system

Abstract

The system of the embodiment aims to automatically identify inconsistencies between design drawings and specifications, and efficiently check laws and regulations. [Solution] The system according to the embodiment includes a discrimination unit, a notifying unit, a checking unit, and a reading unit. The discrimination unit discriminates inconsistencies between the design drawings and the design document. The notifying unit indicates correction information for the inconsistencies identified by the discrimination unit. The checking unit analyzes information sources for laws, regulations, and building standards to check whether the necessary design requirements are met. The reading unit reads the order quantities of components from the design drawings.

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, identifying inconsistencies between design drawings and specifications and checking laws and regulations was done manually, which was inefficient.

[0005] The system of the embodiment aims to automatically identify inconsistencies between design drawings and specifications, and efficiently check laws and regulations. [Means for solving the problem]

[0006] The system according to the embodiment includes a discrimination unit, a notifying unit, a checking unit, and a reading unit. The discrimination unit discriminates inconsistencies between the design drawings and the design document. The notifying unit indicates correction information for the inconsistencies identified by the discrimination unit. The checking unit analyzes information sources for laws, regulations, and building standards to check whether the necessary design requirements are met. The reading unit reads the order quantities of components from the design drawings. [Effects of the Invention]

[0007] The system according to the embodiment can automatically identify inconsistencies between design drawings and specifications, and efficiently check laws and regulations. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The design document review system according to an embodiment of the present invention uses AI to support the review (consistency check) of design documents. This design document review system uses multimodal generation AI to identify inconsistencies between design documents (CAD drawings) and the design documents, and identifies and suggests corrections. For example, if the dimensions listed in the design drawings differ from those listed in the design documents, the generation AI detects the inconsistency and identifies the information that needs to be corrected. Furthermore, by suggesting corrections, the system allows the designer to make corrections quickly. Next, the system provides multifaceted suggestions for checking whether the design meets the necessary design requirements, which are derived from multiple information sources such as laws, regulations, building codes, and their revisions. The generation AI analyzes these information sources and verifies whether the design documents meet the necessary requirements. For example, it checks whether the documents meet the seismic resistance standards set forth in the Building Standards Act and suggests necessary corrections. Furthermore, the system automates the reading of order quantities for various components from the drawings. The generation AI analyzes the design drawings and automatically identifies the types and quantities of required components. This allows designers to avoid the need to manually calculate component quantities, allowing for more efficient ordering. This system makes the review of design documents more efficient and improves design quality. It also reduces the burden on designers, allowing for quick design revisions. As a result, the design document review system can efficiently review design documents and improve design quality.

[0029] The design document review system according to the embodiment includes a discrimination unit, a suggestion unit, a check unit, and a reading unit. The discrimination unit identifies inconsistencies between the design documents and the design documents. For example, if the dimensions listed in the design drawings differ from those listed in the design documents, the discrimination unit can detect the inconsistency. The discrimination unit automatically identifies inconsistencies between the design documents and the design documents using a generation AI. For example, the generation AI compares dimensional information in the design drawings with dimensional information in the design documents and identifies the inconsistencies if any. The discrimination unit can also compare material information in the design drawings with material information in the design documents to detect differences in materials. The suggestion unit suggests correction information for the inconsistencies identified by the discrimination unit. For example, the suggestion unit suggests corrections for the detected inconsistencies. The suggestion unit automatically generates corrections using the generation AI. For example, the generation AI proposes appropriate corrections based on dimensional information in the design drawings. The suggestion unit can also evaluate the impact of the corrections and provide the evaluation to the designer. The checking unit analyzes information sources for laws, regulations, and building codes to check whether the necessary design requirements are met. For example, the checking unit checks whether the earthquake resistance standards under the Building Standards Act are met. The checking unit uses generation AI to analyze information from laws and regulations and automatically check whether the design documents meet the necessary requirements. For example, the generation AI analyzes the provisions of the Building Standards Act and checks whether the design documents meet those standards. The checking unit also obtains information on revisions to laws and regulations in real time, allowing it to always check the compliance of the design documents in an up-to-date state. The reading unit reads the order quantities of components from the design drawings. For example, the reading unit automatically reads the quantities of rebar and concrete listed on the design drawings. The reading unit uses generation AI to analyze the information in the design drawings and automatically calculate the type and quantity of components required. For example, the generation AI analyzes the graphic information in the design drawings and calculates the length of rebar and the volume of concrete. The reading unit can also automatically generate an order list based on the order quantities of components. As a result, the design document review system of the embodiment can efficiently identify inconsistencies between design documents and the design specifications, point out correction information, perform checks based on laws and regulations, and automatically read the order quantities of parts.

[0030] The discrimination unit can detect discrepancies between dimensions described in design drawings and dimensions described in the design document. For example, the discrimination unit compares dimensions described in design drawings with dimensions described in the design document and identifies the location of discrepancies if any. For example, if a dimension described in a design drawing is 100 mm and a dimension described in the design document is 105 mm, the discrimination unit detects the discrepancy. The discrimination unit can also automatically check the dimensional information in the design document based on the dimensional information in the design drawing. For example, the discrimination unit stores the dimensional information in the design drawing in a database and compares it with the dimensional information in the design document in real time. This automatically detects dimensional discrepancies, thereby improving the accuracy of the design. Some or all of the above-described processing in the discrimination unit may be performed using or without the generation AI. For example, the discrimination unit can input dimensional information from the design drawing into the generation AI and cause the generation AI to execute a process to detect dimensional discrepancies.

[0031] The pointing unit can suggest corrections for detected inconsistencies. For example, the pointing unit suggests corrections for detected inconsistencies. For example, if the dimensions described in a design drawing differ from the dimensions described in the design document, the pointing unit proposes an appropriate correction. For example, the pointing unit suggests a correction to align the dimensions in the design drawing with the dimensions in the design document, or a correction to align the dimensions in the design document with the dimensions in the design drawing. The pointing unit can also evaluate the impact of the corrections and provide it to the designer. For example, the pointing unit analyzes the impact of the corrections on other design elements and notifies the designer of the results. This automatically suggests corrections for inconsistencies, thereby streamlining the designer's correction work. Some or all of the above-mentioned processing in the pointing unit may be performed using or without the generation AI. For example, the pointing unit may input information about the detected inconsistencies into the generation AI and cause the generation AI to generate corrections.

[0032] The checking unit can check whether the earthquake resistance standards under the Building Standards Act are met. For example, the checking unit verifies whether the earthquake resistance standards under the Building Standards Act are met. For example, the checking unit analyzes the structural calculations of the design documents and checks whether the earthquake resistance standards are met. The checking unit uses the generating AI to analyze information on laws and regulations and automatically check whether the design documents meet the necessary requirements. For example, the generating AI analyzes the provisions of the Building Standards Act and checks whether the design documents meet the standards. The checking unit also obtains information on revisions to laws and regulations in real time and can always check the compliance of the design documents with the latest information. This automatically checks the earthquake resistance standards, improving the safety of the design. Some or all of the above-mentioned processing in the checking unit may be performed using the generating AI, or may be performed without using the generating AI. For example, the checking unit can input information on the design documents into the generating AI and have the generating AI check the earthquake resistance standards.

