Design assistance device, design assistance method, and recording medium

WO2026203740A1PCT designated stage Publication Date: 2026-10-01HITACHI LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/JP2026/002201
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-03-28
Filing Date
2026-01-23
Publication Date
2026-10-01

Smart Images

  • Figure JP2026002201_01102026_PF_FP_ABST
    Figure JP2026002201_01102026_PF_FP_ABST
Patent Text Reader

Abstract

A design assistance device according to the present invention is characterized by comprising a storage unit that stores a plurality of sets of associated specification information and design information, an input unit for inputting specification information, an extraction unit that extracts specification information that is similar to the inputted specification information and the design information that corresponds to the relevant specification information from the storage unit, a creation unit that creates difference information for the inputted specification information and the extracted specification information, a correction unit that uses the created difference information to correct the extracted design information, and an output unit that outputs the corrected design information. The present invention thereby provides a design assistance device and design assistance method that make it possible not only to extract design information for a similar past project on the basis of given required specifications but also to automatically correct the design information in accordance with the required specifications.
Need to check novelty before this filing date? Find Prior Art

Description

Design support device, design support method, and recording medium

[0001] The present invention relates to a design support device, a design support method, and a recording medium that automatically create design information based on given requirements specifications.

[0002] In designing logistics warehouses and factories, it is necessary to appropriately allocate personnel and equipment according to the overview of the work performed in each warehouse or factory, the personnel, equipment, robots, and shelving required to perform the work, the specifications of the products to be transported or manufactured, and the required specifications of the work. However, since these specifications vary from project to project, skilled personnel must design the appropriate layout for each warehouse or factory on a case-by-case basis, and there is a need to reduce this design man-hour.

[0003] One conventional technique for reducing design man-hours is the control point data generation method described in Patent Document 1. The control point data generation method described in Patent Document 1 is a method for generating control point data corresponding to design drawing data for instrumentation equipment, which is executed by a computer. In this method, the computer accepts keyword input, searches a case database that stores instrumentation drawing data and control point data for multiple past cases using the keyword, and accepts an input operation to select a similar past case from one or more past cases that match the searched keyword. The computer then obtains the instrumentation drawing data and control point data of the similar past case from the case database and stores it in a storage unit. Then, in response to a request to modify the instrumentation drawing data stored in the storage unit, the computer adds, deletes or modifies drawing objects in the instrumentation drawing data stored in the storage unit, and adds, deletes or modifies control point records in the control point data stored in the storage unit in conjunction with the addition, deletion or modification of drawing objects, based on the correspondence information between the drawing objects included in the instrumentation drawing data of the similar past case and the control point records included in the control point data of the similar past case.

[0004] Japanese Patent Publication No. 2008-192009

[0005] The control point data generation method described in Patent Document 1 adds, deletes, or modifies drawing objects in the design drawing data of past projects in response to modification requests entered by the operator. However, it does not have a function to automatically modify the design drawing data of past projects according to the current requirements. In order to reduce design man-hours, it is desirable to be able to automatically modify the design drawing according to the given requirements, not just by selecting a design drawing from a similar past project.

[0006] This invention was made to solve these problems, and aims to provide a design support device and design support method that extracts design information of similar past projects based on given requirements and automatically modifies the design information according to the requirements.

[0007] To solve the above-mentioned problems, the design support device according to the present invention is characterized by comprising: a storage unit that stores a plurality of specification information and design information in association; an input unit that inputs the specification information; an extraction unit that extracts specification information similar to the input specification information and the corresponding design information from the storage unit; a creation unit that creates difference information between the input specification information and the extracted specification information; a modification unit that modifies the extracted design information using the created difference information; and an output unit that outputs the modified design information.

[0008] According to the present invention, it is possible to provide a design support device and a design support method that extract design information of similar past projects based on given requirements and automatically modify the design information according to the requirements. Problems, configurations, and effects other than those described above will be clarified by the following description of embodiments.

[0009] This is a functional block diagram showing the functional configuration of the design support device according to the first embodiment. This is a diagram showing an example of specification information according to the first embodiment. This is a diagram showing an example of design information according to the first embodiment. This is a diagram showing the relationship between specification information, design information, and difference information, etc. This is a diagram showing an example of identifying additional modification locations and performing further modifications when design information is modified based on difference information. This is a flowchart showing the flow of the design support process according to the first embodiment. This is a diagram showing an example of object parameters, coordinate parameters, and constraint conditions between object parameters according to the second embodiment. This is a diagram showing an example of identifying additional modification locations and performing further modifications using whether or not there is a violation of the constraint conditions according to the second embodiment. This is a diagram showing an example of identifying additional modification locations and performing further modifications using the success or failure result of the operation for operation information according to the third embodiment. This is a diagram showing an example of a display screen indicating that the modification failed according to the fifth embodiment. This is a functional block diagram showing the hardware configuration of the computer.

[0010] <<Overview of Design Support Device>> The design support device according to an embodiment of the present invention will be described below. The design support device outputs design information, which is a drawing, CAD (Computer Aided Design), or a simulation space setting file, in which the equipment is arranged to satisfy the requirements based on the specification information, which is the requirements specification expressed in language and images.

