Information processing method, information processing device, and program
The method leverages a generative AI model to streamline assemblability evaluation by reducing parameter dependency, enhancing efficiency and accuracy in assessing assembly feasibility and suggesting improvements.
Patent Information
- Application Number
- PCT/JP2026/005571
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-05-14
- Filing Date
- 2026-02-17
- Publication Date
- 2026-11-19
AI Technical Summary
Conventional assemblability evaluation techniques require setting a large number of parameters, which is inefficient and cumbersome.
An information processing method utilizing a generative AI model to evaluate assemblability by collecting product and evaluation criteria information, generating instruction information, and providing it to the AI model for evaluation without the need for extensive parameter setting.
Enables efficient assemblability evaluation with reduced computational load and response time, allowing for quick and accurate assessment of assembly feasibility and providing improvement suggestions.
Smart Images

Figure JP2026005571_19112026_PF_FP_ABST
Abstract
Description
Information Processing Method, Information Processing Apparatus, and Program
[0001] The present disclosure relates to an information processing method, an information processing apparatus, and a program.
[0002] Conventionally, in the design of products and the like, a technique for evaluating assemblability, which is an index of the ease of assembling products and the like, is known.
[0003] Japanese Unexamined Patent Application Publication No. 9-300145
[0004] However, according to the conventional technique, there is a problem that it is necessary to set an extremely large number of parameters for evaluating assemblability.
[0005] The present disclosure has been made in view of the above, and an object thereof is to provide an information processing method, an information processing apparatus, and a program that can evaluate assemblability without setting a large number of parameters.
[0006] To achieve the above object, an information processing method of the present disclosure is an information processing method executed by an information processing apparatus to provide an assemblability evaluation of a product, the method comprising: a collection step of collecting information related to the product and information on evaluation criteria for the assemblability evaluation of the product; a reception step of receiving an input from a user as a prompt which is information indicating an instruction to a generative AI model and is text information requesting the assemblability evaluation of the product; a generation step of generating instruction information including the information related to the product, the information on the evaluation criteria for the assemblability evaluation of the product, and the prompt; a provision step of providing the instruction information to the generative AI model; and an acquisition step of acquiring the assemblability evaluation generated by the generative AI model.
[0007] According to the information processing method, the information processing apparatus, and the program according to the present disclosure, it is possible to provide an information processing method, an information processing apparatus, and a program that can evaluate assemblability without setting a large number of parameters.
[0008] Figure 1 is a diagram showing the configuration of an information processing system according to the first embodiment. Figure 2 is a block diagram showing an example of the functional configuration of an information processing device according to the first embodiment. Figure 3 is a block diagram showing an example of the functional configuration of a database according to the first embodiment. Figure 4 is a sequence diagram showing an example of processing in the information processing system according to the first embodiment. Figure 5 is a diagram showing an example of a product image created with 3D-CAD software. Figure 6 is a diagram showing an example of a product assembly procedure manual. Figure 7 is a diagram showing an example of evaluation criteria for assembly evaluation. Figure 8 is a diagram showing an example of a UI screen for sending instruction information and receiving assembly evaluation. Figure 9 is a diagram showing an example of video used as information related to the product. Figure 10 is a diagram showing an example of information displayed in the response information area. Figure 11 is a flowchart showing an example of processing in an information processing device according to the first embodiment. Figure 12 is a block diagram showing an example of the functional configuration of an information processing device according to the second embodiment. Figure 13 is a flowchart showing an example of processing in an information processing device according to the second embodiment. Figure 14 is a block diagram showing an example of the hardware configuration of an information processing device according to each embodiment.
[0009] The information processing method, information processing apparatus, and program according to the embodiments of this disclosure will be described in detail below with reference to the attached drawings.
[0010] (First Embodiment) Figure 1 is a diagram showing the configuration of an information processing system 1 according to the first embodiment. As shown in Figure 1, the information processing system 1 comprises an information processing device 10, a database 20, and a server 30. The information processing device 10, the database 20, and the server 30 are connected to each other via a network N so as to be able to communicate.
