system

Abstract

We provide the system. [Solution] Means of collecting construction cost estimate information, A means for detecting anomalies by comparing the collected construction estimate information with past data, A means for analyzing the breakdown of construction estimates based on the aforementioned anomalies and generating a strategy for negotiating price reductions, A means of presenting the aforementioned strategy, receiving user feedback, and improving the system based on the results, A system that includes this.

Description

Technical Field

[0001] The technology of this disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the estimation work of construction projects, it is a common problem that the person in charge has little experience in the project and it is difficult to conduct a proper review of the estimate. In particular, there is a lack of appropriate comparative analysis using past data and generation of strategies for cost reduction negotiation. As a result, unnecessary expenses are incurred and the efficiency of cost management is reduced.

Means for Solving the Problems

[0005] This invention provides a system that collects construction estimate information, standardizes that information, and compares it with past data to detect abnormal unit prices and quantities. Furthermore, it analyzes the detailed breakdown based on the abnormal values ​​and generates strategies to enable price reduction negotiations. The generated strategies are presented to the user, and the system is continuously improved based on user feedback. This feedback is used as training data to improve the accuracy of subsequent analyses. As a result, even inexperienced personnel can effectively scrutinize estimates and manage expenses.

[0006] "Construction estimate information" refers to detailed information such as the breakdown of work, quantities, unit prices, and total costs related to construction work.

[0007] "Means of collection" refers to processes and devices used to retrieve information from external systems and databases.

[0008] "Past data" refers to historical data obtained from existing similar construction projects, which serves as the basis for analysis.

[0009] An "outlier" refers to a numerical value that deviates from the standard or normal range, and in particular indicates an inappropriate value within an estimate.

[0010] "Breakdown" refers to the components of a construction estimate, showing the classification of detailed parts such as material costs, labor costs, and machinery costs.

[0011] "Negotiating a price reduction" refers to the negotiation process undertaken to lower the estimated cost.

[0012] "Strategy" refers to a set of measures and means planned to effectively negotiate a price reduction.

[0013] "Feedback" refers to information from users regarding their usage results and areas for improvement, and the data used to improve the system based on that feedback.

[0014] "Learning data" refers to feedback from users and other information used for the continuous improvement of the system.

[0015] "Analysis accuracy" refers to the accuracy indicating that the analysis results of data are appropriate, and is an index related to the efficiency and reliability of the system.

Brief Explanation of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Modes for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units 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), and the like.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the 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.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention is a system that supports the scrutiny of construction estimates and negotiation of price reductions. The system mainly consists of the following components, each of which plays a specific role in achieving efficiency and accuracy in the estimation process.

[0038] First, the server collects estimate information related to the construction project. This is done by automatically retrieving data from external databases and partner systems. The collected data is then converted into a standard format. This allows for consistent processing of estimate information provided in different formats.

[0039] Next, the user enters new construction estimate information through their device. Here, an interface is provided for entering details such as construction items, quantities, unit prices, and total amounts. This information is instantly sent to the server and stored in the database along with other data.

[0040] The stored data is analyzed by the server. It compares the information sent from the device with similar past data to identify abnormal values ​​or items that may exceed the appropriate range. This analysis utilizes machine learning techniques to produce more accurate results.

[0041] Next, the server analyzes the breakdown of each item in the construction estimate in detail based on the analysis results. It identifies which elements are causing high costs and proposes a strategy to the user for negotiating price reductions. This strategy includes potential alternatives and items where costs can be reduced.

[0042] Finally, the user conducts negotiations based on the presented strategy and inputs the results into the terminal. The server analyzes this feedback and automatically incorporates it as training data for the system. This improves the accuracy of future analyses.

[0043] As a concrete example, a user inputs an estimate for a new base station construction project. In this case, the server detects that the material costs are higher than in previous projects and suggests changing to standard materials. The user can then negotiate based on this advice to reduce costs. In this way, even inexperienced personnel can use the system to conduct proper and effective estimate reviews and negotiations.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server periodically collects the latest construction estimate data from external databases and affiliated systems. It uses a crawler to extract the necessary data and stores it in a local database.

[0047] Step 2:

[0048] The user enters new quote information via a terminal. Through the user interface, the user enters the work items, quantities, unit prices, and total amount into the system, and the entered data is immediately transmitted to the server.

[0049] Step 3:

[0050] The server converts the received estimate data into a standard format. In this process, the data is refined, inconsistencies and omissions are corrected, and it is stored in the database in a unified format.

[0051] Step 4:

[0052] The server analyzes standardized quotation data. By comparing it with historical data, it verifies standard unit prices and reasonableness, and detects values ​​that are unusually high or low.

[0053] Step 5:

[0054] The server then performs a more detailed analysis of the breakdown of each construction item based on the analysis results. It breaks down cost factors such as material costs, labor costs, and machinery costs to identify which elements are influencing the increase in costs.

[0055] Step 6:

[0056] The server generates effective strategies for price reduction negotiations. Based on detected anomalies, it provides users with specific suggestions that consider cost-reduction alternatives and successful examples from other projects.

[0057] Step 7:

[0058] Users negotiate with suppliers using the provided price reduction negotiation strategies as a reference and input the results into their terminal. The input feedback is analyzed on the server and stored as training data to be used for future analysis.

[0059] Step 8:

[0060] The server improves the system's accuracy based on user feedback. By analyzing the feedback and updating the machine learning model, the accuracy of future estimate refinements and price reduction negotiation suggestions can be further enhanced.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] Estimating construction projects often involves a complex interplay of diverse data, making it challenging to quickly and accurately detect anomalies and implement appropriate cost reductions. Furthermore, effectively utilizing accumulated historical negotiation data to learn from and improve the accuracy of future estimates is essential.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes means for automatically acquiring evaluation information related to construction work from an external data storage device and converting the acquired data into a unified format; means for using the evaluation information to compare it with past information and utilizing a learning algorithm to identify abnormal values; and means for analyzing detailed evaluation items based on the identified abnormal values ​​and generating and presenting methods for adjusting the evaluation. This makes it possible to efficiently analyze construction estimates and make appropriate adjustments based on the results. Furthermore, by incorporating user feedback into the learning data to improve the accuracy of subsequent analyses, the learning effect is also improved.

[0066] "Construction-related evaluation information" refers to data on costs and work details in construction and repair projects, and is used for scrutinizing estimates and budgets.

[0067] "External data storage devices" refer to recording media or services used to store data outside a specific organization, such as in enterprises or the cloud, and enable the retrieval of information stored in external systems.

[0068] "Methods for converting to a unified format" refer to processes that organize data existing in various formats into a consistent standard, thereby streamlining subsequent processing.

[0069] "Methods that utilize learning algorithms" refer to methods that use data analysis techniques to compare patterns with past data and detect anomalies, thereby deriving more accurate analysis results.

[0070] "Means of analyzing detailed evaluation items and generating and presenting methods for adjusting evaluations" refers to the process of creating appropriate reduction proposals and negotiation strategies based on detected anomalies and cost-increasing factors, and then presenting them to the user.

[0071] "Incorporating user feedback into training data" refers to accumulating user responses and experiences and incorporating them into a database to be used for future system analysis and performance improvements.

[0072] This invention is a system that supports the scrutiny of construction estimates and negotiation of price reductions. In this system, the server, terminals, and users each play specific roles.

[0073] The server first automatically retrieves evaluation information related to the construction project from an external data storage device. During this process, it collects necessary information via APIs and database connections. The retrieved data is converted to a standard format and stored in the database. Next, the server uses machine learning algorithms to compare the data with historical data and identify which items have abnormal values. This analysis may utilize libraries such as Scikit-learn in Python.

[0074] Users input project evaluation information into the system using a terminal. A dedicated interface is provided, allowing for easy input of details such as project items and unit prices. The entered information is sent to the server and recorded along with other evaluation information. During this process, users can verify the validity of the input data in real time.

[0075] The server then generates and presents strategies to the user for adjusting evaluation items that show abnormalities. These strategies include cost-saving alternatives and negotiation tactics. Based on the proposed strategies, the user engages in negotiations, and the results are fed back to the system via the terminal.

[0076] The server incorporates negotiation results obtained from users as training data to improve the accuracy of future analyses. This feedback loop allows the system to continuously improve, enabling more effective scrutiny and proposal of estimates.

[0077] For example, in a new construction project, if a user enters a material cost that is higher than expected, the server compares this to past projects and suggests changing to standard materials. The user then negotiates based on this suggestion, resulting in cost reduction. In this way, even inexperienced personnel can utilize the system to make appropriate cost adjustments and negotiate effectively.

[0078] An example of a prompt to input into the generating AI model is, "Analyze the cost estimates for a new project and provide specific suggestions for reducing abnormal costs."

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server automatically retrieves evaluation information related to construction projects from external data storage devices. It collects data provided in various formats via APIs and converts it into a standardized format such as CSV or JSON. The input to this process is raw construction data, and the output is formatted data.

[0082] Step 2:

[0083] Users input project evaluation information using the terminal interface. The data entered by the user includes project type, items, quantities, and unit prices. The entered data is checked in real time for format and consistency before being sent to the server. Input is raw data from the user, while output is data that has been verified for consistency.

[0084] Step 3:

[0085] The server stores the collected data and performs comparative analysis within the database using historical and new data. It utilizes machine learning techniques to detect outliers and identify which items exceed the appropriate range. The input is formatted data stored in the database, and the output is the analysis results showing the outliers.

[0086] Step 4:

[0087] Based on the analysis results, the server performs a detailed analysis of the evaluation items and generates alternative plans and negotiation strategies for cost reduction. The generated strategies are displayed to the user, and the proposals include specific methods for cost reduction. The input is the analysis results, and the output is specific strategic proposals.

[0088] Step 5:

[0089] Users conduct negotiations based on strategies provided by the server and input the results into their terminal. They input items subject to negotiation and proposed changes, and the negotiation results are fed back into the system. The input is the negotiation result, and the output is the feedback data.

[0090] Step 6:

[0091] The server takes user negotiation results as training data and continuously improves analysis accuracy. This feedback data is used in subsequent analyses, improving the overall system performance. The input is feedback data, and the output is updated training data.

[0092] (Application Example 1)

[0093] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] In modern construction projects, scrutinizing estimates and reducing costs are critical challenges. However, detecting outliers and developing strategies for negotiating price reductions requires considerable time and expertise. Furthermore, it is difficult to review and adjust estimates in real time at the construction site, which can reduce the overall efficiency of the project. This invention aims to solve these problems and improve the accuracy of estimates and cost management in construction projects.

[0095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0096] In this invention, the server includes means for collecting construction estimate information, means for comparing the collected construction estimate information with past data and detecting anomalies, means for analyzing the breakdown of the construction estimate based on the anomalies and generating a strategy for negotiating price reductions, means for inputting information from the construction site using a remote terminal, and means for instantly transmitting the information received through the remote terminal to the server for analysis. This enables the use of estimate information in real time at the construction site, allowing for efficient scrutiny of estimates and cost management.

[0097] "Construction cost estimate information" refers to detailed data related to the budget and costs of a construction project, including material costs, labor costs, equipment costs, etc.

[0098] "Collection methods" refer to the functions and technologies used to collect construction cost estimate information, including devices and software that automate data acquisition from databases and external systems.

[0099] An "outlier" refers to a numerical value included in construction estimate information that deviates significantly from past data or the normal range, indicating a part that requires review or correction.

[0100] A "strategy for cost reduction negotiations" refers to specific approaches and methods aimed at reducing the costs presented in a construction estimate, and includes plans that may involve proposing alternatives or exploring cost-saving possibilities.

[0101] A "remote terminal" refers to an electronic device that can be connected to outside of a construction site or office, such as a smartphone or tablet, which is a computing device capable of inputting and viewing information.

[0102] The system for implementing this invention first includes a means for efficiently collecting construction cost estimate information. The server automatically retrieves the necessary data from an external database or affiliated system and converts it into a standard format. This makes it possible to consistently process estimate information in different formats.

[0103] Next, users can input estimate information directly from construction sites or offices using a device (e.g., a smartphone or tablet). This device transmits the information to the server in real time, enabling rapid analysis. The server analyzes the data using machine learning libraries such as TENSORFLOW® and detects anomalies. Based on this, it generates strategies useful for price reduction negotiations and proposes them to the user via smartphone or tablet.

[0104] The user proceeds with negotiations based on the proposed strategy and feeds the results back to the server via their terminal. This allows the system to learn and improve the accuracy of future analyses. For example, if the system detects that the material costs for a new construction project are higher than usual, it may suggest switching to more common materials.

[0105] An example of a prompt for a generative AI model would be, "The material costs for the new project are high. Please suggest an alternative." This would allow the system to quickly and accurately provide alternatives, contributing to cost reduction.

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The terminals input estimation information in real time from construction sites or offices. The input data includes detailed information such as construction items, quantities, unit prices, and total amounts. This data is transmitted from the terminals to the server via the network.

[0109] Step 2:

[0110] The server stores the estimate information received from the terminal into a database and converts it to a standard format. The software used here includes data conversion tools to create a consistent dataset even with different formats. This conversion ensures that subsequent analysis processes can be performed accurately.