[0011] The design support system receives specification information corresponding to the requirements, extracts similar specification information and corresponding design information from the database, and generates design information corresponding to the input specification information by modifying the extracted design information based on the difference information between the input specification information and the extracted specification information. In addition, the design support system identifies areas that need further modification in the modified design information and modifies the design information to include the identified areas that need modification.

[0012] Such a design support device makes it possible to generate design information that conforms to the input requirements specifications without performing machine learning based on vast analytical calculations. Furthermore, by sequentially identifying the parts that need to be corrected, even if a correction affects the arrangement of other equipment, it becomes possible to automatically correct it so that the arrangement becomes appropriate. In addition, even if some of the information necessary to determine the equipment arrangement is not included in the input specification information, it is possible to supplement it based on the extracted design information. [First Embodiment] <Configuration of Design Support Device 100> Figure 1 is a functional block diagram showing the functional configuration of the design support device 100 according to the first embodiment. The design support device 100 is realized by a computer 900 which will be described later in Figure 10, and comprises at least a control unit 110 and a storage unit 120. The control unit 110 comprises at least an input unit 111, an extraction unit 112, a creation unit 113, a correction unit 114, and an output unit 115. The storage unit 120 stores at least a specification information database 130, a design information database 140, and a program 150. Program 150 includes various programs for realizing the functions of the input unit 111, extraction unit 112, creation unit 113, modification unit 114, and output unit 115 provided by the control unit 110. Program 150 also includes programs for realizing the design support processing (see Figure 6) described later. The functions of each of these units will be described in detail below. The database etc. stored in the storage unit 120 may also be stored on a cloud server connected via a network. <Specification Information Database> The specification information database 130 stores specification information 351 corresponding to various requirement specifications, associated with design information 451 in the design information database 140 described later. Figure 2 is a diagram showing an example of specification information related to the requirement specifications for unloading goods in a warehouse. Specification information 351 includes, for example, the purpose of use 361, the object to be worked on 362, requirements 363 necessary to achieve the purpose such as throughput, information 364 on the type and number of available equipment and workers, and information 365 on the space in which objects such as buildings are placed. Furthermore, equipment, workers, and other elements placed in a space are collectively referred to as objects.

[0013] Furthermore, schematic diagrams illustrating this information, or actual images of the equipment, may be included. The information may also be presented in a structured data format, such as JSON (JavaScript Object Notation), rather than in unstructured text. It is not necessary to include all of this information; specification information 351 containing only some of the specifications may be used.

[0014] The specification information 351 may include other information related to the requirements specification. For example, it may include relevant information for each design project, such as customer information when designing equipment according to the requirements specification. It may also link to manuals and parts information for each piece of equipment. <Design Information Database> The design information database 140 stores design information 451 corresponding to each piece of specification information 351 stored in the specification information database 130. Figure 3 is a diagram showing an example of design information. The design information 451 includes information about the spatial arrangement of each piece of equipment, such as storage racks 461, workers 462, conveyors 463, robots 464, pallets 465, and other equipment. Specifically, the design information 451 may represent the arrangement of each piece of equipment by setting coordinate axes in space and specifying coordinates in space. Alternatively, the design information 451 may represent the arrangement of each piece of equipment by dividing space into regions and specifying the region for the arrangement of each piece of equipment. Furthermore, the design information 451 may include hierarchical information, such as the type and mounting position of the gripper in the robot 464. In this context, a hierarchical structure means that, in design information, if the first layer is spatial information such as the spatial arrangement of each piece of equipment, the second layer is equipment information such as the types of components and their mounting locations for each piece of equipment, and the third layer is component information such as what options are attached to each component. In this way, information is structured from the whole to the details.

[0015] The design information 451 may include other information related to the design. For example, the design information 451 may include relevant information such as the cost required for the equipment layout and the expected throughput.

[0016] The specification information database 130 and the design information database 140 may be configured as the same database. In that case, either the specification information 351 or the design information 451 may be included in the other. <<Input Unit>> The input unit 111 acquires language expressions (language information) and image expressions (image information) input from the input device 910 or recording medium 912 as specification information 301. For example, the input unit 111 inputs text entered using a keyboard, image files, and files containing text and images such as PDF (Portable Document Format) as specification information 301. In addition, voice input using a microphone (spoken by the user) may be converted into text, and the converted information may be used as specification information 301. Furthermore, images or video information captured using a camera may be included in the specification information 301. <<Extraction Unit>> The extraction unit 112 calculates the similarity between the input specification information 301 and each specification information 351 stored in the specification information database 130. The extraction unit 112 then extracts similar specification information 351 and corresponding design information 451 from the specification information database 130 and the design information database 140, respectively. Figure 4 shows the relationship between the input specification information 301, similar specification information 351, and corresponding design information 451.

