Information processing device, inference device, machine learning device, information processing method, inference method, and machine learning method

Abstract

To provide an information processing device capable of providing information necessary for appropriately selecting a supplier to process or estimate a processed product described in a drawing, without relying on the user's knowledge or experience. [Solution] The information processing device 2A includes a drawing reception unit 202 that receives new drawing data related to processed products, and a candidate destination evaluation unit 203A that, based on the new drawing data D1 received by the drawing reception unit 202, estimates an evaluation score D12 for one or more evaluation items for one or more candidate destinations that are candidates for destinations to request processing or estimation of the processed products in the new drawing data D10.

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an inference device, a machine learning device, an information processing method, an inference method, and a machine learning method. [Background technology]

[0002] Drawings used in various fields such as machinery, architecture, civil engineering, electricity, and apparel contain lines (external lines, dimension lines, etc.) that represent the shape and structure of processed products, as well as various types of information written in text. Because the various types of information written in drawings are important for understanding the details of processing, systems have been developed to utilize this information. For example, Patent Document 1 discloses a support system that acquires text that represents dimensional quantities written in association with the dimension lines of a figure and creates a list showing the dimensional quantities of the figure. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 10-293777 Summary of the Invention [Problem to be solved by the invention]

[0004] As described above, the support system disclosed in Patent Document 1 acquires information about processed products from drawings, but it only goes so far as acquiring information from drawings. Therefore, a user of the support system must select a supplier to request processing or a supplier to request an estimate prior to processing from the information described in the drawings, and the task of selecting an appropriate supplier requires advanced knowledge and experience in processing, making it a highly difficult task.

[0005] The present invention has been made in response to the above-mentioned problems, and aims to provide an information processing device, an inference device, a machine learning device, an information processing method, an inference method, and a machine learning method that can provide the information necessary to appropriately select a party to request processing or an estimate for a processed product shown in a drawing, without relying on the user's knowledge or experience. [Means for solving the problem]

[0006] In order to achieve the above-mentioned object, an information processing device according to one embodiment of the present invention includes a drawing reception unit that receives new drawings related to processed products, and a candidate destination evaluation unit that, based on the new drawing data received by the drawing reception unit, estimates an evaluation score for one or more evaluation items for one or more candidate destinations that are candidates to be requested to process or estimate the processed products in the new drawing data. [Effects of the Invention]

[0007] According to an information processing device of one aspect of the present invention, it is possible to provide the information necessary to appropriately select a party to request processing or an estimate for a processed product shown in a drawing, without relying on the user's knowledge or experience.

[0008] Problems, configurations, and effects other than those described above will become apparent from the detailed description of the invention that follows. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is an overall configuration diagram showing an example of a drawing management system 1. FIG. [Figure 2A] FIG. 10 is a diagram showing an example of drawing data D10 relating to an assembly drawing. [Figure 2B] FIG. 10 is a diagram showing an example of drawing data D10 relating to a part drawing. [Figure 3] FIG. 2 is a diagram showing an example of a drawing database 210. [Figure 4] 1 is a block diagram showing an example of an information processing device 2A according to a first embodiment. [Figure 5]FIG. 2 is a functional explanatory diagram illustrating an example of a learning model generation unit 201A according to the first embodiment. [Figure 6] 2 is a functional explanatory diagram showing an example of a drawing receiving unit 202 and a request destination candidate evaluation unit 203A according to the first embodiment. FIG. [Figure 7] FIG. 9 is a hardware configuration diagram showing an example of a computer 900. [Figure 8] 10 is a flowchart showing an example of a process for evaluating request destination candidates by the information processing device 2A according to the first embodiment. [Figure 9] 10 is a flowchart showing an example of an evaluation score update process by the information processing device 2A according to the first embodiment. [Figure 10] FIG. 10 is a block diagram showing an example of an information processing device 2B according to a second embodiment. [Figure 11] FIG. 10 is a functional explanatory diagram showing an example of a learning model generation unit 201B according to the second embodiment. [Figure 12] FIG. 10 is a functional explanatory diagram showing an example of a drawing receiving unit 202 and a request destination candidate evaluation unit 203B according to the second embodiment. [Figure 13] 10 is a flowchart showing an example of a process for evaluating request destination candidates by an information processing device 2B according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an embodiment for carrying out the present invention will be described with reference to the drawings. The scope necessary for the explanation to achieve the object of the present invention will be schematically shown, and the scope necessary for explaining the relevant parts of the present invention will be mainly explained, and the parts that are omitted from the explanation will be based on publicly known techniques.

[0011] (First embodiment) 1 is a diagram showing an overall configuration of an example of a drawing management system 1. The drawing management system 1 functions as a system for managing drawing data D10 relating to processed products.

[0012] The drawing data D10 handled by the drawing management system 1 is, for example, any drawing recorded as digital data, such as mechanical drawings such as assembly drawings and parts drawings, architectural drawings, electrical circuit drawings, pneumatic circuit drawings, hydraulic circuit drawings, and apparel drawings. In this case, the drawing data D10 may be vector-format data or raster-format data. For example, the drawing data D10 may be CAD data (an example of vector format) output by various CAD software, or image data (an example of raster format) output by scanning a drawing printed on paper using a scanner or the like. The drawing data D10 may be drawn using any projection method or may be a three-dimensional drawing. The drawing data D10 may also include tables, and may be, for example, documents such as slips recorded as digital data.

[0013] As shown in Fig. 1, the drawing management system 1 includes an information processing device 2A and a user terminal device 3. The information processing device 2A and the user terminal device 3 are connected to a wired or wireless network 4 and are configured to be able to send and receive various data to and from each other. Note that the number of information processing devices 2A and user terminal devices 3 and the connection configuration of the network 4 are not limited to the example in Fig. 1 and may be changed as appropriate.

[0014] The information processing device 2A is a server-type computer or a cloud-type computer, and is configured by a general-purpose or dedicated computer (see FIG. 7 described later), etc. The information processing device 2A receives new drawing data D10 (hereinafter referred to as new drawing data D10) from the user terminal device 3 and performs various processes on the new drawing data D10. The information processing device 2A is provided with a drawing database 210 that can register the new drawing data D10 in association with processed product characteristic data D11 and evaluation scores D12 for each evaluation item obtained as a result of processing the new drawing data D10 in the drawing database 210. The information processing device 2A also provides the user terminal device 3 with display information for referring to and editing existing drawing data D10 (hereinafter referred to as existing drawing data D10) registered in the drawing database 210, and the processed product characteristic data D11 and evaluation scores D12 for each evaluation item associated with the existing drawing data D10.