[0033] The reading unit can read the quantity of rebar and concrete from the design drawings. The reading unit, for example, automatically reads the quantity of rebar and concrete listed in the design drawings. For example, the reading unit analyzes the graphic information of the design drawings and calculates the length of the rebar and the volume of the concrete. The reading unit uses the generation AI to analyze the information in the design drawings and automatically calculate the type and quantity of required components. For example, the generation AI calculates the length of the rebar and the volume of the concrete based on the graphic information in the design drawings. The reading unit can also automatically generate an ordering list based on the order quantity of components. For example, the reading unit lists the types and quantities of required components based on the information in the design drawings and generates an ordering list. This automatically reads the quantity of rebar and concrete, thereby streamlining the ordering process. Some or all of the above-mentioned processing in the reading unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the reading unit can input the information in the design drawings into the generation AI and have the generation AI read the quantity of components.

[0034] The indication unit can provide a proposed revision to the designer. The indication unit, for example, provides the proposed revision to the designer. For example, the indication unit proposes an appropriate proposed revision for the detected inconsistency and notifies the designer of the proposed revision. The indication unit automatically generates a proposed revision using the generation AI and provides it to the designer. For example, the generation AI proposes an appropriate proposed revision based on information in the design drawings and notifies the designer of the proposed revision. The indication unit can also evaluate the impact of the proposed revision and provide the result to the designer. For example, the indication unit analyzes the impact of the proposed revision on other design elements and notifies the designer of the result. In this way, by providing the proposed revision to the designer, the designer can make the revision quickly. Some or all of the above-mentioned processing in the indication unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the indication unit can input information about the proposed revision to the generation AI and cause the generation AI to provide the proposed revision.

[0035] The discrimination unit can improve discrimination accuracy by referring to past revision history when discriminating inconsistencies between design drawings and design documents. For example, the discrimination unit can improve discrimination accuracy by referring to past revision history when discriminating inconsistencies between design drawings and design documents. For example, the discrimination unit can prioritize detection of frequently occurring inconsistencies based on past revision history. Furthermore, the discrimination unit can learn mistakes that specific designers often make from past revision history and improve discrimination accuracy. Furthermore, the discrimination unit can analyze past revision history and adjust discrimination accuracy to prevent similar inconsistencies from recurring. Thus, by referring to past revision history, discrimination accuracy can be improved and similar inconsistencies can be prevented from recurring. Some or all of the above-described processing in the discrimination unit may be performed using or without the generation AI. For example, the discrimination unit can input past revision history data into the generation AI and have the generation AI improve discrimination accuracy.

[0036] When determining inconsistencies between design drawings and design documents, the discrimination unit can make the discrimination taking into account the designer's past design style. The discrimination unit, for example, learns the designer's past design style and preferentially detects inconsistencies based on a specific style. The discrimination unit can also detect general inconsistencies by taking into account the designer's past design style. Furthermore, the discrimination unit can detect inconsistencies related to a specific design pattern based on the designer's past design style. In this way, by taking the designer's past design style into consideration, it is possible to preferentially detect inconsistencies based on a specific style. Some or all of the above-mentioned processing in the discrimination unit may be performed using or without the generation AI. For example, the discrimination unit can input the designer's past design style data into the generation AI and have the generation AI perform the discrimination.

[0037] The discrimination unit can make the discrimination by taking into account the geographical location information of the designer when discriminating inconsistencies between the design drawings and the design document. For example, if the designers are in different regions, the discrimination unit discriminates inconsistencies by taking into account the design standards specific to that region. Also, if the designers are in the same region, the discrimination unit can discriminate inconsistencies based on the common design standards of the region. Furthermore, if the designer is traveling, the discrimination unit can also discriminate inconsistencies based on the current geographical location information. In this way, by taking into account the geographical location information of the designer, it is possible to detect inconsistencies based on the design standards specific to the region. Some or all of the above-mentioned processing in the discrimination unit may be performed using or without the generation AI. For example, the discrimination unit can input the geographical location information of the designer to the generation AI and cause the generation AI to perform discrimination based on the geographical location information.

[0038] When determining inconsistencies between design drawings and design documents, the determination unit can analyze the designer's social media activities to prioritize determining relevant inconsistencies. For example, the determination unit can analyze the designer's social media activities to determine recent trends and interests and prioritize determining inconsistencies related to those trends. The determination unit can also collect information related to a specific project from the designer's social media activities and determine inconsistencies based on that information. Furthermore, the determination unit can determine inconsistencies related to a specific design style or pattern based on the designer's social media activities. In this way, by analyzing the designer's social media activities, relevant inconsistencies can be detected prioritized. Some or all of the above-described processing in the determination unit may be performed using or without the generation AI. For example, the determination unit can input the designer's social media activity data into the generation AI and cause the generation AI to perform determination based on the social media activity.

[0039] When suggesting a revision proposal, the suggestion unit can refer to past revision history to suggest the optimal revision proposal. For example, the suggestion unit can prioritize suggesting frequently used revision proposals based on the past revision history. The suggestion unit can also suggest revision proposals that are often adopted by a specific designer based on the past revision history. Furthermore, the suggestion unit can analyze the past revision history to suggest the optimal revision proposal for a similar inconsistency. This allows the optimal revision proposal to be suggested by referring to the past revision history, improving the efficiency of the revision work. Some or all of the above-mentioned processing in the suggestion unit may be performed using or without the generation AI. For example, the suggestion unit can input past revision history data into the generation AI and cause the generation AI to suggest the optimal revision proposal.

[0040] When suggesting a revision proposal, the suggestion unit can customize the revision proposal by taking into account the designer's past design style. For example, the suggestion unit learns the designer's past design style and suggests a revision proposal based on a specific style. The suggestion unit can also suggest a general revision proposal by taking into account the designer's past design style. Furthermore, the suggestion unit can suggest a revision proposal related to a specific design pattern based on the designer's past design style. In this way, by taking the designer's past design style into consideration, it is possible to provide a revision proposal based on a specific style. Some or all of the above-mentioned processing in the suggestion unit may be performed using or without the generation AI. For example, the suggestion unit can input the designer's past design style data into the generation AI and cause the generation AI to customize the revision proposal.

[0041] When suggesting a revision proposal, the suggestion unit can suggest an optimal revision proposal taking into account the geographical location information of the designer. For example, if the designers are in different regions, the suggestion unit can suggest revision proposals taking into account the design standards specific to the region. Also, if the designers are in the same region, the suggestion unit can suggest revision proposals based on the common design standards of the region. Furthermore, if the designer is traveling, the suggestion unit can also suggest revision proposals based on the current geographical location information. In this way, by taking the geographical location information of the designer into consideration, it is possible to provide an optimal revision proposal based on the design standards specific to the region. Some or all of the above-mentioned processing in the suggestion unit may be performed using or without the generation AI. For example, the suggestion unit can input the geographical location information of the designer to the generation AI and cause the generation AI to suggest revision proposals based on the geographical location information.

[0042] When suggesting revision suggestions, the suggestion unit can analyze the designer's social media activity to suggest related revision suggestions. For example, the suggestion unit can analyze recent trends and interests from the designer's social media activity and suggest revision suggestions related to them. The suggestion unit can also collect information related to a specific project from the designer's social media activity and suggest revision suggestions based on that information. Furthermore, the suggestion unit can also suggest revision suggestions related to a specific design style or pattern based on the designer's social media activity. In this way, relevant revision suggestions can be provided by analyzing the designer's social media activity. Some or all of the above-mentioned processing in the suggestion unit may be performed using or without the generation AI. For example, the suggestion unit can input the designer's social media activity data into the generation AI and cause the generation AI to suggest revision suggestions based on the social media activity.