[0017] The extraction unit 112 can calculate similarity using methods such as calculating cosine similarity using Word2Vec in natural language processing, or similar sentence search using Sentence BERT (Bidirectional Encoder Representations from Transformers). It can also calculate similarity using Euclidean distance in image processing, using image features such as SIFT (Scale-Invariant Feature Transform), or using image features acquired by deep learning models such as ResNet (Residual Networks). Alternatively, images can be converted into language using an image caption generation model such as DenseCap (Dense Captioning), and then similarity can be calculated using natural language processing. Furthermore, methods that consider both language and image simultaneously can be used to calculate similarity using multimodal large-scale models such as CLIP (Contrastive Language-Image Pre-training) or LLaVA (Large Language and Vision Assistant).

[0018] The extraction unit 112 may calculate the similarity between specification information not by directly calculating the similarity of the entire specification information, but by calculating the similarity for each partial specification information (such as a sentence or a local image) that is divided into a certain unit. For example, the extraction unit 112 may vote for similar specification information for each partial specification information and extract the specification information with the most votes as similar specification information. <Creation Unit> The creation unit 113 creates difference information 501 between specification information from the input specification information 301 and the similar specification information 351 extracted by the extraction unit 112. The difference information 501 created by the creation unit 113 may include, for example, differences in the type and number of equipment, differences in arrangement (for example, how far apart the arrangements are).

[0019] As a method for creating the difference information 501 performed by the creation unit 113, for example, difference determination using Levenshtein distance in natural language processing or difference generation using a large-scale model such as GPT (Generative Pre-trained Transformer, registered trademark) can be used. Alternatively, it may be created by difference extraction such as Optical Flow in image processing or by extracting differences between captions generated using an image caption generation model. Furthermore, as a difference creation method that considers language and image simultaneously, a multimodal large-scale model such as LLaVA may be used. In addition, the difference information created using these methods may be summarized into a large-scale model such as GPT (registered trademark) and used as difference information. <Modification Unit> The modification unit 114 modifies the design information 451 extracted by the extraction unit 112 using the difference information 501 created by the creation unit 113, and creates design information 401 corresponding to the input specification information 301.

[0020] For example, if the difference information 501 created by the creation unit 113 includes a difference in the type of equipment, the modification unit 114 modifies the corresponding equipment in the design information 451 based on the difference information 501. In this way, the extracted design information 451 can be changed to the design information 401 corresponding to the input specification information 301.

[0021] Furthermore, when the modification unit 114 modifies the design information 451 based on the difference information 501, it may obtain values ​​to be reflected in the design information 451 through the position and orientation calculation process of the modification unit 114. For example, the difference information 501 may include a relative arrangement relationship such as "moving the robot from the front to the side of the conveyor." In such a case, the position and orientation calculation process of the modification unit 114 calculates coordinate information that matches the specified relative position based on the size of the target conveyor and robot and the current coordinate information, and reflects it in the design information 401.

[0022] Here, when the modification unit 114 modifies the design information 451 based on the difference information 501 to create the design information 401, there may be cases where further modifications are necessary. The modification unit 114 identifies areas that require new (additional) modifications (also called modification information 502) by, for example, using interference detection processing between equipment, and modifies them to resolve the interference. In this way, the modification unit 114 creates the newly modified design information 402. Then, the modification unit 114 repeats the process of identifying and modifying new areas until the design information that no longer requires additional modifications becomes the design information 401 corresponding to the input specification information 301 (see steps S15 to S17 in Figure 6 described later).

[0023] Figure 5 shows an example of identifying additional modification points and making further modifications when design information 401 is created by modifying design information 451 based on difference information 501.

[0024] Based on the difference information 501, the modification unit 114 modifies the worker 462 in the design information 451 to a robot 464 and creates design information 401. As a result of this change, interference occurs between the robot 464 (including its movable range indicated by the frame) and the adjacent pallet 465 and conveyor 463 in the design drawing 401. Through interference detection processing between the equipment, the modification unit 114 identifies the equipment that now requires modification, as shown in the modification information 502, and creates design information 402 with the conveyor length and its positional relationship corrected. In the example in Figure 5, the modification unit 114 modifies the six conveyors 463 arranged horizontally by increasing the spacing between them and inserting one conveyor 463 in between.

[0025] In this way, the modification unit 114 can create design information 402 that eliminates equipment interference while reflecting the difference information 501. The modification unit 114 then uses the design information 402 that eliminates equipment interference as design information 401.

[0026] Furthermore, interference detection between equipment can be performed, for example, by comparing the coordinates of each piece of equipment on the spatial coordinate axes included in the design information 401 (402) to determine whether interference between the equipment is occurring. Also, if the placement of each piece of equipment is specified by a spatial area in the design information 401 (402), interference between the equipment can be determined by whether or not multiple pieces of equipment are specified to be placed in the same area. <Output Unit> The output unit 115 outputs the design information 401 that has been modified by the modification unit 114. The output unit 115 may also output similar specification information 351, design information 451, and difference information 501. If the design information is a simulation setting file, the design support device 100 may display the equipment placement via the simulator. Alternatively, the design support device 100 can make it easier for the user to check the changes by highlighting the modified parts added from the design information 451 by changing the color or the like. <Design Support Processing of Design Support Device 100> Next, the design support processing performed by the design support device 100 will be described. Figure 6 is a flowchart showing the flow of design support processing performed by the design support device 100 according to the first embodiment.

