system

Abstract

We provide the system. [Solution] A means by which an electronic computer analyzes and classifies vendor information, A means for automatically generating an application form based on the aforementioned analysis, A method for predicting projects for the next fiscal year by analyzing past bidding data, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] The registration of trading companies and the bidding process for each local government require a lot of time and labor and are inefficient. In particular, since there are different application requirements and document formats for each local government, the business burden on the corporate side increases, and furthermore, the provision of appropriate bidding conditions and prediction information is insufficient. Such a situation leads to problems such as a decrease in the bidding rate and the loss of project acquisition opportunities.

Means for Solving the Problems

[0005] This invention provides a system that uses a computer to analyze and classify vendor information. Based on this analysis, it automatically generates application forms, thereby streamlining registration with local governments. Furthermore, by analyzing past bidding data and predicting projects for the following year, it provides companies with strategic bidding methods. In this way, it significantly automates the processes of transactions and bidding with local governments, thereby improving operational efficiency.

[0006] An "electronic computing device" is a computer system used for calculating and processing data, and includes hardware and software for automating specific tasks.

[0007] "Vendor information" refers to basic data about a specific company or legal entity, including details such as the company name, corporate number, business activities, and address.

[0008] "Analysis" is the process of breaking down input data, analyzing its structure and meaning, and deriving necessary conclusions or classifications.

[0009] "Classification" is a method of organizing and grouping analyzed data based on specific criteria or categories.

[0010] An "application form" is a document containing the information necessary to perform a specific procedure or registration, and it is automatically generated to output the necessary data in a complete format.

[0011] "Automated generation" is a process that creates results without manual intervention, based on predetermined rules or algorithms.

[0012] "Bidding data" refers to records and statistical information about past bidding and proposal processes, and is the basis for predicting future bidding activities through analysis.

[0013] "Next year's project forecast" is an activity that predicts the types of work and projects expected to occur in a specific period in the future, usually in the next fiscal year, based on past bidding data. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple 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.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a 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.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is a system for streamlining the registration and bidding processes of local government businesses, and achieves automation using an electronic computer. This system includes data analysis functions, automatic application form generation functions, and bidding data analysis functions, and operates as described below.

[0036] The server first analyzes the company information received from the user. This analysis uses AI-powered natural language processing technology to classify the company information into specific industry categories. Based on these classifications, the server automatically generates application forms that differ for each local government. This process eliminates the need for users to manually create application forms, resulting in a significant improvement in operational efficiency.

[0037] The server also analyzes past bidding data collected from local governments. Advanced statistical methods are applied to this analysis to predict future projects. For example, based on past performance data, the server models bidding frequency, competition rates, and industry trends to generate project predictions for the following year. This prediction information is provided to users via terminals to aid in the development of bidding strategies.

[0038] Furthermore, the server presents the user with the most suitable bidding conditions. Here, the server learns from past bidding conditions and results, and based on that, makes a proposal optimized for the current project. The user can review the proposed conditions presented by the system on their terminal and make modifications as needed.

[0039] As a concrete example, consider a case where a manufacturer participates in a municipality's equipment upgrade project. By entering its own information into the system, the company automatically generates a registration application for the target municipality. Subsequently, based on the analysis of past bidding data provided by the system, the company learns that an increase in equipment upgrade projects is predicted for the following year. Furthermore, it can receive optimal bidding conditions from the server and prepare a competitive proposal. In this way, companies can participate in bidding efficiently while saving time and resources.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user uses a terminal to enter basic vendor information such as company name, corporate number, and business description. This information is then transmitted to the system.

[0043] Step 2:

[0044] The server analyzes the received company information and classifies it into industry categories using an AI model. Based on this classification, the type of application document required is determined.

[0045] Step 3:

[0046] The server automatically generates application form templates that differ for each municipality based on the classification results. Then, it fills in each item based on the analysis results.

[0047] Step 4:

[0048] Users can review the application form generated on their device and make corrections as needed. The application form is then submitted electronically to the local government.

[0049] Step 5:

[0050] The server collects past bidding data from each local government and stores it in a database. Using this data, AI calculates bidding rates and related indicators.

[0051] Step 6:

[0052] The server analyzes past performance data and uses an AI model to predict projects for the following year. The predicted information indicates trends related to specific industries and regions.

[0053] Step 7:

[0054] The server performs simulations that take into account past bidding conditions and results in the process of generating optimal bidding conditions for companies.

[0055] Step 8:

[0056] The user reviews the optimal bidding conditions provided by the server via their terminal and finalizes their proposal. This completes the process of preparing to participate in the bidding.

[0057] (Example 1)

[0058] 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."

[0059] Traditional local government vendor registration and bidding processes are time-consuming, labor-intensive, and poorly managed. Vendors expend considerable effort preparing applications and reviewing bidding conditions, and the lack of sufficient use of historical data for future forecasts makes effective strategic planning difficult.

[0060] 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.

[0061] In this invention, the server includes means for analyzing vendor information acquired from users by a data processing device using natural language processing technology and classifying that vendor information into industry categories; means for automatically generating application forms that conform to the format of each local government based on the analysis results; and means for analyzing past bidding data using statistical methods and predicting future project occurrences. This automates and streamlines the vendor registration and bidding processes, reducing the workload and enabling strategic decision-making.

[0062] A "data processing device" is a device equipped with computer-based functions for analyzing and classifying vendor information.

[0063] "Natural language processing technology" refers to a set of technologies that enable computers to understand, interpret, and manipulate human language.

[0064] An "industry category" is a classification used to identify the field of business activities of a company.

[0065] "Automatic generation of application forms" refers to the process of automatically creating necessary documents using a computer based on analyzed data.

[0066] "Statistical methods" are mathematical techniques used to analyze data and derive useful patterns and predictions.

[0067] A "machine learning model" is an algorithm that learns from past data and uses that data to make predictions and decisions.

[0068] "Optimal bidding conditions" are the conditions set to allow companies to bid in the most advantageous way possible.

[0069] To implement this invention, a server acts as the core of the entire system. The server first receives vendor information sent from users and analyzes it using natural language processing technology. In this process, natural language processing libraries such as TENSORFLOW® and PyTorch are used to classify the vendor information into specific industry categories. The results of this classification are used to automatically generate application forms that differ for each local government. In the automatic generation of application forms, the data analyzed by AI is embedded into a pre-prepared application form template.

[0070] Furthermore, the server processes historical bidding data collected from local governments and performs detailed analysis using statistical analysis software such as R and scikit-learn. Based on the data obtained, it predicts future project occurrences and provides this information to users. This enables users to efficiently plan their bidding strategies.

[0071] Users receive these analysis results and predictive information through their devices and can review and modify their bidding conditions as needed. The server then presents optimized bidding conditions based on past bidding conditions and results, helping users bid under the most favorable conditions.

[0072] As a concrete example, let's consider a case where a manufacturer participates in a municipality's equipment upgrade project. By inputting their company information into the system, the necessary registration application forms for the municipality are automatically generated, and competitive bidding conditions are presented based on future project predictions derived from an analysis of past bidding data for that project.

[0073] An example of an input prompt for a generating AI model would be: "Please explain in natural language the procedure for a system that streamlines the registration and bidding process for local government contractors."

[0074] In this way, the invention can significantly improve the efficiency of the local government's vendor registration and bidding process through data analysis, automatic generation functions, and analysis and optimization of bidding data.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The server receives vendor information from the user. Basic information such as company name, industry, and location is provided as input data. The server analyzes this information using natural language processing technology and classifies it into a specific industry category. For example, it uses a text analysis algorithm to extract keywords related to the industry and then identifies the industry category based on the results. The classified vendor information is then generated as output.

[0078] Step 2:

[0079] The server automatically generates application forms that differ for each municipality based on classified vendor information. Pre-prepared application form templates and analyzed data are used as input. The server automatically creates the application form by filling in the appropriate data in each field of the template. The completed application form is produced as output. Users can view this application form through their terminal.

[0080] Step 3:

[0081] The server receives historical bidding data collected from local governments and performs statistical analysis on it. Input data includes past bid counts, competition rates, and industry trends. The server processes the data using advanced statistical methods to predict future project occurrences. Specifically, it extracts trends based on historical data and uses them to predict future situations. The output is a forecast of future bidding projects, which is then provided to the user.

[0082] Step 4:

[0083] The server learns from past bidding conditions and results to generate optimal bidding conditions for the current project. Past bidding results and condition data are used as input. The server utilizes machine learning models to calculate the most favorable conditions and creates an optimized proposal for the current bidding project. The generated bidding conditions are presented to the user as output. The user can review this proposal on their terminal and make modifications as needed.

[0084] (Application Example 1)

[0085] 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."

[0086] Logistics facilities face the problem of inefficiency due to the enormous amount of time and effort required in the selection of suppliers and the bidding process. Furthermore, errors and inaccurate future predictions resulting from manual analysis of historical data are also challenges. A system is needed to solve these problems and improve operational efficiency.

[0087] 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.

[0088] In this invention, the server includes means for an electronic computer to analyze and classify vendor information, means for automatically generating application forms based on the analysis, means for analyzing past bidding data to predict projects for the following year, and means for managing business partners at logistics facilities and presenting optimal bidding conditions based on information from an inventory management device. This makes it possible to streamline the selection of business partners and the bidding process at logistics facilities.

[0089] An "electronic computing device" is an information processing device that analyzes and classifies business information.

[0090] "Analysis" refers to the act of analyzing vendor information using natural language processing technology and classifying it into a specific industry category.

[0091] "Automatic application form generation" is a process that electronically creates application forms that differ for each local government based on analysis results.

[0092] "Bidding data analysis" is the act of analyzing past bidding information using statistical methods to predict the occurrence of projects in the following year.

[0093] A "logistics facility" is a general term for warehouses and distribution centers that handle the trading and management of goods.

[0094] An "item management device" is a device that collects and manages information on goods and packages handled within a logistics facility in real time.

[0095] "Presenting bidding conditions" is a function that analyzes the collected information and displays the most suitable conditions.

[0096] To implement this invention, a system is constructed using a server, terminals within the logistics facility, and an inventory management device. The server analyzes vendor information via an electronic computer and classifies it into industry categories using natural language processing technology with a generative AI model. Based on the classification results, it is possible to automatically generate different application forms for each local government. The server performs analysis using TensorFlow and processes the data with its own algorithm.

[0097] The server also receives information from logistics facilities regarding inventory management devices, combines this information with past bidding data, visualizes it in Tableau, and predicts the occurrence of projects in the following year. Furthermore, the server presents optimal bidding conditions based on the collected information and sends the information to the user's smartphone.

[0098] For example, when a user requests a trade for new goods, the server analyzes company information and proposes efficient bids considering the goods processing status at the logistics facility. This process allows logistics facilities to quickly present competitive terms in real time. Specifically, a prompt such as, "Analyze the optimal company information for bidding on new transport vehicles for the logistics center and propose the best bid terms," ​​can be used to drive the generative AI model.

[0099] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0100] Step 1:

[0101] The server receives company information from users as input. This information is analyzed using natural language processing technology with a generative AI model and classified into industry categories. The classification results are stored in an internal database.

[0102] Step 2:

[0103] Based on the classification results, the server automatically generates application forms in different formats for each municipality. In this process, it creates the application form by filling in the necessary items using a template engine and then electronically transmits the results to the user's terminal.

[0104] Step 3:

[0105] The server receives inventory data and transaction information from the inventory management system within the logistics facility as input. This data is visualized in Tableau and combined with past bidding data to predict the occurrence of projects in the following year using statistical methods. The prediction results are stored on the server.

[0106] Step 4:

[0107] The server calculates the optimal bidding conditions based on prediction results and real-time logistics information. The calculation considers historical data and the current facility status, applying an optimization algorithm. The resulting bidding conditions are then notified to the user's smartphone.