[0011] The information processing device 10 is a device that executes an information processing method to provide a user with an evaluation of the assemblyability of a product, and is a device used by the user. The assemblyability evaluation is an evaluation of the assemblyability, which is an indicator of how easy a product is to assemble. The assemblyability evaluation is expressed numerically, for example, as a number of points.
[0012] As the information processing device 10, various mobile devices such as notebook PCs (Personal Computers), tablet devices, and smartphones can be used as appropriate. Alternatively, a stationary terminal such as a regular PC may be used as the information processing device 10. The information processing device 10 transmits instruction information, described later, to the server 30 in response to user operations.
[0013] The database 20 is a device that transmits product-related information and evaluation criteria for assembly evaluation to the information processing device 10 in response to a search request from the information processing device 10. The database 20 is, for example, a dedicated or general-purpose computer. Various mobile devices such as notebook PCs, tablet terminals, and smartphones can be used as the database 20 as appropriate. Alternatively, a stationary terminal such as a regular personal computer may be used as the database 20.
[0014] Server 30 is a device equipped with an Artificial Intelligence (AI) model that generates product assembly evaluation information based on instruction information transmitted by the information processing device 10. Server 30 also transmits the assembly evaluation information generated by the AI model to the information processing device 10. Server 30 is, for example, a dedicated or general-purpose computer.
[0015] Figure 2 is a block diagram showing an example of the functional configuration of an information processing device 10 according to the first embodiment. The information processing device 10 comprises a communication unit 100, an input unit 110, a display unit 120, a generation unit 130, a storage unit 140, and a control unit 150. The communication unit 100, the input unit 110, the display unit 120, the storage unit 140, and the control unit 150 are connected to each other via a bus or the like for communication. The functions of the information processing device 10 are not limited to these.
[0016] The communication unit 100 is a communication interface that communicates various types of information with external devices such as the database 20 and the server 30. For example, the communication unit 100 sends a search request to the database 20 to search for product-related information and information on evaluation criteria for assembly evaluation, and receives the search results from the database 20. The communication unit 100 also sends instruction information, which will be described later, to the server 30 and receives information on the results of the assembly evaluation from the server 30.
[0017] The input unit 110 accepts various operations from the user. The input unit 110 may be, for example, a keyboard and a pointing device such as a mouse, a microphone, etc. The display unit 120 displays or outputs various information. The display unit 120 may be a display that shows various information, a speaker that outputs various sounds, etc. The input unit 110 and the display unit 120 may be integrated into a touch panel. Alternatively, the input unit 110 and the display unit 120 may be configured separately from the information processing device 10. In this case, the input unit 110 and the display unit 120 and the information processing device 10 may be connected to each other in a communication manner.
[0018] The generation unit 130 generates information related to the product, information on evaluation criteria for evaluating the product's assembleability, and instruction information including prompts for the generated AI model.
[0019] The storage unit 140 stores various types of data. The storage unit 140 may be, for example, a semiconductor memory element such as RAM (Random Access Memory) or flash memory, a hard disk, or an optical disk. The storage unit 140 may also be a storage device located outside the information processing device 10. Furthermore, the storage unit 140 may be a storage medium on which programs and various types of information are downloaded and stored or temporarily stored via a LAN (Local Area Network) or the Internet.
[0020] The control unit 150 is a computer that performs information processing in the information processing device 10. The control unit 150 may be implemented by having a processor such as a CPU (Central Processing Unit) execute a program, i.e., by software. The control unit 150 may also be implemented by a dedicated IC or other processor, i.e., by hardware. The storage unit 140 may be implemented using a combination of software and hardware. At least one of the one or more functional units included in the control unit 150 may be mounted on an external information processing device that is communicably connected to the information processing device 10 via a network or the like.
[0021] Figure 3 is a block diagram showing an example of the functional configuration of a database 20 according to the first embodiment. The database 20 comprises a communication unit 200, a storage unit 210, and a control unit 220. The communication unit 200, the storage unit 210, and the control unit 220 are connected to each other via a bus or the like. The functions of the database 20 are not limited to these.