[0027] In step S11, the input unit 111 acquires specification information 301 containing the required specifications. The specification information 301 acquired here does not need to contain all the information necessary to create the design information 401; any missing information can be supplemented using the specification information 351 and design information 451 extracted in step S12, which will be described later.

[0028] In step S12, the extraction unit 112 extracts specification information 351 and corresponding design information 451 that are similar to the input specification information 301 from the specification information database 130 and the design information database 140, respectively, based on the similarity between the specification information.

[0029] In step S13, the creation unit 113 creates difference information 501 between the specification information 301 acquired in step S11 and the specification information 351 extracted in step S12. The difference information 501 created by the creation unit 113 may be a list of all differences included in the specification information 301 and 351, or it may be a summarized difference information 501 in which only the information related to the design information 451 has been selected.

[0030] In step S14, the modification unit 114 modifies the design information 451 extracted in step S12 using the created difference information 501 so that it becomes the design information 401 corresponding to the specification information 301 acquired in step S11.

[0031] In step S15, the modification unit 114 further identifies areas in the design information 401 (402) that require modification due to the modification process in step S14 or the modification process in step S17. For example, the modification unit 114 identifies areas that require modification by using interference detection processing between equipment.

[0032] If a new part requiring modification is identified in step S16, the control unit 110 proceeds to step S17; otherwise, it proceeds to step S18.

[0033] In step S17, the modification unit 114 modifies the newly identified parts requiring modification in step S15 in the design information 401 (402) and creates the design information 402. For example, as a modification method, the modification unit 114 randomly changes equipment not specified in the specification information 301 acquired in step S11 to another related type of equipment.

[0034] In step S17, after the modification unit 114 modifies the design information 401 (402) to create the design information 402, the control unit 110 returns the process to step S15.

[0035] On the other hand, in step S18, the output unit 115 outputs the design information 401 (402) which no longer requires any modification, as design information 401 corresponding to the specification information 301 acquired in step S11.

[0036] It should be noted that the design support processing of the present embodiment is not limited to the above-described one.

[0037] As a correction method of the correction unit 114 in step S17, it has been described that a facility is randomly changed to another related type of facility; however, for example, the correction unit 114 may shift the position of the facility in a random direction to determine whether interference is eliminated, and add a correction that eliminates the interference newly to the design information 401 (402).

[0038] Alternatively, the correction unit 114 may associate candidates for solution methods in advance with a determination method used for specifying other correction portions, such as interference determination processing between facilities. For example, as an example of a combination of a determination method and a solution method candidate, when a conveyor interferes with another facility, the correction unit 114 can associate changing the length of the conveyor or changing an arrangement that separates the facilities from each other as a solution method candidate. With this configuration, when the condition according to the determination method is satisfied, the correction unit 114 can correct the design information 401 by correction using the associated solution method.

[0039] The modification unit 114 may also use the results of machine learning and reinforcement learning that have been previously trained as other modification methods. For example, the modification unit 114 may use a neural network that has been trained to take the modification location as input and the modification method as output to select a modification method and modify the design information 401. The neural network may be stored in the memory unit 120, or it may be stored in an external device, and the design support device 100 may acquire the information from the external device via a network or the like. <Features of the design support device 100> The design support device 100 acquires specification information 301 in which the requirements specifications are described, and extracts similar specification information 351 and corresponding design information 451 from the specification information database 130. Next, the design support device 100 creates difference information 501 between the acquired specification information 301 and the extracted specification information 351, and creates design information 401 by modifying the design information 451 based on the difference information 501. Subsequently, the design support device 100 identifies locations that newly require modification, and if additional modification locations are identified, it modifies the design information 401 again based on these modification locations. Then, the process of adding and modifying sections is repeated until there are no more additions or modifications, at which point the design information 402 is output as design information 401 corresponding to the acquired specification information 301.

[0040] According to the design support apparatus 100 according to the first embodiment, design information of similar past projects can be extracted based on given required specifications, and design information automatically corrected according to the required specifications can be output. Furthermore, when diverting design information corresponding to similar specification information, the design information is created in consideration of both similar portions and differential portions between the similar specification information and the acquired specification information. Therefore, design information that appropriately reflects the input specification information can be created without performing machine learning based on a huge amount of analysis calculation. In addition, since portions that require new correction are identified when diverting design information, if a design problem occurs, the design information can be automatically corrected to achieve an appropriate facility layout. [Second Embodiment: Identification of correction portions based on constraint conditions] In the design support apparatus 100 of the first embodiment, the correction unit 114 identifies portions that require additional correction, for example, by using interference determination processing between facilities. A design support apparatus 100A according to the second embodiment differs from the design support apparatus 100 according to the first embodiment in a correction unit 114A and a design information database 140A. Design information 451A in the design information database 140A includes object parameters related to objects and constraint conditions between the object parameters, and the correction unit 114A identifies portions that require additional correction by determining whether there is any violation of the constraint conditions based on the corrected design information 401A.