[0108] Step 5:

[0109] Users review the optimal bidding conditions displayed on their terminals and adjust them as needed. The server receives the revised information from the user and electronically sends it to the local government or business partners as the final bid proposal.

[0110] 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.

[0111] This invention incorporates an "emotion engine" that recognizes user emotions into a system designed to streamline the registration and bidding processes for local government contractors. This system uses a computer to analyze and classify contractor information, automatically generate application forms, and analyze past bidding data. Furthermore, the emotion engine analyzes the user's emotions in real time during input, and uses the results to adjust the interface and customize proposals.

[0112] The server analyzes company information entered by users and classifies it into industry categories using AI. This analysis is then used to automatically generate application forms for each local government. The generated application forms are reviewed by the user on their terminal and electronically sent to the local government.

[0113] Furthermore, the server analyzes past bidding data obtained from local governments to predict projects for the following year. This predictive data is provided to users and plays a role in supporting strategic bidding activities. By incorporating an emotion engine, a flexible approach that reflects the user's psychological state becomes possible.

[0114] The emotion engine has the ability to analyze emotions using user facial expression recognition technology and patterns in input speed and content. This emotion data is fed back into the bidding condition proposals, generating optimized proposals tailored to the user's stress level and level of interest. The emotion engine can also learn from past emotion data to improve the accuracy of future proposals.

[0115] For example, if the emotion engine determines that a user is feeling stressed about a new bidding project, the server will provide a relaxing interface and present easier bidding options. Conversely, if positive emotions are detected, more challenging options will be proposed, enabling more proactive bidding. In this way, the system reduces the user's mental burden while enabling efficient work execution.

[0116] The following describes the processing flow.

[0117] Step 1:

[0118] The user uses a terminal to enter basic information such as company name, corporate number, and business details into the system. This information is then transmitted to the system.

[0119] Step 2:

[0120] The server analyzes the received vendor information and uses AI to classify it into industry categories. Based on this classification, it identifies which municipality's application form is required.

[0121] Step 3:

[0122] The server automatically creates application form templates according to the classification and fills in each item based on the analysis results. The generated application form is then sent to the user's terminal.

[0123] Step 4:

[0124] The user submits the application form, which they have viewed on their device, electronically to the local government. The server checks the transmission status and receives subsequent feedback.

[0125] Step 5:

[0126] The server retrieves past bidding data from a database and uses AI technology to predict future projects. These predictions are then used by users to formulate their strategies.

[0127] Step 6:

[0128] The emotion engine is activated and analyzes the user's emotional state in real time based on input patterns and sensor information obtained from the user's device.

[0129] Step 7:

[0130] Based on the analysis results from the emotion engine, the server adjusts the interface to match the user's stress level and level of interest. In particular, it generates optimal bidding conditions that correspond to the user's emotional state.

[0131] Step 8:

[0132] Users review bid condition proposals from the server on an interface that reflects an emotion engine, and make the best selection. The proposals are further customized based on the user's emotional feedback.

[0133] (Example 2)

[0134] 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".

[0135] In the local government's vendor registration and bidding process, there is a need to reduce the time and effort required for analyzing vendor information and preparing applications, thereby supporting efficient and strategic bidding activities. Furthermore, there is a desire for a system that reduces user stress and provides flexible proposals tailored to individual psychological states.

[0136] 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.

[0137] In this invention, the server includes means comprising an electronic computer device that analyzes vendor information and classifies the results into industry categories; means for automatically generating application documents based on the analysis; means using artificial intelligence technology that analyzes past bidding data and predicts bidding projects for the following year; means for analyzing user emotions in real time based on user input information and adjusting the interface according to the results; and means for customizing the content of proposals provided to the user based on emotion data. This improves the user's work efficiency, reduces psychological burden, and enables the construction of appropriate and flexible bidding strategies.

[0138] An "electronic computing device" refers to a part or all of a computer system that performs data analysis, processing, storage, and communication.

[0139] "Vendor information" refers to relevant information such as the name, address, industry, and transaction history of companies and organizations.

[0140] An "industry category" is a category used to classify companies based on their business activities and operations.

[0141] An "application document" is a formal document prepared for submission to a local government or related organization.

[0142] "Artificial intelligence technology" is a technology that uses computers to replicate functions similar to human intelligence, enabling data analysis and prediction.

[0143] A "user" is the entity that operates the system and inputs information.

[0144] "Sentiment analysis" is the process of determining a user's emotional state based on input information and user feedback.

[0145] An "interface" refers to the connection point or user interface through which a user and a computer system exchange information.

[0146] "Customizing the proposed content" means adjusting the information and services provided according to the user's needs and circumstances.

[0147] This system is configured to streamline the local government's vendor registration and bidding process through collaboration between servers, terminals, and users. It primarily utilizes electronic computing devices, generative AI models, and sentiment analysis engines to analyze vendor information, automatically generate application documents, predict bidding data, and adjust the interface based on user sentiment.

[0148] The server receives vendor information submitted by users and first performs data cleansing. Then, using a generative AI model, it analyzes the company information using natural language processing (NLP) and classifies the companies into industry categories. This analysis utilizes natural language processing (NLP) techniques and machine learning algorithms.

[0149] Based on the results, the server automatically generates the application document. In this process, it uses a pre-prepared template engine to generate an application document with sections that meet the specified conditions. The generated application document is temporarily stored in cloud storage, making it easily accessible to the user.

[0150] The terminal provides users with a user interface that allows them to review application documents. Here, users can correct any deficiencies and electronically submit the corrected documents to the local government via the server.

[0151] Furthermore, the server stores historical bidding data provided by local governments in a database and uses data science techniques to predict bidding opportunities for the following year. This supports users in strategic bidding activities. Specific techniques include the use of time series analysis and regression models.

[0152] When a user inputs information into the system using a terminal, the emotion analysis engine acquires information in real time and analyzes the user's emotional state. This process includes facial recognition technology and keyboard input pattern analysis. The results of the emotion analysis are sent to a server and used to adjust the user interface and customize the information provided. For example, if a stressed state is detected, an easy-to-understand interface is provided, and suggestions are made that are easier to understand.

[0153] A concrete example of a prompt message is, "Please provide suggestions to offer when a user is feeling stressed about a new project." In this way, the system provides users with flexible and appropriate information, reducing the stress they experience while performing their tasks.

[0154] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0155] Step 1:

[0156] Users enter their company information into the system via a terminal. This information includes company name, address, industry, and past transaction history. This data is then transmitted to the system and delivered to the server.

[0157] Step 2:

[0158] The server puts the received corporate information through a data cleansing process. It checks for abnormal values ​​and formatting errors in the input information and prepares it for a standard format. At this stage, the cleansed data is ready.

[0159] Step 3:

[0160] The server analyzes the cleansed vendor information using a generating AI model. Specifically, it extracts useful information from the data using natural language processing (NLP) techniques and classifies companies into industry categories. The analysis results obtained through this process are then output.

[0161] Step 4:

[0162] Based on the analysis results, the server automatically generates application documents using a template engine. The analysis data is embedded into a pre-configured template, completing the application documents for submission to the local government. The generated documents are saved to cloud storage.

[0163] Step 5:

[0164] Users access application documents stored in the cloud and review their contents on their devices. The user interface allows for necessary modifications, and once editing is complete, the application can be electronically submitted to the local government with a single click.

[0165] Step 6:

[0166] The server collects historical bidding data provided by local governments and stores it in a database. Based on the collected data, it uses data science techniques to predict bidding opportunities for the following year. This process generates predictive analytics output that is useful for bidding strategies.

[0167] Step 7:

[0168] Once the user finishes inputting information, the emotion analysis engine built into the device analyzes the user's facial expressions and input patterns in real time. The resulting emotion information is sent to a server and used for flexible adjustments to the user interface and customization of information provision.

[0169] Step 8:

[0170] The server customizes suggestions based on the user's emotional state. For example, if stress is detected, the interface is changed to a more relaxing one, and simpler conditions are suggested. Suggestions are generated based on emotional data and provided to the user.

[0171] (Application Example 2)

[0172] 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 device 14 will be referred to as the "terminal."

[0173] Current transaction procedures are complex, placing a significant psychological burden on users and making efficient work difficult. Furthermore, the system lacks sufficient consideration for users' emotions and psychological states, resulting in a lack of personalized interfaces.

[0174] 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.

[0175] In this invention, the server includes means for an electronic computer to analyze and classify vendor information, means for automatically generating application forms based on the analysis, means for analyzing past bidding data to predict projects for the following year, means for analyzing the user's mental state using facial expression recognition technology, and means for adjusting the user interface based on the analyzed mental state. This reduces the mental burden on the user and enables more efficient work execution and personalized service provision.

[0176] An "electronic computing device" is a device that has the computing power to analyze and classify business information.

[0177] "Vendor information" refers to various data about companies and organizations involved in a transaction.

[0178] An "application form" is an official document required for business transactions and bidding.

[0179] "Automatic generation" refers to a system generating a specific output without human intervention.

[0180] "Past bidding data" refers to historical information about transactions that have taken place in the past.

[0181] "Prediction" is the process of estimating future events or trends based on past data.

[0182] "Facial expression recognition technology" is a technology that uses cameras and sensors to analyze a person's facial expressions and identify their emotions.

[0183] "Mental state" refers to the user's emotions and psychological condition.

[0184] A "user interface" refers to the screens or control panels that users use to interact with a system.

[0185] "Adjustment" refers to changing settings to achieve the optimal state according to the situation and conditions.

[0186] The system for realizing this invention comprises a computer, facial expression recognition technology, and a user interface. A server acts as the central point, first using the computer to analyze vendor information and classify it. Based on the classified information, an application form is automatically generated and displayed on the user's terminal.

[0187] The system utilizes facial expression recognition technologies such as Google® Cloud Vision API and Microsoft® Face API to analyze the user's psychological state in real time. Based on the analyzed mental state, the server provides an optimal user interface. For example, if the user is experiencing anxiety or stress, the screen design and displayed messages are adjusted to alleviate these feelings. Conversely, if positive emotions are detected, more proactive suggestions can be made, improving the efficiency of the service provider.

[0188] For example, if a user is conducting an online transaction and their tension is evident on their face, a message such as "Please proceed with confidence. This transaction can be canceled" could be displayed to help ensure the transaction proceeds smoothly.

[0189] Regarding the use of generative AI models, prompts such as "Analyze user emotions in real time during online transactions to ensure smooth transactions, provide relaxing messages and support information to nervous users, and add a feature to highlight the next step when emotions are positive" are used.

[0190] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0191] Step 1:

[0192] The server receives vendor information and prepares to begin analysis. It converts the received vendor information into a database format and performs preprocessing for categorization. From this input data, it extracts and organizes keywords such as the vendor's industry and transaction history.

[0193] Step 2:

[0194] The server uses a computer to analyze vendor information and classify it into the appropriate industry category. It extracts features from the input information and classifies them by comparing them with existing databases. The output is the classified vendor information, which is reflected in the display UI.

[0195] Step 3:

[0196] The server automatically generates application forms based on the classification results. It embeds the necessary information into a templated form and customizes it as needed. The generated application form is then formatted and output on the terminal in PDF or other format.

[0197] Step 4:

[0198] The terminal displays the generated application form to the user and prompts them for confirmation. The user reviews the content on the screen and electronically signs it. The confirmed application form then proceeds to the next step, the submission process.

[0199] Step 5:

[0200] The server queries past bidding data and performs analysis to predict the next year's projects. This involves inputting bidding history data and using statistical analysis and AI modeling techniques to identify patterns. The output is a list of predicted projects.

[0201] Step 6:

[0202] The server uses facial expression recognition technology to analyze the user's mental state in real time. Image data acquired by the camera is used as input, processed by an emotion recognition algorithm to identify the emotional state. The output is user interface adjustment information.