[0015] The evaluation score D12 for each evaluation item is a value evaluated for one or more evaluation items set in advance as an evaluation index for the client (candidate client). The evaluation score may be a numerical value or a graded evaluation value such as an A to D rating. In other words, the drawing management system 1 of the present invention holds information on candidate client companies that quantitatively evaluates each evaluation item based on past transaction records (including estimate records and processing records) and the attributes of the company. The evaluation score may be a relative evaluation value compared with other candidate clients, or an absolute evaluation value based on specific evaluation criteria. The calculation rules for each evaluation score can be set arbitrarily.

[0016] The evaluation items for the candidate contractors include, for example, the following items: Cost: Evaluation item regarding the amount of processing costs of processed products Delivery time: Evaluation item regarding the length of time required to process the processed product. Quality: Evaluation items regarding the quality of processed products · Organizational strength: Evaluation items regarding the organizational structure of the candidate client Response ability: Evaluation item regarding the ability to smoothly carry out processing requests (customer response ability) Each of these assessments is described in more detail below.

[0017] The cost aspect is evaluated based on an estimate of the cost (processing cost) required when the candidate contractor processes the processed product. The cost aspect is calculated as a cost score from at least one of information on the actual estimate and information on the actual processing. The lower the estimated processing cost of a candidate contractor, the higher the cost score. As an example of a rule for calculating the cost score, a method may be adopted in which the reciprocal of the actual estimated amount or billed amount when processing requests for processed products with similar characteristics are made for multiple candidate contractors is taken, and this value is normalized to obtain the cost score.

[0018] The delivery time aspect is evaluated based on an estimate of the period (lead time) required from the order receipt to delivery of the processed product at the candidate supplier. The delivery time aspect is calculated as a delivery time score from information on the processing performance. The shorter the estimated lead time of a candidate supplier, the higher the delivery time score. As an example of a rule for calculating the delivery time score, a method may be adopted in which the reciprocal of the actual lead time when processing requests for processed products with similar characteristics are made for multiple candidate suppliers, and this value is normalized to determine the delivery time score. In addition, the delivery time score may be corrected to a lower value if there is a history of delivery delays, etc.

[0019] The quality aspect is evaluated based on an estimate of the quality of the processing performed by the candidate supplier when the processed product is processed. The quality aspect is calculated as a quality score based on information about the processing record. The better the processing quality of the candidate supplier, the higher the quality score. One example of a rule for calculating the quality score is to calculate it from the degree of fulfillment of required specifications such as dimensions and surface properties in the drawings, based on the results of acceptance inspections of past processed products. In addition, the quality score may be adjusted to be lower if there is a history of defective products being delivered in the past.

[0020] Organizational strength is evaluated based on the organizational structure of the candidate client regarding processing. Organizational strength is calculated as an organizational score based on information about the client's attributes. The more robust the organizational structure of the candidate client, the higher the organizational score. One example of rules for calculating the organizational score is the number of employees of the candidate client (number of people in the manufacturing department), the type and number of processing machines owned, and the location of the candidate client (distance from the client's location). Note that the organizational strength score may be adjusted to increase if the candidate client owns specialized processing machines for a specific processing method.

[0021] Response ability is evaluated based on the customer response ability expected from the candidate client when carrying out the processing request. Response ability is calculated as a response ability score from at least one of information on estimate performance, information on processing performance, and information on the client's attributes. The higher the candidate client's customer response ability, the higher the response ability score. The response ability score may be calculated based on at least one of the following, for example: Actual estimate response time from requesting an estimate to submitting an estimate · Experience in handling express orders ·Proven track record of dealing with defects Location of potential clients (distance from the client's location) -Long-term trading history The above evaluation items are merely examples, and the content and number of evaluation items can be set arbitrarily.

[0022] The user terminal device 3 is a client-type computer, and is configured by a general-purpose or dedicated computer (see FIG. 7 described later), etc. The user terminal device 3 accepts various input operations via a display screen such as an application or a browser, and outputs various information via the display screen or voice, in order to register new drawing data D10, refer to and edit existing drawing data D10, etc.

[0023] Fig. 2A is a diagram showing an example of drawing data D10 relating to an assembly drawing, and Fig. 2B is a diagram showing an example of drawing data D10 relating to a part drawing.

[0024] The drawing area 10 of the drawing data D10 includes a shape area 11, a title block 12, and a parts list 13. The drawing area 10 corresponds to the entire area of ​​the paper when the drawing data D10 is printed on a paper medium.

[0025] The shape area 11 is an area where the shape and dimensions of an assembly or part are described using graphics and text. Lines defining the shape and structure of an assembly or part, such as outline lines, dimension lines, hidden lines, center lines, and imaginary lines, are described in the shape area 11. Text indicating dimensions, tolerances, part numbers, and the like is also described in the shape area 11. Note that the shape area 11 is not limited to six-sided drawings based on orthographic projection, and may represent other types of drawings, such as cross-sectional views, perspective views, and exploded views.

[0026] The title block 12 and the parts list 13 are types of tables included in the drawing data D10. Tables have vertical and horizontal lines and boxes separated by the lines. Characters are written in the boxes, and attributes of the characters written in the box are defined for each box. Boxes are also classified by properties that indicate the type of box. Properties include attribute header properties, serial number header properties, attributeless field properties, attributed field properties, etc.

[0027] As shown in FIGS. 2A and 2B , the attributes of the title block 12 include, for example, product name, drawing number, scale, creation date, designer, approver, etc. The boxes in the title block 12 are classified into attribute-containing field properties, attribute header properties, and attribute-free field properties. The boxes classified as attribute-containing field properties contain field characters (in the example of FIG. 2A , “1:2,” “2024 / 1 / 11,” “ASSY A,” and “F1-222-33-A”) as the contents of the title block 12, and attribute characters (in the example of FIG. 2A , “scale,” “creation date,” “product name,” and “drawing number”) that define the attributes of the field characters. The boxes classified as attribute header properties contain attribute characters (in the example of FIG. 2A , “designer,” and “approver”) that define the attributes of the field characters. The boxes classified as attribute-free field properties contain field characters (in the example of FIG. 2A , “AAA” and “BBB”) as the contents of the title block 12.

[0028] As shown in FIG. 2A , the attributes of the BOM 13 include, for example, a number, a product name, a material, and a quantity. The boxes in the first row from the top of the BOM 13 are classified as attribute header properties, and attribute header characters defining the attributes of each column of the BOM 13 as headers (in the example of FIG. 2A , “Number,” “Product Name,” “Material,” and “Quantity”) are entered. The boxes in the first column on the left side of the BOM 13 are classified as serial number header properties, and serial number header characters defining the serial numbers of each row of the BOM 13 as headers (in the example of FIG. 2A , “1,” “2,” and “3”) are entered. The other boxes in the BOM 13 are classified as attributeless field properties, which do not contain attribute characters, and field characters (in the example of FIG. 2A , “COVER,” “PPP,” “1,” “BODY,” “QQQ,” “1,” “LEG,” “RRR,” and “4”) are entered as the contents of the BOM 13.