[0041] FIG. 7 is a diagram showing an example of an object parameter 471, a coordinate parameter 472, and a constraint condition 473 between object parameters according to the second embodiment. Each object included in the design information 451A of the design information database 140A has a unique object parameter 471. As shown in FIG. 7, for example, a pallet 465 has a width w pallet , a depth d pallet , a height h pallet and other parameters, and a camera 466 having an angle of view 467 has an angle of view v cam and a resolution r cam and other parameters. Note that the object parameter 471 may include information indicating whether or not the parameter is a correctable parameter.

[0042] Furthermore, the design information 451A may include coordinate parameters 472 determined by the arrangement of each object, in addition to the object parameters 471 of each object. As shown in FIG. 7, for example, the camera 466 has coordinates (x cam , y cam , z cam ), and the pallet 465 has coordinates (x pallet , y pallet , z pallet ). Note that the coordinates are coordinates in the space where the objects are arranged.

[0043] Furthermore, in the design information 451A, a constraint condition 473 is provided between the object parameters 471. The constraint condition 473 may include the coordinate parameters 472. The constraint condition 473 shown in FIG. 7 is a constraint condition for the camera 466 and the pallet 465 that "the pallet is accommodated within the angle of view of the camera". Note that the object parameters 471 (and the coordinate parameters 472) and the constraint condition 472 between the object parameters may be included in the specification information.

[0044] FIG. 8 is a diagram showing an example in which an additional corrected portion is identified and re-correction is performed by using determination of whether there is a violation of the constraint condition 473.

[0045] Based on the difference information 501A, the modification unit 114A modifies the pallet width in the design information 451A from 1000mm to 1600mm to create design information 401A. This change results in a violation of the constraint condition 473, which represents the relationship between the angle of view 467 of the camera 466 and the pallet 465. Based on this constraint condition violation, the modification unit 114A identifies the equipment that now requires modification, as shown in modification information 502A, and creates design information 402A with the camera placement modified to resolve the constraint condition violation. Generally, the modification unit 114A modifies the constraint condition by changing the values ​​of the parameters included in the constraint condition. In this way, the modification unit 114A can create design information 402A that resolves the constraint condition violation while reflecting the difference information 501A. The modification unit 114A designates the design information 402A with the constraint condition violation resolved as design information 401. ≪Features of the design support device 100A≫ The design support device 100A uses the constraint conditions 473 between the design information 401A modified by the modification unit 114A and the object parameters (and coordinate parameters) to determine whether or not there is a violation of the constraint conditions 473, thereby identifying and correcting additional modification locations.

[0046] This enables the design support device 100A to determine whether additional modifications are necessary based on various constraints, and to efficiently correct design problems in the input specification information. [Third Embodiment: Identification of Modification Locations Based on Operation Information] In the design support device 100 of the first embodiment, the modification unit 114 identifies locations that require additional modifications by, for example, using interference determination processing between equipment. The design support device 100B in the third embodiment differs from the design support device 100 of the first embodiment in its modification unit 114B and design information database 140B. The design information 451B in the design information database 140B includes operation information of equipment and workers, and the modification unit 114B identifies locations that require additional modifications by determining the success or failure of operation based on the modified design information 401B.

[0047] The design information 451B according to the third embodiment includes motion information 481 of equipment including a robot or a worker. The motion information 481 includes, for example, information on robot movements for picking up an object, product processing movements using processing equipment, or product inspection movements by a worker. Furthermore, the motion information 481 is not limited to physical movements, but may also include software movements such as calculating the position and orientation of an object using object recognition.

[0048] These motion information 481 may be information about pre-designed motion trajectories, such as robot trajectories created by manual design, or they may be motion information that determines actions each time based on observational information of the current environment, such as a controller that has been pre-trained using machine learning or reinforcement learning. Alternatively, the motion information 481 may be linguistic information such as motion instructions to a worker, and the physical action may be judged and performed by the worker themselves. Note that the actions included in the motion information 481 do not have to be a single action, but may be a group of actions that are a combination of multiple different actions.

[0049] The modification unit 114B performs an operation based on the modified design information 401B and the operation information 481 included in the design information, and identifies areas requiring further modification by determining whether the operation was successful or not. As a method for determining the success or failure of the operation, the modification unit 114B may also attempt the operation corresponding to the operation information 481 in a simulation and determine the success or failure based on the result of whether the specified operation was completed or not. Alternatively, the modification unit 114B may obtain additional information related to the operation, such as operation time and throughput, from the simulation, and determine whether this information satisfies the requirements described in the specification information to determine the success or failure of the operation.

[0050] Furthermore, the modification unit 114B may determine the success or failure of an operation not only based on simulations but also on the results of testing the operation in a real environment. The design support device 100B may additionally receive trial results from the user, or it may additionally receive images or videos of the operation status captured using an input device such as a camera. The modification unit 114B determines whether an operation has been created or not from the received information based on pre-set criteria for determining whether an operation has been created or not. Alternatively, the modification unit 114B may estimate the success or failure of an operation from the received information using an action recognition device or an operation completion determination device that has been previously trained using methods such as machine learning.

[0051] Figure 9 shows an example of identifying additional areas for correction and performing further corrections using the success or failure result of the operation information 481.