[0203] Step 7:

[0204] The device adjusts the user interface based on the analysis results. If an emotion indicating stress is detected, it displays relaxing colors and messages. The system feeds this information back and uses it to suggest the next interface.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] [Second Embodiment]

[0209] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0210] 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.

[0211] 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).

[0212] 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.

[0213] 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.

[0214] 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).

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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".

[0221] This invention is a system for streamlining the registration and bidding processes of local government businesses, and achieves automation using an electronic computer. This system includes data analysis functions, automatic application form generation functions, and bidding data analysis functions, and operates as described below.

[0222] The server first analyzes the company information received from the user. This analysis uses AI-powered natural language processing technology to classify the company information into specific industry categories. Based on these classifications, the server automatically generates application forms that differ for each local government. This process eliminates the need for users to manually create application forms, resulting in a significant improvement in operational efficiency.

[0223] The server also analyzes past bidding data collected from local governments. Advanced statistical methods are applied to this analysis to predict future projects. For example, based on past performance data, the server models bidding frequency, competition rates, and industry trends to generate project predictions for the following year. This prediction information is provided to users via terminals to aid in the development of bidding strategies.

[0224] Furthermore, the server presents the user with the most suitable bidding conditions. Here, the server learns from past bidding conditions and results, and based on that, makes a proposal optimized for the current project. The user can review the proposed conditions presented by the system on their terminal and make modifications as needed.

[0225] As a concrete example, consider a case where a manufacturer participates in a municipality's equipment upgrade project. By entering its own information into the system, the company automatically generates a registration application for the target municipality. Subsequently, based on the analysis of past bidding data provided by the system, the company learns that an increase in equipment upgrade projects is predicted for the following year. Furthermore, it can receive optimal bidding conditions from the server and prepare a competitive proposal. In this way, companies can participate in bidding efficiently while saving time and resources.

[0226] The following describes the processing flow.

[0227] Step 1:

[0228] The user uses a terminal to enter basic vendor information such as company name, corporate number, and business description. This information is then transmitted to the system.

[0229] Step 2:

[0230] The server analyzes the received company information and classifies it into industry categories using an AI model. Based on this classification, the type of application document required is determined.

[0231] Step 3:

[0232] The server automatically generates application form templates that differ for each municipality based on the classification results. Then, it fills in each item based on the analysis results.

[0233] Step 4:

[0234] Users can review the application form generated on their device and make corrections as needed. The application form is then submitted electronically to the local government.

[0235] Step 5:

[0236] The server collects past bidding data from each local government and stores it in a database. Using this data, AI calculates bidding rates and related indicators.

[0237] Step 6:

[0238] The server analyzes past performance data and uses an AI model to predict projects for the following year. The predicted information indicates trends related to specific industries and regions.

[0239] Step 7:

[0240] The server performs simulations that take into account past bidding conditions and results in the process of generating optimal bidding conditions for companies.

[0241] Step 8:

[0242] The user reviews the optimal bidding conditions provided by the server via their terminal and finalizes their proposal. This completes the process of preparing to participate in the bidding.

[0243] (Example 1)

[0244] 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."

[0245] Traditional local government vendor registration and bidding processes are time-consuming, labor-intensive, and poorly managed. Vendors expend considerable effort preparing applications and reviewing bidding conditions, and the lack of sufficient use of historical data for future forecasts makes effective strategic planning difficult.

[0246] 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.

[0247] In this invention, the server includes means for analyzing vendor information acquired from users by a data processing device using natural language processing technology and classifying that vendor information into industry categories; means for automatically generating application forms that conform to the format of each local government based on the analysis results; and means for analyzing past bidding data using statistical methods and predicting future project occurrences. This automates and streamlines the vendor registration and bidding processes, reducing the workload and enabling strategic decision-making.

[0248] A "data processing device" is a device equipped with computer-based functions for analyzing and classifying vendor information.

[0249] "Natural language processing technology" refers to a set of technologies that enable computers to understand, interpret, and manipulate human language.

[0250] An "industry category" is a classification used to identify the field of business activities of a company.

[0251] "Automatic generation of application forms" refers to the process of automatically creating necessary documents using a computer based on analyzed data.

[0252] "Statistical methods" are mathematical techniques used to analyze data and derive useful patterns and predictions.

[0253] A "machine learning model" is an algorithm that learns from past data and uses that data to make predictions and decisions.

[0254] "Optimal bidding conditions" are the conditions set to allow companies to bid in the most advantageous way possible.

[0255] To implement this invention, a server acts as the core of the entire system. The server first receives vendor information sent from users and analyzes it using natural language processing technology. In this process, natural language processing libraries such as TensorFlow and PyTorch are used to classify the vendor information into specific industry categories. The results of this classification are used to automatically generate application forms that differ for each local government. In the automatic generation of application forms, the data analyzed by the AI ​​is embedded into a pre-prepared application form template.

[0256] Furthermore, the server processes historical bidding data collected from local governments and performs detailed analysis using statistical analysis software such as R and scikit-learn. Based on the data obtained, it predicts future project occurrences and provides this information to users. This enables users to efficiently plan their bidding strategies.

[0257] Users receive these analysis results and predictive information through their devices and can review and modify their bidding conditions as needed. The server then presents optimized bidding conditions based on past bidding conditions and results, helping users bid under the most favorable conditions.

[0258] As a concrete example, let's consider a case where a manufacturer participates in a municipality's equipment upgrade project. By inputting their company information into the system, the necessary registration application forms for the municipality are automatically generated, and competitive bidding conditions are presented based on future project predictions derived from an analysis of past bidding data for that project.

[0259] An example of an input prompt for a generating AI model would be: "Please explain in natural language the procedure for a system that streamlines the registration and bidding process for local government contractors."

[0260] In this way, the invention can significantly improve the efficiency of the local government's vendor registration and bidding process through data analysis, automatic generation functions, and analysis and optimization of bidding data.

[0261] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0262] Step 1:

[0263] The server receives vendor information from the user. Basic information such as company name, industry, and location is provided as input data. The server analyzes this information using natural language processing technology and classifies it into a specific industry category. For example, it uses a text analysis algorithm to extract keywords related to the industry and then identifies the industry category based on the results. The classified vendor information is then generated as output.

[0264] Step 2:

[0265] The server automatically generates application forms that differ for each municipality based on classified vendor information. Pre-prepared application form templates and analyzed data are used as input. The server automatically creates the application form by filling in the appropriate data in each field of the template. The completed application form is produced as output. Users can view this application form through their terminal.

[0266] Step 3:

[0267] The server receives historical bidding data collected from local governments and performs statistical analysis on it. Input data includes past bid counts, competition rates, and industry trends. The server processes the data using advanced statistical methods to predict future project occurrences. Specifically, it extracts trends based on historical data and uses them to predict future situations. The output is a forecast of future bidding projects, which is then provided to the user.

[0268] Step 4:

[0269] The server learns from past bidding conditions and results to generate optimal bidding conditions for the current project. Past bidding results and condition data are used as input. The server utilizes machine learning models to calculate the most favorable conditions and creates an optimized proposal for the current bidding project. The generated bidding conditions are presented to the user as output. The user can review this proposal on their terminal and make modifications as needed.

[0270] (Application Example 1)

[0271] 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 glasses 214 will be referred to as the "terminal."

[0272] Logistics facilities face the problem of inefficiency due to the enormous amount of time and effort required in the selection of suppliers and the bidding process. Furthermore, errors and inaccurate future predictions resulting from manual analysis of historical data are also challenges. A system is needed to solve these problems and improve operational efficiency.

[0273] 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.

[0274] In this invention, the server includes means for an electronic computer to analyze and classify vendor information, means for automatically generating application forms based on the analysis, means for analyzing past bidding data to predict projects for the following year, and means for managing business partners at logistics facilities and presenting optimal bidding conditions based on information from an inventory management device. This makes it possible to streamline the selection of business partners and the bidding process at logistics facilities.

[0275] An "electronic computing device" is an information processing device that analyzes and classifies business information.

[0276] "Analysis" refers to the act of analyzing vendor information using natural language processing technology and classifying it into a specific industry category.

[0277] "Automatic application form generation" is a process that electronically creates application forms that differ for each local government based on analysis results.

[0278] "Bidding data analysis" is the act of analyzing past bidding information using statistical methods to predict the occurrence of projects in the following year.

[0279] A "logistics facility" is a general term for warehouses and distribution centers that handle the trading and management of goods.

[0280] An "item management device" is a device that collects and manages information on goods and packages handled within a logistics facility in real time.

[0281] "Presenting bidding conditions" is a function that analyzes the collected information and displays the most suitable conditions.

[0282] To implement this invention, a system is constructed using a server, terminals within the logistics facility, and an inventory management device. The server analyzes vendor information via an electronic computer and classifies it into industry categories using natural language processing technology with a generative AI model. Based on the classification results, it is possible to automatically generate different application forms for each local government. The server performs analysis using TensorFlow and processes the data with its own algorithm.

[0283] In addition, the server receives information from the article management device in the logistics facility, combines this information, visualizes past bidding data in Tableau, and predicts the occurrence of cases in the next fiscal year. Furthermore, based on the collected information, the server presents optimal bidding conditions and transmits the information to the user's smartphone terminal.

[0284] For example, when a user wishes to conduct a transaction for a new article, the server analyzes the corporate information and proposes an efficient bid considering the article processing status at the logistics facility. Through this process, the logistics facility can promptly present competitive conditions in real time. Specifically, an AI model for generation can be driven using a prompt sentence such as "Analyze the optimal corporate information regarding the bidding for new transport vehicles at the logistics center and propose the best bidding conditions."

[0285] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0286] Step 1:

[0287] The server receives, from the user, the corporate information of the merchant as an input, analyzes this using natural language processing technology with an AI model for generation, and classifies it into industry categories. The classification results are stored in an internal database.

[0288] Step 2:

[0289] Based on the classification results, the server automatically generates application forms in different formats for each local government. In this process, the application form is created by embedding necessary items using a template engine, and the result is electronically transmitted to the user's terminal.

[0290] Step 3:

[0291] The server receives inventory data and transaction information from the inventory management system within the logistics facility as input. This data is visualized in Tableau and combined with past bidding data to predict the occurrence of projects in the following year using statistical methods. The prediction results are stored on the server.

[0292] Step 4:

[0293] The server calculates the optimal bidding conditions based on prediction results and real-time logistics information. The calculation considers historical data and the current facility status, applying an optimization algorithm. The resulting bidding conditions are then notified to the user's smartphone.

[0294] Step 5:

[0295] Users review the optimal bidding conditions displayed on their terminals and adjust them as needed. The server receives the revised information from the user and electronically sends it to the local government or business partners as the final bid proposal.

[0296] 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.

[0297] This invention incorporates an "emotion engine" that recognizes user emotions into a system designed to streamline the registration and bidding processes for local government contractors. This system uses a computer to analyze and classify contractor information, automatically generate application forms, and analyze past bidding data. Furthermore, the emotion engine analyzes the user's emotions in real time during input, and uses the results to adjust the interface and customize proposals.

[0298] The server analyzes company information entered by users and classifies it into industry categories using AI. This analysis is then used to automatically generate application forms for each local government. The generated application forms are reviewed by the user on their terminal and electronically sent to the local government.

[0299] Furthermore, the server analyzes the past bidding data obtained from the local government and predicts the projects for the next year. This predicted data is provided to the user and serves to support strategic bidding activities. By incorporating an emotion engine here, a flexible approach that reflects the user's psychological state becomes possible.

[0300] The emotion engine has the ability to analyze emotions using the user's facial expression recognition technology and the patterns of input speed and content. This emotion data is fed back into the proposal of bidding conditions, and an optimized proposal according to the user's stress level and degree of interest is generated. Also, the emotion engine can learn from past emotion data to improve the accuracy of the next proposal.