[0029] The types of tables included in the drawing data D10 are not limited to the title block 12 and the parts list 13, but may be other types of tables. The arrangement and number of boxes constituting a table may be changed as appropriate depending on the type of table, and the attributes defined for each box are not limited to the above examples.

[0030] 3 is a diagram showing an example of the drawing database 210. In the drawing database 210, existing drawing data D10, processed product characteristic data D11 related to the processed product in the existing drawing data D10, and evaluation scores D12 for each evaluation item are registered in association with each existing drawing data D10.

[0031] The processed product characteristic data D11 is data indicating the characteristics of the processed product in the existing drawing data D10. The processed product characteristic data D11 is acquired from lines, characters, symbols, etc. included in the shape area 11, and characters (mainly field characters) included in the title block 12 and parts list 13. Attributes related to the characteristics of the processed product include, but are not limited to, the creation date, product name, drawing number, scale, shape, material, maximum dimension, quantity, and hole processing, as shown in FIG. 3 . Attributes related to hole processing include, but are not limited to, multiple attributes combining the hole diameter and the processing method (drilling, countersinking, countersinking, etc.).

[0032] For each attribute included in the processed product characteristic data D11, an attribute value in a data format corresponding to the attribute is registered. For attributes related to the product name and drawing number, a character string is registered as the attribute value. For attributes related to scale, shape, material, surface treatment, and welding, a value selected from multiple options prepared in advance is registered as the attribute value. In the example of FIG. 3, for example, "plate" is selected and registered for the shape from options such as plate, bar, and pipe. For attributes related to maximum dimension, quantity, and hole processing, a numerical value is registered as the attribute value. In the example of FIG. 3, for example, the numerical value "200" is registered for the maximum dimension.

[0033] The evaluation score D12 for each evaluation item shown in Figure 3 includes the evaluation score for each evaluation item shown in Figure 1. Furthermore, the evaluation score D12 is associated with information used in calculating the score. The information used in calculating the evaluation score D12 includes the following: Information about estimate results -Information about processing results Information about the attributes of the request recipient

[0034] Information about the performance of estimates includes, for example: ·Quote request date Request ID Drawing number Estimate response date Estimated price ·deadline The information regarding the results of the estimate may be any type of performance information generated by obtaining the estimate, and may include other items.

[0035] Information on processing performance includes, for example: Order date Request ID Drawing number Order amount Delivery time ·Billed amount ·Processing quality The information regarding the processing results may be any type of performance information generated by the processing order, and may include other items.

[0036] The information about the attributes of the request destination includes, for example: Request ID ·name ·location Number of employees ·Owned facilities The information regarding the attributes of the requestee may be information regarding the organizational structure of the requestee, and may include other items.

[0037] The information about the attributes of the request destination includes, for example: ·Trading history Number of defects ·Average response period Special Notes In other words, the information about the attributes of the client may also include various statistical information that is a statistical compilation of past transaction results. The various statistical information may include, for example, the number of past orders, the average estimated price of similar orders, a manual evaluation value, the average estimated price of similar processed products, etc. The manual evaluation value may include a review value within the company, a reputation value from others, etc.

[0038] For the information on the attributes of the request recipients, information on a request recipient list (not shown) in which request recipients are registered in advance may be referenced. In the request recipient list, for example, various types of attribute information are registered for an identifier uniquely assigned to each request recipient. New request recipients may be added to the request recipient list, and existing request recipients may be deleted.

[0039] In addition, the drawing database 210 may be configured to allow data other than those described above to be registered, and the data formats of the attributes and attribute values ​​included in the processed product characteristic data D11 and the evaluation score D12 for each evaluation item are not limited to the above examples.

[0040] Fig. 4 is a block diagram showing an example of an information processing device 2A according to the first embodiment. Fig. 5 is a functional explanatory diagram showing an example of a learning model generation unit 201A according to the first embodiment. Fig. 6 is a functional explanatory diagram showing an example of a drawing reception unit 202 and a request destination candidate evaluation unit 203A according to the first embodiment.

[0041] The information processing device 2A includes a control unit 20, a data storage unit 21, a trained model storage unit 22, a communication unit 23, an input unit 24, and an output unit 25.

[0042] The communication unit 23 is connected to an external device (e.g., the user terminal device 3, etc.) via the network 4, and functions as a communication interface for transmitting and receiving various types of data. The input unit 24 accepts various input operations, and the output unit 25 functions as a user interface by outputting various types of information via a display screen or voice. Note that the input unit 24 and the output unit 25 may be omitted.

[0043] The data storage unit 21 stores a drawing database 210 and a drawing processing program 211A. As shown in Fig. 3, existing drawing data D10 and various information obtained from the existing drawing data D10 are registered in the drawing database 210 in association with each other. The specific configuration of the drawing database 210 is not limited to the example shown in Fig. 3 and may be designed as appropriate.

[0044] The trained model storage unit 22 stores a trained first training model 220A and a trained second training model 220B. The training models 220A and 220B stored in the trained model storage unit 22 may be provided to other devices via the network 4, a recording medium, or the like. Furthermore, the number of training models 220A and 220B stored in the trained model storage unit 22 is not limited to one each. For example, multiple training models 220A and 220B with different conditions, such as differences in machine learning methods or data, may be stored and made available selectively or in parallel.

[0045] 3, the data storage unit 21 and the trained model storage unit 22 are shown as two storage units, but they may be configured as a single storage unit or three or more storage units. Furthermore, at least one of the data storage unit 21 and the trained model storage unit 22 may be configured as a storage unit of an external computer (for example, a server-type computer or a cloud-type computer).

[0046] The control unit 20 functions as a transmission / reception control unit 200, a learning model generation unit 201A, a drawing reception unit 202, a request destination candidate evaluation unit 203A, and a database management unit 204 by executing the drawing processing program 211A recorded in the data storage unit 21.

[0047] (Transmission and reception control unit 200) The transmission / reception control unit 200 transmits and receives various types of data to and from an external device (such as the user terminal device 3). For example, the transmission / reception control unit 200 transmits display information to the user terminal device 3 for outputting various display screens on the user terminal device 3, and receives operation information from the user terminal device 3 for accepting input operations performed on the display screen of the user terminal device 3. In this case, the transmission / reception control unit 200 cooperates with the respective units 201 to 204 to transmit display information to the user terminal device 3 and receive operation information from the user terminal device 3.

[0048] (Learning model generation unit 201A) As shown in FIGS. 4 and 5, the learning model generation unit 201A includes a learning data acquisition unit 2010A and a machine learning unit 2011A.

[0049] The learning data acquisition unit 2010A refers to the drawing database 210 and acquires first learning data D13A and second learning data D13B, each of which is composed of input data and output data. The learning data D13A and D13B are data used as teacher data (training data), verification data, and test data in supervised learning. The output data constituting the learning data D13A and D13B is data used as a correct answer label in supervised learning.