[0043] When analyzing information sources such as laws, regulations, and building standards, the checking unit can improve the accuracy of the check by referring to past check history. For example, the checking unit can prioritize checking frequently occurring violations based on the past check history. The checking unit can also learn from the past check history the mistakes that specific designers often make and improve the accuracy of the check. Furthermore, the past check history can be analyzed to adjust the accuracy of the check so that similar violations do not occur again. By referring to the past check history, the checking accuracy can be improved and the recurrence of similar violations can be prevented. Some or all of the above-described processing in the checking unit may be performed using or without the generation AI. For example, the checking unit can input past check history data into the generation AI and have the generation AI improve the checking accuracy.

[0044] When analyzing information sources such as laws, regulations, and building standards, the checking unit can perform checks taking into account the designer's past design style. For example, the checking unit can learn the designer's past design style and prioritize checking for violations based on a specific style. The checking unit can also check for general violations taking into account the designer's past design style. Furthermore, the checking unit can check for violations related to a specific design pattern based on the designer's past design style. In this way, by taking the designer's past design style into consideration, it is possible to prioritize checking for violations based on a specific style. Some or all of the above-mentioned processing in the checking unit may be performed using or without the generation AI. For example, the checking unit can input the designer's past design style data into the generation AI and have the generation AI perform the check.

[0045] The checking unit can perform checks taking into account the designer's geographical location information when analyzing information sources such as laws, regulations, and building standards. For example, if the designers are in different regions, the checking unit can perform checks taking into account regulations specific to those regions. Also, if the designers are in the same region, the checking unit can perform checks based on regulations common to the region. Furthermore, if the designer is traveling, the checking unit can also perform checks based on the designer's current geographical location information. In this way, checks based on region-specific regulations can be performed by taking the designer's geographical location information into account. Some or all of the above-mentioned processing in the checking unit may be performed using or without the generation AI. For example, the checking unit can input the designer's geographical location information into the generation AI and have the generation AI perform checks based on the geographical location information.

[0046] When analyzing information sources such as laws, regulations, and building standards, the checking unit can analyze the designer's social media activities and prioritize analysis of related check items. For example, the checking unit can analyze recent trends and interests from the designer's social media activities and prioritize analysis of check items related to those. The checking unit can also collect information related to a specific project from the designer's social media activities and prioritize analysis of check items based on that information. Furthermore, based on the designer's social media activities, it can also prioritize analysis of check items related to a specific design style or pattern. In this way, by analyzing the designer's social media activities, related check items can be prioritized for analysis. Some or all of the above-mentioned processing in the checking unit may be performed using or without the generation AI. For example, the checking unit can input the designer's social media activity data into the generation AI and have the generation AI analyze the check items based on the social media activity.

[0047] When reading the order quantity of components from design drawings, the reading unit can improve the reading accuracy by referring to past order history. For example, the reading unit can prioritize reading the quantity of frequently used components based on past order history. The reading unit can also improve reading accuracy by learning the quantities of components frequently ordered by a specific designer from past order history. Furthermore, the reading unit can analyze past order history and adjust the reading accuracy by referring to the order quantities of components in similar projects. By referring to past order history, the reading accuracy can be improved, and the order quantities of components in similar projects can be accurately read. Some or all of the above-described processing in the reading unit may be performed using or without the generation AI. For example, the reading unit can input past order history data into the generation AI and have the generation AI improve the reading accuracy.

[0048] When reading the order quantity of components from design drawings, the reading unit can take into account the designer's past design style. For example, the reading unit can learn the designer's past design style and preferentially read the order quantity of components based on a specific style. The reading unit can also read the order quantity of general components by taking into account the designer's past design style. Furthermore, the reading unit can read the order quantity of components related to a specific design pattern based on the designer's past design style. This makes it possible to accurately read the order quantity of components based on a specific style by taking into account the designer's past design style. Some or all of the above-mentioned processing in the reading unit may be performed using or without the generation AI. For example, the reading unit can input the designer's past design style data into the generation AI and have the generation AI perform the reading.

[0049] When reading the order quantity of components from the design drawings, the reading unit can take into account the designer's geographical location information. For example, if the designers are in different regions, the reading unit reads the order quantity of components taking into account the design standards specific to that region. Also, if the designers are in the same region, the reading unit can read the order quantity of components based on the common design standards for the region. Furthermore, if the designer is traveling, the reading unit can also read the order quantity of components based on the current geographical location information. In this way, by taking the designer's geographical location information into account, the order quantity of components based on the design standards specific to the region can be accurately read. Some or all of the above-mentioned processing in the reading unit may be performed using or without the generation AI. For example, the reading unit can input the designer's geographical location information into the generation AI and cause the generation AI to perform reading based on the geographical location information.

[0050] When reading the order quantity of components from design drawings, the reading unit can analyze the designer's social media activity and prioritize reading the order quantity of related components. For example, the reading unit can analyze recent trends and interests from the designer's social media activity and prioritize reading the order quantity of components related to those trends. The reading unit can also collect information related to a specific project from the designer's social media activity and read the order quantity of components based on that information. Furthermore, the reading unit can also read the order quantity of components related to a specific design style or pattern based on the designer's social media activity. In this way, by analyzing the designer's social media activity, the order quantity of related components can be accurately read. Some or all of the above-mentioned processing in the reading unit may be performed using or without the generation AI. For example, the reading unit can input the designer's social media activity data into the generation AI and cause the generation AI to read the order quantity of components based on the social media activity.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] When identifying inconsistencies in design documents, the discrimination unit can improve discrimination accuracy by referencing data from the designer's past design projects. For example, it can prioritize detection of inconsistencies that frequently occurred in past projects. It can also learn mistakes that specific designers often make and focus on checking those mistakes. It can also analyze data from past projects and adjust discrimination accuracy to prevent similar inconsistencies from recurring. In this way, by referring to past project data, discrimination accuracy can be improved and similar inconsistencies can be prevented from recurring.

[0053] When suggesting a revision, the suggesting unit can provide the optimal revision by referring to the designer's past revision history. For example, it can prioritize suggestions of revisions that have been used frequently based on revisions that have been adopted in the past. It can also learn the revisions that a particular designer often adopts and provide revisions that are suitable for that designer. Furthermore, it can analyze the past revision history and suggest the optimal revision for similar inconsistencies. This allows the system to provide the optimal revision by referring to the past revision history, improving the efficiency of the revision work.

[0054] When analyzing information on laws and regulations, the checking unit can perform checks taking into account the designer's geographical location information. For example, if the designers are in different regions, checks are performed taking into account regulations specific to those regions. Also, if the designers are in the same region, checks can be performed based on common regulations for the region. Furthermore, if the designer is moving, checks can also be performed based on the designer's current geographical location information. In this way, by taking into account the designer's geographical location information, checks can be performed based on region-specific regulations.

[0055] When reading the order quantities of parts from design drawings, the reading unit can analyze the designer's social media activity and prioritize reading the order quantities of related parts. For example, the reading unit can analyze the designer's social media activity for recent trends and interests and prioritize reading the order quantities of parts related to those. It can also collect information related to a specific project and read the order quantities of parts based on that information. It can also read the order quantities of parts related to a specific design style or pattern. In this way, by analyzing the designer's social media activity, it is possible to accurately read the order quantities of related parts.

[0056] When determining inconsistencies between design drawings and design documents, the discrimination unit can make the discrimination taking into account the designer's past design style. For example, the discrimination unit can learn the designer's past design style and preferentially detect inconsistencies based on a specific style. The discrimination unit can also detect general inconsistencies by taking into account the designer's past design style. Furthermore, the discrimination unit can detect inconsistencies related to a specific design pattern based on the designer's past design style. In this way, by taking into account the designer's past design style, it is possible to preferentially detect inconsistencies based on a specific style.