[0301] For example, when the emotion engine determines that the user is feeling stressed about a new bidding project, the server provides a relaxing interface and presents a bidding condition plan with a low level of difficulty. Also, when positive emotions are detected, a challenging condition plan is proposed to enable a more proactive bid. In this way, this system realizes efficient business performance while reducing the user's mental burden.

[0302] The following describes the processing flow.

[0303] Step 1:

[0304] The user uses the terminal to input basic information such as the company name, corporate number, and business content into the system. This information is sent to the system.

[0305] Step 2:

[0306] The server analyzes the received vendor information and classifies it into industry categories using AI. Based on this classification result, it identifies which local government applications are required.

[0307] Step 3:

[0308] The server automatically creates application form templates according to the classification and fills in each item based on the analysis results. The generated application form is then sent to the user's terminal.

[0309] Step 4:

[0310] The user submits the application form, which they have viewed on their device, electronically to the local government. The server checks the transmission status and receives subsequent feedback.

[0311] Step 5:

[0312] The server retrieves past bidding data from a database and uses AI technology to predict future projects. These predictions are then used by users to formulate their strategies.

[0313] Step 6:

[0314] The emotion engine is activated and analyzes the user's emotional state in real time based on input patterns and sensor information obtained from the user's device.

[0315] Step 7:

[0316] Based on the analysis results from the emotion engine, the server adjusts the interface to match the user's stress level and level of interest. In particular, it generates optimal bidding conditions according to the user's emotional state.

[0317] Step 8:

[0318] Users review bid proposals from the server on an interface that reflects an emotion engine, and make the best selection. The proposals are further customized based on the user's emotional feedback.

[0319] (Example 2)

[0320] 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".

[0321] In the local government's vendor registration and bidding process, there is a need to reduce the time and effort required for analyzing vendor information and preparing applications, thereby supporting efficient and strategic bidding activities. Furthermore, there is a desire for a system that reduces user stress and provides flexible proposals tailored to individual psychological states.

[0322] 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.

[0323] In this invention, the server includes means comprising an electronic computer device that analyzes vendor information and classifies the results into industry categories; means for automatically generating application documents based on the analysis; means using artificial intelligence technology that analyzes past bidding data and predicts bidding projects for the following year; means for analyzing user emotions in real time based on user input information and adjusting the interface according to the results; and means for customizing the content of proposals provided to the user based on emotion data. This improves the user's work efficiency, reduces psychological burden, and enables the construction of appropriate and flexible bidding strategies.

[0324] An "electronic computing device" refers to a part or all of a computer system that performs data analysis, processing, storage, and communication.

[0325] "Vendor information" refers to relevant information such as the name, address, industry, and transaction history of companies and organizations.

[0326] An "industry category" is a category used to classify companies based on their business activities and operations.

[0327] An "application document" is a formal document prepared for submission to a local government or related organization.

[0328] "Artificial intelligence technology" is a technology that uses computers to replicate functions similar to human intelligence, enabling data analysis and prediction.

[0329] A "user" is the entity that operates the system and inputs information.

[0330] "Sentiment analysis" is the process of determining a user's emotional state based on input information and user feedback.

[0331] An "interface" refers to the connection point or user interface through which a user and a computer system exchange information.

[0332] "Customizing the proposed content" means adjusting the information and services provided according to the user's needs and circumstances.

[0333] This system is configured to streamline the local government's vendor registration and bidding process through collaboration between servers, terminals, and users. It primarily utilizes electronic computing devices, generative AI models, and sentiment analysis engines to analyze vendor information, automatically generate application documents, predict bidding data, and adjust the interface based on user sentiment.

[0334] The server receives vendor information submitted by users and first performs data cleansing. Then, using a generative AI model, it analyzes the company information using natural language processing (NLP) and classifies the companies into industry categories. This analysis utilizes natural language processing (NLP) techniques and machine learning algorithms.

[0335] Based on the results, the server automatically generates the application document. In this process, it uses a pre-prepared template engine to generate an application document with sections that meet the specified conditions. The generated application document is temporarily stored in cloud storage, making it easily accessible to the user.

[0336] The terminal provides users with a user interface that allows them to review application documents. Here, users can correct any deficiencies and electronically submit the corrected documents to the local government via the server.

[0337] Furthermore, the server stores historical bidding data provided by local governments in a database and uses data science techniques to predict bidding opportunities for the following year. This supports users in strategic bidding activities. Specific techniques include the use of time series analysis and regression models.

[0338] When a user inputs information into the system using a terminal, the emotion analysis engine acquires information in real time and analyzes the user's emotional state. This process includes facial recognition technology and keyboard input pattern analysis. The results of the emotion analysis are sent to a server and used to adjust the user interface and customize the information provided. For example, if a stressed state is detected, an easy-to-understand interface is provided, and suggestions are made that are easier to understand.

[0339] A concrete example of a prompt message is, "Please provide suggestions to offer when a user is feeling stressed about a new project." In this way, the system provides users with flexible and appropriate information, reducing the stress they experience while performing their tasks.

[0340] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0341] Step 1:

[0342] Users enter their company information into the system via a terminal. This information includes company name, address, industry, and past transaction history. This data is then transmitted to the system and delivered to the server.

[0343] Step 2:

[0344] The server puts the received corporate information through a data cleansing process. It checks for abnormal values ​​and formatting errors in the input information and prepares it for a standard format. At this stage, the cleansed data is ready.

[0345] Step 3:

[0346] The server analyzes the cleansed vendor information using a generating AI model. Specifically, it extracts useful information from the data using natural language processing (NLP) techniques and classifies companies into industry categories. The analysis results obtained through this process are then output.

[0347] Step 4:

[0348] Based on the analysis results, the server automatically generates application documents using a template engine. The analysis data is embedded into a pre-configured template, completing the application documents for submission to the local government. The generated documents are saved to cloud storage.

[0349] Step 5:

[0350] Users access application documents stored in the cloud and review their contents on their devices. The user interface allows for necessary modifications, and once editing is complete, the application can be electronically submitted to the local government with a single click.

[0351] Step 6:

[0352] The server collects historical bidding data provided by local governments and stores it in a database. Based on the collected data, it uses data science techniques to predict bidding opportunities for the following year. This process generates predictive analytics output that is useful for bidding strategies.

[0353] Step 7:

[0354] Once the user finishes inputting information, the emotion analysis engine built into the device analyzes the user's facial expressions and input patterns in real time. The resulting emotion information is sent to a server and used for flexible adjustments to the user interface and customization of information provision.

[0355] Step 8:

[0356] The server customizes suggestions based on the user's emotional state. For example, if stress is detected, the interface is changed to a more relaxing one, and simpler conditions are suggested. Suggestions are generated based on emotional data and provided to the user.

[0357] (Application Example 2)

[0358] 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."

[0359] Current transaction procedures are complex, placing a significant psychological burden on users and making efficient work difficult. Furthermore, the system lacks sufficient consideration for users' emotions and psychological states, resulting in a lack of personalized interfaces.

[0360] 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.

[0361] In this invention, the server includes means for an electronic computer to analyze and classify vendor information, means for automatically generating application forms based on the analysis, means for analyzing past bidding data to predict projects for the following year, means for analyzing the user's mental state using facial expression recognition technology, and means for adjusting the user interface based on the analyzed mental state. This reduces the mental burden on the user and enables more efficient work execution and personalized service provision.

[0362] An "electronic computing device" is a device that has the computing power to analyze and classify business information.

[0363] "Vendor information" refers to various data about companies and organizations involved in a transaction.

[0364] An "application form" is an official document required for business transactions and bidding.

[0365] "Automatic generation" refers to a system generating a specific output without human intervention.

[0366] "Past bidding data" refers to historical information about transactions that have taken place in the past.

[0367] "Prediction" is the process of estimating future events or trends based on past data.

[0368] "Facial expression recognition technology" is a technology that uses cameras and sensors to analyze a person's facial expressions and identify their emotions.

[0369] "Mental state" refers to the user's emotions and psychological condition.

[0370] A "user interface" refers to the screens or control panels that users use to interact with a system.

[0371] "Adjustment" refers to changing settings to achieve the optimal state according to the situation and conditions.

[0372] The system for realizing this invention comprises a computer, facial expression recognition technology, and a user interface. A server acts as the central point, first using the computer to analyze vendor information and classify it. Based on the classified information, an application form is automatically generated and displayed on the user's terminal.

[0373] The system utilizes facial expression recognition technology, such as Google Cloud Vision API and Microsoft Face API, to analyze the user's psychological state in real time. Based on the analyzed mental state, the server provides an optimal user interface. For example, if the user is experiencing anxiety or stress, the screen design and displayed messages are adjusted to alleviate these feelings. Conversely, if positive emotions are detected, more proactive suggestions can be made, improving the efficiency of the service provider.

[0374] For example, if a user is conducting an online transaction and their tension is evident on their face, a message such as "Please proceed with confidence. This transaction can be canceled" could be displayed to help ensure the transaction proceeds smoothly.

[0375] Regarding the use of generative AI models, prompts such as "Analyze user emotions in real time during online transactions to ensure smooth transactions, provide relaxing messages and support information to nervous users, and add a feature to highlight the next step when emotions are positive" are used.

[0376] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0377] Step 1:

[0378] The server receives vendor information and prepares to begin analysis. It converts the received vendor information into a database format and performs preprocessing for categorization. From this input data, it extracts and organizes keywords such as the vendor's industry and transaction history.

[0379] Step 2:

[0380] The server uses a computer to analyze vendor information and classify it into the appropriate industry category. It extracts features from the input information and classifies them by comparing them with existing databases. The output is the classified vendor information, which is reflected in the display UI.

[0381] Step 3:

[0382] The server automatically generates application forms based on the classification results. It embeds the necessary information into a templated form and customizes it as needed. The generated application form is then formatted and output on the terminal in PDF or other format.

[0383] Step 4:

[0384] The terminal displays the generated application form to the user and prompts them for confirmation. The user reviews the content on the screen and electronically signs it. The confirmed application form then proceeds to the next step, the submission process.

[0385] Step 5:

[0386] The server queries past bidding data and performs analysis to predict the next year's projects. This involves inputting bidding history data and using statistical analysis and AI modeling techniques to identify patterns. The output is a list of predicted projects.

[0387] Step 6:

[0388] The server uses facial expression recognition technology to analyze the user's mental state in real time. Image data acquired by the camera is used as input, processed by an emotion recognition algorithm to identify the emotional state. The output is user interface adjustment information.

[0389] Step 7:

[0390] The device adjusts the user interface based on the analysis results. If an emotion indicating stress is detected, it displays relaxing colors and messages. The system feeds this information back and uses it to suggest the next interface.

[0391] 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.

[0392] 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.

[0393] 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.

[0394] [Third Embodiment]

[0395] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0396] 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.

[0397] 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).

[0398] 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.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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".

[0407] This invention is a system for streamlining the registration and bidding processes of local government businesses, and achieves automation using an electronic computer. This system includes data analysis functions, automatic application form generation functions, and bidding data analysis functions, and operates as described below.

[0408] The server first analyzes the company information received from the user. This analysis uses AI-powered natural language processing technology to classify the company information into specific industry categories. Based on these classifications, the server automatically generates application forms that differ for each local government. This process eliminates the need for users to manually create application forms, resulting in a significant improvement in operational efficiency.

[0409] The server also analyzes past bidding data collected from local governments. Advanced statistical methods are applied to this analysis to predict future projects. For example, based on past performance data, the server models bidding frequency, competition rates, and industry trends to generate project predictions for the following year. This prediction information is provided to users via terminals to aid in the development of bidding strategies.