[0050] As shown in FIG. 5, the input data constituting the first learning data D13A may include existing drawing data D10. The existing drawing data D10 included in the input data of the first learning data D13A may be data corresponding to the entire drawing area 10, or may be data corresponding to a partial area (e.g., shape area 11) cut out from the drawing area 10. The learning data D13A may also include, in addition to the existing drawing data D10, part data regarding the parts included in the existing drawing data D10, the input date, a desired deadline for replying to a delivery date, a desired delivery deadline for a processed product, and other remarks. The other remarks include special processing instructions. The learning data D13A may also include past transaction performance data and company information. These data may be included in the existing drawing data D10 or may be data different from the existing drawing data D10.

[0051] The output data constituting the first learning data D13A includes processed product characteristic data D11 that indicates the characteristics of the processed product in the existing drawing data D10. In this case, the processed product characteristic data D11 included in the output data of the first learning data D13A may relate to some of the multiple attributes related to the characteristics of the processed product shown in FIG.

[0052] When a selection from multiple options prepared in advance, such as shape, material, surface treatment, or welding, is specified, the processed product characteristic data D11 included in the output data of the first learning data D13A is defined as data in which "1" is assigned only to the flag corresponding to the selected option. For example, when "plate" is selected from options such as plate, bar, and tube for shape, the processed product characteristic data D11 included in the output data of the first learning data D13A is defined as data in which "1" is assigned only to the flag corresponding to "plate," such as "plate = 1, bar = 0, tube = 0."

[0053] Furthermore, when a maximum dimension, quantity, or drilling is specified as a numerical value, the processed product characteristic data D11 included in the output data of the first learning data D13A is defined as data into which the specified numerical value (which may be a normalized numerical value) is substituted. For example, when "200" is specified for the maximum dimension, the processed product characteristic data D11 included in the output data of the first learning data D13A is defined as data into which "200" is substituted for the maximum dimension parameter, such as "maximum dimension = 200." Note that when normalized with an upper limit of "1000," the processed product characteristic data D11 may be defined as data into which "0.2" is substituted for the maximum dimension parameter, such as "maximum dimension = 0.2."

[0054] The input data constituting the second training data D13B includes processed product characteristic data D11 that indicates the characteristics of the processed product in the existing drawing data D10, and is defined in the same manner as the processed product characteristic data D11 included in the output data of the first training data D13A. Note that, like the processed product characteristic data D11 included in the output data of the first training data D13A, the processed product characteristic data D11 included in the input data of the second training data D13B may relate to some of the multiple attributes related to the characteristics of the processed product shown in FIG. 3.

[0055] The output data constituting the second learning data D13B includes evaluation scores D12 for each evaluation item for candidate contractors to whom processing or estimates for processed products are requested in the existing drawing data D10. The processed product characteristic data D11 included in the output data of the second learning data D13B relates to at least the candidate contractors for processing or estimates among the multiple attributes related to the contractors shown in FIG.

[0056] In this case, when multiple request destinations are pre-registered as a request destination list for a request destination, such as "S001, S002, ..., S011, S012, ..., S020," and "S011" is specified as the request destination, the processed product characteristic data D11 included in the output data of the second learning data D13B may be defined as data in which "1" is assigned to only the flag for "S011," such as "S001=0, S002=0, ..., S011=1, S012=0, ..., S020=0."

[0057] The learning data acquisition unit 2010A acquires first learning data D13A by referring to existing drawing data D10 registered in the drawing database 210 and processed product characteristic data D11 associated with the existing drawing data D10. The learning data acquisition unit 2010A also acquires second learning data D13B by referring to the processed product characteristic data D11 registered in the drawing database 210 and the evaluation score D12 for each evaluation item associated with the processed product characteristic data D11.

[0058] For example, the learning data acquisition unit 2010A acquires the first learning data D13A and the second learning data D13B by displaying on a display screen a list of existing drawing data D10 registered in the drawing database 210 on the information processing device 2A or the user terminal device 3, and reading out the existing drawing data D10 specified on the display screen, the processed product characteristic data D11 associated with the existing drawing data D10, and the evaluation score D12 for each evaluation item from the drawing database 210. The learning data acquisition unit 2010A may acquire the first learning data D13A and the second learning data D13B in cooperation with an external device connected via the network 4.

[0059] The machine learning unit 2011A performs machine learning to make the first learning model 220A learn the correlation between the input data (existing drawing data D10) and the output data (processed product characteristic data D11) using a plurality of sets of first learning data D13A acquired by the learning data acquisition unit 2010A. Also, the machine learning unit 2011A performs machine learning to make the second learning model 220B learn the correlation between the input data (processed product characteristic data D11) and the output data (evaluation score D12 for each evaluation item) using a plurality of sets of second learning data D13B acquired by the learning data acquisition unit 2010A.

[0060] Examples of learning models 220A and 220B that can be used include neural network types (including deep learning) such as convolutional neural networks, recurrent neural networks, and vision transformers, tree types such as decision trees and regression trees, ensemble learning such as bagging and boosting, clustering types such as hierarchical clustering, non-hierarchical clustering, k-nearest neighbors, and k-means, multivariate analyses such as principal component analysis, factor analysis, and logistic regression, and support vector machines.

[0061] The timing at which the machine learning unit 2011A performs machine learning may be when the number of data items in the existing drawing data D10 registered in the drawing database 210 exceeds a predetermined number, when instructions are received from the user, or when the evaluation score is updated by the update process described below, but is not limited to these.

[0062] (Drawing reception unit 202) 4 accepts new drawing data D10, for example, by receiving the drawing data D10 from the user terminal device 3 via the transmission / reception control unit 200. At that time, the drawing accepting unit 202 may accept a designation as to whether to select a party to request processing or a party to request an estimate.

[0063] (Request destination candidate evaluation unit 203A) The candidate destination evaluation unit 203A shown in Figure 4 selects candidate destinations to request processing or estimation of the processed product in the new drawing data D10 based on the new drawing data D10 received by the drawing receiving unit 202, and estimates an evaluation score for each candidate destination for one or more evaluation items.

[0064] For example, when the drawing receiving unit 202 receives a designation of a destination for processing or a destination for an estimate, the candidate destination evaluation unit 203A estimates an evaluation score for one or more evaluation items for one or more candidate destinations that are candidates for processing and an estimate, based on that designation. The number of candidate destinations may be one or more. When estimating evaluation scores for multiple candidate destinations, the candidate destination evaluation unit 203A outputs an evaluation score for one or more evaluation items for each of the multiple candidate destinations. In other words, the number of evaluation items may be one or more. Furthermore, the evaluation scores for multiple evaluation items may be added together to output a single overall score.