[0052] Based on the difference information 501B, the modification unit 114B modifies the design information 451B by changing the pallet 465 to a shelf 461 and creates the design information 401B. Due to this change, the item 468 is no longer within the field of view 467 of the camera 466, and recognition of the item 468 fails, meaning a failure occurs in the operation information 481. Based on this failure determination in the operation information 481, the modification unit 114B identifies the equipment that now requires modification, as shown in the modification information 502B, and sets the orientation of the camera 466 at the time of recognition to θ cam from θ' cam Furthermore, by creating design information 402B in which the suction direction during object suction is corrected from the vertical direction to the horizontal direction, it is possible to create design information 402B that reflects the difference information 501B while resolving the failure of the operation. The correction unit 114B uses the design information 402B in which the failure of the operation has been resolved as design information 401. <Features of the design support device 100B> The design support device 100B identifies additional correction locations and makes corrections based on the design information 401B corrected by the correction unit 114B and the success or failure result of the operation based on the operation information 481.

[0053] This enables the design support device 100B to modify the design information, including not only the placement of equipment and workers, but also their movements. [Fourth Embodiment: Division and Similarity Determination of Specification Information] The design support device 100 of the first embodiment extracts one similar specification information 351 from the input specification information 301 (see step S12 in Figure 6). The design support device 100C in the fourth embodiment differs from the design support device 100 of the first embodiment (see Figure 1) in its extraction unit 112C, creation unit 113C, modification unit 114C, and specification information database 130C. The design support device 100C divides the input specification information 301 into a plurality of partial information and extracts similar specification information for each divided partial information.

[0054] Similar to the first embodiment, the specification information database 130C stores specification information 351 corresponding to various requirement specifications, associated with design information 451. Furthermore, the specification information 351 is divided into multiple partial specification information 351C, and the divided partial specification information 351C is stored linked to the original specification information 351. Examples of methods for dividing the specification information 351 include dividing the text into sections of a certain number of characters or words, or dividing it into paragraphs and topics. Also, if the specification information 351 includes images, each image or local images obtained by dividing each image may be treated as a single partial information.

[0055] The extraction unit 112C divides the input specification information 301 into a plurality of partial specification information 301C, and extracts partial specification information 351C similar to each partial specification information 301C and corresponding design information 451C from the specification information database 130C and the design information database 140, respectively. The method used by the extraction unit 112C to divide the input specification information 301 may be the same as or different from the method used to divide the specification information 351C in the specification information database 130C. The design information 451C consists of a plurality of design information corresponding to each of the partial specification information 351C.

[0056] The creation unit 113C creates partial difference information 501C between each partial specification information 301C obtained by dividing the input specification information 301 and the extracted partial specification information 351C. The creation unit 113C may also summarize each of the created partial difference information 501C into one or more partial difference information 501C.

[0057] The modification unit 114C modifies the multiple design information 451C extracted by the extraction unit 112C using the partial difference information 501C created by the creation unit 113C, and creates design information 401C. Specifically, the modification unit 114C modifies the relevant parts of the multiple design information 451C corresponding to each extracted partial specification information 351C using the partial difference information 501C, and integrates them to create a single design information 401C. Alternatively, the modification unit 114C may select one design information 451C from among the multiple design information 451C and create design information 401C by reflecting each partial difference information 501C in this design information 451C. As a method of selection in this case, the modification unit 114C may randomly select one design information 451C, or it may select the design information 451C that had the most extractions among the design information 451C extracted for each partial specification information 351C.

[0058] The design information 401C created by the modification unit 114C by integrating multiple design information 451C and modifying it using partial difference information 501C may, for example, have interference between equipment. In such cases, the modification unit 114C identifies and modifies additional modification locations, similar to the first embodiment. <Features of the design support device 100C> The design support device 100C does not extract and modify a single specification information 351 and design information 451 that are similar to the entire input specification information 301, but rather extracts partial specification information 351C and design information 451C that are similar to each partial specification information 301C of the specification information 301 from the specification information database 130C and the design information database 140, respectively.

[0059] As a result, the design support device 100C can efficiently create design information corresponding to the input specification information by combining partially similar specification information and design information. [Fifth embodiment: Notification to the user in cases where modification is difficult, etc.] In the design support device 100 of the first embodiment, the modification unit 114 outputs the modified design information 401 (see step S18 in Figure 6). The design support device 100D in the fifth embodiment differs from the design support device 100 of the first embodiment (see Figure 1) in that the input unit 111D, modification unit 114D, and output unit 115D. In the design support device 100D, if the modification unit 114D is unable to complete the modification, the output unit 115D outputs that the modification failed, and the input unit 111D receives additional specification information 301D, etc.

[0060] The modification unit 114D determines that the modification has failed if it is unable to modify the identified modification locations, or if new modification locations are identified even after modifying the design information 401 (402) within a predetermined maximum number of modification attempts. If it is determined that the modification has failed, the output unit 115D notifies that the modification has failed. In addition to modification failures, the output unit 115D may also output that the extraction failed if the extraction unit 112 is unable to extract similar specification information 351 from the specification information database 130.