[0022] The communication unit 200 is a communication interface that communicates with the information processing device 10. The communication unit 200 also communicates various types of information with external devices.
[0023] The storage unit 210 stores various types of information. The storage unit 210 may be, for example, a semiconductor memory element such as RAM or flash memory, a hard disk, or an optical disk. The storage unit 210 may also be a storage device located outside the database 20. Alternatively, the storage unit 210 may be a storage medium that stores or temporarily stores programs and various types of information downloaded via a LAN or the Internet.
[0024] The control unit 220 is a computer that performs information processing in the database 20. The control unit 220 may be implemented by having a processor such as a CPU execute a program, i.e., by software. The control unit 220 may also be implemented by a dedicated IC or other processor, i.e., by hardware. The storage unit 210 may be implemented using a combination of software and hardware. At least one of the one or more functional units included in the control unit 220 may be mounted on an external information processing device that is connected to the database 20 via a network or the like in a way that allows communication.
[0025] Figure 4 is a sequence diagram showing an example of processing in the information processing system 1 according to the first embodiment. First, the control unit 150 of the information processing device 10 sends a search request from the communication unit 100 to the database 20 to collect information related to the product and evaluation criteria for the product's assembleability (step S1). Here, if the information related to the product and the evaluation criteria for the product's assembleability are already stored in the storage unit 140, the control unit 150 may omit sending a search request for that information. Also, even if that information is stored in the storage unit 140, the control unit 150 may send a search request to collect the latest information.
[0026] The communication unit 200 of the database 20 receives a search request from the information processing device 10, and the control unit 220 searches the storage unit 210 for information related to the product and information on evaluation criteria for the assembly evaluation of the product (step S2). The control unit 220 transmits the search results to the information processing device 10 via the communication unit 200 (step S3).
[0027] Next, the generation unit 130 of the information processing device 10 generates information related to the product, information on evaluation criteria for evaluating the product's assembleability, and instruction information including prompts for the generated AI model (step S4). Here, the prompt is information indicating a command to the generated AI model, and is, for example, text information entered by the user operating the input unit 110.
[0028] The generation unit 130 may extract features useful for evaluating assembleability from product-related information to generate feature quantity information and include it in the instruction information. The generation unit 130 may, for example, calculate the number of parts, number of fastening points, candidate interferences between parts, grippable area, constraints on insertion direction, etc., from CAD (Computer-Aided Design) model data or images created with CAD software, and generate these as feature quantities associated with evaluation items.
[0029] Here, "number of fastening points" refers to the number of places where the components constituting the product are fastened together, and is not limited to mechanical fastening such as screws, bolts, and rivets, but may also include the number of places corresponding to joining methods such as welding, crimping, and bonding.
[0030] Furthermore, "potential interference candidates for parts" refers to combinations or areas where parts may interfere with each other during the assembly process. Potential interference candidates for parts may be extracted based, for example, on the overlap of part shapes on the CAD model, proximity less than a predetermined clearance, or the possibility of collision during movement along an assumed insertion path (including estimation by simple collision detection or bounding box detection).
[0031] Furthermore, "gripping area" refers to the area or area index of the outer surface of a part that can be gripped by a gripping means (human hand, gripper, etc.) during assembly work. The gripping area may be calculated, for example, as the area of a surface region that satisfies a predetermined level of flatness or curvature and has a predetermined clearance around it.
[0032] Furthermore, "insertion direction constraints" refer to limitations on the relative movement directions permitted to guide a part into its assembly position. Insertion direction constraints may be, for example, permissible directions (or permissible angular ranges) defined based on the mating shape, guide shape, interference with surrounding parts, or access conditions of the fixture or tool.
[0033] The generation unit 130 may extract keyframes from video information of the product manufacturing process, as described later, and generate feature quantities by estimating work characteristics such as the parts supply method (aligned / individual supply, etc.), the posture during fastening work, and whether or not tools are used.
[0034] By including feature information in the instruction information, compared to directly transmitting the raw data (high-resolution video or CAD model data) to the generated AI model, the amount of communication bandwidth used and the number of tokens input to the generated AI model can be reduced, thereby reducing response time and computational load.