[0065] Specifically, the candidate destination evaluation unit 203A performs a feature acquisition process to acquire processed product feature data D11 indicating the features of the processed product in the new drawing data D10 from the new drawing data D10 accepted by the drawing accepting unit 202, and a candidate destination evaluation process to acquire evaluation scores D12 for each evaluation item for the candidate destinations for the processed product in the new drawing data D10 based on the processed product feature data D11 acquired in the feature acquisition process, and select candidate destinations based on the evaluation scores D12 for each evaluation item.

[0066] In this embodiment, as shown in Figure 6, the candidate request recipient evaluation unit 203A inputs new drawing data D10 accepted by the drawing accepting unit 202 into the first learning model 220A as a feature acquisition process, thereby acquiring processed product feature data D11 for the processed product in the new drawing data D10.

[0067] At this time, for attributes defined by options, the first learning model 220A outputs a score for each attribute value, for example, for shape, such as "plate = 0.9, rod = 0.04, pipe = 0.06," and the "plate" with the highest score is acquired as the shape for the new drawing data D10. Also, for attributes defined by numerical values, for example, for maximum dimension, it outputs "maximum dimension = 250" (or "maximum dimension = 0.2" when normalized), and therefore "250" (or "0.2" when normalized) is acquired as the maximum dimension for the new drawing data D10.

[0068] In addition, as a candidate destination evaluation process, the candidate destination evaluation unit 203A inputs the processed product characteristic data D11 acquired in the characteristic acquisition process into the second learning model 220B to obtain an evaluation score D12 for each evaluation item for the new drawing data D10 accepted by the drawing acceptance unit 202, and selects a candidate destination based on the evaluation score D12 for each evaluation item.

[0069] At this time, as shown in FIG. 6, the second learning model 220B outputs evaluation scores for each evaluation item for multiple request recipients included in the request recipient list. In the example shown, evaluation scores for each of five evaluation items are output for three request recipient candidates (request recipient candidate IDs). In the example shown, a graded evaluation value based on A to D judgments is output as the evaluation score, but a score value may also be output. Also, a total score for all items may be calculated. Note that when multiple request recipient candidates are selected, request recipients may be selected in descending order of score up to a predetermined rank, or request recipients with scores equal to or greater than a predetermined reference value may be selected.

[0070] Furthermore, the request destination candidate evaluation unit 203A calculates an evaluation score for each evaluation item using at least one of information on the past performance of processing for each request destination regarding processed products, information on the performance of estimates for each request destination, and information on the attributes of the request destination. Specifically, the request destination candidate evaluation unit 203A calculates an evaluation score for each evaluation item, for example, at the following times: When a preset update timing is reached When the number of newly registered performance information or new request information in the drawing database 210 exceeds a predetermined number. When instructions are received from the user

[0071] The request destination candidate evaluation unit 203A associates the evaluation score for each evaluation item calculated for the specific request destination with the drawing data D10 and updates the drawing database 210. This updates the evaluation score for each evaluation item for the request destination.

[0072] (Database Management Department 204) The database management unit 204 shown in Fig. 4 associates the processed product characteristic data D11 acquired as a processing result of the characteristic acquisition process for the new drawing data D10 with the new drawing data D10 and registers the data in the drawing database 210. The database management unit 204 also transmits display information for displaying the processing result of the request-destination candidate evaluation unit 203A to the user terminal device 3 via the transmission / reception control unit 200. When the request-destination candidate(s) based on the evaluation scores D12 for each evaluation item are displayed on the user terminal device 3, an input operation for instructing the user to make a final decision on the request destination may be accepted. In this case, the database management unit 204 may transmit request information regarding the processing request or estimate request to the request destination corresponding to the input operation via the transmission / reception control unit 200.

[0073] Furthermore, the database management unit 204 reads out existing drawing data D10 registered in the drawing database 210 and transmits display information for displaying the existing drawing data D10 to the user terminal device 3 via the transmission / reception control unit 200. Then, when the database management unit 204 receives operation information for editing the existing drawing data D10 from the user terminal device 3 via the transmission / reception control unit 200, it modifies the existing drawing data D10 registered in the drawing database 210.

[0074] (Hardware configuration of each device) 7 is a hardware configuration diagram showing an example of a computer 900. The information processing device 2A and the user terminal device 3 in the drawing management system 1 are configured by a general-purpose or dedicated computer 900.

[0075] 7, the computer 900 includes, as its main components, a bus 910, a processor 912, a memory 914, an input device 916, an output device 917, a display device 918, a storage device 920, a communication I / F (interface) unit 922, an external device I / F unit 924, an I / O (input / output) device I / F unit 926, and a media input / output unit 928. Note that the above components may be omitted as appropriate depending on the application of the computer 900.

[0076] The processor 912 is composed of one or more arithmetic processing devices (such as a central processing unit (CPU), a micro-processing unit (MPU), a digital signal processor (DSP), or a graphics processing unit (GPU)), and operates as a control unit that controls the entire computer 900. The memory 914 stores various data and programs 930, and is composed of, for example, a volatile memory (such as a DRAM or SRAM) that functions as a main memory, a non-volatile memory (ROM), a flash memory, etc.

[0077] The input device 916 is composed of, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, a microphone, etc., and functions as an input unit. The output device 917 is composed of, for example, a sound (audio) output device, a vibration device, etc., and functions as an output unit. The display device 918 is composed of, for example, a liquid crystal display, an organic EL display, electronic paper, a projector, etc., and functions as an output unit. The input device 916 and the display device 918 may be integrated into one device, such as a touch panel display. The storage device 920 is composed of, for example, an HDD, an SSD, etc., and functions as a storage unit. The storage device 920 stores various data necessary for executing the operating system and the program 930.

[0078] The communication I / F unit 922 is connected to a network 940 (which may be the same as network 4 in FIG. 1 ) such as the Internet or an intranet via a wired or wireless connection, and functions as a communication unit that transmits and receives data to and from other computers in accordance with a predetermined communication protocol. The external device I / F unit 924 is connected to an external device 950 (such as a camera, printer, scanner, or reader / writer) via a wired or wireless connection, and functions as a communication unit that transmits and receives data to and from the external device 950 in accordance with a predetermined communication protocol. The I / O device I / F unit 926 is connected to I / O devices 960 (such as various sensors and actuators), and functions as a communication unit that transmits and receives various signals and data, such as detection signals from sensors and control signals to actuators, to and from the I / O devices 960. The media input / output unit 928 is formed by a drive device such as a DVD drive or a CD drive, and reads and writes data from and to media (non-transitory storage media) 970 (such as DVDs and CDs).

[0079] In the computer 900 having the above configuration, the processor 912 loads a program 930 stored in the storage device 920 into the memory 914, executes the program, and controls each unit of the computer 900 via the bus 910. The program 930 may be stored in the memory 914 instead of the storage device 920. The program 930 may be recorded on the medium 970 in an installable file format or an executable file format and provided to the computer 900 via the media input / output unit 928. The program 930 may be provided to the computer 900 by being downloaded via the network 940 via the communication I / F unit 922. Furthermore, the computer 900 may implement various functions realized by the processor 912 executing the program 930 using hardware such as an FPGA or an ASIC.