[0111] Step 3:

[0112] The server analyzes stored data using machine learning models such as TensorFlow. It uses past construction data and current estimation information as input, performs comparative calculations, and identifies anomalies. As a result, it outputs unusual patterns and high-cost items.

[0113] Step 4:

[0114] The server generates a strategy for price reduction negotiations based on the analysis results. Utilizing a generative AI model, it creates candidate alternatives from data input using prompts. Specifically, in response to the user input "Suggest alternatives for expensive materials," it generates the output "A cheaper material X is available."

[0115] Step 5:

[0116] Users review strategies presented by the server on their smartphones or tablets and proceed with negotiations based on those strategies. They then input the negotiation results from their devices and send them back to the server. This feedback data is used later as training data.

[0117] Step 6:

[0118] The server updates the entire system model based on user feedback. This improves the accuracy of future analyses by incorporating the feedback data as training data for machine learning and refining the generated AI model.

[0119] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0120] This invention provides a support system for the construction cost estimation process that also takes into account the user's emotions. This system effectively collects, compares, and analyzes construction cost estimation information, and incorporates an emotion engine to enable the processing of suggestions and feedback that take into account the user's emotional state.

[0121] First, the server automatically collects quotation data from external databases and affiliated information sources. This data is converted to a standard format and stored in an internal database. Users enter quotation information using a terminal, and this information is also sent to the server and stored in a unified format.

[0122] Next, the server analyzes the collected estimate data and compares it with historical data to detect anomalies. For any detected anomalies, it performs a detailed analysis of the breakdown and generates strategies to aid in price reduction negotiations. These strategic proposals are presented to the user, who can then review and implement them on their own device.

[0123] Furthermore, the present invention utilizes an emotion engine to recognize the user's emotional state when receiving user feedback. For example, if a user feels uneasy about the strategy provided, the server uses this emotional information to support the user by adding more detailed explanations or adjusting the suggestions. The emotional information is stored as part of the feedback data and used to improve the system in the future.

[0124] As a concrete example, suppose a user enters an estimate for a new construction project, and the server detects an anomaly. Based on the anomaly, the server creates a proposal for cost reduction and notifies the user. In this process, the emotion engine analyzes the user's reaction, and if it detects that the user is experiencing stress, the server provides supplementary information to reassure them about the proposal. This allows the user to proceed with negotiations with confidence.

[0125] In this way, the system of the present invention provides advanced support for users to perform appropriate and effective estimation scrutiny. The introduction of an emotion engine further deepens user interaction and enables a more sophisticated service.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The server automatically collects construction estimate data from external databases and related systems. This data is retrieved using crawler technology, converted to a standard format, and stored in the database.

[0129] Step 2:

[0130] The user uses a terminal to enter estimate data for a new construction project. The input form includes construction items, required quantities, unit prices, and total amounts, and the entered data is immediately sent to the server.

[0131] Step 3:

[0132] The server compares the received estimate data with previously collected historical data. It applies machine learning algorithms to detect outliers that may be outside the normal range.

[0133] Step 4:

[0134] The server further analyzes the data in which anomalies were detected, breaking down cost components such as material costs and labor costs. It identifies which elements are contributing to the increase in costs and looks for areas where improvements can be made.

[0135] Step 5:

[0136] Based on the detected anomalies, the server generates an effective strategy for price reduction negotiations. This strategy includes suggesting alternative materials and specific cost-saving possibilities based on past success stories.

[0137] Step 6:

[0138] The server provides the generated strategy to the user, who then reviews it on their device. During this process, the emotion engine recognizes the user's emotions from their facial expressions and voice, and analyzes how the user is receiving the proposal.

[0139] Step 7:

[0140] The user initiates negotiations with the supplier based on the proposal. They input the negotiation results and emotional feedback into their device and send it to the server.

[0141] Step 8:

[0142] The server receives user feedback and sentiment information, and stores it as training data for future analysis and suggestion generation. This improves the user experience and the accuracy of suggestions in the future.

[0143] (Example 2)

[0144] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0145] In the estimation process for construction activities, not only is it difficult to detect data inconsistencies and anomalies, but user sentiment can be ignored, leading to inappropriate negotiation outcomes. In such situations, the accuracy of estimates and the effectiveness of negotiations are compromised, necessitating new solutions.

[0146] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0147] In this invention, the server includes means for collecting evaluation information related to construction activities, means for comparing the collected evaluation information with past records to detect anomalies, and means for analyzing the breakdown of evaluations based on the anomalies and generating measures to reduce costs. This improves the accuracy and efficiency of the estimation process and enables useful suggestions that take into account the user's feelings.

[0148] "Construction activities" refer to a set of tasks and operations related to the design, planning, construction, renovation, or maintenance of buildings and structures.

[0149] "Evaluation information" refers to information including costs, materials, work details, and related data associated with construction work.

[0150] An "abnormality" refers to a value or pattern that deviates from past records or standard judgment criteria, and is considered to be outside the normal range.

[0151] "Measures to reduce costs" refers to proposals and plans to reduce unnecessary expenses in the estimation process and optimize the process.

[0152] A "server" refers to a computer system that manages and executes the collection, analysis, storage, and interaction with users of information.

[0153] An "emotion analysis engine" refers to a program or mechanism that uses natural language processing technology to analyze a user's emotional state based on their input and feedback.

[0154] "Natural language processing technology" refers to all technologies and methods for analyzing, processing, and understanding human language using computers.

[0155] This invention is a system for effectively supporting the estimation process in construction activities, and by taking user emotions into consideration, it enables more refined proposals and feedback.

[0156] First, the server automatically collects evaluation information related to construction activities from external databases and partners. This data is converted into a common format and stored in an internal information storage device. Specific tools used for collection include a "data collection API" and an "information ingestion engine."

[0157] Next, the user enters new quote information using a terminal. This input is done via a dedicated exit or a simplified input form, and the entered data is sent to the server and integrated with existing records.

[0158] Subsequently, the server analyzes the collected evaluation information and compares it with past records to detect anomalies. This analysis uses a "data analysis engine" and an "anomaly detection algorithm." If an anomaly is detected, the server further analyzes its details and generates strategies to reduce the amount.

[0159] The proposed solutions are sent to the user via email or a dedicated user interface. The user can review them on their device and proceed with negotiations as needed. During this process, the "emotion analysis engine" understands the user's emotional state and adjusts the proposed solutions as necessary. Natural language processing technology is used for emotion analysis.

[0160] As a concrete example, consider a user who has entered an estimate for a new construction project. When the server detects an anomaly in the project, it forms and notifies the user of possible price adjustments. In this case, the system analyzes the user's feelings of anxiety regarding the proposal and provides additional information to alleviate those anxieties. This leads to more successful negotiations.

[0161] Here are some examples of prompts to input into a generative AI model:

[0162] "Please register the estimate data for the new project. If any anomalies are detected, propose specific adjustment measures and analyze user sentiment towards the proposals. Also, provide additional information to alleviate concerns."

[0163] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0164] Step 1:

[0165] The server collects evaluation information related to construction activities from external sources and databases. Input is raw data obtained via APIs and scraping tools. The server converts this raw data into a common format (e.g., CSV, JSON) and stores it in an internal database. This process ensures data consistency and integrity.

[0166] Step 2:

[0167] Users input new quotation information into the system using a terminal. The input is data based on a form provided through the user interface. The terminal sends the input data to the server, where it is integrated with existing evaluation information. The server standardizes the data format, checks for inconsistencies, and then stores it in the database.

[0168] Step 3:

[0169] The server analyzes the collected evaluation information. This analysis uses algorithms to detect anomalies by comparing them with past records. The input is integrated evaluation information, and the output is a list of the parts where anomalies were detected. The server analyzes the breakdown of the anomalies in detail and stores the analysis results in an internal database.

[0170] Step 4:

[0171] The server generates specific measures to reduce costs based on the results of the anomaly analysis. The input is the result of the anomaly analysis, and the output is the generated proposal. The server uses email or a dedicated user interface to notify the user of this proposal.

[0172] Step 5:

[0173] The user reviews the policies sent from the server via their device. The input is the proposal provided by the server, and the output is the user's feedback. The device collects the user's feedback and sends it to the server.

[0174] Step 6:

[0175] The server uses an emotion analysis engine to analyze the emotional state contained in the user's feedback. The input is the user's feedback, and the output is the detected emotional state. Natural language processing techniques are used for emotion analysis.

[0176] Step 7:

[0177] The server adjusts the suggestions as needed based on the sentiment analysis results. The input is the user's emotional state and the original suggestion, and the output is the revised suggestion. The server then notifies the user of the revised suggestion again and awaits further feedback.

[0178] (Application Example 2)

[0179] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0180] In the construction estimation process, it was difficult to detect anomalies in the collected data, generate effective negotiation strategies, and provide support that took into account the user's emotional state. Traditional systems failed to improve the accuracy of estimates and the quality of proposals by incorporating user reactions and emotions, resulting in a lack of improvement in the user experience.

[0181] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0182] In this invention, the server includes means for collecting construction estimate information, means for comparing the collected construction estimate information with past data to detect anomalies, and means for analyzing the breakdown of the construction estimate based on the anomalies and generating a strategy for negotiating price reductions. This makes it possible to propose strategies that take into account the user's emotional state in the construction estimate, and to proceed with negotiations while providing a sense of security.

[0183] "Construction cost estimate information" is a collection of data that calculates the expenses and resource requirements related to construction work.

[0184] An "outlier" is a value that differs significantly from past data or predicted values, and refers to data that requires special attention.

[0185] "Negotiating a price reduction" refers to the negotiation process aimed at lowering the proposed estimated cost.

[0186] A "strategy" is a set of actions planned to achieve a goal, and is particularly used to conduct negotiations effectively.

[0187] "Emotional state" refers to the user's psychological response and the degree of their emotions, and is particularly used to evaluate the user's response to system proposals.

[0188] "Feedback data" refers to data on user reactions and evaluations, collected to help improve the system.

[0189] The system for carrying out this invention includes a program that comprehensively performs tasks such as collecting construction cost estimate information, detecting anomalies, generating cost reduction negotiation strategies, and recognizing and processing user emotions. The processing details of this program are described below.

[0190] The server automatically collects construction estimate information from external sources and databases, converts it to a standard format, and then stores it in an internal database. Users can input the necessary estimate information using devices such as smartphones or smart glasses, and this information is sent to the server and stored in the same standard format.

[0191] The server uses the collected data to compare it with historical estimates and detects outliers using algorithms. Pandas and NumPy are used as data analysis software for this data calculation. For detected outliers, the system analyzes the details and automatically generates cost-reduction strategies. These strategy proposals are sent to the user's terminal for review and application.

[0192] Furthermore, the server uses an emotion recognition library (for example, Microsoft® Azure®'s Emotion API) to analyze the user's emotional state. If the user feels anxious about the proposed strategy, the system takes that emotional state into consideration and provides additional information to reassure them. In this process, emotional information is collected and stored as feedback data, which is used to improve the quality of future analyses and strategy proposals.

[0193] As a concrete example, a user uses smart glasses to capture on-site video, which is immediately transmitted to a server via the cloud for analysis of the estimation information. During this process, a generative AI model is used to detect stress and anxiety, and to propose appropriate strategies. Based on the user's feedback, the following prompt example is used: "The price quoted for today's project estimate exceeds the predicted cost. Please generate a reassuring proposal based on sentiment analysis."

[0194] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0195] Step 1:

[0196] The server automatically collects construction cost estimate information from external sources and databases. The input at this stage is raw data obtained from various sources, which the server converts to a standard format and stores in its internal database. This process ensures data consistency and integrity.

[0197] Step 2:

[0198] Users input estimate-related information collected on-site using their devices. This input is done through various interfaces, such as camera apps and voice input, and is sent to the server in real time. The server converts the received data into a standard format and adds it to its internal database.

[0199] Step 3:

[0200] The server uses collected estimated data to detect anomalies by comparing it with historical data. This detection process employs statistical methods and data analysis tools such as Pandas and NumPy. The inputs are current estimated data and historical data, and the output is the detected anomalies and their causal analysis.

[0201] Step 4:

[0202] The server analyzes the breakdown of detected anomalies and generates a strategy for price reduction negotiations. This process uses algorithms to analyze data points in detail and identify elements that can be reduced. The output is a draft negotiation strategy that the user can use as a reference.

[0203] Step 5:

[0204] Users review strategic proposals presented by the server via their devices. They then assess whether the proposals are acceptable and provide feedback. This feedback is sent to the server for system improvement. Sentiment recognition is also performed simultaneously.

[0205] Step 6:

[0206] The server uses an emotion recognition library to analyze the user's emotional state. It analyzes user input, feedback tone, facial expressions, and other input data, and adjusts the suggestions based on detected anxiety or stress. The output consists of the adjusted suggestions and additional information as needed.

[0207] Step 7:

[0208] Users review additional information based on their emotions and provide further feedback. The server uses this feedback to improve the accuracy of future data analysis and the quality of strategic recommendations.

