM information 113 and information of the past schedule information 114 related to the case No. 112a of the similar case extracted in Step S003.

[0063] Then, the BOM / Schedule Forecasting Unit 131 calculates the usage probability for each address in the BOM / Schedule (Step S005). Specifically, the BOM / Schedule Forecasting Unit 131 uses the past BOM information 113 and the past schedule information 114 specified in Step S004 to calculate the usage probability for each part used at the same address and the usage probability for each adopted process, and stores them in the BOM Forecasting Information 118 and the schedule Forecasting Information 119.

[0064] Then, the constituent company prediction unit 132 calculates the selection probability by company for each manufacturing process according to the selection probability of the company for the subsequent process (step S006). Specifically, the constituent company prediction unit 132 calculates the selection probability for the candidate company in charge of the subsequent process of the target process by referring to the constituent company performance information 115 (this is referred to as the subsequent process company selection probability), and calculates the selection probability of the candidate company for the target process for each subsequent process company (this is referred to as the target process company selection probability). The constituent company prediction unit 132 then calculates the selection probability by company for each manufacturing process (this is referred to as the modified target process company selection probability) by multiplying the target process company selection probability by the subsequent process company selection probability and tabulating the result for each candidate company for the target process.

[0065] Then, the cost prediction unit 133 calculates the expected cost using the probability of using the manufacturing process, the probability of selecting the company, the company's cost, the transportation cost, and the customs duty (step S007). Specifically, the cost prediction unit 133 divides the expected cost into the manufacturing cost and the transportation cost of the manufacturing project and predicts each of them. For example, the cost prediction unit 133 calculates the process cost by adding up the probability of using each process, the probability of selecting the company in charge of the process, and the cost of the company in charge of the process between the candidate companies in charge of the process, and predicts the manufacturing cost by adding up the process costs between the processes. In addition, the cost prediction unit 133 predicts the transportation cost using the probability of using each process, the probability of selecting the company in charge of the process, the probability of using an adjacent process adjacent to the process, the probability of selecting the company in charge of the adjacent process, and the transportation cost and customs duty between the adjacent processes.

[0066] The specific manufacturing cost can be calculated using the following formula (1).

[0067] Manufacturing cost per process = Probability of using the process × Probability of the target company selecting the modified target process in the process × Cost of the target company in the process... Equation (1)

[0068] Then, by accumulating the results of equation (1) for all processes, the manufacturing cost of the product can be calculated.

[0069] In addition, the specific transportation cost can be calculated using the following formula (2).

[0070] Transportation cost between processes = Probability of using the target process × Probability of the target company selecting a company in the modified target process at the process × Probability of using the previous process at the process × Probability of the target company selecting a company in the previous process at the modified target process × (Transportation cost + Customs duty) Equation (2)

[0071] Then, by accumulating the results of equation (2) for all processes, the transportation costs during product manufacturing can be calculated.

[0072] The expected cost of the product can be calculated by adding the above manufacturing cost and the above transportation cost and multiplying the sum by the order quantity.

[0073] Then, the order probability prediction unit 135 performs an order probability prediction process, which will be described later (step S008).

[0074] The above is an example of the flow of the order forecasting process. According to the order forecasting process, the required BOM and process schedule can be predicted based on the attributes of the inquiry project, using the BOM and process schedule of the details of similar past projects, and the expected cost can be calculated according to the prediction probability.

[0075] 16 is a diagram showing an example of a flow of the order probability prediction process. The order probability prediction process starts in step S008 of the order prediction process.

[0076] First, the gross profit prediction unit 134 calculates gross profit using the calculated cost and the customer budget (step S101). Specifically, the gross profit prediction unit 134 calculates gross profit for each job by subtracting the expected cost calculated in step S007 of the order forecast process from the customer budget 111g of the job.

[0077] Then, the order probability prediction unit 135 narrows down the similar past cases to those similar in negotiation status and gross profit (step S102). Specifically, as a criterion for determining whether the negotiation status and gross profit are similar, the order probability prediction unit 135 determines, for example, similarity in the progress state, probability, number of visits, and gross profit of the case, but is not limited to this. In addition, the attributes of the negotiation status may be vectorized using an existing algorithm and a determination may be made according to the distance between the vectors, or other determination algorithms may be used.

[0078] Then, for each case with an inquiry, the order probability prediction unit 135 identifies the period until the narrowed-down similar case is received or lost, and tabulates it by month (step S103). Specifically, the order probability prediction unit 135 identifies the current progress state for each case with an inquiry, and calculates the period (number of days) from the similar progress state of the similar case narrowed down in step S102 to the date of confirmation of the order or the date of confirmation of the loss. Then, the order probability prediction unit 135 plots the time elapsed since the data update date of the latest progress state of the case with an inquiry, and counts the number of received cases and the number of lost cases for each month of receiving or losing.

[0079] Then, the order probability prediction unit 135 multiplies the process usage probability, the component company selection probability, and the order probability for each component company and process address to calculate the order probability for each component company by month (step S104).

[0080] The above is an example of the flow of the order probability prediction process. According to the flow of the order probability prediction process, it is possible to perform highly accurate order prediction before an order is received from a company in charge of a process.

[0081] 17 is a diagram showing an example of an output screen for order forecasting processing. In the example screen 700, input of the case number to be forecasted can be accepted in a forecast target case number input field 701. When input is accepted in the forecast target case number input field 701, the example screen 700 displays the bill of materials, schedule, and constituent companies, cost, and forecast of order probability of the target case as tables and graphs.