[0080] The computer 900 is an electronic device of any type, such as a desktop computer or a portable computer. The computer 900 may be a client computer, a server computer, a cloud computer, or an embedded computer such as a control panel or a controller (including a microcomputer, a programmable logic controller, or a sequencer).

[0081] (Operation of information processing device 2A) 8 is a flowchart showing an example of a process for evaluating request destination candidates by the information processing device 2A according to the first embodiment. Note that the series of information processing methods by the information processing device 2A shown in FIG. 8 will be described as being executed when the information processing device 2A receives new drawing data D10 from a user terminal device 3 operated by a user. Also, the description will be given assuming that the learned model storage unit 22 stores a trained first learning model 220A and a trained second learning model 220B by performing a training data acquisition step, a machine learning step, and a trained model storage step by the learning model generation unit 201A as shown in FIG. 5.

[0082] First, in step S110 (drawing reception step), the drawing reception unit 202 receives new drawing data D10 from the user terminal device 3, thereby receiving the new drawing data D10. At this time, the drawing reception unit 202 may receive a plurality of pieces of new drawing data D10.

[0083] Next, in step S111 (characteristics acquisition step), the request destination candidate evaluation unit 203A inputs the new drawing data D10 received in step S100 into the first learning model 220A as a characteristic acquisition process, thereby acquiring processed product characteristic data D11 for the processed product in the new drawing data D10. Note that when the drawing receiving unit 202 receives multiple pieces of new drawing data D10, it acquires processed product characteristic data D11 for each of the new drawing data D10.

[0084] Next, in step S112 (candidate destination evaluation process), the candidate destination evaluation unit 203A performs a candidate destination evaluation process by inputting the processed product characteristic data D11 acquired in step S111 into the second learning model 220B, thereby acquiring, for each candidate destination, an evaluation score D12 for each evaluation item for the candidate destination for the processed product in the new drawing data D10 accepted in step S110. The candidate destination evaluation unit 203A then uses the evaluation score D12 for each evaluation item to select a candidate destination to be requested to process or estimate the processed product in the new drawing data D10 accepted in step S110. Here, only one candidate destination may be selected, or multiple candidates may be selected. Note that when the drawing accepting unit 202 accepts multiple pieces of new drawing data D10, the candidate destination evaluation unit 203A acquires the evaluation score D12 for each evaluation item for each piece of new drawing data D10, and selects candidate destinations.

[0085] Then, in step S113, the database management unit 204 transmits display information for displaying the processing results of steps S111 and S112 to the user terminal device 3. Specifically, information on one or more selected candidate request destinations is output to the user terminal device 3 along with the evaluation score values ​​for each evaluation item. As a result, the processed product characteristic data D11 registered for the new drawing data D10 and the evaluation scores D12 for each evaluation item are displayed for each candidate request destination on the display screen of the user terminal device 3. Here, the display screen may display information on the candidate request destinations in descending order of the estimated evaluation scores D12, starting from the top to a predetermined rank. In addition to the evaluation scores D12, the display screen may also display company information (particularly information that will be an appealing point) that gives each candidate request destination an advantage over other candidates. The company information may include, for example, "staff structure," "ownership of dedicated processing machines," "track record of express service," and "number of past transactions." The user checks the evaluation score D12 for each evaluation item for each of the displayed candidate contractors along with the company information, and makes a decision about the contractor to whom he or she should request an estimate or processing.

[0086] As described above, according to the information processing device 2A and information processing method of the first embodiment, by using the first learning model 220A and the second learning model 220B that have been trained to use evaluation scores calculated from multifaceted information such as past trading history and attributes of the client for existing drawing data D10, it is possible to provide the information necessary to appropriately select a client to process or estimate the processed product described in the drawing, without relying on the user's knowledge or experience.

[0087] Furthermore, according to the information processing device 2A and the information processing method of the first embodiment, evaluation scores for multiple evaluation items are output, so the user can select the evaluation items that he or she values ​​most, and then select the final candidate client. That is, for example, in the case of a request for processing a single item where quality is more important than cost, and the order is placed with a small, specialized local factory even if it is expensive, the user can arbitrarily select the evaluation items to be used for the final decision, taking into account the background of the processing request, for candidate clients that are difficult to select based on a comprehensive evaluation.

[0088] Fig. 9 is a flowchart showing an example of an evaluation score update process by the information processing device 2A according to the first embodiment. Note that the series of information processing methods by the information processing device 2A shown in Fig. 9 will be described as being executed when the information processing device 2A receives support for updating the evaluation score from a user.

[0089] First, in step S120, the request-receiver candidate evaluation unit 203A refers to a request-receiver list (not shown) and acquires information about newly added request-receivers (request-receiver candidates). At this time, if there is statistical information that statistically compiles past transaction results for each request-receiver, the request-receiver candidate evaluation unit 203A acquires that information.

[0090] Next, in step S121, the request destination candidate evaluation unit 203A acquires the estimate and processing performance values ​​for the request destination that have been added after the most recent update of the evaluation score. At this time, all past estimate and processing performance values ​​may be acquired.

[0091] Next, in step S122, the request destination candidate evaluation unit 203A calculates an evaluation score for each evaluation item for the request destination to be evaluated. Specifically, the request destination candidate evaluation unit 203A calculates an evaluation score for each evaluation item based on preset rules for calculating evaluation scores. At this time, for existing request destinations, each evaluation score is updated based on the newly acquired estimate and processing results, using the most recent evaluation score as the standard.

[0092] Next, in step S122, the request destination candidate evaluation unit 203A outputs the calculated evaluation score for each evaluation item to the drawing database 210. Specifically, the request destination candidate evaluation unit 203A associates the calculated evaluation score for each evaluation item with the corresponding drawing data D10 and registers it in the drawing database 210. This causes the score for each evaluation item at each request destination to become the latest value.

[0093] In this way, since the information processing device 2A updates the evaluation score, it is possible to comprehensively incorporate into the evaluation the efforts or negligence in the daily business activities of each client, such as improvements in processing quality at the client or delays in delivery dates, thereby ensuring the validity of the evaluation score.

[0094] (Second embodiment) Fig. 10 is a block diagram showing an example of an information processing device 2B according to the second embodiment. Fig. 11 is a functional explanatory diagram showing an example of a learning model generation unit 201B according to the second embodiment. Fig. 12 is a functional explanatory diagram showing an example of a drawing reception unit 202 and a request destination candidate evaluation unit 203B according to the second embodiment.

[0095] The second embodiment differs from the first embodiment in that the information processing device 2B uses one learning model 220 instead of two learning models 220A and 220B to estimate evaluation scores for each evaluation item for candidate contractors for processed products in new drawing data D10. The following describes the information processing device 2B according to the second embodiment, focusing on the differences from the first embodiment.