[0035] Furthermore, the control unit 150 may verify whether the evaluation results obtained from the generated AI model are consistent with the evaluation criteria, and if there is a discrepancy, it may cause the generation unit 130 to generate instruction information including a request for re-evaluation of the generated AI model.
[0036] The control unit 150 of the information processing device 10 transmits, i.e., provides, the generated instruction information to the server 30 via the communication unit 100 (step S5). The generation AI model on the server 30 performs an assembly evaluation of the product based on the instruction information (step S6). Then, the control unit 150 of the information processing device 10 receives, i.e., acquires, the evaluation results generated by the generation AI model via the communication unit 100 (step S7).
[0037] The information processing system 1 may be configured such that the generated AI model is included in the information processing device 10. In that case, the information processing system 1 has the information processing device 10 and the database 20, and steps S5 to S6 described above are executed by the information processing device 10. That is, in step S5, the control unit 150 inputs, i.e., provides, the generated instruction information to the generated AI model. Also, in step S7, the control unit 150 acquires the evaluation results generated by the generated AI model.
[0038] The text information entered by the user as a prompt is text information requesting an evaluation of the product's assembleability. In addition to the request for an evaluation of assembleability, this text information may also include requests for the assembly man-hours of the product, requests for assembly instructions, requests for suggestions for improving assembleability, requests for an estimated cost of the product, and so on.
[0039] Product-related information includes, for example, images created with CAD (Computer-Aided Design) software, videos of the manufacturing process in which the product is assembled, and product assembly instructions. It also includes CAD model data, BOM (Bill of Materials), bill of materials, and assembly process data (process sequence, jigs, fastening conditions, etc.). Product-related information includes at least one of these. The video information is an example of video information showing the product's manufacturing process.
[0040] Figure 5 shows an example of a product image created using 3D-CAD software. Note that 2D-CAD software may also be used. The image information created with the CAD software is an example of CAD image information.
[0041] Product-related information may include product design information from CAD software or design information for existing products similar to the product in question. This design information may include part names, material names, costs of parts and materials, part shapes, dimensions, weight, wall thickness data, surface orientation, area, screw data, constraint conditions, constraint dimensions, part interference, assembly sequence, and parent-child relationships of parts. By collecting this information, the information processing device 10 can include various product information for assembly evaluation in the instruction information for the generated AI model.
[0042] Product-related information may include information about past problems in the assembly of the product. This information may include, for example, data summarizing known problems that occurred in existing designs and their solutions in a tabular format. This allows the generating AI model to determine whether the proposed improvement has the same problems as in the past when generating improvement proposals.
[0043] Product-related information may include intellectual property rights and quality information. This information, for example, may include information on intellectual property rights held by other companies regarding the parts used in the product or alternative parts. This allows the generating AI model to determine whether or not an improvement proposal may infringe on the intellectual property rights of other companies when generating improvement proposals.
[0044] The information related to a product may be information on a target value for the cost of the product. This information is, for example, the target cost value per unit of the product. As a result, the generative AI model can determine the estimated cost value while referring to the target cost value when calculating the estimated cost value.
[0045] FIG. 6 is a diagram illustrating an example of an assembly procedure manual for a product. As shown in FIG. 6, the information in the assembly procedure manual includes, for example, the part name, model number of the parts, and a description of the part mounting procedure.
[0046] The information on the evaluation criteria for product assemblability evaluation is information that includes, for each element such as part supply performance, gripping performance, and coupling performance, evaluation points indicating the ease or difficulty of assembly. FIG. 7 is a diagram illustrating an example of evaluation criteria for assemblability evaluation. As shown in FIG. 7, the evaluation criteria include item information such as supply form and outer shape regarding part supply performance, item information such as dimensions and fragility regarding part gripping performance, and item information such as coupling method regarding coupling performance. The evaluation criteria also include information on evaluation points set for each feature of each item.