[0057] When suggesting revision suggestions, the suggestion unit can suggest optimal revision suggestions taking into account the geographical location information of the designer. For example, if the designers are in different regions, the suggestion unit can suggest revision suggestions taking into account the design standards specific to those regions. Also, if the designers are in the same region, the suggestion unit can suggest revision suggestions based on the common design standards of the region. Furthermore, if the designer is traveling, the suggestion unit can also suggest revision suggestions based on the designer's current geographical location information. In this way, by taking into account the designer's geographical location information, it is possible to provide optimal revision suggestions based on the design standards specific to the region.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The discrimination unit determines inconsistencies between the design drawings and the design documents. For example, if the dimensions listed in the design drawings differ from those listed in the design documents, the discrimination unit can detect the inconsistency. The discrimination unit uses the generation AI to automatically determine inconsistencies between the design drawings and the design documents. For example, the generation AI compares the dimensional information in the design drawings with the dimensional information in the design documents, and identifies the inconsistencies if any exist. The discrimination unit can also compare the material information in the design drawings with the material information in the design documents to detect differences in materials. Step 2: The indication unit indicates correction information for the inconsistencies identified by the discrimination unit. For example, the indication unit suggests corrections for the detected inconsistencies. The indication unit automatically generates corrections using a generation AI. For example, the generation AI proposes appropriate corrections based on dimensional information in the design drawings. The indication unit can also evaluate the impact of the corrections and provide the results to the designer. Step 3: The checking unit analyzes information sources for laws, regulations, and building standards to check whether the necessary design requirements are met. For example, the checking unit checks whether the earthquake resistance standards based on the Building Standards Act are met. The checking unit uses the generating AI to analyze information from laws and regulations and automatically check whether the design documents meet the necessary requirements. For example, the generating AI analyzes the provisions of the Building Standards Act and checks whether the design documents meet those standards. The checking unit also obtains information on revisions to laws and regulations in real time, allowing it to always check the compliance of the design documents with the latest information. Step 4: The reading unit reads the order quantities of components from the design drawings. For example, the reading unit automatically reads the quantities of rebar and concrete listed on the design drawings. The reading unit uses the generation AI to analyze the information on the design drawings and automatically calculate the type and quantity of components required. For example, the generation AI analyzes the graphic information on the design drawings and calculates the length of rebar and the volume of concrete. The reading unit can also automatically generate an order list based on the order quantities of components.

[0060] (Example 2) The design document review system according to an embodiment of the present invention uses AI to support the review (consistency check) of design documents. This design document review system uses multimodal generation AI to identify inconsistencies between design documents (CAD drawings) and the design documents, and identifies and suggests corrections. For example, if the dimensions listed in the design drawings differ from those listed in the design documents, the generation AI detects the inconsistency and identifies the information that needs to be corrected. Furthermore, by suggesting corrections, the system allows the designer to make corrections quickly. Next, the system provides multifaceted suggestions for checking whether the design meets the necessary design requirements, which are derived from multiple information sources such as laws, regulations, building codes, and their revisions. The generation AI analyzes these information sources and verifies whether the design documents meet the necessary requirements. For example, it checks whether the documents meet the seismic resistance standards set forth in the Building Standards Act and suggests necessary corrections. Furthermore, the system automates the reading of order quantities for various components from the drawings. The generation AI analyzes the design drawings and automatically identifies the types and quantities of required components. This allows designers to avoid the need to manually calculate component quantities, allowing for more efficient ordering. This system makes the review of design documents more efficient and improves design quality. It also reduces the burden on designers, allowing for quick design revisions. As a result, the design document review system can efficiently review design documents and improve design quality.

[0061] The design document review system according to the embodiment includes a discrimination unit, a suggestion unit, a check unit, and a reading unit. The discrimination unit identifies inconsistencies between the design documents and the design documents. For example, if the dimensions listed in the design drawings differ from those listed in the design documents, the discrimination unit can detect the inconsistency. The discrimination unit automatically identifies inconsistencies between the design documents and the design documents using a generation AI. For example, the generation AI compares dimensional information in the design drawings with dimensional information in the design documents and identifies the inconsistencies if any. The discrimination unit can also compare material information in the design drawings with material information in the design documents to detect differences in materials. The suggestion unit suggests correction information for the inconsistencies identified by the discrimination unit. For example, the suggestion unit suggests corrections for the detected inconsistencies. The suggestion unit automatically generates corrections using the generation AI. For example, the generation AI proposes appropriate corrections based on dimensional information in the design drawings. The suggestion unit can also evaluate the impact of the corrections and provide the evaluation to the designer. The checking unit analyzes information sources for laws, regulations, and building codes to check whether the necessary design requirements are met. For example, the checking unit checks whether the earthquake resistance standards under the Building Standards Act are met. The checking unit uses generation AI to analyze information from laws and regulations and automatically check whether the design documents meet the necessary requirements. For example, the generation AI analyzes the provisions of the Building Standards Act and checks whether the design documents meet those standards. The checking unit also obtains information on revisions to laws and regulations in real time, allowing it to always check the compliance of the design documents in an up-to-date state. The reading unit reads the order quantities of components from the design drawings. For example, the reading unit automatically reads the quantities of rebar and concrete listed on the design drawings. The reading unit uses generation AI to analyze the information in the design drawings and automatically calculate the type and quantity of components required. For example, the generation AI analyzes the graphic information in the design drawings and calculates the length of rebar and the volume of concrete. The reading unit can also automatically generate an order list based on the order quantities of components. As a result, the design document review system of the embodiment can efficiently identify inconsistencies between design documents and the design specifications, point out correction information, perform checks based on laws and regulations, and automatically read the order quantities of parts.

[0062] The discrimination unit can detect discrepancies between dimensions described in design drawings and dimensions described in the design document. For example, the discrimination unit compares dimensions described in design drawings with dimensions described in the design document and identifies the location of discrepancies if any. For example, if a dimension described in a design drawing is 100 mm and a dimension described in the design document is 105 mm, the discrimination unit detects the discrepancy. The discrimination unit can also automatically check the dimensional information in the design document based on the dimensional information in the design drawing. For example, the discrimination unit stores the dimensional information in the design drawing in a database and compares it with the dimensional information in the design document in real time. This automatically detects dimensional discrepancies, thereby improving the accuracy of the design. Some or all of the above-described processing in the discrimination unit may be performed using or without the generation AI. For example, the discrimination unit can input dimensional information from the design drawing into the generation AI and cause the generation AI to execute a process to detect dimensional discrepancies.

[0063] The pointing unit can suggest corrections for detected inconsistencies. For example, the pointing unit suggests corrections for detected inconsistencies. For example, if the dimensions described in a design drawing differ from the dimensions described in the design document, the pointing unit proposes an appropriate correction. For example, the pointing unit suggests a correction to align the dimensions in the design drawing with the dimensions in the design document, or a correction to align the dimensions in the design document with the dimensions in the design drawing. The pointing unit can also evaluate the impact of the corrections and provide it to the designer. For example, the pointing unit analyzes the impact of the corrections on other design elements and notifies the designer of the results. This automatically suggests corrections for inconsistencies, thereby streamlining the designer's correction work. Some or all of the above-mentioned processing in the pointing unit may be performed using or without the generation AI. For example, the pointing unit may input information about the detected inconsistencies into the generation AI and cause the generation AI to generate corrections.