[0209] Throughout each step, the system interactively utilizes the generated AI model, improving the quality of the user experience by using the following prompt: "The price quoted for today's project estimate exceeds the predicted cost. Please generate a reassuring proposal based on sentiment analysis."

[0210] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0211] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0212] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0213] [Second Embodiment]

[0214] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0215] As shown in Figure 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.

[0216] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0217] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0218] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0219] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0220] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0221] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0222] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0223] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0224] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0225] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0226] This invention is a system that supports the scrutiny of construction estimates and negotiation of price reductions. The system mainly consists of the following components, each of which plays a specific role in achieving efficiency and accuracy in the estimation process.

[0227] First, the server collects estimate information related to the construction project. This is done by automatically retrieving data from external databases and partner systems. The collected data is then converted into a standard format. This allows for consistent processing of estimate information provided in different formats.

[0228] Next, the user enters new construction estimate information through their device. Here, an interface is provided for entering details such as construction items, quantities, unit prices, and total amounts. This information is instantly sent to the server and stored in the database along with other data.

[0229] The stored data is analyzed by the server. It compares the information sent from the device with similar past data to identify abnormal values ​​or items that may exceed the appropriate range. This analysis utilizes machine learning techniques to produce more accurate results.

[0230] Next, the server analyzes the breakdown of each item in the construction estimate in detail based on the analysis results. It identifies which elements are causing high costs and proposes a strategy to the user for negotiating price reductions. This strategy includes potential alternatives and items where costs can be reduced.

[0231] Finally, the user conducts negotiations based on the presented strategy and inputs the results into the terminal. The server analyzes this feedback and automatically incorporates it as training data for the system. This improves the accuracy of future analyses.

[0232] As a concrete example, a user inputs an estimate for a new base station construction project. In this case, the server detects that the material costs are higher than in previous projects and suggests changing to standard materials. The user can then negotiate based on this advice to reduce costs. In this way, even inexperienced personnel can use the system to conduct proper and effective estimate reviews and negotiations.

[0233] The following describes the processing flow.

[0234] Step 1:

[0235] The server periodically collects the latest construction estimate data from external databases and affiliated systems. It uses a crawler to extract the necessary data and stores it in a local database.

[0236] Step 2:

[0237] The user enters new quote information via a terminal. Through the user interface, the user enters the work items, quantities, unit prices, and total amount into the system, and the entered data is immediately transmitted to the server.

[0238] Step 3:

[0239] The server converts the received estimate data into a standard format. In this process, the data is refined, inconsistencies and omissions are corrected, and it is stored in the database in a unified format.

[0240] Step 4:

[0241] The server analyzes standardized quotation data. By comparing it with historical data, it verifies standard unit prices and reasonableness, and detects values ​​that are unusually high or low.

[0242] Step 5:

[0243] The server then performs a more detailed analysis of the breakdown of each construction item based on the analysis results. It breaks down cost factors such as material costs, labor costs, and machinery costs to identify which elements are influencing the increase in costs.

[0244] Step 6:

[0245] The server generates effective strategies for price reduction negotiations. Based on detected anomalies, it provides users with specific suggestions that consider cost-reduction alternatives and successful examples from other projects.

[0246] Step 7:

[0247] Users negotiate with suppliers using the provided price reduction negotiation strategies as a reference and input the results into their terminal. The input feedback is analyzed on the server and stored as training data to be used for future analysis.

[0248] Step 8:

[0249] The server improves the system's accuracy based on user feedback. By analyzing the feedback and updating the machine learning model, the accuracy of future estimate refinements and price reduction negotiation suggestions can be further enhanced.

[0250] (Example 1)

[0251] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0252] Estimating construction projects often involves a complex interplay of diverse data, making it challenging to quickly and accurately detect anomalies and implement appropriate cost reductions. Furthermore, effectively utilizing accumulated historical negotiation data to learn from and improve the accuracy of future estimates is essential.

[0253] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0254] In this invention, the server includes means for automatically acquiring evaluation information related to construction work from an external data storage device and converting the acquired data into a unified format; means for using the evaluation information to compare it with past information and utilizing a learning algorithm to identify abnormal values; and means for analyzing detailed evaluation items based on the identified abnormal values ​​and generating and presenting methods for adjusting the evaluation. This makes it possible to efficiently analyze construction estimates and make appropriate adjustments based on the results. Furthermore, by incorporating user feedback into the learning data to improve the accuracy of subsequent analyses, the learning effect is also improved.

[0255] "Construction-related evaluation information" refers to data on costs and work details in construction and repair projects, and is used for scrutinizing estimates and budgets.

[0256] "External data storage devices" refer to recording media or services used to store data outside a specific organization, such as in enterprises or the cloud, and enable the retrieval of information stored in external systems.

[0257] "Methods for converting to a unified format" refer to processes that organize data existing in various formats into a consistent standard, thereby streamlining subsequent processing.

[0258] "Methods that utilize learning algorithms" refer to methods that use data analysis techniques to compare patterns with past data and detect anomalies, thereby deriving more accurate analysis results.

[0259] "Means of analyzing detailed evaluation items and generating and presenting methods for adjusting evaluations" refers to the process of creating appropriate reduction proposals and negotiation strategies based on detected anomalies and cost-increasing factors, and then presenting them to the user.

[0260] "Incorporating user feedback into training data" refers to accumulating user responses and experiences and incorporating them into a database to be used for future system analysis and performance improvements.

[0261] This invention is a system that supports the scrutiny of construction estimates and negotiation of price reductions. In this system, the server, terminals, and users each play specific roles.

[0262] The server first automatically retrieves evaluation information related to the construction project from an external data storage device. During this process, it collects necessary information via APIs and database connections. The retrieved data is converted to a standard format and stored in the database. Next, the server uses machine learning algorithms to compare the data with historical data and identify which items have abnormal values. This analysis may utilize libraries such as Scikit-learn in Python.

[0263] Users input project evaluation information into the system using a terminal. A dedicated interface is provided, allowing for easy input of details such as project items and unit prices. The entered information is sent to the server and recorded along with other evaluation information. During this process, users can verify the validity of the input data in real time.

[0264] The server then generates and presents strategies to the user for adjusting evaluation items that show abnormalities. These strategies include cost-saving alternatives and negotiation tactics. Based on the proposed strategies, the user engages in negotiations, and the results are fed back to the system via the terminal.

[0265] The server incorporates negotiation results obtained from users as training data to improve the accuracy of future analyses. This feedback loop allows the system to continuously improve, enabling more effective scrutiny and proposal of estimates.

[0266] For example, in a new construction project, if a user enters a material cost that is higher than expected, the server compares this to past projects and suggests changing to standard materials. The user then negotiates based on this suggestion, resulting in cost reduction. In this way, even inexperienced personnel can utilize the system to make appropriate cost adjustments and negotiate effectively.

[0267] An example of a prompt to input into the generating AI model is, "Analyze the cost estimates for a new project and provide specific suggestions for reducing abnormal costs."

[0268] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0269] Step 1:

[0270] The server automatically retrieves evaluation information related to construction projects from external data storage devices. It collects data provided in various formats via APIs and converts it into a standardized format such as CSV or JSON. The input to this process is raw construction data, and the output is formatted data.

[0271] Step 2:

[0272] Users input project evaluation information using the terminal interface. The data entered by the user includes project type, items, quantities, and unit prices. The entered data is checked in real time for format and consistency before being sent to the server. Input is raw data from the user, while output is data that has been verified for consistency.

[0273] Step 3:

[0274] The server stores the collected data and performs comparative analysis within the database using historical and new data. It utilizes machine learning techniques to detect outliers and identify which items exceed the appropriate range. The input is formatted data stored in the database, and the output is the analysis results showing the outliers.

[0275] Step 4:

[0276] Based on the analysis results, the server conducts a detailed analysis of the evaluation items and generates alternative solutions and negotiation strategies for cost reduction. The generated strategies are displayed to the user, and the proposed content includes specific methods for cost reduction. The input is the analysis results, and the output is a specific strategic proposal.

[0277] Step 5:

[0278] The user conducts negotiations based on the strategies provided by the server and inputs the results into the terminal. Items to be negotiated and proposed changes are input, and the negotiation results are fed back to the system. The input is the negotiation results, and the output is the fed-back data.

[0279] Step 6:

[0280] The server takes in the negotiation results from the user as learning data and continuously improves the analysis accuracy. This feedback data is utilized in subsequent analyses, and the performance of the entire system is improved. The input is the feedback data, and the output is the updated learning data.

[0281] (Application Example 1)

[0282] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0283] In modern construction projects, the scrutiny of estimates and cost reduction are important issues. On the other hand, formulating strategies for outlier detection and reduction negotiation requires a lot of time and specialized knowledge. Also, it is difficult to confirm and adjust estimates in real time at the construction site, which may reduce the efficiency of the entire project. This invention aims to solve these problems and improve the estimation accuracy and cost management of construction projects.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0285] In this invention, the server includes means for collecting construction estimate information, means for comparing the collected construction estimate information with past data to detect outliers, means for analyzing the breakdown of the construction estimate based on the outliers and generating a strategy for negotiation for cost reduction, means for inputting information from the construction site using a remote terminal, and means for immediately transmitting the information received through the remote terminal to the server for use in analysis. Thereby, even at the construction site, the estimate information can be utilized in real time, enabling efficient scrutiny of estimates and cost management.

[0286] "Construction estimate information" refers to detailed data related to the budget and costs of a construction project, including material costs, labor costs, equipment costs, etc.

[0287] "Collection means" refers to the functions and technologies used to collect construction estimate information, and refers to devices and software that automate data acquisition from databases and external systems.

[0288] "Outlier" refers to a value that is significantly deviated from past data or the normal range among the numerical values included in the construction estimate information, indicating a part that requires consideration and correction.

[0289] "Strategy for negotiation for cost reduction" refers to specific approaches and methods aimed at reducing the costs presented in the construction estimate, and is a plan including the proposal of alternatives and the possibility of cost reduction.

[0290] "Remote terminal" refers to an electronic device that can be connected even outside the construction site or office, and is a computing device such as a smartphone or tablet that enables input and browsing of information.

[0291] The system for implementing this invention first includes a means for efficiently collecting construction cost estimate information. The server automatically retrieves the necessary data from an external database or affiliated system and converts it into a standard format. This makes it possible to consistently process estimate information in different formats.

[0292] Next, users can input estimate information directly from construction sites or offices using a device (e.g., a smartphone or tablet). This device sends the information to the server in real time, enabling rapid analysis. The server analyzes the data using machine learning libraries such as TensorFlow and detects anomalies. Based on this, it generates strategies useful for price reduction negotiations and proposes them to the user via smartphone or tablet.

[0293] The user proceeds with negotiations based on the proposed strategy and feeds the results back to the server via their terminal. This allows the system to learn and improve the accuracy of future analyses. For example, if the system detects that the material costs for a new construction project are higher than usual, it may suggest switching to more common materials.

[0294] An example of a prompt for a generative AI model would be, "The material costs for the new project are high. Please suggest an alternative." This would allow the system to quickly and accurately provide alternatives, contributing to cost reduction.

[0295] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0296] Step 1:

[0297] The terminals input estimation information in real time from construction sites or offices. The input data includes detailed information such as construction items, quantities, unit prices, and total amounts. This data is transmitted from the terminals to the server via the network.

[0298] Step 2:

[0299] The server stores the estimate information received from the terminal into a database and converts it to a standard format. The software used here includes data conversion tools to create a consistent dataset even with different formats. This conversion ensures that subsequent analysis processes can be performed accurately.

[0300] Step 3:

[0301] The server analyzes stored data using machine learning models such as TensorFlow. It uses past construction data and current estimation information as input, performs comparative calculations, and identifies anomalies. As a result, it outputs unusual patterns and high-cost items.

[0302] Step 4:

[0303] The server generates a strategy for price reduction negotiations based on the analysis results. Utilizing a generative AI model, it creates candidate alternatives from data input using prompts. Specifically, in response to the user input "Suggest alternatives for expensive materials," it generates the output "A cheaper material X is available."

[0304] Step 5:

[0305] Users review strategies presented by the server on their smartphones or tablets and proceed with negotiations based on those strategies. They then input the negotiation results from their devices and send them back to the server. This feedback data is used later as training data.

[0306] Step 6:

[0307] The server updates the entire system model based on user feedback. This improves the accuracy of future analyses by incorporating the feedback data as training data for machine learning and refining the generated AI model.

[0308] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion specific model 59 and perform specific processing using the user's emotion.

[0309] The present invention provides a support system that takes into account the user's emotion in the estimation process of construction work. This system incorporates an emotion engine to effectively collect, compare, and analyze construction estimate information, and further enable the processing of proposals and feedback considering the user's emotional state.

[0310] First, the server automatically collects estimate data from an external database or a partnered information source. This data is converted into a standard format and stored in an internal database. The user inputs estimate information using a terminal, and this information is also sent to the server and stored in a unified format.

[0311] Next, the server analyzes the collected estimate data and detects outliers by comparing it with past data. For the detected outliers, the breakdown is analyzed in detail, and a strategy useful for price reduction negotiation is generated. This strategy proposal is presented to the user, and the user can confirm and execute it on their own terminal.