[0047] The evaluation points are set, for example, such that in terms of supply form, the value is 0 when each part has the feature of being separated and aligned in one direction, -3 when each part has the feature of being separated and arranged in multiple directions, and -4 when the part has the feature of being supplied in a part box. Here, it is assumed that the larger the evaluation point, the higher the assemblability. Note that the evaluation points are relative evaluation values, and for example, may be values to which a predetermined offset value is added so as not to include negative evaluation points.
[0048] Note that the information processing apparatus 10 may use a technique called Retrieval-Augmented Generation (RAG) to combine information collected from the storage unit 140, the database 20, a Web server, and the like, to collect necessary information.
[0049] The generative AI model provided by server 30 may be either a general generative AI model or a generative AI model fine-tuned for a specific application. The generative AI model may include, for example, at least one of a language model and an image generation model that has been trained using existing product information as training data. By including an image generation model, the generative AI model can create output information more efficiently.
[0050] Language models are computer programs and systems used in fields such as Natural Language Processing (NLP) that are capable of performing tasks such as question answering and text generation. Examples of language models include Large Language Models (LLMs), Generative Language Models (for example, GPT (Generative Pretrained Transformer)), Representational Language Models (for example, Bidirectional Encoder Representations from Transformers (BERT)), and / or any other type of language model.
[0051] The generative AI model may include, for example, a language model pre-trained using a large amount of text data from various fields. Here, the generative AI model may undergo so-called fine-tuning, where it is retrained on a dataset from a specific field to correspond to a particular task, thereby becoming a model specialized for that field. In this embodiment, the specific task is, for example, generating and outputting information for evaluating the assembleability of a product based on instruction information.
[0052] Next, we will describe the UI (User Interface) screen displayed on the display unit 120 of the information processing device 10. Figure 8 shows an example of a UI screen 400 that transmits instruction information and receives assembly evaluations.
[0053] As shown in Figure 8, the UI screen 400 has a prompt area 410, a product information area 420, a send button 430, and a response information area 440.
[0054] Figure 8(a) shows an example of sending instruction information, where the prompt area 410 displays prompts for the generated AI model that the user has entered by operating the input unit 110. The product information area 420 displays the file name of a file containing product-related information collected by the control unit 150, and the file name of a file containing information on evaluation criteria for the product's assembleability evaluation. The user can, for example, double-click the file name with a pointing device to display and confirm the contents of the file.
[0055] For example, by pressing the send button 430, the user can send to the server 30 information generated by the generation unit 130, including product-related information, evaluation criteria for product assembly evaluation, and instruction information including prompts for the generating AI.
[0056] Figure 8(b) shows an example of when an assembly feasibility evaluation is received, and the response information area 440 displays the product assembly feasibility evaluation information received from the server 30.
[0057] In the example in Figure 8, the analysis results for each item generated by the generating AI model, the evaluation results for each item, and the overall evaluation result are displayed in the response information area 440, based on the "Product A Assembly Procedure" and the evaluation criteria for the joining method included in the "Product A Assembleability Evaluation Criteria".
[0058] As product-related information, while assembly procedure information was used above, video footage of the product being assembled may also be used. This video footage may include information such as the method of supplying screws and the placement of parts when workers or robots assemble the product. This allows the generated AI model to determine, for example, whether the screws are haphazardly placed in the parts box.
[0059] Figure 9 shows an example of video footage used as product-related information. As shown in Figure 9, the video footage shows a predetermined process in which an operator assembles product A. The video footage may be either a video of the predetermined process or a series of still images of the predetermined process taken using a time-lapse technique. The generating AI model generates evaluation result information, such as that displayed in the response information area 440 of Figure 8(b), based on, for example, the video information included in the instruction information and the evaluation criteria for the method of combining the "Product A Assembly Evaluation Criteria".
[0060] The instructions that the user includes in the prompt may include the various requests described above, in addition to the request for assembly feasibility assessment. If the request for assembly effort is included, the prompt's instruction may be, for example, "...evaluate assembly feasibility and estimate assembly effort." If the request for creating an assembly procedure manual is included, the prompt's instruction may be, for example, "...evaluate assembly feasibility and create an assembly procedure manual."