[0410] Furthermore, the server presents the user with the most suitable bidding conditions. Here, the server learns from past bidding conditions and results, and based on that, makes a proposal optimized for the current project. The user can review the proposed conditions presented by the system on their terminal and make modifications as needed.

[0411] As a concrete example, consider a case where a manufacturer participates in a municipality's equipment upgrade project. By entering its own information into the system, the company automatically generates a registration application for the target municipality. Subsequently, based on the analysis of past bidding data provided by the system, the company learns that an increase in equipment upgrade projects is predicted for the following year. Furthermore, it can receive optimal bidding conditions from the server and prepare a competitive proposal. In this way, companies can participate in bidding efficiently while saving time and resources.

[0412] The following describes the processing flow.

[0413] Step 1:

[0414] The user uses a terminal to enter basic vendor information such as company name, corporate number, and business description. This information is then transmitted to the system.

[0415] Step 2:

[0416] The server analyzes the received company information and classifies it into industry categories using an AI model. Based on this classification, the type of application document required is determined.

[0417] Step 3:

[0418] The server automatically generates application form templates that differ for each municipality based on the classification results. Then, it fills in each item based on the analysis results.

[0419] Step 4:

[0420] Users can review the application form generated on their device and make corrections as needed. The application form is then submitted electronically to the local government.

[0421] Step 5:

[0422] The server collects past bidding data from each local government and stores it in a database. Using this data, AI calculates bidding rates and related indicators.

[0423] Step 6:

[0424] The server analyzes past performance data and uses an AI model to predict projects for the following year. The predicted information indicates trends related to specific industries and regions.

[0425] Step 7:

[0426] The server performs simulations that take into account past bidding conditions and results in the process of generating optimal bidding conditions for companies.

[0427] Step 8:

[0428] The user reviews the optimal bidding conditions provided by the server via their terminal and finalizes their proposal. This completes the process of preparing to participate in the bidding.

[0429] (Example 1)

[0430] 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."

[0431] Traditional local government vendor registration and bidding processes are time-consuming, labor-intensive, and poorly managed. Vendors expend considerable effort preparing applications and reviewing bidding conditions, and the lack of sufficient use of historical data for future forecasts makes effective strategic planning difficult.

[0432] 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.

[0433] In this invention, the server includes means for analyzing vendor information acquired from users by a data processing device using natural language processing technology and classifying that vendor information into industry categories; means for automatically generating application forms that conform to the format of each local government based on the analysis results; and means for analyzing past bidding data using statistical methods and predicting future project occurrences. This automates and streamlines the vendor registration and bidding processes, reducing the workload and enabling strategic decision-making.

[0434] A "data processing device" is a device equipped with computer-based functions for analyzing and classifying vendor information.

[0435] "Natural language processing technology" refers to a set of technologies that enable computers to understand, interpret, and manipulate human language.

[0436] An "industry category" is a classification used to identify the field of business activities of a company.

[0437] "Automatic generation of application forms" refers to the process of automatically creating necessary documents using a computer based on analyzed data.

[0438] "Statistical methods" are mathematical techniques used to analyze data and derive useful patterns and predictions.

[0439] A "machine learning model" is an algorithm that learns from past data and uses that data to make predictions and decisions.

[0440] "Optimal bidding conditions" are the conditions set to allow companies to bid in the most advantageous way possible.

[0441] To implement this invention, a server acts as the core of the entire system. The server first receives vendor information sent from users and analyzes it using natural language processing technology. In this process, natural language processing libraries such as TensorFlow and PyTorch are used to classify the vendor information into specific industry categories. The results of this classification are used to automatically generate application forms that differ for each local government. In the automatic generation of application forms, the data analyzed by the AI ​​is embedded into a pre-prepared application form template.

[0442] Furthermore, the server processes historical bidding data collected from local governments and performs detailed analysis using statistical analysis software such as R and scikit-learn. Based on the data obtained, it predicts future project occurrences and provides this information to users. This enables users to efficiently plan their bidding strategies.

[0443] Users receive these analysis results and predictive information through their devices and can review and modify their bidding conditions as needed. The server then presents optimized bidding conditions based on past bidding conditions and results, helping users bid under the most favorable conditions.

[0444] As a concrete example, let's consider a case where a manufacturer participates in a municipality's equipment upgrade project. By inputting their company information into the system, the necessary registration application forms for the municipality are automatically generated, and competitive bidding conditions are presented based on future project predictions derived from an analysis of past bidding data for that project.

[0445] An example of an input prompt for a generating AI model would be: "Please explain in natural language the procedure for a system that streamlines the registration and bidding process for local government contractors."

[0446] In this way, the invention can significantly improve the efficiency of the local government's vendor registration and bidding process through data analysis, automatic generation functions, and analysis and optimization of bidding data.

[0447] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0448] Step 1:

[0449] The server receives vendor information from the user. Basic information such as company name, industry, and location is provided as input data. The server analyzes this information using natural language processing technology and classifies it into a specific industry category. For example, it uses a text analysis algorithm to extract keywords related to the industry and then identifies the industry category based on the results. The classified vendor information is then generated as output.

[0450] Step 2:

[0451] The server automatically generates application forms that differ for each municipality based on classified vendor information. Pre-prepared application form templates and analyzed data are used as input. The server automatically creates the application form by filling in the appropriate data in each field of the template. The completed application form is produced as output. Users can view this application form through their terminal.

[0452] Step 3:

[0453] The server receives historical bidding data collected from local governments and performs statistical analysis on it. Input data includes past bid counts, competition rates, and industry trends. The server processes the data using advanced statistical methods to predict future project occurrences. Specifically, it extracts trends based on historical data and uses them to predict future situations. The output is a forecast of future bidding projects, which is then provided to the user.

[0454] Step 4:

[0455] The server learns from past bidding conditions and results to generate optimal bidding conditions for the current project. Past bidding results and condition data are used as input. The server utilizes machine learning models to calculate the most favorable conditions and creates an optimized proposal for the current bidding project. The generated bidding conditions are presented to the user as output. The user can review this proposal on their terminal and make modifications as needed.

[0456] (Application Example 1)

[0457] 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."

[0458] Logistics facilities face the problem of inefficiency due to the enormous amount of time and effort required in the selection of suppliers and the bidding process. Furthermore, errors and inaccurate future predictions resulting from manual analysis of historical data are also challenges. A system is needed to solve these problems and improve operational efficiency.

[0459] 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.

[0460] In this invention, the server includes means for an electronic computer to analyze and classify vendor information, means for automatically generating application forms based on the analysis, means for analyzing past bidding data to predict projects for the following year, and means for managing business partners at logistics facilities and presenting optimal bidding conditions based on information from an inventory management device. This makes it possible to streamline the selection of business partners and the bidding process at logistics facilities.

[0461] An "electronic computing device" is an information processing device that analyzes and classifies business information.

[0462] "Analysis" refers to the act of analyzing vendor information using natural language processing technology and classifying it into a specific industry category.

[0463] "Automatic application form generation" is a process that electronically creates application forms that differ for each local government based on analysis results.

[0464] "Bidding data analysis" is the act of analyzing past bidding information using statistical methods to predict the occurrence of projects in the following year.

[0465] A "logistics facility" is a general term for warehouses and distribution centers that handle the trading and management of goods.

[0466] An "item management device" is a device that collects and manages information on goods and packages handled within a logistics facility in real time.

[0467] "Presenting bidding conditions" is a function that analyzes the collected information and displays the most suitable conditions.

[0468] To implement this invention, a system is constructed using a server, terminals within the logistics facility, and an inventory management device. The server analyzes vendor information via an electronic computer and classifies it into industry categories using natural language processing technology with a generative AI model. Based on the classification results, it is possible to automatically generate different application forms for each local government. The server performs analysis using TensorFlow and processes the data with its own algorithm.

[0469] The server also receives information from logistics facilities regarding inventory management devices, combines this information with past bidding data, visualizes it in Tableau, and predicts the occurrence of projects in the following year. Furthermore, the server presents optimal bidding conditions based on the collected information and sends the information to the user's smartphone.

[0470] For example, when a user requests a trade for new goods, the server analyzes company information and proposes efficient bids considering the goods processing status at the logistics facility. This process allows logistics facilities to quickly present competitive terms in real time. Specifically, a prompt such as, "Analyze the optimal company information for bidding on new transport vehicles for the logistics center and propose the best bid terms," ​​can be used to drive the generative AI model.

[0471] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0472] Step 1:

[0473] The server receives company information from users as input. This information is analyzed using natural language processing technology with a generative AI model and classified into industry categories. The classification results are stored in an internal database.

[0474] Step 2:

[0475] Based on the classification results, the server automatically generates application forms in different formats for each municipality. In this process, it creates the application form by filling in the necessary items using a template engine and then electronically transmits the results to the user's terminal.

[0476] Step 3:

[0477] The server receives inventory data and transaction information from the inventory management system within the logistics facility as input. This data is visualized in Tableau and combined with past bidding data to predict the occurrence of projects in the following year using statistical methods. The prediction results are stored on the server.

[0478] Step 4:

[0479] The server calculates the optimal bidding conditions based on prediction results and real-time logistics information. The calculation considers historical data and the current facility status, applying an optimization algorithm. The resulting bidding conditions are then notified to the user's smartphone.

[0480] Step 5:

[0481] Users review the optimal bidding conditions displayed on their terminals and adjust them as needed. The server receives the revised information from the user and electronically sends it to the local government or business partners as the final bid proposal.

[0482] 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.

[0483] This invention incorporates an "emotion engine" that recognizes user emotions into a system designed to streamline the registration and bidding processes for local government contractors. This system uses a computer to analyze and classify contractor information, automatically generate application forms, and analyze past bidding data. Furthermore, the emotion engine analyzes the user's emotions in real time during input, and uses the results to adjust the interface and customize proposals.

[0484] The server analyzes company information entered by users and classifies it into industry categories using AI. This analysis is then used to automatically generate application forms for each local government. The generated application forms are reviewed by the user on their terminal and electronically sent to the local government.

[0485] Furthermore, the server analyzes past bidding data obtained from local governments to predict projects for the following year. This predictive data is provided to users and plays a role in supporting strategic bidding activities. By incorporating an emotion engine, a flexible approach that reflects the user's psychological state becomes possible.

[0486] The emotion engine has the ability to analyze emotions using user facial expression recognition technology and patterns in input speed and content. This emotion data is fed back into the bidding condition proposals, generating optimized proposals tailored to the user's stress level and level of interest. The emotion engine can also learn from past emotion data to improve the accuracy of future proposals.

[0487] For example, if the emotion engine determines that a user is feeling stressed about a new bidding project, the server will provide a relaxing interface and present easier bidding options. Conversely, if positive emotions are detected, more challenging options will be proposed, enabling more proactive bidding. In this way, the system reduces the user's mental burden while enabling efficient work execution.

[0488] The following describes the processing flow.

[0489] Step 1:

[0490] The user uses a terminal to enter basic information such as company name, corporate number, and business details into the system. This information is then transmitted to the system.

[0491] Step 2:

[0492] The server analyzes the received vendor information and uses AI to classify it into industry categories. Based on this classification, it identifies which municipality's application form is required.

[0493] Step 3:

[0494] The server automatically creates application form templates according to the classification and fills in each item based on the analysis results. The generated application form is then sent to the user's terminal.

[0495] Step 4:

[0496] The user submits the application form, which they have viewed on their device, electronically to the local government. The server checks the transmission status and receives subsequent feedback.

[0497] Step 5:

[0498] The server retrieves past bidding data from a database and uses AI technology to predict future projects. These predictions are then used by users to formulate their strategies.

[0499] Step 6:

[0500] The emotion engine is activated and analyzes the user's emotional state in real time based on input patterns and sensor information obtained from the user's device.