[0312] Furthermore, the present invention utilizes the emotion engine to recognize the user's emotional state during feedback from the user. For example, when the user feels不安 about the provided strategy, the server supports the user by adding a more detailed explanation or adjusting the proposed content based on this emotion information. The emotion information is stored as part of the feedback data and used for future improvement of the system.

[0313] As a concrete example, suppose a user enters an estimate for a new construction project, and the server detects an anomaly. Based on the anomaly, the server creates a proposal for cost reduction and notifies the user. In this process, the emotion engine analyzes the user's reaction, and if it detects that the user is experiencing stress, the server provides supplementary information to reassure them about the proposal. This allows the user to proceed with negotiations with confidence.

[0314] In this way, the system of the present invention provides advanced support for users to perform appropriate and effective estimation scrutiny. The introduction of an emotion engine further deepens user interaction and enables a more sophisticated service.

[0315] The following describes the processing flow.

[0316] Step 1:

[0317] The server automatically collects construction estimate data from external databases and related systems. This data is retrieved using crawler technology, converted to a standard format, and stored in the database.

[0318] Step 2:

[0319] The user uses a terminal to enter estimate data for a new construction project. The input form includes construction items, required quantities, unit prices, and total amounts, and the entered data is immediately sent to the server.

[0320] Step 3:

[0321] The server compares the received estimate data with previously collected historical data. It applies machine learning algorithms to detect outliers that may be outside the normal range.

[0322] Step 4:

[0323] The server further analyzes the data in which anomalies were detected, breaking down cost components such as material costs and labor costs. It identifies which elements are contributing to the increase in costs and looks for areas where improvements can be made.

[0324] Step 5:

[0325] Based on the detected anomalies, the server generates an effective strategy for price reduction negotiations. This strategy includes suggesting alternative materials and specific cost-saving possibilities based on past success stories.

[0326] Step 6:

[0327] The server provides the generated strategy to the user, who then reviews it on their device. During this process, the emotion engine recognizes the user's emotions from their facial expressions and voice, and analyzes how the user is receiving the proposal.

[0328] Step 7:

[0329] The user initiates negotiations with the supplier based on the proposal. They input the negotiation results and emotional feedback into their device and send it to the server.

[0330] Step 8:

[0331] The server receives user feedback and sentiment information, and stores it as training data for future analysis and suggestion generation. This improves the user experience and the accuracy of suggestions in the future.

[0332] (Example 2)

[0333] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0334] In the estimation process for construction activities, not only is it difficult to detect data inconsistencies and anomalies, but user sentiment can be ignored, leading to inappropriate negotiation outcomes. In such situations, the accuracy of estimates and the effectiveness of negotiations are compromised, necessitating new solutions.

[0335] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0336] In this invention, the server includes means for collecting evaluation information related to construction activities, means for comparing the collected evaluation information with past records to detect anomalies, and means for analyzing the breakdown of evaluations based on the anomalies and generating measures to reduce costs. This improves the accuracy and efficiency of the estimation process and enables useful suggestions that take into account the user's feelings.

[0337] "Construction activities" refer to a set of tasks and operations related to the design, planning, construction, renovation, or maintenance of buildings and structures.

[0338] "Evaluation information" refers to information including costs, materials, work details, and related data associated with construction work.

[0339] An "abnormality" refers to a value or pattern that deviates from past records or standard judgment criteria, and is considered to be outside the normal range.

[0340] "Measures to reduce costs" refers to proposals and plans to reduce unnecessary expenses in the estimation process and optimize the process.

[0341] A "server" refers to a computer system that manages and executes the collection, analysis, storage, and interaction with users of information.

[0342] An "emotion analysis engine" refers to a program or mechanism that uses natural language processing technology to analyze a user's emotional state based on their input and feedback.

[0343] "Natural language processing technology" refers to all technologies and methods for analyzing, processing, and understanding human language using computers.

[0344] This invention is a system for effectively supporting the estimation process in construction activities, and by taking user emotions into consideration, it enables more refined proposals and feedback.

[0345] First, the server automatically collects evaluation information related to construction activities from external databases and partners. This data is converted into a common format and stored in an internal information storage device. Specific tools used for collection include a "data collection API" and an "information ingestion engine."

[0346] Next, the user enters new quote information using a terminal. This input is done via a dedicated exit or a simplified input form, and the entered data is sent to the server and integrated with existing records.

[0347] Subsequently, the server analyzes the collected evaluation information and compares it with past records to detect anomalies. This analysis uses a "data analysis engine" and an "anomaly detection algorithm." If an anomaly is detected, the server further analyzes its details and generates strategies to reduce the amount.

[0348] The proposed solutions are sent to the user via email or a dedicated user interface. The user can review them on their device and proceed with negotiations as needed. During this process, the "emotion analysis engine" understands the user's emotional state and adjusts the proposed solutions as necessary. Natural language processing technology is used for emotion analysis.

[0349] As a concrete example, consider a user who has entered an estimate for a new construction project. When the server detects an anomaly in the project, it forms and notifies the user of possible price adjustments. In this case, the system analyzes the user's feelings of anxiety regarding the proposal and provides additional information to alleviate those anxieties. This leads to more successful negotiations.

[0350] Here are some examples of prompts to input into a generative AI model:

[0351] "Please register the estimate data for the new project. If any anomalies are detected, propose specific adjustment measures and analyze user sentiment towards the proposals. Also, provide additional information to alleviate concerns."

[0352] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0353] Step 1:

[0354] The server collects evaluation information related to construction activities from external sources and databases. Input is raw data obtained via APIs and scraping tools. The server converts this raw data into a common format (e.g., CSV, JSON) and stores it in an internal database. This process ensures data consistency and integrity.

[0355] Step 2:

[0356] Users input new quotation information into the system using a terminal. The input is data based on a form provided through the user interface. The terminal sends the input data to the server, where it is integrated with existing evaluation information. The server standardizes the data format, checks for inconsistencies, and then stores it in the database.

[0357] Step 3:

[0358] The server analyzes the collected evaluation information. This analysis uses algorithms to detect anomalies by comparing them with past records. The input is integrated evaluation information, and the output is a list of the parts where anomalies were detected. The server analyzes the breakdown of the anomalies in detail and stores the analysis results in an internal database.

[0359] Step 4:

[0360] The server generates specific measures to reduce costs based on the results of the anomaly analysis. The input is the result of the anomaly analysis, and the output is the generated proposal. The server uses email or a dedicated user interface to notify the user of this proposal.

[0361] Step 5:

[0362] The user reviews the policies sent from the server via their device. The input is the proposal provided by the server, and the output is the user's feedback. The device collects the user's feedback and sends it to the server.

[0363] Step 6:

[0364] The server uses an emotion analysis engine to analyze the emotional state contained in the user's feedback. The input is the user's feedback, and the output is the detected emotional state. Natural language processing techniques are used for emotion analysis.

[0365] Step 7:

[0366] The server adjusts the suggestions as needed based on the sentiment analysis results. The input is the user's emotional state and the original suggestion, and the output is the revised suggestion. The server then notifies the user of the revised suggestion again and awaits further feedback.

[0367] (Application Example 2)

[0368] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0369] In the construction estimation process, it was difficult to detect anomalies in the collected data, generate effective negotiation strategies, and provide support that took into account the user's emotional state. Traditional systems failed to improve the accuracy of estimates and the quality of proposals by incorporating user reactions and emotions, resulting in a lack of improvement in the user experience.

[0370] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0371] In this invention, the server includes means for collecting construction estimate information, means for comparing the collected construction estimate information with past data to detect anomalies, and means for analyzing the breakdown of the construction estimate based on the anomalies and generating a strategy for negotiating price reductions. This makes it possible to propose strategies that take into account the user's emotional state in the construction estimate, and to proceed with negotiations while providing a sense of security.

[0372] "Construction cost estimate information" is a collection of data that calculates the expenses and resource requirements related to construction work.

[0373] An "outlier" is a value that differs significantly from past data or predicted values, and refers to data that requires special attention.

[0374] "Negotiating a price reduction" refers to the negotiation process aimed at lowering the proposed estimated cost.

[0375] A "strategy" is a set of actions planned to achieve a goal, and is particularly used to conduct negotiations effectively.

[0376] "Emotional state" refers to the user's psychological response and the degree of their emotions, and is particularly used to evaluate the user's response to system proposals.

[0377] "Feedback data" refers to data on user reactions and evaluations, collected to help improve the system.

[0378] The system for carrying out this invention includes a program that comprehensively performs tasks such as collecting construction cost estimate information, detecting anomalies, generating cost reduction negotiation strategies, and recognizing and processing user emotions. The processing details of this program are described below.

[0379] The server automatically collects construction estimate information from external sources and databases, converts it to a standard format, and then stores it in an internal database. Users can input the necessary estimate information using devices such as smartphones or smart glasses, and this information is sent to the server and stored in the same standard format.

[0380] The server uses the collected data to compare it with historical estimates and detects outliers using algorithms. Pandas and NumPy are used as data analysis software for this data calculation. For detected outliers, the system analyzes the details and automatically generates cost-reduction strategies. These strategy proposals are sent to the user's terminal for review and application.

[0381] Furthermore, the server uses an emotion recognition library (for example, Microsoft Azure's Emotion API) to analyze the user's emotional state. If the user feels anxious about the proposed strategy, the system takes that emotional state into consideration and provides additional information to reassure them. In this process, emotional information is collected and stored as feedback data, which is used to improve the quality of future analyses and strategy proposals.

[0382] As a concrete example, a user uses smart glasses to capture on-site video, which is immediately transmitted to a server via the cloud for analysis of the estimation information. During this process, a generative AI model is used to detect stress and anxiety, and to propose appropriate strategies. Based on the user's feedback, the following prompt example is used: "The price quoted for today's project estimate exceeds the predicted cost. Please generate a reassuring proposal based on sentiment analysis."

[0383] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0384] Step 1:

[0385] The server automatically collects construction cost estimate information from external sources and databases. The input at this stage is raw data obtained from various sources, which the server converts to a standard format and stores in its internal database. This process ensures data consistency and integrity.

[0386] Step 2:

[0387] Users input estimate-related information collected on-site using their devices. This input is done through various interfaces, such as camera apps and voice input, and is sent to the server in real time. The server converts the received data into a standard format and adds it to its internal database.

[0388] Step 3:

[0389] The server uses collected estimated data to detect anomalies by comparing it with historical data. This detection process employs statistical methods and data analysis tools such as Pandas and NumPy. The inputs are current estimated data and historical data, and the output is the detected anomalies and their causal analysis.

[0390] Step 4:

[0391] The server analyzes the breakdown of detected anomalies and generates a strategy for price reduction negotiations. This process uses algorithms to analyze data points in detail and identify elements that can be reduced. The output is a draft negotiation strategy that the user can use as a reference.

[0392] Step 5:

[0393] Users review strategic proposals presented by the server via their devices. They then assess whether the proposals are acceptable and provide feedback. This feedback is sent to the server for system improvement. Sentiment recognition is also performed simultaneously.

[0394] Step 6:

[0395] The server uses an emotion recognition library to analyze the user's emotional state. It analyzes user input, feedback tone, facial expressions, and other input data, and adjusts the suggestions based on detected anxiety or stress. The output consists of the adjusted suggestions and additional information as needed.

[0396] Step 7:

[0397] Users review additional information based on their emotions and provide further feedback. The server uses this feedback to improve the accuracy of future data analysis and the quality of strategic recommendations.

[0398] Throughout each step, the system interactively utilizes the generated AI model, improving the quality of the user experience by using the following prompt: "The price quoted for today's project estimate exceeds the predicted cost. Please generate a reassuring proposal based on sentiment analysis."

[0399] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0400] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0401] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0402] [Third Embodiment]

[0403] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0404] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0405] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0406] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0407] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0408] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0409] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0410] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0411] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0412] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0413] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0414] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0415] This invention is a system that supports the scrutiny of construction estimates and negotiation of price reductions. The system mainly consists of the following components, each of which plays a specific role in achieving efficiency and accuracy in the estimation process.

[0416] First, the server collects estimate information related to the construction project. This is done by automatically retrieving data from external databases and partner systems. The collected data is then converted into a standard format. This allows for consistent processing of estimate information provided in different formats.

[0417] Next, the user enters new construction estimate information through their device. Here, an interface is provided for entering details such as construction items, quantities, unit prices, and total amounts. This information is instantly sent to the server and stored in the database along with other data.

[0418] The stored data is analyzed by the server. It compares the information sent from the device with similar past data to identify abnormal values ​​or items that may exceed the appropriate range. This analysis utilizes machine learning techniques to produce more accurate results.

[0419] Next, the server analyzes the breakdown of each item in the construction estimate in detail based on the analysis results. It identifies which elements are causing high costs and proposes a strategy to the user for negotiating price reductions. This strategy includes potential alternatives and items where costs can be reduced.

[0420] Finally, the user conducts negotiations based on the presented strategy and inputs the results into the terminal. The server analyzes this feedback and automatically incorporates it as training data for the system. This improves the accuracy of future analyses.