[0064] The checking unit can check whether the earthquake resistance standards under the Building Standards Act are met. For example, the checking unit verifies whether the earthquake resistance standards under the Building Standards Act are met. For example, the checking unit analyzes the structural calculations of the design documents and checks whether the earthquake resistance standards are met. The checking unit uses the generating AI to analyze information on laws and regulations and automatically check whether the design documents meet the necessary requirements. For example, the generating AI analyzes the provisions of the Building Standards Act and checks whether the design documents meet the standards. The checking unit also obtains information on revisions to laws and regulations in real time and can always check the compliance of the design documents with the latest information. This automatically checks the earthquake resistance standards, improving the safety of the design. Some or all of the above-mentioned processing in the checking unit may be performed using the generating AI, or may be performed without using the generating AI. For example, the checking unit can input information on the design documents into the generating AI and have the generating AI check the earthquake resistance standards.

[0065] The reading unit can read the quantity of rebar and concrete from the design drawings. The reading unit, for example, automatically reads the quantity of rebar and concrete listed in the design drawings. For example, the reading unit analyzes the graphic information of the design drawings and calculates the length of the rebar and the volume of the concrete. The reading unit uses the generation AI to analyze the information in the design drawings and automatically calculate the type and quantity of required components. For example, the generation AI calculates the length of the rebar and the volume of the concrete based on the graphic information in the design drawings. The reading unit can also automatically generate an ordering list based on the order quantity of components. For example, the reading unit lists the types and quantities of required components based on the information in the design drawings and generates an ordering list. This automatically reads the quantity of rebar and concrete, thereby streamlining the ordering process. Some or all of the above-mentioned processing in the reading unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the reading unit can input the information in the design drawings into the generation AI and have the generation AI read the quantity of components.

[0066] The indication unit can provide a proposed revision to the designer. The indication unit, for example, provides the proposed revision to the designer. For example, the indication unit proposes an appropriate proposed revision for the detected inconsistency and notifies the designer of the proposed revision. The indication unit automatically generates a proposed revision using the generation AI and provides it to the designer. For example, the generation AI proposes an appropriate proposed revision based on information in the design drawings and notifies the designer of the proposed revision. The indication unit can also evaluate the impact of the proposed revision and provide the result to the designer. For example, the indication unit analyzes the impact of the proposed revision on other design elements and notifies the designer of the result. In this way, by providing the proposed revision to the designer, the designer can make the revision quickly. Some or all of the above-mentioned processing in the indication unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the indication unit can input information about the proposed revision to the generation AI and cause the generation AI to provide the proposed revision.

[0067] The discrimination unit can estimate the user's emotion and adjust the discrimination accuracy of the inconsistency points based on the estimated user emotion. For example, the discrimination unit can estimate the user's emotion and adjust the discrimination accuracy of the inconsistency points based on the estimated user emotion. For example, when the user is stressed, the discrimination accuracy can be increased to detect inconsistencies in detail. When the user is relaxed, the discrimination accuracy can be set to normal to detect standard inconsistencies. When the user is in a hurry, the discrimination accuracy can be lowered to detect only major inconsistencies. This enables more appropriate detection of inconsistencies by adjusting the discrimination accuracy according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the discrimination unit can be performed using the generation AI, or can be performed without the generation AI. For example, the discrimination unit can input user emotion data into the generation AI and cause the generation AI to adjust the discrimination accuracy based on the emotion.

[0068] The discrimination unit can improve discrimination accuracy by referring to past revision history when discriminating inconsistencies between design drawings and design documents. For example, the discrimination unit can improve discrimination accuracy by referring to past revision history when discriminating inconsistencies between design drawings and design documents. For example, the discrimination unit can prioritize detection of frequently occurring inconsistencies based on past revision history. Furthermore, the discrimination unit can learn mistakes that specific designers often make from past revision history and improve discrimination accuracy. Furthermore, the discrimination unit can analyze past revision history and adjust discrimination accuracy to prevent similar inconsistencies from recurring. Thus, by referring to past revision history, discrimination accuracy can be improved and similar inconsistencies can be prevented from recurring. Some or all of the above-described processing in the discrimination unit may be performed using or without the generation AI. For example, the discrimination unit can input past revision history data into the generation AI and have the generation AI improve discrimination accuracy.

[0069] When determining inconsistencies between design drawings and design documents, the discrimination unit can make the discrimination taking into account the designer's past design style. The discrimination unit, for example, learns the designer's past design style and preferentially detects inconsistencies based on a specific style. The discrimination unit can also detect general inconsistencies by taking into account the designer's past design style. Furthermore, the discrimination unit can detect inconsistencies related to a specific design pattern based on the designer's past design style. In this way, by taking the designer's past design style into consideration, it is possible to preferentially detect inconsistencies based on a specific style. Some or all of the above-mentioned processing in the discrimination unit may be performed using or without the generation AI. For example, the discrimination unit can input the designer's past design style data into the generation AI and have the generation AI perform the discrimination.

[0070] The discrimination unit can estimate the user's emotion and adjust the display method of the discrimination result based on the estimated user emotion. For example, the discrimination unit can estimate the user's emotion and adjust the display method of the discrimination result based on the estimated user emotion. For example, if the user is stressed, a simple, highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is in a hurry, a display method that focuses on the main points can be provided. By adjusting the display method according to the user's emotion, visibility is improved and the burden on the user is reduced. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the discrimination unit can be performed using the generation AI, or can be performed without using the generation AI. For example, the discrimination unit can input user emotion data into the generation AI and cause the generation AI to adjust the display method based on the emotion.

[0071] The discrimination unit can make the discrimination by taking into account the geographical location information of the designer when discriminating inconsistencies between the design drawings and the design document. For example, if the designers are in different regions, the discrimination unit discriminates inconsistencies by taking into account the design standards specific to that region. Also, if the designers are in the same region, the discrimination unit can discriminate inconsistencies based on the common design standards of the region. Furthermore, if the designer is traveling, the discrimination unit can also discriminate inconsistencies based on the current geographical location information. In this way, by taking into account the geographical location information of the designer, it is possible to detect inconsistencies based on the design standards specific to the region. Some or all of the above-mentioned processing in the discrimination unit may be performed using or without the generation AI. For example, the discrimination unit can input the geographical location information of the designer to the generation AI and cause the generation AI to perform discrimination based on the geographical location information.

[0072] When determining inconsistencies between design drawings and design documents, the determination unit can analyze the designer's social media activities to prioritize determining relevant inconsistencies. For example, the determination unit can analyze the designer's social media activities to determine recent trends and interests and prioritize determining inconsistencies related to those trends. The determination unit can also collect information related to a specific project from the designer's social media activities and determine inconsistencies based on that information. Furthermore, the determination unit can determine inconsistencies related to a specific design style or pattern based on the designer's social media activities. In this way, by analyzing the designer's social media activities, relevant inconsistencies can be detected prioritized. Some or all of the above-described processing in the determination unit may be performed using or without the generation AI. For example, the determination unit can input the designer's social media activity data into the generation AI and cause the generation AI to perform determination based on the social media activity.

[0073] The suggestion unit can estimate the user's emotions and adjust the way the proposed revision is expressed based on the estimated user's emotions. For example, the suggestion unit can estimate the user's emotions and adjust the way the proposed revision is expressed based on the estimated user's emotions. For example, if the user is stressed, the suggestion unit can provide a simple and clear revision. If the user is relaxed, the suggestion unit can provide a revision with detailed explanations. If the user is in a hurry, the suggestion unit can provide a revision that focuses on the main points. This allows the suggestion unit to adjust the way the proposed revision is expressed based on the user's emotions, thereby providing a more appropriate revision. The estimation of emotions is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit can be performed using the generation AI, or can be performed without the generation AI. For example, the suggestion unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the way the proposed revision is expressed based on the emotion.