[0501] Step 7:

[0502] Based on the analysis results from the emotion engine, the server adjusts the interface to match the user's stress level and level of interest. In particular, it generates optimal bidding conditions according to the user's emotional state.

[0503] Step 8:

[0504] Users review bid proposals from the server on an interface that reflects an emotion engine, and make the best selection. The proposals are further customized based on the user's emotional feedback.

[0505] (Example 2)

[0506] 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."

[0507] In the local government's vendor registration and bidding process, there is a need to reduce the time and effort required for analyzing vendor information and preparing applications, thereby supporting efficient and strategic bidding activities. Furthermore, there is a desire for a system that reduces user stress and provides flexible proposals tailored to individual psychological states.

[0508] 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.

[0509] In this invention, the server includes means comprising an electronic computer device that analyzes vendor information and classifies the results into industry categories; means for automatically generating application documents based on the analysis; means using artificial intelligence technology that analyzes past bidding data and predicts bidding projects for the following year; means for analyzing user emotions in real time based on user input information and adjusting the interface according to the results; and means for customizing the content of proposals provided to the user based on emotion data. This improves the user's work efficiency, reduces psychological burden, and enables the construction of appropriate and flexible bidding strategies.

[0510] An "electronic computing device" refers to a part or all of a computer system that performs data analysis, processing, storage, and communication.

[0511] "Vendor information" refers to relevant information such as the name, address, industry, and transaction history of companies and organizations.

[0512] An "industry category" is a category used to classify companies based on their business activities and operations.

[0513] An "application document" is a formal document prepared for submission to a local government or related organization.

[0514] "Artificial intelligence technology" is a technology that uses computers to replicate functions similar to human intelligence, enabling data analysis and prediction.

[0515] A "user" is the entity that operates the system and inputs information.

[0516] "Sentiment analysis" is the process of determining a user's emotional state based on input information and user feedback.

[0517] An "interface" refers to the connection point or user interface through which a user and a computer system exchange information.

[0518] "Customizing the proposed content" means adjusting the information and services provided according to the user's needs and circumstances.

[0519] This system is configured to streamline the local government's vendor registration and bidding process through collaboration between servers, terminals, and users. It primarily utilizes electronic computing devices, generative AI models, and sentiment analysis engines to analyze vendor information, automatically generate application documents, predict bidding data, and adjust the interface based on user sentiment.

[0520] The server receives vendor information submitted by users and first performs data cleansing. Then, using a generative AI model, it analyzes the company information using natural language processing (NLP) and classifies the companies into industry categories. This analysis utilizes natural language processing (NLP) techniques and machine learning algorithms.

[0521] Based on the results, the server automatically generates the application document. In this process, it uses a pre-prepared template engine to generate an application document with sections that meet the specified conditions. The generated application document is temporarily stored in cloud storage, making it easily accessible to the user.

[0522] The terminal provides users with a user interface that allows them to review application documents. Here, users can correct any deficiencies and electronically submit the corrected documents to the local government via the server.

[0523] Furthermore, the server stores historical bidding data provided by local governments in a database and uses data science techniques to predict bidding opportunities for the following year. This supports users in strategic bidding activities. Specific techniques include the use of time series analysis and regression models.

[0524] When a user inputs information into the system using a terminal, the emotion analysis engine acquires information in real time and analyzes the user's emotional state. This process includes facial recognition technology and keyboard input pattern analysis. The results of the emotion analysis are sent to a server and used to adjust the user interface and customize the information provided. For example, if a stressed state is detected, an easy-to-understand interface is provided, and suggestions are made that are easier to understand.

[0525] A concrete example of a prompt message is, "Please provide suggestions to offer when a user is feeling stressed about a new project." In this way, the system provides users with flexible and appropriate information, reducing the stress they experience while performing their tasks.

[0526] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0527] Step 1:

[0528] Users enter their company information into the system via a terminal. This information includes company name, address, industry, and past transaction history. This data is then transmitted to the system and delivered to the server.

[0529] Step 2:

[0530] The server puts the received corporate information through a data cleansing process. It checks for abnormal values ​​and formatting errors in the input information and prepares it for a standard format. At this stage, the cleansed data is ready.

[0531] Step 3:

[0532] The server analyzes the cleansed vendor information using a generating AI model. Specifically, it extracts useful information from the data using natural language processing (NLP) techniques and classifies companies into industry categories. The analysis results obtained through this process are then output.

[0533] Step 4:

[0534] Based on the analysis results, the server automatically generates application documents using a template engine. The analysis data is embedded into a pre-configured template, completing the application documents for submission to the local government. The generated documents are saved to cloud storage.

[0535] Step 5:

[0536] Users access application documents stored in the cloud and review their contents on their devices. The user interface allows for necessary modifications, and once editing is complete, the application can be electronically submitted to the local government with a single click.

[0537] Step 6:

[0538] The server collects historical bidding data provided by local governments and stores it in a database. Based on the collected data, it uses data science techniques to predict bidding opportunities for the following year. This process generates predictive analytics output that is useful for bidding strategies.

[0539] Step 7:

[0540] Once the user finishes inputting information, an emotion analysis engine built into the device analyzes the user's facial expressions and input patterns in real time. The resulting emotion information is sent to a server and used for flexible adjustments to the user interface and customization of information provision.

[0541] Step 8:

[0542] The server customizes suggestions based on the user's emotional state. For example, if stress is detected, the interface is changed to a more relaxing one, and simpler conditions are suggested. Suggestions are generated based on emotional data and provided to the user.

[0543] (Application Example 2)

[0544] 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."

[0545] Current transaction procedures are complex, placing a significant psychological burden on users and making efficient work difficult. Furthermore, the system lacks sufficient consideration for users' emotions and psychological states, resulting in a lack of personalized interfaces.

[0546] 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.

[0547] In this invention, the server includes means for an electronic computer to analyze and classify vendor information, means for automatically generating application forms based on the analysis, means for analyzing past bidding data to predict projects for the following year, means for analyzing the user's mental state using facial expression recognition technology, and means for adjusting the user interface based on the analyzed mental state. This reduces the mental burden on the user and enables more efficient work execution and personalized service provision.

[0548] An "electronic computing device" is a device that has the computing power to analyze and classify business information.

[0549] "Vendor information" refers to various data about companies and organizations involved in a transaction.

[0550] An "application form" is an official document required for business transactions and bidding.

[0551] "Automatic generation" refers to a system generating a specific output without human intervention.

[0552] "Past bidding data" refers to historical information about transactions that have taken place in the past.

[0553] "Prediction" is the process of estimating future events or trends based on past data.

[0554] "Facial expression recognition technology" is a technology that uses cameras and sensors to analyze a person's facial expressions and identify their emotions.

[0555] "Mental state" refers to the user's emotions and psychological condition.

[0556] A "user interface" refers to the screens or control panels that users use to interact with a system.

[0557] "Adjustment" refers to changing settings to achieve the optimal state according to the situation and conditions.

[0558] The system for realizing this invention comprises a computer, facial expression recognition technology, and a user interface. A server acts as the central point, first using the computer to analyze vendor information and classify it. Based on the classified information, an application form is automatically generated and displayed on the user's terminal.

[0559] The system utilizes facial expression recognition technology, such as Google Cloud Vision API and Microsoft Face API, to analyze the user's psychological state in real time. Based on the analyzed mental state, the server provides an optimal user interface. For example, if the user is experiencing anxiety or stress, the screen design and displayed messages are adjusted to alleviate these feelings. Conversely, if positive emotions are detected, more proactive suggestions can be made, improving the efficiency of the service provider.

[0560] For example, if a user is conducting an online transaction and their tension is evident on their face, a message such as "Please proceed with confidence. This transaction can be canceled" could be displayed to help ensure the transaction proceeds smoothly.

[0561] Regarding the use of generative AI models, prompts such as "Analyze user emotions in real time during online transactions to ensure smooth transactions, provide relaxing messages and support information to nervous users, and add a feature to highlight the next step when emotions are positive" are used.

[0562] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0563] Step 1:

[0564] The server receives vendor information and prepares to begin analysis. It converts the received vendor information into a database format and performs preprocessing for categorization. From this input data, it extracts and organizes keywords such as the vendor's industry and transaction history.

[0565] Step 2:

[0566] The server uses a computer to analyze vendor information and classify it into the appropriate industry category. It extracts features from the input information and classifies them by comparing them with existing databases. The output is the classified vendor information, which is reflected in the display UI.

[0567] Step 3:

[0568] The server automatically generates application forms based on the classification results. It embeds the necessary information into a templated form and customizes it as needed. The generated application form is then formatted and output on the terminal in PDF or other format.

[0569] Step 4:

[0570] The terminal displays the generated application form to the user and prompts them for confirmation. The user reviews the content on the screen and electronically signs it. The confirmed application form then proceeds to the next step, the submission process.

[0571] Step 5:

[0572] The server queries past bidding data and performs analysis to predict the next year's projects. This involves inputting bidding history data and using statistical analysis and AI modeling techniques to identify patterns. The output is a list of predicted projects.

[0573] Step 6:

[0574] The server uses facial expression recognition technology to analyze the user's mental state in real time. Image data acquired by the camera is used as input, processed by an emotion recognition algorithm to identify the emotional state. The output is user interface adjustment information.

[0575] Step 7:

[0576] The device adjusts the user interface based on the analysis results. If an emotion indicating stress is detected, it displays relaxing colors and messages. The system feeds this information back and uses it to suggest the next interface.

[0577] 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.

[0578] 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.

[0579] 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.

[0580] [Fourth Embodiment]

[0581] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0582] 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.

[0583] 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).

[0584] 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.

[0585] 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.

[0586] 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).

[0587] 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.

[0588] 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.

[0589] 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.

[0590] 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.

[0591] 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.

[0592] 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.

[0593] 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".

[0594] This invention is a system for streamlining the registration and bidding processes of local government businesses, and achieves automation using an electronic computer. This system includes data analysis functions, automatic application form generation functions, and bidding data analysis functions, and operates as described below.

[0595] The server first analyzes the company information received from the user. This analysis uses AI-powered natural language processing technology to classify the company information into specific industry categories. Based on these classifications, the server automatically generates application forms that differ for each local government. This process eliminates the need for users to manually create application forms, resulting in a significant improvement in operational efficiency.

[0596] The server also analyzes past bidding data collected from local governments. Advanced statistical methods are applied to this analysis to predict future projects. For example, based on past performance data, the server models bidding frequency, competition rates, and industry trends to generate project predictions for the following year. This prediction information is provided to users via terminals to aid in the development of bidding strategies.

[0597] Furthermore, the server presents the user with the most suitable bidding conditions. Here, the server learns from past bidding conditions and results, and based on that, makes a proposal optimized for the current project. The user can review the proposed conditions presented by the system on their terminal and make modifications as needed.

[0598] As a concrete example, consider a case where a manufacturer participates in a municipality's equipment upgrade project. By entering its own information into the system, the company automatically generates a registration application for the target municipality. Subsequently, based on the analysis of past bidding data provided by the system, the company learns that an increase in equipment upgrade projects is predicted for the following year. Furthermore, it can receive optimal bidding conditions from the server and prepare a competitive proposal. In this way, companies can participate in bidding efficiently while saving time and resources.

[0599] The following describes the processing flow.

[0600] Step 1:

[0601] The user uses a terminal to enter basic vendor information such as company name, corporate number, and business description. This information is then transmitted to the system.

[0602] Step 2:

[0603] The server analyzes the received company information and classifies it into industry categories using an AI model. Based on this classification, the type of application document required is determined.

[0604] Step 3:

[0605] The server automatically generates application form templates that differ for each municipality based on the classification results. Then, it fills in each item based on the analysis results.

[0606] Step 4:

[0607] Users can review the application form generated on their device and make corrections as needed. The application form is then submitted electronically to the local government.