[0421] As a concrete example, a user inputs an estimate for a new base station construction project. In this case, the server detects that the material costs are higher than in previous projects and suggests changing to standard materials. The user can then negotiate based on this advice to reduce costs. In this way, even inexperienced personnel can use the system to conduct proper and effective estimate reviews and negotiations.

[0422] The following describes the processing flow.

[0423] Step 1:

[0424] The server periodically collects the latest construction estimate data from external databases and affiliated systems. It uses a crawler to extract the necessary data and stores it in a local database.

[0425] Step 2:

[0426] The user enters new quote information via a terminal. Through the user interface, the user enters the work items, quantities, unit prices, and total amount into the system, and the entered data is immediately transmitted to the server.

[0427] Step 3:

[0428] The server converts the received estimate data into a standard format. In this process, the data is refined, inconsistencies and omissions are corrected, and it is stored in the database in a unified format.

[0429] Step 4:

[0430] The server analyzes standardized quotation data. By comparing it with historical data, it verifies standard unit prices and reasonableness, and detects values ​​that are unusually high or low.

[0431] Step 5:

[0432] The server then performs a more detailed analysis of the breakdown of each construction item based on the analysis results. It breaks down cost factors such as material costs, labor costs, and machinery costs to identify which elements are influencing the increase in costs.

[0433] Step 6:

[0434] The server generates effective strategies for price reduction negotiations. Based on detected anomalies, it provides users with specific suggestions that consider cost-reduction alternatives and successful examples from other projects.

[0435] Step 7:

[0436] Users negotiate with suppliers using the provided price reduction negotiation strategies as a reference and input the results into their terminal. The input feedback is analyzed on the server and stored as training data to be used for future analysis.

[0437] Step 8:

[0438] The server improves the system's accuracy based on user feedback. By analyzing the feedback and updating the machine learning model, the accuracy of future estimate refinements and price reduction negotiation suggestions can be further enhanced.

[0439] (Example 1)

[0440] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0441] Estimating construction projects often involves a complex interplay of diverse data, making it challenging to quickly and accurately detect anomalies and implement appropriate cost reductions. Furthermore, effectively utilizing accumulated historical negotiation data to learn from and improve the accuracy of future estimates is essential.

[0442] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0443] In this invention, the server includes means for automatically acquiring evaluation information related to construction work from an external data storage device and converting the acquired data into a unified format; means for using the evaluation information to compare it with past information and utilizing a learning algorithm to identify abnormal values; and means for analyzing detailed evaluation items based on the identified abnormal values ​​and generating and presenting methods for adjusting the evaluation. This makes it possible to efficiently analyze construction estimates and make appropriate adjustments based on the results. Furthermore, by incorporating user feedback into the learning data to improve the accuracy of subsequent analyses, the learning effect is also improved.

[0444] "Construction-related evaluation information" refers to data on costs and work details in construction and repair projects, and is used for scrutinizing estimates and budgets.

[0445] "External data storage devices" refer to recording media or services used to store data outside a specific organization, such as in enterprises or the cloud, and enable the retrieval of information stored in external systems.

[0446] "Methods for converting to a unified format" refer to processes that organize data existing in various formats into a consistent standard, thereby streamlining subsequent processing.

[0447] "Methods that utilize learning algorithms" refer to methods that use data analysis techniques to compare patterns with past data and detect anomalies, thereby deriving more accurate analysis results.

[0448] "Means of analyzing detailed evaluation items and generating and presenting methods for adjusting evaluations" refers to the process of creating appropriate reduction proposals and negotiation strategies based on detected anomalies and cost-increasing factors, and then presenting them to the user.

[0449] "Incorporating user feedback into training data" refers to accumulating user responses and experiences and incorporating them into a database to be used for future system analysis and performance improvements.

[0450] This invention is a system that supports the scrutiny of construction estimates and negotiation of price reductions. In this system, the server, terminals, and users each play specific roles.

[0451] The server first automatically retrieves evaluation information related to the construction project from an external data storage device. During this process, it collects necessary information via APIs and database connections. The retrieved data is converted to a standard format and stored in the database. Next, the server uses machine learning algorithms to compare the data with historical data and identify which items have abnormal values. This analysis may utilize libraries such as Scikit-learn in Python.

[0452] Users input project evaluation information into the system using a terminal. A dedicated interface is provided, allowing for easy input of details such as project items and unit prices. The entered information is sent to the server and recorded along with other evaluation information. During this process, users can verify the validity of the input data in real time.

[0453] The server then generates and presents strategies to the user for adjusting evaluation items that show abnormalities. These strategies include cost-saving alternatives and negotiation tactics. Based on the proposed strategies, the user engages in negotiations, and the results are fed back to the system via the terminal.

[0454] The server incorporates negotiation results obtained from users as training data to improve the accuracy of future analyses. This feedback loop allows the system to continuously improve, enabling more effective scrutiny and proposal of estimates.

[0455] For example, in a new construction project, if a user enters a material cost that is higher than expected, the server compares this to past projects and suggests changing to standard materials. The user then negotiates based on this suggestion, resulting in cost reduction. In this way, even inexperienced personnel can utilize the system to make appropriate cost adjustments and negotiate effectively.

[0456] An example of a prompt to input into the generating AI model is, "Analyze the cost estimates for a new project and provide specific suggestions for reducing abnormal costs."

[0457] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0458] Step 1:

[0459] The server automatically retrieves evaluation information related to construction projects from external data storage devices. It collects data provided in various formats via APIs and converts it into a standardized format such as CSV or JSON. The input to this process is raw construction data, and the output is formatted data.

[0460] Step 2:

[0461] Users input project evaluation information using the terminal interface. The data entered by the user includes project type, items, quantities, and unit prices. The entered data is checked in real time for format and consistency before being sent to the server. Input is raw data from the user, while output is data that has been verified for consistency.

[0462] Step 3:

[0463] The server stores the collected data and performs comparative analysis within the database using historical and new data. It utilizes machine learning techniques to detect outliers and identify which items exceed the appropriate range. The input is formatted data stored in the database, and the output is the analysis results showing the outliers.

[0464] Step 4:

[0465] Based on the analysis results, the server performs a detailed analysis of the evaluation items and generates alternative plans and negotiation strategies for cost reduction. The generated strategies are displayed to the user, and the proposals include specific methods for cost reduction. The input is the analysis results, and the output is specific strategic proposals.

[0466] Step 5:

[0467] Users conduct negotiations based on strategies provided by the server and input the results into their terminal. They input items subject to negotiation and proposed changes, and the negotiation results are fed back into the system. The input is the negotiation result, and the output is the feedback data.

[0468] Step 6:

[0469] The server takes user negotiation results as training data and continuously improves analysis accuracy. This feedback data is used in subsequent analyses, improving the overall system performance. The input is feedback data, and the output is updated training data.

[0470] (Application Example 1)

[0471] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0472] In modern construction projects, scrutinizing estimates and reducing costs are critical challenges. However, detecting outliers and developing strategies for negotiating price reductions requires considerable time and expertise. Furthermore, it is difficult to review and adjust estimates in real time at the construction site, which can reduce the overall efficiency of the project. This invention aims to solve these problems and improve the accuracy of estimates and cost management in construction projects.

[0473] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0474] In this invention, the server includes means for collecting construction estimate information, means for comparing the collected construction estimate information with past data and detecting anomalies, means for analyzing the breakdown of the construction estimate based on the anomalies and generating a strategy for negotiating price reductions, means for inputting information from the construction site using a remote terminal, and means for instantly transmitting the information received through the remote terminal to the server for analysis. This enables the use of estimate information in real time at the construction site, allowing for efficient scrutiny of estimates and cost management.

[0475] "Construction cost estimate information" refers to detailed data related to the budget and costs of a construction project, including material costs, labor costs, equipment costs, etc.

[0476] "Collection methods" refer to the functions and technologies used to collect construction cost estimate information, including devices and software that automate data acquisition from databases and external systems.

[0477] An "outlier" refers to a numerical value included in construction estimate information that deviates significantly from past data or the normal range, indicating a part that requires review or correction.

[0478] A "strategy for cost reduction negotiations" refers to specific approaches and methods aimed at reducing the costs presented in a construction estimate, and includes plans that may involve proposing alternatives or exploring cost-saving possibilities.

[0479] A "remote terminal" refers to an electronic device that can be connected to outside of a construction site or office, such as a smartphone or tablet, which is a computing device capable of inputting and viewing information.

[0480] The system for implementing this invention first includes a means for efficiently collecting construction cost estimate information. The server automatically retrieves the necessary data from an external database or affiliated system and converts it into a standard format. This makes it possible to consistently process estimate information in different formats.

[0481] Next, users can input estimate information directly from construction sites or offices using a device (e.g., a smartphone or tablet). This device sends the information to the server in real time, enabling rapid analysis. The server analyzes the data using machine learning libraries such as TensorFlow and detects anomalies. Based on this, it generates strategies useful for price reduction negotiations and proposes them to the user via smartphone or tablet.

[0482] The user proceeds with negotiations based on the proposed strategy and feeds the results back to the server via their terminal. This allows the system to learn and improve the accuracy of future analyses. For example, if the system detects that the material costs for a new construction project are higher than usual, it may suggest switching to more common materials.

[0483] An example of a prompt for a generative AI model would be, "The material costs for the new project are high. Please suggest an alternative." This would allow the system to quickly and accurately provide alternatives, contributing to cost reduction.

[0484] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0485] Step 1:

[0486] The terminals input estimation information in real time from construction sites or offices. The input data includes detailed information such as construction items, quantities, unit prices, and total amounts. This data is transmitted from the terminals to the server via the network.

[0487] Step 2:

[0488] The server stores the estimate information received from the terminal into a database and converts it to a standard format. The software used here includes data conversion tools to create a consistent dataset even with different formats. This conversion ensures that subsequent analysis processes can be performed accurately.

[0489] Step 3:

[0490] The server analyzes stored data using machine learning models such as TensorFlow. It uses past construction data and current estimation information as input, performs comparative calculations, and identifies anomalies. As a result, it outputs unusual patterns and high-cost items.

[0491] Step 4:

[0492] The server generates a strategy for price reduction negotiations based on the analysis results. Utilizing a generative AI model, it creates candidate alternatives from data input using prompts. Specifically, in response to the user input "Suggest alternatives for expensive materials," it generates the output "A cheaper material X is available."

[0493] Step 5:

[0494] Users review strategies presented by the server on their smartphones or tablets and proceed with negotiations based on those strategies. They then input the negotiation results from their devices and send them back to the server. This feedback data is used later as training data.

[0495] Step 6:

[0496] The server updates the entire system model based on user feedback. This improves the accuracy of future analyses by incorporating the feedback data as training data for machine learning and refining the generated AI model.

[0497] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0498] This invention provides a support system for the construction cost estimation process that also takes into account the user's emotions. This system effectively collects, compares, and analyzes construction cost estimation information, and incorporates an emotion engine to enable the processing of suggestions and feedback that take into account the user's emotional state.

[0499] First, the server automatically collects quotation data from external databases and affiliated information sources. This data is converted to a standard format and stored in an internal database. Users enter quotation information using a terminal, and this information is also sent to the server and stored in a unified format.

[0500] Next, the server analyzes the collected estimate data and compares it with historical data to detect anomalies. For any detected anomalies, it performs a detailed analysis of the breakdown and generates strategies to aid in price reduction negotiations. These strategic proposals are presented to the user, who can then review and implement them on their own device.

[0501] Furthermore, the present invention utilizes an emotion engine to recognize the user's emotional state when receiving user feedback. For example, if a user feels uneasy about the strategy provided, the server uses this emotional information to support the user by adding more detailed explanations or adjusting the suggestions. The emotional information is stored as part of the feedback data and used to improve the system in the future.

[0502] As a concrete example, suppose a user enters an estimate for a new construction project, and the server detects an anomaly. Based on the anomaly, the server creates a proposal for cost reduction and notifies the user. In this process, the emotion engine analyzes the user's reaction, and if it detects that the user is experiencing stress, the server provides supplementary information to reassure them about the proposal. This allows the user to proceed with negotiations with confidence.

[0503] In this way, the system of the present invention provides advanced support for users to perform appropriate and effective estimation scrutiny. The introduction of an emotion engine further deepens user interaction and enables a more sophisticated service.

[0504] The following describes the processing flow.

[0505] Step 1:

[0506] The server automatically collects construction estimate data from external databases and related systems. This data is retrieved using crawler technology, converted to a standard format, and stored in the database.

[0507] Step 2:

[0508] The user uses a terminal to enter estimate data for a new construction project. The input form includes construction items, required quantities, unit prices, and total amounts, and the entered data is immediately sent to the server.

[0509] Step 3:

[0510] The server compares the received estimate data with previously collected historical data. It applies machine learning algorithms to detect outliers that may be outside the normal range.

[0511] Step 4:

[0512] The server further analyzes the data in which anomalies were detected, breaking down cost components such as material costs and labor costs. It identifies which elements are contributing to the increase in costs and looks for areas where improvements can be made.