[0074] When suggesting a revision proposal, the suggestion unit can refer to past revision history to suggest the optimal revision proposal. For example, the suggestion unit can prioritize suggesting frequently used revision proposals based on the past revision history. The suggestion unit can also suggest revision proposals that are often adopted by a specific designer based on the past revision history. Furthermore, the suggestion unit can analyze the past revision history to suggest the optimal revision proposal for a similar inconsistency. This allows the optimal revision proposal to be suggested by referring to the past revision history, improving the efficiency of the revision work. Some or all of the above-mentioned processing in the suggestion unit may be performed using or without the generation AI. For example, the suggestion unit can input past revision history data into the generation AI and cause the generation AI to suggest the optimal revision proposal.

[0075] When suggesting a revision proposal, the suggestion unit can customize the revision proposal by taking into account the designer's past design style. For example, the suggestion unit learns the designer's past design style and suggests a revision proposal based on a specific style. The suggestion unit can also suggest a general revision proposal by taking into account the designer's past design style. Furthermore, the suggestion unit can suggest a revision proposal related to a specific design pattern based on the designer's past design style. In this way, by taking the designer's past design style into consideration, it is possible to provide a revision proposal based on a specific style. Some or all of the above-mentioned processing in the suggestion unit may be performed using or without the generation AI. For example, the suggestion unit can input the designer's past design style data into the generation AI and cause the generation AI to customize the revision proposal.

[0076] The suggestion unit can estimate the user's emotions and prioritize revision suggestions based on the estimated user emotions. For example, the suggestion unit can estimate the user's emotions and prioritize revision suggestions based on the estimated user emotions. For example, if the user is stressed, important revision suggestions can be presented preferentially. Also, if the user is relaxed, all revision suggestions can be presented equally. Furthermore, if the user is in a hurry, important revision suggestions can be presented preferentially. Thus, by prioritizing revision suggestions according to the user's emotions, important revision suggestions can be presented preferentially. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the suggestion unit can be performed using the generation AI, or can be performed without using the generation AI. For example, the suggestion unit can input user emotion data into the generation AI and cause the generation AI to prioritize revision suggestions based on emotions.

[0077] When suggesting a revision proposal, the suggestion unit can suggest an optimal revision proposal taking into account the geographical location information of the designer. For example, if the designers are in different regions, the suggestion unit can suggest revision proposals taking into account the design standards specific to the region. Also, if the designers are in the same region, the suggestion unit can suggest revision proposals based on the common design standards of the region. Furthermore, if the designer is traveling, the suggestion unit can also suggest revision proposals based on the current geographical location information. In this way, by taking the geographical location information of the designer into consideration, it is possible to provide an optimal revision proposal based on the design standards specific to the region. Some or all of the above-mentioned processing in the suggestion unit may be performed using or without the generation AI. For example, the suggestion unit can input the geographical location information of the designer to the generation AI and cause the generation AI to suggest revision proposals based on the geographical location information.

[0078] When suggesting revision suggestions, the suggestion unit can analyze the designer's social media activity to suggest related revision suggestions. For example, the suggestion unit can analyze recent trends and interests from the designer's social media activity and suggest revision suggestions related to them. The suggestion unit can also collect information related to a specific project from the designer's social media activity and suggest revision suggestions based on that information. Furthermore, the suggestion unit can also suggest revision suggestions related to a specific design style or pattern based on the designer's social media activity. In this way, relevant revision suggestions can be provided by analyzing the designer's social media activity. Some or all of the above-mentioned processing in the suggestion unit may be performed using or without the generation AI. For example, the suggestion unit can input the designer's social media activity data into the generation AI and cause the generation AI to suggest revision suggestions based on the social media activity.

[0079] The check unit can estimate the user's emotions and adjust the display method of the check based on the estimated user's emotions. For example, the check unit can estimate the user's emotions and adjust the display method of the check based on the estimated user's emotions. For example, if the user is feeling stressed, a simple, highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is in a hurry, a display method that focuses on the main points can be provided. This adjusts the display method according to the user's emotions, improving visibility and reducing the user's burden. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the check unit can be performed using the generation AI, or can be performed without using the generation AI. For example, the check unit can input user emotion data into the generation AI and cause the generation AI to adjust the display method based on the emotion.

[0080] When analyzing information sources such as laws, regulations, and building standards, the checking unit can improve the accuracy of the check by referring to past check history. For example, the checking unit can prioritize checking frequently occurring violations based on the past check history. The checking unit can also learn from the past check history the mistakes that specific designers often make and improve the accuracy of the check. Furthermore, the past check history can be analyzed to adjust the accuracy of the check so that similar violations do not occur again. By referring to the past check history, the checking accuracy can be improved and the recurrence of similar violations can be prevented. Some or all of the above-described processing in the checking unit may be performed using or without the generation AI. For example, the checking unit can input past check history data into the generation AI and have the generation AI improve the checking accuracy.

[0081] When analyzing information sources such as laws, regulations, and building standards, the checking unit can perform checks taking into account the designer's past design style. For example, the checking unit can learn the designer's past design style and prioritize checking for violations based on a specific style. The checking unit can also check for general violations taking into account the designer's past design style. Furthermore, the checking unit can check for violations related to a specific design pattern based on the designer's past design style. In this way, by taking the designer's past design style into consideration, it is possible to prioritize checking for violations based on a specific style. Some or all of the above-mentioned processing in the checking unit may be performed using or without the generation AI. For example, the checking unit can input the designer's past design style data into the generation AI and have the generation AI perform the check.

[0082] The check unit can estimate the user's emotions and determine the priority of check items based on the estimated user emotions. For example, the check unit can estimate the user's emotions and determine the priority of check items based on the estimated user emotions. For example, if the user is feeling stressed, important check items can be presented preferentially. Also, if the user is relaxed, all check items can be presented evenly. Furthermore, if the user is in a hurry, major check items can be presented preferentially. Thus, by determining the priority of check items according to the user's emotions, important check items can be presented preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the check unit can be performed using the generation AI, or can be performed without using the generation AI. For example, the check unit can input user emotion data into the generation AI and have the generation AI determine the priority of check items based on emotions.

[0083] The checking unit can perform checks taking into account the designer's geographical location information when analyzing information sources such as laws, regulations, and building standards. For example, if the designers are in different regions, the checking unit can perform checks taking into account regulations specific to those regions. Also, if the designers are in the same region, the checking unit can perform checks based on regulations common to the region. Furthermore, if the designer is traveling, the checking unit can also perform checks based on the designer's current geographical location information. In this way, checks based on region-specific regulations can be performed by taking the designer's geographical location information into account. Some or all of the above-mentioned processing in the checking unit may be performed using or without the generation AI. For example, the checking unit can input the designer's geographical location information into the generation AI and have the generation AI perform checks based on the geographical location information.

[0084] When analyzing information sources such as laws, regulations, and building standards, the checking unit can analyze the designer's social media activities and prioritize analysis of related check items. For example, the checking unit can analyze recent trends and interests from the designer's social media activities and prioritize analysis of check items related to those. The checking unit can also collect information related to a specific project from the designer's social media activities and prioritize analysis of check items based on that information. Furthermore, based on the designer's social media activities, it can also prioritize analysis of check items related to a specific design style or pattern. In this way, by analyzing the designer's social media activities, related check items can be prioritized for analysis. Some or all of the above-mentioned processing in the checking unit may be performed using or without the generation AI. For example, the checking unit can input the designer's social media activity data into the generation AI and have the generation AI analyze the check items based on the social media activity.