[0061] Figure 10 shows an example of the information displayed in the response information area 440. In this example, when the prompt includes a request for assembly man-hours and procedure manual creation, an example of assembly man-hours and a procedure manual is shown to be displayed in the response information area 440. The generating AI model generates information on assembly man-hours and procedure manual information, which lists the assembly steps for a given process, as shown in Figure 10, based on video footage of a predetermined process for assembling product A. This reduces the effort required for users to calculate assembly man-hours and create procedure manuals.
[0062] If the user includes a request for improvement suggestions in the prompt, the prompt's instructions may be something like, "...evaluate the ease of assembly and suggest improvements to reduce material costs." The requested improvements may also include suggestions for designs that are easier for workers to assemble, suggestions to reduce assembly costs, etc.
[0063] The generating AI model sends evaluation results to the information processing device 10 as a suggestion to reduce material costs, such as, "Changing part A to part B will reduce the cost by XX yen per unit." This allows the user to reduce product costs.
[0064] The generated AI model sends evaluation results to the information processing device 10 as suggestions for an easy-to-assemble design, such as, "By installing guide members when attaching component C, the burden on workers and variations in work can be reduced." This allows users to improve ease of assembly while ensuring product quality.
[0065] The generating AI model sends evaluation results to the information processing device 10 as suggestions for reducing assembly costs, such as, "By doing this, part A can be deleted. Also, by doing this, shaping of part B becomes unnecessary." This allows the user to reduce assembly costs while ensuring product quality.
[0066] If the user includes a request for a product cost estimate in the prompt, the prompt's instruction may be something like, "Evaluate the assembleability and estimate the product cost." The generating AI model sends an evaluation result to the information processing device 10 as the product cost, for example, "Component costs are XX yen / unit, assembly costs are XX yen / unit, and loss due to defects is XX%." This allows the user to recognize the cost of the product and further improve the design by comparing it with the costs of existing models or other similar models.
[0067] Figure 11 is a flowchart showing an example of processing by the information processing device 10 according to the first embodiment. First, the communication unit 100 collects information related to the product and information on evaluation criteria for product assembly evaluation (step S100), and the input unit 110 accepts prompt input from the user (step S101). Step S100 is an example of a collection step, and step S101 is an example of a reception step.
[0068] Next, the generation unit 130 generates information related to the product, information on evaluation criteria for product assembly evaluation, and instruction information including prompts (step S102). The control unit 150 then transmits, i.e., provides, the generated instruction information to the generated AI model in the server 30 via the communication unit 100 (step S103). If the generated AI model is included in the information processing device 10, in step S103, the control unit 150 provides the instruction information to the generated AI model in the information processing device 10. Note that step S102 is an example of a generation step, and step S103 is an example of a provision step.
[0069] Then, the control unit 150 receives, i.e., acquires, the assembly evaluation information generated by the server 30's generation AI model via the communication unit 100 (step S104). The control unit 150 may also receive other information, such as product assembly procedure information, depending on the content of the prompt. If the generation AI model is included in the information processing device 10, the control unit 150 acquires the information generated from the generation AI model in the information processing device 10. Note that step S104 is an example of an acquisition step.
[0070] Thus, according to this embodiment, the assembly feasibility can be evaluated without setting many parameters by using the information collected by the control unit 150 and prompts received from the user.
[0071] (Second Embodiment) Next, a second embodiment will be described.
[0072] In the second embodiment, if the results of the assembly evaluation received by the information processing device 10 from the server 30 are insufficient, the information processing device 10 sends instruction information to the server 30 requesting improvement suggestions, and receives improvement suggestions from the server 30. In the following description of the second embodiment, the description of parts that are the same as in the first embodiment will be omitted, and the parts that differ from the first embodiment will be described.
[0073] Figure 12 is a block diagram showing an example of the functional configuration of the information processing device 10 according to the second embodiment. The difference from Figure 3 is that the information processing device 10 further includes an evaluation and determination unit 160 and an improvement request unit 170.