[0513] Step 5:

[0514] Based on the detected anomalies, the server generates an effective strategy for price reduction negotiations. This strategy includes suggesting alternative materials and specific cost-saving possibilities based on past success stories.

[0515] Step 6:

[0516] The server provides the generated strategy to the user, who then reviews it on their device. During this process, the emotion engine recognizes the user's emotions from their facial expressions and voice, and analyzes how the user is receiving the proposal.

[0517] Step 7:

[0518] The user initiates negotiations with the supplier based on the proposal. They input the negotiation results and emotional feedback into their device and send it to the server.

[0519] Step 8:

[0520] The server receives user feedback and sentiment information, and stores it as training data for future analysis and suggestion generation. This improves the user experience and the accuracy of suggestions in the future.

[0521] (Example 2)

[0522] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0523] In the estimation process for construction activities, not only is it difficult to detect data inconsistencies and anomalies, but user sentiment can be ignored, leading to inappropriate negotiation outcomes. In such situations, the accuracy of estimates and the effectiveness of negotiations are compromised, necessitating new solutions.

[0524] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0525] In this invention, the server includes means for collecting evaluation information related to construction activities, means for comparing the collected evaluation information with past records to detect anomalies, and means for analyzing the breakdown of evaluations based on the anomalies and generating measures to reduce costs. This improves the accuracy and efficiency of the estimation process and enables useful suggestions that take into account the user's feelings.

[0526] "Construction activities" refer to a set of tasks and operations related to the design, planning, construction, renovation, or maintenance of buildings and structures.

[0527] "Evaluation information" refers to information including costs, materials, work details, and related data associated with construction work.

[0528] An "abnormality" refers to a value or pattern that deviates from past records or standard judgment criteria, and is considered to be outside the normal range.

[0529] "Measures to reduce costs" refers to proposals and plans to reduce unnecessary expenses in the estimation process and optimize the process.

[0530] A "server" refers to a computer system that manages and executes the collection, analysis, storage, and interaction with users of information.

[0531] An "emotion analysis engine" refers to a program or mechanism that uses natural language processing technology to analyze a user's emotional state based on their input and feedback.

[0532] "Natural language processing technology" refers to all technologies and methods for analyzing, processing, and understanding human language using computers.

[0533] This invention is a system for effectively supporting the estimation process in construction activities, and by taking user emotions into consideration, it enables more refined proposals and feedback.

[0534] First, the server automatically collects evaluation information related to construction activities from external databases and partners. This data is converted into a common format and stored in an internal information storage device. Specific tools used for collection include a "data collection API" and an "information ingestion engine."

[0535] Next, the user enters new quote information using a terminal. This input is done via a dedicated exit or a simplified input form, and the entered data is sent to the server and integrated with existing records.

[0536] Subsequently, the server analyzes the collected evaluation information and compares it with past records to detect anomalies. This analysis uses a "data analysis engine" and an "anomaly detection algorithm." If an anomaly is detected, the server further analyzes its details and generates strategies to reduce the amount.

[0537] The proposed solutions are sent to the user via email or a dedicated user interface. The user can review them on their device and proceed with negotiations as needed. During this process, the "emotion analysis engine" understands the user's emotional state and adjusts the proposed solutions as necessary. Natural language processing technology is used for emotion analysis.

[0538] As a concrete example, consider a user who has entered an estimate for a new construction project. When the server detects an anomaly in the project, it forms and notifies the user of possible price adjustments. In this case, the system analyzes the user's feelings of anxiety regarding the proposal and provides additional information to alleviate those anxieties. This leads to more successful negotiations.

[0539] Here are some examples of prompts to input into a generative AI model:

[0540] "Please register the estimate data for the new project. If any anomalies are detected, propose specific adjustment measures and analyze user sentiment towards the proposals. Also, provide additional information to alleviate concerns."

[0541] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0542] Step 1:

[0543] The server collects evaluation information related to construction activities from external sources and databases. Input is raw data obtained via APIs and scraping tools. The server converts this raw data into a common format (e.g., CSV, JSON) and stores it in an internal database. This process ensures data consistency and integrity.

[0544] Step 2:

[0545] Users input new quotation information into the system using a terminal. The input is data based on a form provided through the user interface. The terminal sends the input data to the server, where it is integrated with existing evaluation information. The server standardizes the data format, checks for inconsistencies, and then stores it in the database.

[0546] Step 3:

[0547] The server analyzes the collected evaluation information. This analysis uses algorithms to detect anomalies by comparing them with past records. The input is integrated evaluation information, and the output is a list of the parts where anomalies were detected. The server analyzes the breakdown of the anomalies in detail and stores the analysis results in an internal database.

[0548] Step 4:

[0549] The server generates specific measures to reduce costs based on the results of the anomaly analysis. The input is the result of the anomaly analysis, and the output is the generated proposal. The server uses email or a dedicated user interface to notify the user of this proposal.

[0550] Step 5:

[0551] The user reviews the policies sent from the server via their device. The input is the proposal provided by the server, and the output is the user's feedback. The device collects the user's feedback and sends it to the server.

[0552] Step 6:

[0553] The server uses an emotion analysis engine to analyze the emotional state contained in the user's feedback. The input is the user's feedback, and the output is the detected emotional state. Natural language processing techniques are used for emotion analysis.

[0554] Step 7:

[0555] The server adjusts the suggestions as needed based on the sentiment analysis results. The input is the user's emotional state and the original suggestion, and the output is the revised suggestion. The server then notifies the user of the revised suggestion again and awaits further feedback.

[0556] (Application Example 2)

[0557] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0558] In the construction estimation process, it was difficult to detect anomalies in the collected data, generate effective negotiation strategies, and provide support that took into account the user's emotional state. Traditional systems failed to improve the accuracy of estimates and the quality of proposals by incorporating user reactions and emotions, resulting in a lack of improvement in the user experience.

[0559] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0560] In this invention, the server includes means for collecting construction estimate information, means for comparing the collected construction estimate information with past data to detect anomalies, and means for analyzing the breakdown of the construction estimate based on the anomalies and generating a strategy for negotiating price reductions. This makes it possible to propose strategies that take into account the user's emotional state in the construction estimate, and to proceed with negotiations while providing a sense of security.

[0561] "Construction cost estimate information" is a collection of data that calculates the expenses and resource requirements related to construction work.

[0562] An "outlier" is a value that differs significantly from past data or predicted values, and refers to data that requires special attention.

[0563] "Negotiating a price reduction" refers to the negotiation process aimed at lowering the proposed estimated cost.

[0564] A "strategy" is a set of actions planned to achieve a goal, and is particularly used to conduct negotiations effectively.

[0565] "Emotional state" refers to the user's psychological response and the degree of their emotions, and is particularly used to evaluate the user's response to system proposals.

[0566] "Feedback data" refers to data on user reactions and evaluations, collected to help improve the system.

[0567] The system for carrying out this invention includes a program that comprehensively performs tasks such as collecting construction cost estimate information, detecting anomalies, generating cost reduction negotiation strategies, and recognizing and processing user emotions. The processing details of this program are described below.

[0568] The server automatically collects construction estimate information from external sources and databases, converts it to a standard format, and then stores it in an internal database. Users can input the necessary estimate information using devices such as smartphones or smart glasses, and this information is sent to the server and stored in the same standard format.

[0569] The server uses the collected data to compare it with historical estimates and detects outliers using algorithms. Pandas and NumPy are used as data analysis software for this data calculation. For detected outliers, the system analyzes the details and automatically generates cost-reduction strategies. These strategy proposals are sent to the user's terminal for review and application.

[0570] Furthermore, the server uses an emotion recognition library (for example, Microsoft Azure's Emotion API) to analyze the user's emotional state. If the user feels anxious about the proposed strategy, the system takes that emotional state into consideration and provides additional information to reassure them. In this process, emotional information is collected and stored as feedback data, which is used to improve the quality of future analyses and strategy proposals.

[0571] As a concrete example, a user uses smart glasses to capture on-site video, which is immediately transmitted to a server via the cloud for analysis of the estimation information. During this process, a generative AI model is used to detect stress and anxiety, and to propose appropriate strategies. Based on the user's feedback, the following prompt example is used: "The price quoted for today's project estimate exceeds the predicted cost. Please generate a reassuring proposal based on sentiment analysis."

[0572] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0573] Step 1:

[0574] The server automatically collects construction cost estimate information from external sources and databases. The input at this stage is raw data obtained from various sources, which the server converts to a standard format and stores in its internal database. This process ensures data consistency and integrity.

[0575] Step 2:

[0576] Users input estimate-related information collected on-site using their devices. This input is done through various interfaces, such as camera apps and voice input, and is sent to the server in real time. The server converts the received data into a standard format and adds it to its internal database.

[0577] Step 3:

[0578] The server uses collected estimated data to detect anomalies by comparing it with historical data. This detection process employs statistical methods and data analysis tools such as Pandas and NumPy. The inputs are current estimated data and historical data, and the output is the detected anomalies and their causal analysis.

[0579] Step 4:

[0580] The server analyzes the breakdown of detected anomalies and generates a strategy for price reduction negotiations. This process uses algorithms to analyze data points in detail and identify elements that can be reduced. The output is a draft negotiation strategy that the user can use as a reference.

[0581] Step 5:

[0582] Users review strategic proposals presented by the server via their devices. They then assess whether the proposals are acceptable and provide feedback. This feedback is sent to the server for system improvement. Sentiment recognition is also performed simultaneously.

[0583] Step 6:

[0584] The server uses an emotion recognition library to analyze the user's emotional state. It analyzes user input, feedback tone, facial expressions, and other input data, and adjusts the suggestions based on detected anxiety or stress. The output consists of the adjusted suggestions and additional information as needed.

[0585] Step 7:

[0586] Users review additional information based on their emotions and provide further feedback. The server uses this feedback to improve the accuracy of future data analysis and the quality of strategic recommendations.

[0587] Throughout each step, the system interactively utilizes the generated AI model, improving the quality of the user experience by using the following prompt: "The price quoted for today's project estimate exceeds the predicted cost. Please generate a reassuring proposal based on sentiment analysis."

[0588] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0589] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0590] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0591] [Fourth Embodiment]

[0592] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0593] As shown in Figure 7, the 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.

[0594] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0595] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0596] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0597] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0598] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0599] The controlled 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0600] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0601] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0602] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0603] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0604] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0605] This invention is a system that supports the scrutiny of construction estimates and negotiation of price reductions. The system mainly consists of the following components, each of which plays a specific role in achieving efficiency and accuracy in the estimation process.

[0606] First, the server collects estimate information related to the construction project. This is done by automatically retrieving data from external databases and partner systems. The collected data is then converted into a standard format. This allows for consistent processing of estimate information provided in different formats.

[0607] Next, the user enters new construction estimate information through their device. Here, an interface is provided for entering details such as construction items, quantities, unit prices, and total amounts. This information is instantly sent to the server and stored in the database along with other data.

[0608] The stored data is analyzed by the server. It compares the information sent from the device with similar past data to identify abnormal values ​​or items that may exceed the appropriate range. This analysis utilizes machine learning techniques to produce more accurate results.

[0609] Next, the server analyzes the breakdown of each item in the construction estimate in detail based on the analysis results. It identifies which elements are causing high costs and proposes a strategy to the user for negotiating price reductions. This strategy includes potential alternatives and items where costs can be reduced.

[0610] Finally, the user conducts negotiations based on the presented strategy and inputs the results into the terminal. The server analyzes this feedback and automatically incorporates it as training data for the system. This improves the accuracy of future analyses.

[0611] As a concrete example, a user inputs an estimate for a new base station construction project. In this case, the server detects that the material costs are higher than in previous projects and suggests changing to standard materials. The user can then negotiate based on this advice to reduce costs. In this way, even inexperienced personnel can use the system to conduct proper and effective estimate reviews and negotiations.

[0612] The following describes the processing flow.

[0613] Step 1:

[0614] The server periodically collects the latest construction estimate data from external databases and affiliated systems. It uses a crawler to extract the necessary data and stores it in a local database.

[0615] Step 2:

[0616] The user enters new quote information via a terminal. Through the user interface, the user enters the work items, quantities, unit prices, and total amount into the system, and the entered data is immediately transmitted to the server.

[0617] Step 3:

[0618] The server converts the received estimate data into a standard format. In this process, the data is refined, inconsistencies and omissions are corrected, and it is stored in the database in a unified format.

[0619] Step 4:

[0620] The server analyzes standardized quotation data. By comparing it with historical data, it verifies standard unit prices and reasonableness, and detects values ​​that are unusually high or low.

[0621] Step 5:

[0622] The server then performs a more detailed analysis of the breakdown of each construction item based on the analysis results. It breaks down cost factors such as material costs, labor costs, and machinery costs to identify which elements are influencing the increase in costs.

[0623] Step 6:

[0624] The server generates effective strategies for price reduction negotiations. Based on detected anomalies, it provides users with specific suggestions that consider cost-reduction alternatives and successful examples from other projects.

[0625] Step 7:

[0626] Users negotiate with suppliers using the provided price reduction negotiation strategies as a reference and input the results into their terminal. The input feedback is analyzed on the server and stored as training data to be used for future analysis.