[0061] Figure 10 shows an example of a display screen indicating that the correction unit 114D failed to make corrections. The output unit 115D displays the design information 401D that failed to be corrected on the screen of an output device 911 (described later in Figure 11). The output unit 115D may also display the correction areas that could not be resolved. In Figure 10, the output unit 115D displays in text 470 that the interference between the warehouse column 469 and the pallet 465 could not be resolved.

[0062] If the modification fails, the input unit 111D receives new specification information 301D and restarts the design support process shown in Figure 6. Alternatively, the input unit 111D may receive information regarding changes to the specification information 301 and create new specification information 301D by making changes to the input specification information 301.

[0063] Furthermore, the input unit 111D may not only receive the specification information 301D, but may also directly receive modification information that will be used to modify the design information 402. Based on the received modification information, the modification unit 114D may further modify the design information 402. If the design information 401 (402) is a simulation setting file or the like, the modification unit 114D may receive input via the input unit 111 to change the equipment layout displayed in the simulation, and use that input to modify the design information 402.

[0064] When the input unit 111D receives a method for modifying the design information 402, the modification unit 114D may store the received modification information in the storage unit 120 (or register it as additional information in the design information database 140) as a method for modifying the modification location. Furthermore, when the modification unit 114D selects a modification method using a learned neural network, the modification unit 114D may further train the neural network with the modification information that will be used as a method for modifying the design information received by the input unit 111D. This ensures that if the same modification is needed again, the modification unit 114D can modify the design information 401 (402) without failure.

[0065] Furthermore, the creation unit 113 may create information included in the extracted similar specification information 351 but not in the input specification information 301 as uninputted specification information, or include it in the difference information. In this case, the output unit 115D may output the uninputted specification information. By doing so, the design support device 100D can present the uninputted specification information to the user and prompt them to input new specification information 301D. <Features of the design support device 100D> The design support device 100D notifies the user that the correction has failed and receives additional new specification information or a method for correcting the design information.

[0066] As a result, even if the modification unit 114D is unable to make the modification, the design support device 100D can complete the modification of the design information using the additionally received specification information or modification method. [Computer Hardware Configuration] The design support device 100 according to the above embodiment (100A, 100B, 100C, and 100D are similar, and will be referred to as 100 below) is realized by a computer 900 having a configuration such as that shown in Figure 11. Figure 11 is a functional block diagram showing the hardware configuration of the computer 900 that realizes the functions of the design support device 100.

[0067] The computer 900 includes at least a CPU 901, ROM 902, RAM 903, storage 904, input / output interface 905 (referred to as input / output I / F (Interface) in Figure 11), communication interface 906 (referred to as communication I / F in Figure 11), and media interface 907 (referred to as media I / F in Figure 11), which are connected via a bus 908.

[0068] The CPU (Central Processing Unit) 901 functions as a processor (arithmetic processing unit) responsible for information processing. By reading each program stored in the ROM 902 and storage 904 into the RAM 903 and executing it, the functions of the control unit 110 shown in Figure 1—the input unit 102, extraction unit 112, creation unit 113, modification unit 114, and output unit 115—are executed. Devices such as a GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), and ASIC (Application Specific Integrated Circuit) may be included as auxiliary devices to the CPU.

[0069] ROM (Read Only Memory) 902 is a non-volatile memory that permanently stores boot programs executed by the CPU 901 when the computer 900 starts up, as well as programs and data such as the BIOS (Basic Input / Output System).

[0070] The RAM (Random Access Memory) 903 is a volatile memory that temporarily holds programs, data, etc., loaded from storage 904, ROM 902, etc., and also has a work area used by the CPU 901 to perform various processing.

[0071] The storage 904 is composed of an SSD (Solid State Drive) or an HDD (Hard Disk Drive), etc. The storage 904 is connected to the CPU 901 and is configured to enable writing and reading operations by the CPU 901. The memory unit 120 shown in Figure 1 is composed of the storage 904, which stores source files and programs 150 for the CPU 901 to perform various calculations, and also stores programs 150 for realizing the functions of the input unit 102, extraction unit 112, creation unit 113, modification unit 114, and output unit 115 of the control unit 110 shown in Figure 1. In addition, the storage 904 also stores a specification information database 130 and a design information database 140.

[0072] The input / output interface 905 is an interface for inputting and outputting data, and external devices are connected to it to perform data input and output. For example, a keyboard, mouse, or other pointing device may be connected to the input / output interface 905 as an input device 910. Also, a display, speaker, printer, or the like may be connected to the input / output interface 905 as an output device 911. The CPU 901 controls these devices via the input / output interface 905 to perform data input and output. Furthermore, the input / output interface 905 constitutes the input section 111 and output section 115 of the design support device 100.

[0073] The communication interface 906 connects to and communicates with external devices via a network, and performs network communication control processing. For example, it can communicate using TCP / IP (Transmission Protocol / Internet Protocol).