[0608] Step 5:

[0609] The server collects past bidding data from each local government and stores it in a database. Using this data, AI calculates bidding rates and related indicators.

[0610] Step 6:

[0611] The server analyzes past performance data and uses an AI model to predict projects for the following year. The predicted information indicates trends related to specific industries and regions.

[0612] Step 7:

[0613] The server performs simulations that take into account past bidding conditions and results in the process of generating optimal bidding conditions for companies.

[0614] Step 8:

[0615] The user reviews the optimal bidding conditions provided by the server via their terminal and finalizes their proposal. This completes the process of preparing to participate in the bidding.

[0616] (Example 1)

[0617] 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".

[0618] Traditional local government vendor registration and bidding processes are time-consuming, labor-intensive, and poorly managed. Vendors expend considerable effort preparing applications and reviewing bidding conditions, and the lack of sufficient use of historical data for future forecasts makes effective strategic planning difficult.

[0619] 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.

[0620] In this invention, the server includes means for analyzing vendor information acquired from users by a data processing device using natural language processing technology and classifying that vendor information into industry categories; means for automatically generating application forms that conform to the format of each local government based on the analysis results; and means for analyzing past bidding data using statistical methods and predicting future project occurrences. This automates and streamlines the vendor registration and bidding processes, reducing the workload and enabling strategic decision-making.

[0621] A "data processing device" is a device equipped with computer-based functions for analyzing and classifying vendor information.

[0622] "Natural language processing technology" refers to a set of technologies that enable computers to understand, interpret, and manipulate human language.

[0623] An "industry category" is a classification used to identify the field of business activities of a company.

[0624] "Automatic generation of application forms" refers to the process of automatically creating necessary documents using a computer based on analyzed data.

[0625] "Statistical methods" are mathematical techniques used to analyze data and derive useful patterns and predictions.

[0626] A "machine learning model" is an algorithm that learns from past data and uses that data to make predictions and decisions.

[0627] "Optimal bidding conditions" are the conditions set to allow companies to bid in the most advantageous way possible.

[0628] To implement this invention, a server acts as the core of the entire system. The server first receives vendor information sent from users and analyzes it using natural language processing technology. In this process, natural language processing libraries such as TensorFlow and PyTorch are used to classify the vendor information into specific industry categories. The results of this classification are used to automatically generate application forms that differ for each local government. In the automatic generation of application forms, the data analyzed by the AI ​​is embedded into a pre-prepared application form template.

[0629] Furthermore, the server processes historical bidding data collected from local governments and performs detailed analysis using statistical analysis software such as R and scikit-learn. Based on the data obtained, it predicts future project occurrences and provides this information to users. This enables users to efficiently plan their bidding strategies.

[0630] Users receive these analysis results and predictive information through their devices and can review and modify their bidding conditions as needed. The server then presents optimized bidding conditions based on past bidding conditions and results, helping users bid under the most favorable conditions.

[0631] As a concrete example, let's consider a case where a manufacturer participates in a municipality's equipment upgrade project. By inputting their company information into the system, the necessary registration application forms for the municipality are automatically generated, and competitive bidding conditions are presented based on future project predictions derived from an analysis of past bidding data for that project.

[0632] An example of an input prompt for a generating AI model would be: "Please explain in natural language the procedure for a system that streamlines the registration and bidding process for local government contractors."

[0633] In this way, the invention can significantly improve the efficiency of the local government's vendor registration and bidding process through data analysis, automatic generation functions, and analysis and optimization of bidding data.

[0634] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0635] Step 1:

[0636] The server receives vendor information from the user. Basic information such as company name, industry, and location is provided as input data. The server analyzes this information using natural language processing technology and classifies it into a specific industry category. For example, it uses a text analysis algorithm to extract keywords related to the industry and then identifies the industry category based on the results. The classified vendor information is then generated as output.

[0637] Step 2:

[0638] The server automatically generates application forms that differ for each municipality based on classified vendor information. Pre-prepared application form templates and analyzed data are used as input. The server automatically creates the application form by filling in the appropriate data in each field of the template. The completed application form is produced as output. Users can view this application form through their terminal.

[0639] Step 3:

[0640] The server receives historical bidding data collected from local governments and performs statistical analysis on it. Input data includes past bid counts, competition rates, and industry trends. The server processes the data using advanced statistical methods to predict future project occurrences. Specifically, it extracts trends based on historical data and uses them to predict future situations. The output is a forecast of future bidding projects, which is then provided to the user.

[0641] Step 4:

[0642] The server learns from past bidding conditions and results to generate optimal bidding conditions for the current project. Past bidding results and condition data are used as input. The server utilizes machine learning models to calculate the most favorable conditions and creates an optimized proposal for the current bidding project. The generated bidding conditions are presented to the user as output. The user can review this proposal on their terminal and make modifications as needed.

[0643] (Application Example 1)

[0644] 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".

[0645] Logistics facilities face the problem of inefficiency due to the enormous amount of time and effort required in the selection of suppliers and the bidding process. Furthermore, errors and inaccurate future predictions resulting from manual analysis of historical data are also challenges. A system is needed to solve these problems and improve operational efficiency.

[0646] 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.

[0647] In this invention, the server includes means for an electronic computer to analyze and classify vendor information, means for automatically generating application forms based on the analysis, means for analyzing past bidding data to predict projects for the following year, and means for managing business partners at logistics facilities and presenting optimal bidding conditions based on information from an inventory management device. This makes it possible to streamline the selection of business partners and the bidding process at logistics facilities.

[0648] An "electronic computing device" is an information processing device that analyzes and classifies business information.

[0649] "Analysis" refers to the act of analyzing vendor information using natural language processing technology and classifying it into a specific industry category.

[0650] "Automatic application form generation" is a process that electronically creates application forms that differ for each local government based on analysis results.

[0651] "Bidding data analysis" is the act of analyzing past bidding information using statistical methods to predict the occurrence of projects in the following year.

[0652] A "logistics facility" is a general term for warehouses and distribution centers that handle the trading and management of goods.

[0653] An "item management device" is a device that collects and manages information on goods and packages handled within a logistics facility in real time.

[0654] "Presenting bidding conditions" is a function that analyzes the collected information and displays the most suitable conditions.

[0655] To implement this invention, a system is constructed using a server, terminals within the logistics facility, and an inventory management device. The server analyzes vendor information via an electronic computer and classifies it into industry categories using natural language processing technology with a generative AI model. Based on the classification results, it is possible to automatically generate different application forms for each local government. The server performs analysis using TensorFlow and processes the data with its own algorithm.

[0656] The server also receives information from logistics facilities regarding inventory management devices, combines this information with past bidding data, visualizes it in Tableau, and predicts the occurrence of projects in the following year. Furthermore, the server presents optimal bidding conditions based on the collected information and sends the information to the user's smartphone.

[0657] For example, when a user requests a trade for new goods, the server analyzes company information and proposes efficient bids considering the goods processing status at the logistics facility. This process allows logistics facilities to quickly present competitive terms in real time. Specifically, a prompt such as, "Analyze the optimal company information for bidding on new transport vehicles for the logistics center and propose the best bid terms," ​​can be used to drive the generative AI model.

[0658] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0659] Step 1:

[0660] The server receives company information from users as input. This information is analyzed using natural language processing technology with a generative AI model and classified into industry categories. The classification results are stored in an internal database.

[0661] Step 2:

[0662] Based on the classification results, the server automatically generates application forms in different formats for each municipality. In this process, it creates the application form by filling in the necessary items using a template engine and then electronically transmits the results to the user's terminal.

[0663] Step 3:

[0664] The server receives inventory data and transaction information from the inventory management system within the logistics facility as input. This data is visualized in Tableau and combined with past bidding data to predict the occurrence of projects in the following year using statistical methods. The prediction results are stored on the server.

[0665] Step 4:

[0666] The server calculates the optimal bidding conditions based on prediction results and real-time logistics information. The calculation considers historical data and the current facility status, applying an optimization algorithm. The resulting bidding conditions are then notified to the user's smartphone.

[0667] Step 5:

[0668] Users review the optimal bidding conditions displayed on their terminals and adjust them as needed. The server receives the revised information from the user and electronically sends it to the local government or business partners as the final bid proposal.

[0669] 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.

[0670] This invention incorporates an "emotion engine" that recognizes user emotions into a system designed to streamline the registration and bidding processes for local government contractors. This system uses a computer to analyze and classify contractor information, automatically generate application forms, and analyze past bidding data. Furthermore, the emotion engine analyzes the user's emotions in real time during input, and uses the results to adjust the interface and customize proposals.

[0671] The server analyzes company information entered by users and classifies it into industry categories using AI. This analysis is then used to automatically generate application forms for each local government. The generated application forms are reviewed by the user on their terminal and electronically sent to the local government.

[0672] Furthermore, the server analyzes past bidding data obtained from local governments to predict projects for the following year. This predictive data is provided to users and plays a role in supporting strategic bidding activities. By incorporating an emotion engine, a flexible approach that reflects the user's psychological state becomes possible.

[0673] The emotion engine has the ability to analyze emotions using user facial expression recognition technology and patterns in input speed and content. This emotion data is fed back into the bidding condition proposals, generating optimized proposals tailored to the user's stress level and level of interest. The emotion engine can also learn from past emotion data to improve the accuracy of future proposals.

[0674] For example, if the emotion engine determines that a user is feeling stressed about a new bidding project, the server will provide a relaxing interface and present easier bidding options. Conversely, if positive emotions are detected, more challenging options will be proposed, enabling more proactive bidding. In this way, the system reduces the user's mental burden while enabling efficient work execution.

[0675] The following describes the processing flow.

[0676] Step 1:

[0677] The user uses a terminal to enter basic information such as company name, corporate number, and business details into the system. This information is then transmitted to the system.

[0678] Step 2:

[0679] The server analyzes the received vendor information and uses AI to classify it into industry categories. Based on this classification, it identifies which municipality's application form is required.

[0680] Step 3:

[0681] The server automatically creates application form templates according to the classification and fills in each item based on the analysis results. The generated application form is then sent to the user's terminal.

[0682] Step 4:

[0683] The user submits the application form, which they have viewed on their device, electronically to the local government. The server checks the transmission status and receives subsequent feedback.

[0684] Step 5:

[0685] The server retrieves past bidding data from a database and uses AI technology to predict future projects. These predictions are then used by users to formulate their strategies.

[0686] Step 6:

[0687] The emotion engine is activated and analyzes the user's emotional state in real time based on input patterns and sensor information obtained from the user's device.

[0688] Step 7:

[0689] Based on the analysis results from the emotion engine, the server adjusts the interface to match the user's stress level and level of interest. In particular, it generates optimal bidding conditions according to the user's emotional state.

[0690] Step 8:

[0691] Users review bid proposals from the server on an interface that reflects an emotion engine, and make the best selection. The proposals are further customized based on the user's emotional feedback.

[0692] (Example 2)

[0693] 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".

[0694] In the local government's vendor registration and bidding process, there is a need to reduce the time and effort required for analyzing vendor information and preparing applications, thereby supporting efficient and strategic bidding activities. Furthermore, there is a desire for a system that reduces user stress and provides flexible proposals tailored to individual psychological states.

[0695] 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.

[0696] In this invention, the server includes means comprising an electronic computer device that analyzes vendor information and classifies the results into industry categories; means for automatically generating application documents based on the analysis; means using artificial intelligence technology that analyzes past bidding data and predicts bidding projects for the following year; means for analyzing user emotions in real time based on user input information and adjusting the interface according to the results; and means for customizing the content of proposals provided to the user based on emotion data. This improves the user's work efficiency, reduces psychological burden, and enables the construction of appropriate and flexible bidding strategies.

[0697] An "electronic computing device" refers to a part or all of a computer system that performs data analysis, processing, storage, and communication.