[0627] Step 8:

[0628] The server improves the system's accuracy based on user feedback. By analyzing the feedback and updating the machine learning model, the accuracy of future estimate refinements and price reduction negotiation suggestions can be further enhanced.

[0629] (Example 1)

[0630] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0631] Estimating construction projects often involves a complex interplay of diverse data, making it challenging to quickly and accurately detect anomalies and implement appropriate cost reductions. Furthermore, effectively utilizing accumulated historical negotiation data to learn from and improve the accuracy of future estimates is essential.

[0632] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0633] In this invention, the server includes means for automatically acquiring evaluation information related to construction work from an external data storage device and converting the acquired data into a unified format; means for using the evaluation information to compare it with past information and utilizing a learning algorithm to identify abnormal values; and means for analyzing detailed evaluation items based on the identified abnormal values ​​and generating and presenting methods for adjusting the evaluation. This makes it possible to efficiently analyze construction estimates and make appropriate adjustments based on the results. Furthermore, by incorporating user feedback into the learning data to improve the accuracy of subsequent analyses, the learning effect is also improved.

[0634] "Construction-related evaluation information" refers to data on costs and work details in construction and repair projects, and is used for scrutinizing estimates and budgets.

[0635] "External data storage devices" refer to recording media or services used to store data outside a specific organization, such as in enterprises or the cloud, and enable the retrieval of information stored in external systems.

[0636] "Methods for converting to a unified format" refer to processes that organize data existing in various formats into a consistent standard, thereby streamlining subsequent processing.

[0637] "Methods that utilize learning algorithms" refer to methods that use data analysis techniques to compare patterns with past data and detect anomalies, thereby deriving more accurate analysis results.

[0638] "Means of analyzing detailed evaluation items and generating and presenting methods for adjusting evaluations" refers to the process of creating appropriate reduction proposals and negotiation strategies based on detected anomalies and cost-increasing factors, and then presenting them to the user.

[0639] "Incorporating user feedback into training data" refers to accumulating user responses and experiences and incorporating them into a database to be used for future system analysis and performance improvements.

[0640] This invention is a system that supports the scrutiny of construction estimates and negotiation of price reductions. In this system, the server, terminals, and users each play specific roles.

[0641] The server first automatically retrieves evaluation information related to the construction project from an external data storage device. During this process, it collects necessary information via APIs and database connections. The retrieved data is converted to a standard format and stored in the database. Next, the server uses machine learning algorithms to compare the data with historical data and identify which items have abnormal values. This analysis may utilize libraries such as Scikit-learn in Python.

[0642] Users input project evaluation information into the system using a terminal. A dedicated interface is provided, allowing for easy input of details such as project items and unit prices. The entered information is sent to the server and recorded along with other evaluation information. During this process, users can verify the validity of the input data in real time.

[0643] The server then generates and presents strategies to the user for adjusting evaluation items that show abnormalities. These strategies include cost-saving alternatives and negotiation tactics. Based on the proposed strategies, the user engages in negotiations, and the results are fed back to the system via the terminal.

[0644] The server incorporates negotiation results obtained from users as training data to improve the accuracy of future analyses. This feedback loop allows the system to continuously improve, enabling more effective scrutiny and proposal of estimates.

[0645] For example, in a new construction project, if a user enters a material cost that is higher than expected, the server compares this to past projects and suggests changing to standard materials. The user then negotiates based on this suggestion, resulting in cost reduction. In this way, even inexperienced personnel can utilize the system to make appropriate cost adjustments and negotiate effectively.

[0646] An example of a prompt to input into the generating AI model is, "Analyze the cost estimates for a new project and provide specific suggestions for reducing abnormal costs."

[0647] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0648] Step 1:

[0649] The server automatically retrieves evaluation information related to construction projects from external data storage devices. It collects data provided in various formats via APIs and converts it into a standardized format such as CSV or JSON. The input to this process is raw construction data, and the output is formatted data.

[0650] Step 2:

[0651] Users input project evaluation information using the terminal interface. The data entered by the user includes project type, items, quantities, and unit prices. The entered data is checked in real time for format and consistency before being sent to the server. Input is raw data from the user, while output is data that has been verified for consistency.

[0652] Step 3:

[0653] The server stores the collected data and performs comparative analysis within the database using historical and new data. It utilizes machine learning techniques to detect outliers and identify which items exceed the appropriate range. The input is formatted data stored in the database, and the output is the analysis results showing the outliers.

[0654] Step 4:

[0655] Based on the analysis results, the server performs a detailed analysis of the evaluation items and generates alternative plans and negotiation strategies for cost reduction. The generated strategies are displayed to the user, and the proposals include specific methods for cost reduction. The input is the analysis results, and the output is specific strategic proposals.

[0656] Step 5:

[0657] Users conduct negotiations based on strategies provided by the server and input the results into their terminal. They input items subject to negotiation and proposed changes, and the negotiation results are fed back into the system. The input is the negotiation result, and the output is the feedback data.

[0658] Step 6:

[0659] The server takes user negotiation results as training data and continuously improves analysis accuracy. This feedback data is used in subsequent analyses, improving the overall system performance. The input is feedback data, and the output is updated training data.

[0660] (Application Example 1)

[0661] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0662] In modern construction projects, scrutinizing estimates and reducing costs are critical challenges. However, detecting outliers and developing strategies for negotiating price reductions requires considerable time and expertise. Furthermore, it is difficult to review and adjust estimates in real time at the construction site, which can reduce the overall efficiency of the project. This invention aims to solve these problems and improve the accuracy of estimates and cost management in construction projects.

[0663] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0664] In this invention, the server includes means for collecting construction estimate information, means for comparing the collected construction estimate information with past data and detecting anomalies, means for analyzing the breakdown of the construction estimate based on the anomalies and generating a strategy for negotiating price reductions, means for inputting information from the construction site using a remote terminal, and means for instantly transmitting the information received through the remote terminal to the server for analysis. This enables the use of estimate information in real time at the construction site, allowing for efficient scrutiny of estimates and cost management.

[0665] "Construction cost estimate information" refers to detailed data related to the budget and costs of a construction project, including material costs, labor costs, equipment costs, etc.

[0666] "Collection methods" refer to the functions and technologies used to collect construction cost estimate information, including devices and software that automate data acquisition from databases and external systems.

[0667] An "outlier" refers to a numerical value included in construction estimate information that deviates significantly from past data or the normal range, indicating a part that requires review or correction.

[0668] A "strategy for cost reduction negotiations" refers to specific approaches and methods aimed at reducing the costs presented in a construction estimate, and includes plans that may involve proposing alternatives or exploring cost-saving possibilities.

[0669] A "remote terminal" refers to an electronic device that can be connected to outside of a construction site or office, such as a smartphone or tablet, which is a computing device capable of inputting and viewing information.

[0670] The system for implementing this invention first includes a means for efficiently collecting construction cost estimate information. The server automatically retrieves the necessary data from an external database or affiliated system and converts it into a standard format. This makes it possible to consistently process estimate information in different formats.

[0671] Next, users can input estimate information directly from construction sites or offices using a device (e.g., a smartphone or tablet). This device sends the information to the server in real time, enabling rapid analysis. The server analyzes the data using machine learning libraries such as TensorFlow and detects anomalies. Based on this, it generates strategies useful for price reduction negotiations and proposes them to the user via smartphone or tablet.

[0672] The user proceeds with negotiations based on the proposed strategy and feeds the results back to the server via their terminal. This allows the system to learn and improve the accuracy of future analyses. For example, if the system detects that the material costs for a new construction project are higher than usual, it may suggest switching to more common materials.

[0673] An example of a prompt for a generative AI model would be, "The material costs for the new project are high. Please suggest an alternative." This would allow the system to quickly and accurately provide alternatives, contributing to cost reduction.

[0674] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0675] Step 1:

[0676] The terminals input estimation information in real time from construction sites or offices. The input data includes detailed information such as construction items, quantities, unit prices, and total amounts. This data is transmitted from the terminals to the server via the network.

[0677] Step 2:

[0678] The server stores the estimate information received from the terminal into a database and converts it to a standard format. The software used here includes data conversion tools to create a consistent dataset even with different formats. This conversion ensures that subsequent analysis processes can be performed accurately.

[0679] Step 3:

[0680] The server analyzes stored data using machine learning models such as TensorFlow. It uses past construction data and current estimation information as input, performs comparative calculations, and identifies anomalies. As a result, it outputs unusual patterns and high-cost items.

[0681] Step 4:

[0682] The server generates a strategy for price reduction negotiations based on the analysis results. Utilizing a generative AI model, it creates candidate alternatives from data input using prompts. Specifically, in response to the user input "Suggest alternatives for expensive materials," it generates the output "A cheaper material X is available."

[0683] Step 5:

[0684] Users review strategies presented by the server on their smartphones or tablets and proceed with negotiations based on those strategies. They then input the negotiation results from their devices and send them back to the server. This feedback data is used later as training data.

[0685] Step 6:

[0686] The server updates the entire system model based on user feedback. This improves the accuracy of future analyses by incorporating the feedback data as training data for machine learning and refining the generated AI model.

[0687] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0688] This invention provides a support system for the construction cost estimation process that also takes into account the user's emotions. This system effectively collects, compares, and analyzes construction cost estimation information, and incorporates an emotion engine to enable the processing of suggestions and feedback that take into account the user's emotional state.

[0689] First, the server automatically collects quotation data from external databases and affiliated information sources. This data is converted to a standard format and stored in an internal database. Users enter quotation information using a terminal, and this information is also sent to the server and stored in a unified format.

[0690] Next, the server analyzes the collected estimate data and compares it with historical data to detect anomalies. For any detected anomalies, it performs a detailed analysis of the breakdown and generates strategies to aid in price reduction negotiations. These strategic proposals are presented to the user, who can then review and implement them on their own device.

[0691] Furthermore, the present invention utilizes an emotion engine to recognize the user's emotional state when receiving user feedback. For example, if a user feels uneasy about the strategy provided, the server uses this emotional information to support the user by adding more detailed explanations or adjusting the suggestions. The emotional information is stored as part of the feedback data and used to improve the system in the future.

[0692] As a concrete example, suppose a user enters an estimate for a new construction project, and the server detects an anomaly. Based on the anomaly, the server creates a proposal for cost reduction and notifies the user. In this process, the emotion engine analyzes the user's reaction, and if it detects that the user is experiencing stress, the server provides supplementary information to reassure them about the proposal. This allows the user to proceed with negotiations with confidence.

[0693] In this way, the system of the present invention provides advanced support for users to perform appropriate and effective estimation scrutiny. The introduction of an emotion engine further deepens user interaction and enables a more sophisticated service.

[0694] The following describes the processing flow.

[0695] Step 1:

[0696] The server automatically collects construction estimate data from external databases and related systems. This data is retrieved using crawler technology, converted to a standard format, and stored in the database.

[0697] Step 2:

[0698] The user uses a terminal to enter estimate data for a new construction project. The input form includes construction items, required quantities, unit prices, and total amounts, and the entered data is immediately sent to the server.

[0699] Step 3:

[0700] The server compares the received estimate data with previously collected historical data. It applies machine learning algorithms to detect outliers that may be outside the normal range.

[0701] Step 4:

[0702] The server further analyzes the data in which anomalies were detected, breaking down cost components such as material costs and labor costs. It identifies which elements are contributing to the increase in costs and looks for areas where improvements can be made.

[0703] Step 5:

[0704] Based on the detected anomalies, the server generates an effective strategy for price reduction negotiations. This strategy includes suggesting alternative materials and specific cost-saving possibilities based on past success stories.

[0705] Step 6:

[0706] The server provides the generated strategy to the user, who then reviews it on their device. During this process, the emotion engine recognizes the user's emotions from their facial expressions and voice, and analyzes how the user is receiving the proposal.

[0707] Step 7:

[0708] The user initiates negotiations with the supplier based on the proposal. They input the negotiation results and emotional feedback into their device and send it to the server.

[0709] Step 8:

[0710] The server receives user feedback and sentiment information, and stores it as training data for future analysis and suggestion generation. This improves the user experience and the accuracy of suggestions in the future.

[0711] (Example 2)

[0712] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0713] In the estimation process for construction activities, not only is it difficult to detect data inconsistencies and anomalies, but user sentiment can be ignored, leading to inappropriate negotiation outcomes. In such situations, the accuracy of estimates and the effectiveness of negotiations are compromised, necessitating new solutions.

[0714] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0715] In this invention, the server includes means for collecting evaluation information related to construction activities, means for comparing the collected evaluation information with past records to detect anomalies, and means for analyzing the breakdown of evaluations based on the anomalies and generating measures to reduce costs. This improves the accuracy and efficiency of the estimation process and enables useful suggestions that take into account the user's feelings.

[0716] "Construction activities" refer to a set of tasks and operations related to the design, planning, construction, renovation, or maintenance of buildings and structures.

[0717] "Evaluation information" refers to information including costs, materials, work details, and related data associated with construction work.