[0096] The trained model storage unit 22 stores trained learning models 220.

[0097] The control unit 20 functions as a transmission / reception control unit 200, a learning model generation unit 201B, a drawing reception unit 202, a request destination candidate evaluation unit 203B, and a database management unit 204 by executing the drawing processing program 211B recorded in the data storage unit 21.

[0098] (Learning model generation unit 201B) As shown in FIGS. 10 and 11, the learning model generation unit 201B includes a learning data acquisition unit 2010B and a machine learning unit 2011B.

[0099] The learning data acquisition unit 2010B refers to the drawing database 210 and acquires the learning data D13.

[0100] The input data constituting the learning data D13 includes existing drawing data D10. The existing drawing data D10 included in the input data of the learning data D13 is the same data as the existing drawing data D10 included in the input data of the first learning data D13A in the first embodiment, and therefore a detailed description thereof will be omitted.

[0101] The output data constituting the learning data D13 includes evaluation scores D12 for each evaluation item for candidate contractors to whom processing or estimates for processed products in the existing drawing data D10 are requested. The evaluation scores D12 for each evaluation item included in the output data of the learning data D13 are similar to the evaluation scores D12 for each evaluation item included in the output data of the second learning data D13B in the first embodiment, and therefore will not be described in detail.

[0102] The learning data acquisition unit 2010B acquires learning data D13 by referring to the existing drawing data D10 registered in the drawing database 210 and the evaluation score D12 for each evaluation item associated with the existing drawing data D10. For example, as in the first embodiment, the learning data acquisition unit 2010B displays a list of the existing drawing data D10 registered in the drawing database 210 on a display screen of the information processing device 2B or the user terminal device 3, and acquires the learning data D13 by reading out the existing drawing data D10 specified on the display screen and the evaluation score D12 for each evaluation item associated with the existing drawing data D10 from the drawing database 210.

[0103] The machine learning unit 2011B performs machine learning using multiple sets of learning data D13 acquired by the learning data acquisition unit 2010B to make the learning model 220 learn the correlation between the input data (existing drawing data D10) and the output data (evaluation score D12 for each evaluation item).

[0104] (Request candidate evaluation unit 203B) As shown in Figure 12, the candidate contractor evaluation unit 203B inputs new drawing data D10 accepted by the drawing accepting unit 202 into the learning model 220, and obtains evaluation scores D12 for each evaluation item for the candidate contractors for the processed products in the new drawing data D10.

[0105] (Operation of information processing device 2B) Fig. 13 is a flowchart showing an example of a process for evaluating request destination candidates by the information processing device 2B according to the second embodiment. Note that the steps having the same step numbers as those in the flowchart shown in Fig. 8 are the same as those in the first embodiment, and therefore the following description will focus on the parts that are different from the first embodiment.

[0106] First, in step S110 (drawing reception step), the drawing reception unit 202 receives new drawing data D10.

[0107] Next, in step S211 (candidate destination evaluation step), the candidate destination evaluation unit 203B inputs the new drawing data D10 received in step S100 into the learning model 220, thereby acquiring evaluation scores D12 for each evaluation item for the candidate destinations for the processed product in the new drawing data D10. Then, the candidate destination evaluation unit 203A evaluates the candidate destinations indicated by the evaluation scores D12 for each evaluation item using the acquired evaluation scores for each evaluation item.

[0108] Next, in step S113, the database management unit 204 transmits display information for displaying the processing results of step S112 to the user terminal device 3. The user terminal device 3 displays information about one or more selected candidate request destinations on a display screen, along with the value of the evaluation score D12 for each evaluation item. The display screen may display information about the candidate request destinations in descending order of the estimated evaluation score D12, from the top to a predetermined rank. Along with the evaluation score D12, the display screen may also display company information (particularly information that will be an appealing point) that gives each candidate request destination an advantage over other candidates. The company information may include, for example, "staff structure," "ownership of specialized processing machines," "track record of express service," and "number of past transactions."

[0109] As described above, the information processing device 2B and information processing method according to the second embodiment use the learning model 220 that has learned evaluation scores calculated from multifaceted information such as past transaction records and attributes of the client, thereby providing the information necessary to appropriately select a client to process or estimate the processed product shown in the drawing, without relying on the user's knowledge or experience.

[0110] Furthermore, the information processing device 2B and the information processing method according to the second embodiment output an evaluation score for each evaluation item, allowing the user to have some flexibility in selecting a final candidate for the client based on the evaluation scores of the evaluation items that the user values. That is, even if the candidate for the client is difficult to select based on a comprehensive evaluation, such as when ordering a single item for which quality is more important than cost and delivery time from a small, specialized local factory, the user can freely select the evaluation items to be used in the final decision, taking into account the background of the processing request.

[0111] Furthermore, the information processing device 2B performs the evaluation score update process in the same manner as in the first embodiment, according to the flowchart shown in Fig. 8. This process is the same as in the first embodiment, and detailed description thereof will be omitted.

[0112] (Other embodiments) The present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit and scope of the present invention, all of which are included in the technical concept of the present invention.

[0113] In the above embodiment, the information processing devices 2A and 2B are described as being configured as a single device, but they may be configured as multiple devices. For example, by distributing the units 200 to 204 of the information processing devices 2A and 2B across multiple devices, the drawing management system 1 may be configured as a machine learning device that includes learning model generation units 201A and 201B and performs the machine learning process, and a request destination selection device that includes request destination candidate evaluation units 203A and 203B and performs the request destination candidate evaluation process. In this case, each unit (each process) of each of the above devices may be realized by a program executable by the computer 900.

[0114] In the above embodiment, the case has been described in which the information processing devices 2A and 2B receive new drawing data D10 from the user terminal device 3 and select a destination for processing the product in the drawing data D10. However, the user terminal device 3 may function as the information processing devices 2A and 2B.

[0115] In the above embodiment, the request destination candidate evaluation units 203A and 203B of the information processing devices 2A and 2B acquire evaluation scores D12 for each evaluation item for new drawing data D10. However, useful information for processing requests and estimate requests may also be acquired. As useful information, the request destination candidate evaluation units 203A and 203B may acquire detailed processing information, such as the type of processing equipment used in the processing, the processing time required for the processing, and whether manual labor is required. The detailed processing information may be included in the output data of either the first learning model 220A or the second learning model 220B, or may be included in the output data of the learning model 220. Furthermore, the detailed processing information may be registered in the drawing database 210 and acquired by referring to the drawing database 210.