[0074] The media interface 907 is also an interface for inputting and outputting data, and the recording medium 912 is connected to it for data input and output. The recording medium 912 is a semiconductor-based USB memory, an optical recording medium such as a DVD (Digital Versatile Disk), a magneto-optical recording medium such as an MO (Magneto Optical disk), a magnetic recording medium, or a conductive memory tape medium. The CPU 901 controls the recording medium 912 via the media interface 907 and performs input and output of data stored in the recording medium 912. [Other Modifications] Although several embodiments of the present invention have been described above, these embodiments are merely illustrative and do not limit the technical scope of the present invention. For example, the equipment and machinery are not limited to robots and conveyors, but may also be lathes and welding equipment. Furthermore, the design information to which the present invention can be applied is not limited to the arrangement of equipment in a warehouse, but may also be line designs in a factory or procedure manuals showing their operation flow, and can be used to create such design information. The design object is not limited to equipment and machinery, but may also include buildings / structures such as buildings, bridges, and tunnels.

[0075] The present invention can take on various other embodiments, and furthermore, various modifications such as omissions and substitutions can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention as described herein, and are also included in the scope of the invention and its equivalents as described in the claims.

[0076] 100, 100A, 100B, 100C, 100D... Design support device, 110... Control unit, 111, 111D... Input unit, 112, 112C... Extraction unit, 113, 113C... Creation unit, 114, 114A, 114B, 114C... Modification unit, 115, 115D... Output unit, 120... Storage unit, 130, 130C... Specification information database, 140, 140A, 140B... Design information database, 301, 301D, 351... Specification information, 301C, 351C... Partial specification information, 361... Purpose of use, 362... Work object, 363... Requirements, 364... Available equipment, 365... Spatial information, 401, 402, 451, 451C... Design information, 461... Storage shelf, shelf, 462...Worker, 463...Conveyor, 464...Robot, 465...Pallet, 466...Camera, 467...Camera field of view, 468...Item, 469...Column, 471...Object parameters, 472...Coordinate parameters, 473...Constraints, 481...Motion information, 501...Difference information, 501C...Partial difference information, 900...Computer, 901...CPU, 902...ROM, 903...RAM, 904...Storage, 905...Input / Output I / F, 906...Communication I / F, 907...Media I / F, 908...Bus, 910...Input device, 911...Output device, 912...Recording medium

Claims

1. A design support device comprising: a storage unit that stores multiple sets of specification information and design information in association; an input unit that inputs the specification information; an extraction unit that extracts specification information similar to the input specification information and the corresponding design information from the storage unit; a creation unit that creates difference information between the input specification information and the extracted specification information; a modification unit that modifies the extracted design information using the created difference information; and an output unit that outputs the modified design information.

2. A design support device according to claim 1, wherein the modification unit, when modifying the design information using the difference information, identifies a new part that requires modification that is different from the modified part, and modifies the modified design information to include the newly modified part.

3. A design support device according to claim 2, wherein the modification unit repeatedly identifies newly modified parts and modifies the design information until no more parts need to be modified can be identified in the modified design information.

4. A design support device according to claim 1, characterized in that the specification information includes information about the space in which objects are placed and information about the number of objects that can be placed.

5. A design support device according to claim 1, wherein the design information includes information regarding the arrangement of objects in space.

6. A design support device according to claim 1, wherein the design information includes object parameters relating to an object and constraints between the object parameters, and the modification unit determines whether or not the constraints are violated when the design information is modified using the difference information, and if there is a violation, it further modifies the design information to satisfy the constraints.

7. A design support device according to claim 1, characterized in that the design information includes operational information of equipment or workers.

8. A design support device according to claim 7, wherein the modification unit determines whether the operation corresponding to the operation information will succeed when the design information is modified using the difference information, and if it does not succeed, it further modifies the design information so that it will succeed.

9. A design support device according to claim 8, wherein the modification unit uses simulation to determine whether or not the operation with respect to the operation information is successful.

10. A design support device according to claim 1, wherein the storage unit stores the specification information divided into a plurality of partial specification information, and each divided partial specification information in correspondence with the design information; the extraction unit divides the input specification information into a plurality of partial specification information, and extracts from the storage unit partial specification information similar to the divided partial specification information and the design information corresponding to said partial specification information; the creation unit creates partial difference information between the partial specification information of the input specification information and the extracted partial specification information; and the modification unit modifies the extracted design information using the created partial difference information.

11. A design support device according to claim 1, wherein the output unit further outputs the extracted specification information and design information and the created difference information.

12. A design support device according to claim 1, wherein the creation unit creates uninputted specification information that is included in the extracted specification information but not included in the input specification information, and the output unit further outputs the uninputted specification information.

13. A design support device according to claim 1, wherein the modification unit determines whether or not the modification of the extracted design information has failed, and the output unit notifies that the modification has failed if the modification of the design information has failed.

14. A design support method performed by a design support device equipped with a storage unit that stores multiple sets of specification information and design information in association, characterized in that: input the specification information; extract specification information similar to the input specification information and the corresponding design information from the storage unit; create difference information between the input specification information and the extracted specification information; modify the extracted design information using the created difference information; and output the modified design information.

15. A recording medium that stores a program causing a processor to execute the following processes: a process for storing multiple sets of specification information and design information in association; a process for inputting the specification information; a process for extracting specification information similar to the input specification information and the corresponding design information from the storage unit; a process for creating difference information between the input specification information and the extracted specification information; a process for modifying the extracted design information using the created difference information; and a process for outputting the modified design information.