[0698] "Vendor information" refers to relevant information such as the name, address, industry, and transaction history of companies and organizations.

[0699] An "industry category" is a category used to classify companies based on their business activities and operations.

[0700] An "application document" is a formal document prepared for submission to a local government or related organization.

[0701] "Artificial intelligence technology" is a technology that uses computers to replicate functions similar to human intelligence, enabling data analysis and prediction.

[0702] A "user" is the entity that operates the system and inputs information.

[0703] "Sentiment analysis" is the process of determining a user's emotional state based on input information and user feedback.

[0704] An "interface" refers to the connection point or user interface through which a user and a computer system exchange information.

[0705] "Customizing the proposed content" means adjusting the information and services provided according to the user's needs and circumstances.

[0706] This system is configured to streamline the local government's vendor registration and bidding process through collaboration between servers, terminals, and users. It primarily utilizes electronic computing devices, generative AI models, and sentiment analysis engines to analyze vendor information, automatically generate application documents, predict bidding data, and adjust the interface based on user sentiment.

[0707] The server receives vendor information submitted by users and first performs data cleansing. Then, using a generative AI model, it analyzes the company information using natural language processing (NLP) and classifies the companies into industry categories. This analysis utilizes natural language processing (NLP) techniques and machine learning algorithms.

[0708] Based on the results, the server automatically generates the application document. In this process, it uses a pre-prepared template engine to generate an application document with sections that meet the specified conditions. The generated application document is temporarily stored in cloud storage, making it easily accessible to the user.

[0709] The terminal provides users with a user interface that allows them to review application documents. Here, users can correct any deficiencies and electronically submit the corrected documents to the local government via the server.

[0710] Furthermore, the server stores historical bidding data provided by local governments in a database and uses data science techniques to predict bidding opportunities for the following year. This supports users in strategic bidding activities. Specific techniques include the use of time series analysis and regression models.

[0711] When a user inputs information into the system using a terminal, the emotion analysis engine acquires information in real time and analyzes the user's emotional state. This process includes facial recognition technology and keyboard input pattern analysis. The results of the emotion analysis are sent to a server and used to adjust the user interface and customize the information provided. For example, if a stressed state is detected, an easy-to-understand interface is provided, and suggestions are made that are easier to understand.

[0712] A concrete example of a prompt message is, "Please provide suggestions to offer when a user is feeling stressed about a new project." In this way, the system provides users with flexible and appropriate information, reducing the stress they experience while performing their tasks.

[0713] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0714] Step 1:

[0715] Users enter their company information into the system via a terminal. This information includes company name, address, industry, and past transaction history. This data is then transmitted to the system and delivered to the server.

[0716] Step 2:

[0717] The server puts the received corporate information through a data cleansing process. It checks for abnormal values ​​and formatting errors in the input information and prepares it for a standard format. At this stage, the cleansed data is ready.

[0718] Step 3:

[0719] The server analyzes the cleansed vendor information using a generating AI model. Specifically, it extracts useful information from the data using natural language processing (NLP) techniques and classifies companies into industry categories. The analysis results obtained through this process are then output.

[0720] Step 4:

[0721] Based on the analysis results, the server automatically generates application documents using a template engine. The analysis data is embedded into a pre-configured template, completing the application documents for submission to the local government. The generated documents are saved to cloud storage.

[0722] Step 5:

[0723] Users access application documents stored in the cloud and review their contents on their devices. The user interface allows for necessary modifications, and once editing is complete, the application can be electronically submitted to the local government with a single click.

[0724] Step 6:

[0725] The server collects historical bidding data provided by local governments and stores it in a database. Based on the collected data, it uses data science techniques to predict bidding opportunities for the following year. This process generates predictive analytics output that is useful for bidding strategies.

[0726] Step 7:

[0727] Once the user finishes inputting information, an emotion analysis engine built into the device analyzes the user's facial expressions and input patterns in real time. The resulting emotion information is sent to a server and used for flexible adjustments to the user interface and customization of information provision.

[0728] Step 8:

[0729] The server customizes suggestions based on the user's emotional state. For example, if stress is detected, the interface is changed to a more relaxing one, and simpler conditions are suggested. Suggestions are generated based on emotional data and provided to the user.

[0730] (Application Example 2)

[0731] 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".

[0732] Current transaction procedures are complex, placing a significant psychological burden on users and making efficient work difficult. Furthermore, the system lacks sufficient consideration for users' emotions and psychological states, resulting in a lack of personalized interfaces.

[0733] 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.

[0734] In this invention, the server includes means for an electronic computer to analyze and classify vendor information, means for automatically generating application forms based on the analysis, means for analyzing past bidding data to predict projects for the following year, means for analyzing the user's mental state using facial expression recognition technology, and means for adjusting the user interface based on the analyzed mental state. This reduces the mental burden on the user and enables more efficient work execution and personalized service provision.

[0735] An "electronic computing device" is a device that has the computing power to analyze and classify business information.

[0736] "Vendor information" refers to various data about companies and organizations involved in a transaction.

[0737] An "application form" is an official document required for business transactions and bidding.

[0738] "Automatic generation" refers to a system generating a specific output without human intervention.

[0739] "Past bidding data" refers to historical information about transactions that have taken place in the past.

[0740] "Prediction" is the process of estimating future events or trends based on past data.

[0741] "Facial expression recognition technology" is a technology that uses cameras and sensors to analyze a person's facial expressions and identify their emotions.

[0742] "Mental state" refers to the user's emotions and psychological condition.

[0743] A "user interface" refers to the screens or control panels that users use to interact with a system.

[0744] "Adjustment" refers to changing settings to achieve the optimal state according to the situation and conditions.

[0745] The system for realizing this invention comprises a computer, facial expression recognition technology, and a user interface. A server acts as the central point, first using the computer to analyze vendor information and classify it. Based on the classified information, an application form is automatically generated and displayed on the user's terminal.

[0746] The system utilizes facial expression recognition technology, such as Google Cloud Vision API and Microsoft Face API, to analyze the user's psychological state in real time. Based on the analyzed mental state, the server provides an optimal user interface. For example, if the user is experiencing anxiety or stress, the screen design and displayed messages are adjusted to alleviate these feelings. Conversely, if positive emotions are detected, more proactive suggestions can be made, improving the efficiency of the service provider.

[0747] For example, if a user is conducting an online transaction and their tension is evident on their face, a message such as "Please proceed with confidence. This transaction can be canceled" could be displayed to help ensure the transaction proceeds smoothly.

[0748] Regarding the use of generative AI models, prompts such as "Analyze user emotions in real time during online transactions to ensure smooth transactions, provide relaxing messages and support information to nervous users, and add a feature to highlight the next step when emotions are positive" are used.

[0749] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0750] Step 1:

[0751] The server receives vendor information and prepares to begin analysis. It converts the received vendor information into a database format and performs preprocessing for categorization. From this input data, it extracts and organizes keywords such as the vendor's industry and transaction history.

[0752] Step 2:

[0753] The server uses a computer to analyze vendor information and classify it into the appropriate industry category. It extracts features from the input information and classifies them by comparing them with existing databases. The output is the classified vendor information, which is reflected in the display UI.

[0754] Step 3:

[0755] The server automatically generates application forms based on the classification results. It embeds the necessary information into a templated form and customizes it as needed. The generated application form is then formatted and output on the terminal in PDF or other format.

[0756] Step 4:

[0757] The terminal displays the generated application form to the user and prompts them for confirmation. The user reviews the content on the screen and electronically signs it. The confirmed application form then proceeds to the next step, the submission process.

[0758] Step 5:

[0759] The server queries past bidding data and performs analysis to predict the next year's projects. This involves inputting bidding history data and using statistical analysis and AI modeling techniques to identify patterns. The output is a list of predicted projects.

[0760] Step 6:

[0761] The server uses facial expression recognition technology to analyze the user's mental state in real time. Image data acquired by the camera is used as input, processed by an emotion recognition algorithm to identify the emotional state. The output is user interface adjustment information.

[0762] Step 7:

[0763] The device adjusts the user interface based on the analysis results. If an emotion indicating stress is detected, it displays relaxing colors and messages. The system feeds this information back and uses it to suggest the next interface.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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."

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] The following is further disclosed regarding the embodiments described above.

[0786] (Claim 1)

[0787] A means by which an electronic computer analyzes and classifies vendor information,

[0788] A means for automatically generating an application form based on the aforementioned analysis,

[0789] A method for predicting projects for the next fiscal year by analyzing past bidding data,

[0790] A system that includes this.

[0791] (Claim 2)

[0792] The system according to claim 1, which transmits the aforementioned application form electronically.

[0793] (Claim 3)

[0794] The system according to claim 1, which automatically generates bidding conditions based on the classified information.

[0795] "Example 1"

[0796] (Claim 1)

[0797] A data processing device analyzes vendor information obtained from users using natural language processing technology and classifies that vendor information into industry categories.

[0798] A means for automatically generating application forms that conform to the format of each local government based on the aforementioned analysis results,

[0799] A method for predicting future project occurrences by analyzing past bidding data using statistical methods,

[0800] A means of using a machine learning model to provide optimal bidding conditions based on past bidding conditions and results,

[0801] A system that includes this.

[0802] (Claim 2)

[0803] The system according to claim 1, wherein the aforementioned application form is provided electronically.

[0804] (Claim 3)

[0805] The system according to claim 1, which optimizes and automatically generates bidding conditions based on the categorized vendor information.

[0806] "Application Example 1"

[0807] (Claim 1)

[0808] A means by which an electronic computer analyzes and classifies vendor information,

[0809] A means for automatically generating an application form based on the aforementioned analysis,

[0810] A method for predicting projects for the next fiscal year by analyzing past bidding data,

[0811] A means of managing trading partners in a logistics facility and presenting optimal bidding conditions based on information from an inventory management system,

[0812] ...

[0813] A system that includes this.

[0814] (Claim 2)

[0815] The system according to claim 1, which transmits the aforementioned application form electronically.

[0816] (Claim 3)

[0817] The system according to claim 1, which automatically generates bidding conditions based on the classified information and provides optimized bids.

[0818] "Example 2 of combining an emotion engine"

[0819] (Claim 1)

[0820] A means comprising an electronic computer device that analyzes vendor information and classifies the results into industry categories,

[0821] A means for automatically generating application documents based on the aforementioned analysis,

[0822] This method uses artificial intelligence technology to analyze past bidding data and predict bidding projects for the following year,

[0823] A means of analyzing user emotions in real time based on user input information and adjusting the interface accordingly,

[0824] A means of customizing the suggestions provided to users based on emotional data,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1 for electronically transmitting the aforementioned application document.

[0828] (Claim 3)

[0829] The system according to claim 1, which automatically generates bidding conditions based on the classified vendor information and sentiment data, and adapts them to the user's psychological state.

[0830] "Application example 2 when combining with an emotional engine"

[0831] (Claim 1)

[0832] A means by which an electronic computer analyzes and classifies vendor information,

[0833] A means for automatically generating an application form based on the aforementioned analysis,

[0834] A method for predicting projects for the next fiscal year by analyzing past bidding data,

[0835] A means of analyzing the user's mental state using facial expression recognition technology,

[0836] Means for adjusting the user interface based on the analyzed mental state,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, which transmits the aforementioned application form electronically.

[0840] (Claim 3)

[0841] The system according to claim 1, which automatically generates bidding conditions based on the classified information and the analyzed mental state. [Explanation of Symbols]

[0842] 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. A means by which an electronic computer analyzes and classifies vendor information, A means for automatically generating an application form based on the aforementioned analysis, A method for predicting projects for the next fiscal year by analyzing past bidding data, A system that includes this.

2. The system according to claim 1, which electronically transmits the aforementioned application form.

3. The system according to claim 1, which automatically generates bidding conditions based on the classified information.

Images