[0085] The reading unit can estimate the user's emotions and adjust the accuracy of reading the component order quantities based on the estimated user emotions. For example, the reading unit estimates the user's emotions and adjusts the accuracy of reading the component order quantities based on the estimated user emotions. For example, if the user is stressed, the reading accuracy can be increased to read the component order quantities in detail. Alternatively, if the user is relaxed, the reading accuracy can be set to normal and the order quantities of standard components can be read. Furthermore, if the user is in a hurry, the reading accuracy can be lowered to read only the order quantities of major components. This allows for adjusting the reading accuracy according to the user's emotions to read more appropriate component order quantities. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reading unit can be performed using the generation AI, or can be performed without using the generation AI. For example, the reading unit can input the user's emotional data into the generation AI and cause the generation AI to adjust the reading accuracy based on the emotion.

[0086] When reading the order quantity of components from design drawings, the reading unit can improve the reading accuracy by referring to past order history. For example, the reading unit can prioritize reading the quantity of frequently used components based on past order history. The reading unit can also improve reading accuracy by learning the quantities of components frequently ordered by a specific designer from past order history. Furthermore, the reading unit can analyze past order history and adjust the reading accuracy by referring to the order quantities of components in similar projects. By referring to past order history, the reading accuracy can be improved, and the order quantities of components in similar projects can be accurately read. Some or all of the above-described processing in the reading unit may be performed using or without the generation AI. For example, the reading unit can input past order history data into the generation AI and have the generation AI improve the reading accuracy.

[0087] When reading the order quantity of components from design drawings, the reading unit can take into account the designer's past design style. For example, the reading unit can learn the designer's past design style and preferentially read the order quantity of components based on a specific style. The reading unit can also read the order quantity of general components by taking into account the designer's past design style. Furthermore, the reading unit can read the order quantity of components related to a specific design pattern based on the designer's past design style. This makes it possible to accurately read the order quantity of components based on a specific style by taking into account the designer's past design style. Some or all of the above-mentioned processing in the reading unit may be performed using or without the generation AI. For example, the reading unit can input the designer's past design style data into the generation AI and have the generation AI perform the reading.

[0088] The reading unit can estimate the user's emotions and adjust the display method of the order quantity of the parts based on the estimated user emotions. For example, the reading unit can estimate the user's emotions and adjust the display method of the order quantity of the parts based on the estimated user emotions. For example, if the user is stressed, a simple, highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is in a hurry, a display method that focuses on the main points can be provided. This adjusts the display method according to the user's emotions, improving visibility and reducing the user's burden. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reading unit can be performed using the generation AI, or can be performed without the generation AI. For example, the reading unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the display method based on the emotion.

[0089] When reading the order quantity of components from the design drawings, the reading unit can take into account the designer's geographical location information. For example, if the designers are in different regions, the reading unit reads the order quantity of components taking into account the design standards specific to that region. Also, if the designers are in the same region, the reading unit can read the order quantity of components based on the common design standards for the region. Furthermore, if the designer is traveling, the reading unit can also read the order quantity of components based on the current geographical location information. In this way, by taking the designer's geographical location information into account, the order quantity of components based on the design standards specific to the region can be accurately read. Some or all of the above-mentioned processing in the reading unit may be performed using or without the generation AI. For example, the reading unit can input the designer's geographical location information into the generation AI and cause the generation AI to perform reading based on the geographical location information.

[0090] When reading the order quantity of components from design drawings, the reading unit can analyze the designer's social media activity and prioritize reading the order quantity of related components. For example, the reading unit can analyze recent trends and interests from the designer's social media activity and prioritize reading the order quantity of components related to those trends. The reading unit can also collect information related to a specific project from the designer's social media activity and read the order quantity of components based on that information. Furthermore, the reading unit can also read the order quantity of components related to a specific design style or pattern based on the designer's social media activity. In this way, by analyzing the designer's social media activity, the order quantity of related components can be accurately read. Some or all of the above-mentioned processing in the reading unit may be performed using or without the generation AI. For example, the reading unit can input the designer's social media activity data into the generation AI and cause the generation AI to read the order quantity of components based on the social media activity. === Hard Collateral 1-1 === Each of the above-described elements, including the discrimination unit, the indication unit, the check unit, and the reading unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the discrimination unit detects inconsistencies between the design drawings and the design document using the camera 42 and microphone 38B of the smart device 14, and the control unit 46A determines the inconsistencies. The indication unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and generates correction proposals for the detected inconsistencies. The checking unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes information on laws and regulations to confirm whether the design drawings meet the necessary requirements. The reading unit is implemented, for example, by the control unit 46A of the smart device 14 and automatically reads the order quantities of components from the design drawings. === Hard Collateral 1-2 === Each of the multiple elements, including the discrimination unit, the indication unit, the check unit, and the reading unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the discrimination unit detects inconsistencies between the design drawings and the design document using the camera 42 and microphone 238 of the smart glasses 214, and the control unit 46A determines the inconsistencies. The indication unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates correction proposals for the detected inconsistencies. The checking unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes information on laws and regulations to confirm whether the design drawings meet the necessary requirements. The reading unit is realized, for example, by the control unit 46A of the smart glasses 214, and automatically reads the order quantities of components from the design drawings. === Hard Collateral 1-3 === Each of the multiple elements, including the determination unit, indication unit, check unit, and reading unit, described above, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the determination unit detects inconsistencies between the design drawings and the design document using the camera 42 and microphone 238 of the headset terminal 314, and the control unit 46A determines the inconsistencies. The indication unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates correction proposals for the detected inconsistencies. The checking unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes information on laws and regulations to confirm whether the design drawings meet the necessary requirements. The reading unit is realized, for example, by the control unit 46A of the headset terminal 314, and automatically reads the order quantities of components from the design drawings. === Hard Collateral 1-4 === Each of the above-described elements, including the discrimination unit, the indication unit, the check unit, and the reading unit, is implemented, for example, by at least one of the robot 414 and the data processing device 12. For example, the discrimination unit detects inconsistencies between the design drawings and the design document using the camera 42 and microphone 238 of the robot 414, and the control unit 46A identifies the inconsistencies. The indication unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and generates correction proposals for the detected inconsistencies. The checking unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes information on laws and regulations to confirm whether the design drawings meet the necessary requirements. The reading unit is implemented, for example, by the control unit 46A of the robot 414 and automatically reads the order quantities of components from the design drawings.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] When identifying inconsistencies in design documents, the discrimination unit can improve discrimination accuracy by referencing data from the designer's past design projects. For example, it can prioritize detection of inconsistencies that frequently occurred in past projects. It can also learn mistakes that specific designers often make and focus on checking those mistakes. It can also analyze data from past projects and adjust discrimination accuracy to prevent similar inconsistencies from recurring. In this way, by referring to past project data, discrimination accuracy can be improved and similar inconsistencies can be prevented from recurring.

[0093] When suggesting a revision, the suggesting unit can provide the optimal revision by referring to the designer's past revision history. For example, it can prioritize suggestions of revisions that have been used frequently based on revisions that have been adopted in the past. It can also learn the revisions that a particular designer often adopts and provide revisions that are suitable for that designer. Furthermore, it can analyze the past revision history and suggest the optimal revision for similar inconsistencies. This allows the system to provide the optimal revision by referring to the past revision history, improving the efficiency of the revision work.