[0074] The evaluation and determination unit 160 determines whether the assembly evaluation value received from the server 30 is equal to or greater than a predetermined threshold. Here, the predetermined threshold is a value set in advance, for example, through experiments.
[0075] The improvement request unit 170 sends instruction information to the server 30, including a request for improvement suggestions regarding product assembly, when the value of the assemblyability evaluation received from the server 30 is smaller than a predetermined threshold. This instruction information includes text information such as, for example, "Suggest assembly improvements so that the assemblyability evaluation is XX points or higher," as a prompt to the generated AI model. "XX points" is, for example, text indicating the number of points corresponding to a predetermined threshold.
[0076] Figure 13 is a flowchart showing an example of processing by the information processing device 10 according to the second embodiment. The difference from Figure 11 is the addition of steps S205 to S208, which determine the value of the assembly evaluation, request improvement suggestions, and reflect the received improvement suggestions. Each of the processes in steps S200 to S204 in Figure 13 is the same as each of the processes in steps S100 to S104 in Figure 11, so their explanation is omitted.
[0077] The evaluation determination unit 160 determines whether the assembly performance evaluation value is equal to or greater than a threshold (step S205). If the assembly performance evaluation value is equal to or greater than a threshold (step S205: Yes), the process ends. On the other hand, if the assembly performance evaluation value is not equal to or greater than a threshold (step S205: No), the process proceeds to step S206.
[0078] The improvement request unit 170 sends a request for improvement proposals to the server 30 (step S206). More specifically, the improvement request unit 170 sends instruction information to the server 30, which includes a request for improvement proposals related to product assembly.
[0079] Next, the communication unit 100 receives information on improvement suggestions created by the generated AI model from the server 30 (step S207), and the display unit 120 displays the received improvement suggestions in the response information area 440 of the UI screen 400.
[0080] The user then refers to the improvement suggestions displayed in the response information area 440 and incorporates them into the product design document and assembly procedure manual (step S208). The information processing device 10 may also use an AI model to modify the design document and assembly procedure manual and automatically incorporate the improvement suggestions. For example, a trained AI model, which has been trained using the procedure manual before improvement and information on the improvement suggestions, may be stored in the storage unit 140. The procedure manual used for the assembly evaluation and the improvement suggestions received from the server 30 may be used as input, and the AI model may output a procedure manual that incorporates the improvement suggestions.
[0081] In step S202, following step S208, the generation unit 130 generates instruction information using the product design document and assembly procedure manual that reflect the improvement proposal. As a result, in the subsequent step S204, the communication unit 100 receives an assembly feasibility evaluation from the server 30 based on the improved design document and assembly procedure manual. The processing in steps S202 to S206 is then repeated in step S205 until the assembly feasibility evaluation exceeds a threshold.
[0082] Thus, according to this embodiment, the assembly feasibility can be evaluated without setting many parameters by using the information collected by the control unit 150 and prompts received from the user. Furthermore, if the value of the assembly feasibility evaluation is smaller than a predetermined threshold, improvement suggestions regarding product assembly can be received from the AI model generated by the server 30, making it easy to improve the product design document and assembly procedure manual.
[0083] (Hardware Configuration) Figure 14 is a block diagram showing an example of the hardware configuration of the information processing device 10 according to each embodiment. The information processing device 10 has a processor 121, main memory 122, auxiliary storage device 123, and device I / F 124, etc., which are interconnected by a bus 125, and has a hardware configuration that uses a normal computer.
[0084] The processor 121 is, for example, a CPU, which is an arithmetic unit that controls the information processing device 10. The main memory 122 is, for example, RAM, which stores programs and the like that realize information processing by the processor 121. The auxiliary memory 123 is, for example, ROM (Read Only Memory), which stores data necessary for various processes by the processor 121. The device I / F 124 is connected to the communication unit 100, the storage unit 140, etc., and is an interface for sending and receiving data. In the information processing device 10, the processor 121 reads a program from the auxiliary memory 123 onto the main memory 122 and executes it, thereby realizing each of the above-mentioned functions on the computer.