[0116] In the above embodiment, an example using a trained model is described, but this is not limiting. For example, the information processing devices 2A and 2B may estimate evaluation scores for each evaluation item of candidate destinations for the processed product in the new drawing data D10 by performing a feature acquisition process and a candidate destination evaluation process using rule-based processing without using a trained model. In this case, for example, the candidate destination evaluation unit 203A may perform a character recognition process on the new drawing data D10 received by the drawing receiving unit 202 as the feature acquisition process to acquire processed product feature data D11 indicating the features of the processed product in the new drawing data D10.

[0117] The candidate-request-destination evaluation unit 203A may evaluate the candidate request destinations based on the evaluation scores for each evaluation item of the candidate request destinations associated with similar drawing data similar to the processed product characteristic data D11 for the new drawing data D10 acquired in the characteristic acquisition process as the candidate request destination evaluation process. With this configuration, by using the drawing database 210 in which past performance data when request destinations were selected for the existing drawing data D10 is registered, it is possible to provide information necessary for appropriately selecting a destination to process or estimate the processed product described in the drawing, without relying on the user's knowledge or experience.

[0118] In the above embodiment, the drawing receiving unit 202 of the information processing device 2A, 2B receives the input of new drawing data D10 as input information. However, this is not a limitation. That is, the information processing device 2A-2B may receive, as input information, part data regarding parts included in the new drawing data D10, the input date, the desired deadline for replying to the delivery date, the desired delivery deadline for the processed product, and other remarks, along with the new drawing data D10. The other remarks include special processing instructions. Furthermore, past transaction performance data and company information may be received as input information. These data may be included in the new drawing data D10, or may be input separately from the new drawing data D10.

[0119] Furthermore, in response to a request for processing and quotation from one requester, the evaluation score for each item of the candidate requester may be estimated using statistical information on the past quotation records and transaction records of other requesters different from the one requester. In this case, other requesters similar to the one requester may be identified, and statistical information on the past quotation records and transaction records of the other requesters may be obtained. The similarity between requesters may be evaluated based on various attribute information registered in advance for the requesters.

[0120] Evaluation scores for the requestees may be set for evaluation items different from those described in the above embodiment. Furthermore, the rules for calculating the evaluation scores are not limited to those in the above embodiment. For example, the requestees may be evaluated based on transaction records between multiple companies. Specifically, attribute information and transaction records between all companies included in the requestee list may be accumulated, and the requestees may be clustered in advance based on this information. Evaluations may be made to increase the evaluation scores of other requestees that are frequently requested by specific companies that are highly similar to the company.

[0121] (Inference device, inference method and inference program) The present invention can be provided not only in the form of the information processing devices 2A and 2B (information processing methods or drawing processing programs) according to the above-described embodiments, but also in the form of an inference device (inference method or inference program) used to infer candidate destinations for a processed product in new drawing data D10. In this case, the inference device (inference method or inference program) includes a memory and a processor, and the processor can execute a series of processes. The series of processes includes a data acquisition process (data acquisition step) for acquiring new drawing data D10 related to the processed product, and an inference process (inference step) for inferring candidate destinations for processing or estimating the processed product in the new drawing data D10 once the new drawing data D10 has been acquired by the data acquisition process. [Explanation of symbols]

[0122] 1...Drawing management system, 2A-2B...Information processing device, 3...User terminal device 10...Drawing area, 11...Shape area, 12...Title block, 13...Bill of materials, 20...control unit, 21...data storage unit, 22...trained model storage unit, 23...communication unit, 24...input unit, 25...output unit, 200...transmission and reception control unit, 201A, 201B...learning model generation unit, 202...drawing reception unit, 203A, 203B...request candidate evaluation unit, 204...database management unit, 210...drawing database, 211A, 211B...Drawing processing program, 220...Learning model, 220A...first learning model, 220B...second learning model, 2010A, 2010B...Learning data acquisition section, 2011A, 2011B…Machine Learning Department

Claims

1. a drawing receiving unit that receives new drawing data related to the processed product; a candidate destination evaluation unit that estimates evaluation scores for each of a plurality of evaluation items for a plurality of candidate destinations that are candidates for destinations to be requested to process or estimate the processed product in the new drawing data, based on the new drawing data received by the drawing receiving unit, The request destination candidate evaluation unit The new drawing data received by the drawing receiving unit is input into a learning model, and the candidate request recipients and the evaluation scores for each of the evaluation items for the candidate request recipients are output for each of the multiple candidate request recipients based on the new drawing data; Increasing a part of the evaluation score based on a relationship with a request destination made by another request source that has a high similarity to the request source; The learning model is An information processing device that uses machine learning to learn the correlation between existing drawing data related to a processed product and evaluation scores for each evaluation item of the candidate contractor for the processed product.

2. The information processing device according to claim 1, wherein the candidate destination evaluation unit outputs an evaluation score for each evaluation item using at least one of information regarding past processing performance of each destination regarding processed products, information regarding estimate performance of each destination, and information regarding attributes of the destination.

3. The request destination candidate evaluation unit performing a feature acquisition process for acquiring processed product feature data indicating features of the processed product in the new drawing data from the new drawing data accepted by the drawing acceptance unit; The information processing device according to claim 1 , further comprising: an information processing device configured to output an evaluation score for one or more evaluation items for one or more candidate request destinations based on the processed product characteristic data acquired in the characteristic acquisition process.

4. The request destination candidate evaluation unit As the feature acquisition process, the new drawing data accepted by the drawing acceptance unit is input into a first learning model to acquire the processed product feature data for the processed product in the new drawing data; The first learning model is The information processing apparatus according to claim 3 , wherein the information processing apparatus learns a correlation between existing drawing data relating to a processed product and the processed product characteristic data for the processed product in the existing drawing data by machine learning.

5. The request destination candidate evaluation unit The processed product feature data acquired in the feature acquisition process is input into a second learning model to acquire the evaluation scores for each evaluation item of the candidate request recipient for the processed product in the new drawing data accepted by the drawing acceptance unit; The second learning model is 5. The information processing device according to claim 3, wherein the correlation between the processed product characteristic data and the evaluation scores for each evaluation item of the candidate destination for the processed product having the characteristics indicated by the processed product characteristic data is learned by machine learning.

6. 1. A computer-implemented information processing method, comprising: a drawing receiving step of receiving new drawing data relating to the processed product; and a candidate-request-destination evaluation step of evaluating a plurality of candidate requesters who are candidates for requesting processing or an estimate for the processed product in the new drawing data based on the new drawing data received by the drawing receiving step, using evaluation scores for each of a plurality of evaluation items, The request candidate evaluation step includes: The new drawing data received in the drawing receiving step is input into a learning model, and the candidate request recipients and the evaluation scores for each of the evaluation items for the candidate request recipients are output for each of the multiple candidate request recipients based on the new drawing data; Increasing a part of the evaluation score based on a relationship with a request destination made by another request source that has a high similarity to the request source; The learning model is An information processing method in which the correlation between existing drawing data relating to a processed product and the evaluation scores for each evaluation item of the candidate contractor for the processed product is learned by machine learning.

Images