[0718] An "abnormality" refers to a value or pattern that deviates from past records or standard judgment criteria, and is considered to be outside the normal range.

[0719] "Measures to reduce costs" refers to proposals and plans to reduce unnecessary expenses in the estimation process and optimize the process.

[0720] A "server" refers to a computer system that manages and executes the collection, analysis, storage, and interaction with users of information.

[0721] An "emotion analysis engine" refers to a program or mechanism that uses natural language processing technology to analyze a user's emotional state based on their input and feedback.

[0722] "Natural language processing technology" refers to all technologies and methods for analyzing, processing, and understanding human language using computers.

[0723] This invention is a system for effectively supporting the estimation process in construction activities, and by taking user emotions into consideration, it enables more refined proposals and feedback.

[0724] First, the server automatically collects evaluation information related to construction activities from external databases and partners. This data is converted into a common format and stored in an internal information storage device. Specific tools used for collection include a "data collection API" and an "information ingestion engine."

[0725] Next, the user enters new quote information using a terminal. This input is done via a dedicated exit or a simplified input form, and the entered data is sent to the server and integrated with existing records.

[0726] Subsequently, the server analyzes the collected evaluation information and compares it with past records to detect anomalies. This analysis uses a "data analysis engine" and an "anomaly detection algorithm." If an anomaly is detected, the server further analyzes its details and generates strategies to reduce the amount.

[0727] The proposed solutions are sent to the user via email or a dedicated user interface. The user can review them on their device and proceed with negotiations as needed. During this process, the "emotion analysis engine" understands the user's emotional state and adjusts the proposed solutions as necessary. Natural language processing technology is used for emotion analysis.

[0728] As a concrete example, consider a user who has entered an estimate for a new construction project. When the server detects an anomaly in the project, it forms and notifies the user of possible price adjustments. In this case, the system analyzes the user's feelings of anxiety regarding the proposal and provides additional information to alleviate those anxieties. This leads to more successful negotiations.

[0729] Here are some examples of prompts to input into a generative AI model:

[0730] "Please register the estimate data for the new project. If any anomalies are detected, propose specific adjustment measures and analyze user sentiment towards the proposals. Also, provide additional information to alleviate concerns."

[0731] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0732] Step 1:

[0733] The server collects evaluation information related to construction activities from external sources and databases. Input is raw data obtained via APIs and scraping tools. The server converts this raw data into a common format (e.g., CSV, JSON) and stores it in an internal database. This process ensures data consistency and integrity.

[0734] Step 2:

[0735] Users input new quotation information into the system using a terminal. The input is data based on a form provided through the user interface. The terminal sends the input data to the server, where it is integrated with existing evaluation information. The server standardizes the data format, checks for inconsistencies, and then stores it in the database.

[0736] Step 3:

[0737] The server analyzes the collected evaluation information. This analysis uses algorithms to detect anomalies by comparing them with past records. The input is integrated evaluation information, and the output is a list of the parts where anomalies were detected. The server analyzes the breakdown of the anomalies in detail and stores the analysis results in an internal database.

[0738] Step 4:

[0739] The server generates specific measures to reduce costs based on the results of the anomaly analysis. The input is the result of the anomaly analysis, and the output is the generated proposal. The server uses email or a dedicated user interface to notify the user of this proposal.

[0740] Step 5:

[0741] The user reviews the policies sent from the server via their device. The input is the proposal provided by the server, and the output is the user's feedback. The device collects the user's feedback and sends it to the server.

[0742] Step 6:

[0743] The server uses an emotion analysis engine to analyze the emotional state contained in the user's feedback. The input is the user's feedback, and the output is the detected emotional state. Natural language processing techniques are used for emotion analysis.

[0744] Step 7:

[0745] The server adjusts the suggestions as needed based on the sentiment analysis results. The input is the user's emotional state and the original suggestion, and the output is the revised suggestion. The server then notifies the user of the revised suggestion again and awaits further feedback.

[0746] (Application Example 2)

[0747] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0748] In the construction estimation process, it was difficult to detect anomalies in the collected data, generate effective negotiation strategies, and provide support that took into account the user's emotional state. Traditional systems failed to improve the accuracy of estimates and the quality of proposals by incorporating user reactions and emotions, resulting in a lack of improvement in the user experience.

[0749] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0750] In this invention, the server includes means for collecting construction estimate information, means for comparing the collected construction estimate information with past data to detect anomalies, and means for analyzing the breakdown of the construction estimate based on the anomalies and generating a strategy for negotiating price reductions. This makes it possible to propose strategies that take into account the user's emotional state in the construction estimate, and to proceed with negotiations while providing a sense of security.

[0751] "Construction cost estimate information" is a collection of data that calculates the expenses and resource requirements related to construction work.

[0752] An "outlier" is a value that differs significantly from past data or predicted values, and refers to data that requires special attention.

[0753] "Negotiating a price reduction" refers to the negotiation process aimed at lowering the proposed estimated cost.

[0754] A "strategy" is a set of actions planned to achieve a goal, and is particularly used to conduct negotiations effectively.

[0755] "Emotional state" refers to the user's psychological response and the degree of their emotions, and is particularly used to evaluate the user's response to system proposals.

[0756] "Feedback data" refers to data on user reactions and evaluations, collected to help improve the system.

[0757] The system for carrying out this invention includes a program that comprehensively performs tasks such as collecting construction cost estimate information, detecting anomalies, generating cost reduction negotiation strategies, and recognizing and processing user emotions. The processing details of this program are described below.

[0758] The server automatically collects construction estimate information from external sources and databases, converts it to a standard format, and then stores it in an internal database. Users can input the necessary estimate information using devices such as smartphones or smart glasses, and this information is sent to the server and stored in the same standard format.

[0759] The server uses the collected data to compare it with historical estimates and detects outliers using algorithms. Pandas and NumPy are used as data analysis software for this data calculation. For detected outliers, the system analyzes the details and automatically generates cost-reduction strategies. These strategy proposals are sent to the user's terminal for review and application.

[0760] Furthermore, the server uses an emotion recognition library (for example, Microsoft Azure's Emotion API) to analyze the user's emotional state. If the user feels anxious about the proposed strategy, the system takes that emotional state into consideration and provides additional information to reassure them. In this process, emotional information is collected and stored as feedback data, which is used to improve the quality of future analyses and strategy proposals.

[0761] As a concrete example, a user uses smart glasses to capture on-site video, which is immediately transmitted to a server via the cloud for analysis of the estimation information. During this process, a generative AI model is used to detect stress and anxiety, and to propose appropriate strategies. Based on the user's feedback, the following prompt example is used: "The price quoted for today's project estimate exceeds the predicted cost. Please generate a reassuring proposal based on sentiment analysis."

[0762] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0763] Step 1:

[0764] The server automatically collects construction cost estimate information from external sources and databases. The input at this stage is raw data obtained from various sources, which the server converts to a standard format and stores in its internal database. This process ensures data consistency and integrity.

[0765] Step 2:

[0766] Users input estimate-related information collected on-site using their devices. This input is done through various interfaces, such as camera apps and voice input, and is sent to the server in real time. The server converts the received data into a standard format and adds it to its internal database.

[0767] Step 3:

[0768] The server uses collected estimated data to detect anomalies by comparing it with historical data. This detection process employs statistical methods and data analysis tools such as Pandas and NumPy. The inputs are current estimated data and historical data, and the output is the detected anomalies and their causal analysis.

[0769] Step 4:

[0770] The server analyzes the breakdown of detected anomalies and generates a strategy for price reduction negotiations. This process uses algorithms to analyze data points in detail and identify elements that can be reduced. The output is a draft negotiation strategy that the user can use as a reference.

[0771] Step 5:

[0772] Users review strategic proposals presented by the server via their devices. They then assess whether the proposals are acceptable and provide feedback. This feedback is sent to the server for system improvement. Sentiment recognition is also performed simultaneously.

[0773] Step 6:

[0774] The server uses an emotion recognition library to analyze the user's emotional state. It analyzes user input, feedback tone, facial expressions, and other input data, and adjusts the suggestions based on detected anxiety or stress. The output consists of the adjusted suggestions and additional information as needed.

[0775] Step 7:

[0776] Users review additional information based on their emotions and provide further feedback. The server uses this feedback to improve the accuracy of future data analysis and the quality of strategic recommendations.

[0777] Throughout each step, the system interactively utilizes the generated AI model, improving the quality of the user experience by using the following prompt: "The price quoted for today's project estimate exceeds the predicted cost. Please generate a reassuring proposal based on sentiment analysis."

[0778] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0779] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0780] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0781] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0782] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0783] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0784] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0785] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0786] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0787] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0788] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0789] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0790] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0791] 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.

[0792] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0793] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0794] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0795] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0796] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0797] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0798] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0799] The following is further disclosed regarding the embodiments described above.

[0800] (Claim 1)

[0801] Means of collecting construction cost estimate information,

[0802] A means for detecting anomalies by comparing the collected construction estimate information with past data,

[0803] A means for analyzing the breakdown of construction estimates based on the aforementioned anomalies and generating a strategy for negotiating price reductions,

[0804] A means of presenting the aforementioned strategy, receiving user feedback, and improving the system based on the results,

[0805] A system that includes this.

[0806] (Claim 2)

[0807] The system according to claim 1, which converts collected data into a standard format.

[0808] (Claim 3)

[0809] The system according to claim 1, which incorporates user feedback as training data to improve the accuracy of subsequent analyses.

[0810] "Example 1"

[0811] (Claim 1)

[0812] A means for automatically acquiring evaluation information related to construction work from an external data storage device and converting the acquired data into a unified format,

[0813] A means of using the aforementioned evaluation information to compare it with past information and utilizing a learning algorithm to identify abnormal values,

[0814] A means for analyzing detailed evaluation items based on the identified anomalies, and for generating and presenting methods for adjusting the evaluation,

[0815] A means for collecting user responses based on the aforementioned method, analyzing those responses, and incorporating them into subsequent analyses,

[0816] A system that includes this.

[0817] (Claim 2)

[0818] The system according to claim 1, wherein evaluation information entered by the user is transmitted from the terminal and the collected information is stored in a central control unit.

[0819] (Claim 3)

[0820] The system according to claim 1, which obtains the results of negotiations conducted based on the presented method from the user, analyzes the results, and incorporates them as learning material to improve evaluation accuracy.

[0821] "Application Example 1"

[0822] (Claim 1)

[0823] Means of collecting construction cost estimate information,

[0824] A means for detecting anomalies by comparing the collected construction estimate information with past data,

[0825] A means for analyzing the breakdown of construction estimates based on the aforementioned anomalies and generating a strategy for negotiating price reductions,

[0826] A means of presenting the aforementioned strategy, receiving user feedback, and improving the system based on the results,

[0827] A method of inputting information from the construction site using a remote terminal,

[0828] A means for instantly transmitting information received through the remote terminal to a server for analysis,

[0829] A system that includes this.

[0830] (Claim 2)

[0831] The system according to claim 1, which converts collected data into a standard format.

[0832] (Claim 3)

[0833] The system according to claim 1, which incorporates user feedback as training data to improve the accuracy of subsequent analyses.

[0834] "Example 2 of combining an emotion engine"

[0835] (Claim 1)

[0836] Means for collecting evaluation information related to construction activities,

[0837] A means for detecting anomalies by comparing the collected evaluation information with past records,

[0838] A means for analyzing the breakdown of the evaluation based on the aforementioned anomaly and generating measures to reduce the amount,

[0839] A means of presenting the aforementioned measures, receiving user feedback, and optimizing the system based on the results,

[0840] A means including an emotion analysis engine using natural language processing technology to analyze the emotional state of a user,

[0841] A means for adjusting the content of the proposal based on the emotional state of the user,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, which converts collected information into a common format.

[0845] (Claim 3)

[0846] The system according to claim 1, which takes user responses as input data and improves the accuracy of subsequent analyses.

[0847] "Application example 2 when combining with an emotional engine"

[0848] (Claim 1)

[0849] Means of collecting construction cost estimate information,

[0850] A means for detecting anomalies by comparing the collected construction estimate information with past data,

[0851] A means for analyzing the breakdown of construction estimates based on the aforementioned anomalies and generating a strategy for negotiating price reductions,

[0852] A means of presenting the aforementioned strategy, recognizing the user's emotional state, and adjusting additional information and suggestions based on their response,

[0853] A means of receiving user feedback and improving the system based on the results,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, which converts the collected data into a standard format and incorporates the user's emotional information as feedback data.

[0857] (Claim 3)

[0858] The system according to claim 1, which improves the accuracy of analysis by taking into account the user's emotional state, and improves the quality of future strategic proposals. [Explanation of Symbols]

[0859] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting construction cost estimate information, A means for detecting anomalies by comparing the collected construction estimate information with past data, A means for analyzing the breakdown of construction estimates based on the aforementioned anomalies and generating a strategy for negotiating price reductions, A means of presenting the aforementioned strategy, receiving user feedback, and improving the system based on the results, A system that includes this.

2. The system according to claim 1, which converts collected data into a standard format.

3. The system according to claim 1, which incorporates user feedback as training data to improve the accuracy of subsequent analyses.

Images