[0082] The BOM display area 702 displays information on BOM forecast information 118 in table format. The process schedule and constituent company display area 703 displays information obtained by merging process schedule forecast information 119 and constituent company forecast information 120 in table format. The cost display area 704 displays information on cost forecast information 121 in table format with manufacturing costs and transportation costs clearly indicated. The order probability display area 705 displays information on order probability forecast information 122 in graph format. The order probability display area 705 further displays information on order probability forecast information 122 for a project control company that controls the project as a whole and for constituent companies by process separately.

[0083] According to the screen example 700, it is possible to refer to the details of the predicted bill of materials and schedule of the project, and the probability of the order timing of the constituent companies. This allows for more detailed cost evaluation and order acceptance decisions for the project to be made. In addition, since the order timing prediction can be known not only for the project control company but also for each process stage of the constituent companies, it becomes easier to grasp the business performance forecast of the constituent companies before the project is concluded, and it becomes easier for the constituent companies to procure management resources such as fund raising, securing personnel, and capital investment.

[0084] The above is the configuration of the order forecasting system 1 according to the embodiment. The order forecasting system 1 can perform highly accurate order forecasting for the company in charge of the process before receiving the order.

[0085] The present invention is not limited to the above-mentioned examples, and includes various modified examples. The above-mentioned embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those having all of the configurations described. It is possible to replace a part of the configuration of the embodiment with another configuration. It is also possible to delete a part of the configuration of the embodiment.

[0086] In addition, 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. In addition, 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 program, table, file, etc. that realizes each function can be stored in a memory, a recording device such as a hard disk, or a storage medium such as an IC card, an SD card, or a DVD.

[0087] 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]

[0088] 1: order forecast system, 50: network, 100: order forecast device, 110: memory unit, 111: inquiry information, 112: past case information, 113: past parts table information, 114: past schedule information, 115: constituent company performance information, 116: constituent company information, 117: transportation cost information, 118: parts table forecast information, 119: schedule forecast information, 120: constituent company forecast information, 121: cost forecast information, 122: order probability forecast information, 130: processing unit, 131: parts table / schedule forecast unit, 132: constituent company forecast unit, 133: cost forecast unit, 134: gross profit forecast unit, 135: order probability forecast unit, 140: input unit, 150: output unit, 160: communication unit, 200: user terminal

Claims

1. a gross profit prediction unit that predicts gross profit for each manufacturing project by using at least the usage probability of each process of the manufacturing project and the selection probability of a process-performing company that is selected to be in charge of the process; an order probability prediction unit that predicts an order probability of the company in charge of the process by using the order record of the company in charge of the process for each of the processes adopted in similar manufacturing projects, including the gross profit; An order forecasting device comprising:

2. 2. The order forecasting device according to claim 1, the order probability prediction unit identifies the similar manufacturing jobs according to the gross profit, attributes of the manufacturing jobs, and a negotiation status; An order forecasting device comprising:

3. 2. The order forecasting device according to claim 1, a bill of materials and schedule forecasting unit that identifies the probability of use of each of the processes by using a track record value of the probability of use of each of the processes of a manufacturing project that is similar to the manufacturing project in terms of any one or a combination of a customer business type, a product type, and a required quality; An order forecasting device comprising:

4. 2. The order forecasting device according to claim 1, a bill of materials and process schedule prediction unit that predicts a bill of materials and a usage probability of the product by using actual results of a manufacturing project similar to the manufacturing project in terms of a customer industry, a product type, and / or a combination thereof, and specifies a usage probability of each process according to the bill of materials; An order forecasting device comprising:

5. 2. The order forecasting device according to claim 1, A cost prediction unit predicts a manufacturing cost of the manufacturing project, the cost prediction unit calculates a process cost by adding up the probability of use of each process, the probability of selection of the process-performing company, and the cost of the process-performing company among the candidate process-performing companies, and predicts the manufacturing cost by adding up the process costs among the processes; The gross profit prediction unit causes the cost prediction unit to predict the manufacturing cost in a process of predicting the gross profit. An order forecasting device comprising:

6. 2. The order forecasting device according to claim 1, a cost prediction unit for predicting a transportation cost of the manufacturing order, the cost prediction unit predicts the transportation cost using the utilization probability of each process, the selection probability of the process-performing company, the utilization probability of an adjacent process adjacent to the process and the selection probability of the process-performing company of the adjacent process, and transportation costs and tariffs between the adjacent processes; The gross profit prediction unit causes the cost prediction unit to predict the transportation cost in the process of predicting the gross profit. An order forecasting device comprising:

7. 2. The order forecasting device according to claim 1, a constituent company prediction unit that calculates a selection probability of a downstream process company that is in charge of a downstream process of the process using the performance values ​​of the similar manufacturing cases, and calculates a selection probability of the process company in accordance with the selection probability of the downstream process company; An order forecasting device comprising:

8. An order prediction system using an order prediction device, The order forecasting device includes: a gross profit prediction step of predicting gross profit for each manufacturing project using at least the usage probability of each process of the manufacturing project and the selection probability of a process-performing company that is selected to be in charge of the process; an order probability prediction step of predicting an order probability of the company in charge of the process by using the order record of the company in charge of the process for each of the processes adopted in similar manufacturing projects, including the gross profit; The order forecast system includes a processing unit that performs the above steps.

9. An order forecasting method using an order forecasting device, comprising: The order forecasting device includes: a gross profit prediction step of predicting gross profit for each manufacturing project using at least the usage probability of each process of the manufacturing project and the selection probability of a process-performing company that is selected to be in charge of the process; an order probability prediction step of predicting an order probability of the company in charge of the process by using the order record of the company in charge of the process for each of the processes adopted in similar manufacturing projects, including the gross profit; The order forecast method is characterized by carrying out the steps of:

Images