[0085] The program for executing the processing in the information processing device 10 according to each embodiment may be stored in an HDD (hard disk drive). Alternatively, the program for executing the above processing may be pre-installed and provided in the main memory 122.
[0086] Furthermore, the program for performing the above processing may be provided as a computer program product by being stored in an installable or executable file format on a computer-readable storage medium such as a CD (Compact Disc)-ROM, CD-R (Rerecordable), memory card, DVD (Digital Versatile Disc), or flexible disk (FD).
[0087] Alternatively, the program for performing the above processing may be stored on a computer connected to a network such as the Internet and provided by allowing users to download it via the network. Furthermore, the program for performing the above processing may be provided or distributed via a network such as the Internet.
[0088] Although embodiments have been described above, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications 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 well as in the claims of the invention and its equivalents.
[0089] 1 Information Processing System 10 Information Processing Device 20 Database 30 Server 100 Communication Unit 110 Input Unit 120 Display Unit 121 Processor 122 Main Memory 123 Auxiliary Memory 124 Device I / F 125 Bus 130 Generation Unit 140 Storage Unit 150 Control Unit 160 Evaluation and Judgment Unit 170 Improvement Request Unit
Claims
1. An information processing method executed on an information processing device to provide an assembly evaluation of a product, comprising: a collection step of collecting information related to the product and information of evaluation criteria for the assembly evaluation of the product; a reception step of receiving input from a user as a prompt, which is text information indicating a command to a generating AI model and requesting an assembly evaluation of the product; a generation step of generating instruction information including information related to the product, information of evaluation criteria for the assembly evaluation of the product, and the prompt; a provision step of providing the instruction information to the generating AI model; and an acquisition step of acquiring the assembly evaluation generated by the generating AI model.
2. The information processing method according to claim 1, wherein the information related to the product is CAD image information of the product.
3. The information processing method according to claim 1, wherein the information related to the product is video information of the manufacturing process of the product.
4. The information processing method according to claim 3, wherein the video information of the manufacturing process of the product includes video of the manufacturing process performed by a worker or a robot.
5. The information processing method according to claim 1, wherein the information relating to the product is at least one of design information for existing products similar to the product and information regarding known problems.
6. The information processing method according to claim 1, wherein the information relating to the product is at least one of the following: information on the intellectual property rights of the product, information on the quality of the product, information on the material costs of the product, and information on the target cost of the product.
7. The information processing method according to claim 1, wherein the reception step further receives input as a prompt at least one of the following: a request for the assembly man-hours of the product, a request for an assembly procedure manual, a request for suggestions for improving the assembleability, or a request for an estimate of the product cost.
8. The information processing method according to claim 1, wherein the acquisition step further acquires from the generated AI model at least one of the assembly man-hours for the product and the assembly procedure manual for the product.
9. The information processing method according to claim 1, wherein the acquisition step further acquires improvement proposals regarding the assembly of the product from the generated AI model.
10. The information processing method according to claim 1, wherein the acquisition step further acquires an estimated cost of the product from the generated AI model.
11. An information processing device comprising: a communication unit that collects information related to a product and information of evaluation criteria for evaluating the assembleability of the product; an input unit that accepts input from a user as a prompt, which is text information indicating a command to a generating AI model and requesting an evaluation of the assembleability of the product; a generation unit that generates instruction information including information related to the product, information of evaluation criteria for evaluating the assembleability of the product, and the prompt; and a control unit that provides the instruction information to the generating AI model and obtains the assembleability evaluation generated by the generating AI model.
12. A program that causes a computer to function as an information processing device for providing product assembly evaluation, comprising: a collection means for collecting information related to the product and information of evaluation criteria for product assembly evaluation; a reception means for receiving input from a user as a prompt, which is text information indicating a command to a generating AI model and requesting product assembly evaluation; a generation means for generating instruction information including information related to the product, information of evaluation criteria for product assembly evaluation, and the prompt; a provision means for providing the instruction information to the generating AI model; and an acquisition means for acquiring the assembly evaluation generated by the generating AI model.