[0094] When analyzing information on laws and regulations, the checking unit can perform checks taking into account the designer's geographical location information. For example, if the designers are in different regions, checks are performed taking into account regulations specific to those regions. Also, if the designers are in the same region, checks can be performed based on common regulations for the region. Furthermore, if the designer is moving, checks can also be performed based on the designer's current geographical location information. In this way, by taking into account the designer's geographical location information, checks can be performed based on region-specific regulations.

[0095] When reading the order quantities of parts from design drawings, the reading unit can analyze the designer's social media activity and prioritize reading the order quantities of related parts. For example, the reading unit can analyze the designer's social media activity for recent trends and interests and prioritize reading the order quantities of parts related to those. It can also collect information related to a specific project and read the order quantities of parts based on that information. It can also read the order quantities of parts related to a specific design style or pattern. In this way, by analyzing the designer's social media activity, it is possible to accurately read the order quantities of related parts.

[0096] The discrimination unit can estimate the user's emotions and adjust the discrimination accuracy of inconsistencies based on the estimated user emotions. For example, if the user is feeling stressed, the discrimination accuracy can be increased to detect inconsistencies in detail. Alternatively, if the user is relaxed, the discrimination accuracy can be set to normal to detect standard inconsistencies. Furthermore, if the user is in a hurry, the discrimination accuracy can be lowered to detect only major inconsistencies. In this way, by adjusting the discrimination accuracy according to the user's emotions, more appropriate detection of inconsistencies becomes possible.

[0097] The suggestion unit can estimate the user's emotions and adjust the way in which the suggested revisions are presented based on the estimated user's emotions. For example, if the user is feeling stressed, a simple and clear suggested revision can be provided. If the user is relaxed, a suggested revision with detailed explanations can be provided. Furthermore, if the user is in a hurry, a suggested revision that focuses on the main points can be provided. In this way, by adjusting the way in which the suggested revisions are presented according to the user's emotions, more appropriate suggested revisions can be provided.

[0098] The check unit can estimate the user's emotions and adjust the display method of the check based on the estimated user's emotions. For example, if the user is feeling stressed, a simple, highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is in a hurry, a display method that focuses on the main points can be provided. In this way, by adjusting the display method according to the user's emotions, visibility is improved and the burden on the user is reduced.

[0099] The reading unit can estimate the user's emotions and adjust the accuracy of reading the component order quantities based on the estimated user emotions. For example, if the user is feeling stressed, the reading accuracy can be increased to read the component order quantities in detail. Alternatively, if the user is relaxed, the reading accuracy can be set to normal to read the standard component order quantities. Furthermore, if the user is in a hurry, the reading accuracy can be lowered to read only the main component order quantities. In this way, by adjusting the reading accuracy according to the user's emotions, a more appropriate component order quantity can be read.

[0100] When determining inconsistencies between design drawings and design documents, the discrimination unit can make the discrimination taking into account the designer's past design style. For example, the discrimination unit can learn the designer's past design style and preferentially detect inconsistencies based on a specific style. The discrimination unit can also detect general inconsistencies by taking into account the designer's past design style. Furthermore, the discrimination unit can detect inconsistencies related to a specific design pattern based on the designer's past design style. In this way, by taking into account the designer's past design style, it is possible to preferentially detect inconsistencies based on a specific style.

[0101] When suggesting revision suggestions, the suggestion unit can suggest optimal revision suggestions taking into account the geographical location information of the designer. For example, if the designers are in different regions, the suggestion unit can suggest revision suggestions taking into account the design standards specific to those regions. Also, if the designers are in the same region, the suggestion unit can suggest revision suggestions based on the common design standards of the region. Furthermore, if the designer is traveling, the suggestion unit can also suggest revision suggestions based on the designer's current geographical location information. In this way, by taking into account the designer's geographical location information, it is possible to provide optimal revision suggestions based on the design standards specific to the region.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The discrimination unit determines inconsistencies between the design drawings and the design documents. For example, if the dimensions listed in the design drawings differ from those listed in the design documents, the discrimination unit can detect the inconsistency. The discrimination unit uses the generation AI to automatically determine inconsistencies between the design drawings and the design documents. For example, the generation AI compares the dimensional information in the design drawings with the dimensional information in the design documents, and identifies the inconsistencies if any exist. The discrimination unit can also compare the material information in the design drawings with the material information in the design documents to detect differences in materials. Step 2: The indication unit indicates correction information for the inconsistencies identified by the discrimination unit. For example, the indication unit suggests corrections for the detected inconsistencies. The indication unit automatically generates corrections using a generation AI. For example, the generation AI proposes appropriate corrections based on dimensional information in the design drawings. The indication unit can also evaluate the impact of the corrections and provide the results to the designer. Step 3: The checking unit analyzes information sources for laws, regulations, and building standards to check whether the necessary design requirements are met. For example, the checking unit checks whether the earthquake resistance standards based on the Building Standards Act are met. The checking unit uses the generating AI to analyze information from laws and regulations and automatically check whether the design documents meet the necessary requirements. For example, the generating AI analyzes the provisions of the Building Standards Act and checks whether the design documents meet those standards. The checking unit also obtains information on revisions to laws and regulations in real time, allowing it to always check the compliance of the design documents with the latest information. Step 4: The reading unit reads the order quantities of components from the design drawings. For example, the reading unit automatically reads the quantities of rebar and concrete listed on the design drawings. The reading unit uses the generation AI to analyze the information on the design drawings and automatically calculate the type and quantity of components required. For example, the generation AI analyzes the graphic information on the design drawings and calculates the length of rebar and the volume of concrete. The reading unit can also automatically generate an order list based on the order quantities of components.

[0104] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0105] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0106] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0107] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0108] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0109] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0110] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0111] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0112] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0113] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0114] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0115] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0116] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0117] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0118] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0119] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0120] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0121] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0122] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0123] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0124] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0125] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0126] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0127] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0128] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0129] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0130] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0131] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0132] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0133] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0134] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0135] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0136] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0137] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0138] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0139] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0140] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0141] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0142] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0143] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0144] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0145] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0146] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0147] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0148] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0149] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0150] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0151] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0152] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0153] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0154] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0155] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0156] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0157] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0158] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0159] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0160] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0161] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0162] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0163] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0164] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0165] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0166] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0167] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0168] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0169] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0170] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0171] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0172] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0173] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0174] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0175] [Explanation of symbols]

[0176] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A determination unit that determines inconsistencies between the design documents and the design documents; a notifying unit that indicates correction information for the inconsistent portion determined by the determining unit; A checking department analyzes information sources from laws, regulations, and building standards to check whether the necessary design requirements are met; A reading unit that reads the order quantity of the parts from the design drawing. A system characterized by:

2. The determination unit Detect discrepancies between dimensions listed on engineering drawings and those listed in engineering documents 2. The system of claim 1.

3. The indicating unit Suggest fixes for detected inconsistencies 2. The system of claim 1.

4. The checking unit Check whether the building meets earthquake resistance standards based on the Building Standards Act 2. The system of claim 1.

5. The reading unit Reading the quantities of rebar and concrete from design drawings 2. The system of claim 1.

6. The indicating unit Providing suggested revisions to the designer 2. The system of claim 1.

7. The determination unit The user's emotions are estimated, and the accuracy of identifying inconsistencies is adjusted based on the estimated user emotions.

2. The system of claim 1.

8. The determination unit When determining inconsistencies between design drawings and specifications, improve accuracy by referencing past revision history 2. The system of claim 1.

Images