System

Abstract

A system is provided.SOLUTION: This system is provided with a means for collecting job offer information, a means for analyzing the collected job offer information, and for specifying a mechanizable task, a means for screening the specified enterprise, a means for generating a mechanization plan for each screened enterprise, and a means for notifying the enterprise of the generated mechanization plan.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Improving productivity is an urgent priority in countries currently facing a declining population. However, while many companies, particularly small and medium-sized enterprises, understand the potential of mechanization and automation, they face the challenge of finding specific methods and paths to achieving this. Furthermore, in the job market, there are many job openings for tasks that can be mechanized, exacerbating the labor shortage. To resolve these issues, concrete support is needed to promote digital transformation (DX). [Means for solving the problem]

[0005] The present invention provides a system that collects job information, analyzes the collected job information to identify tasks that can be mechanized, screens identified companies, generates mechanization plans for each screened company, and notifies the companies of the generated mechanization plans. This system consistently performs processes from analyzing job information to providing specific mechanization plans, thereby supporting companies in their digital transformation efforts. This system collects job information from publicly available websites via scraping or API, and generates mechanization plans in the form of reports that include implementation costs, benefits, and implementation procedures, providing a concrete path for companies to actually implement digital transformation.

[0006] "Means for collecting job information" refers to an element that has the function of periodically obtaining publicly available job information from the Internet using scraping technology or an API.

[0007] "Means for analyzing collected job information and identifying tasks that can be mechanized" refers to algorithms or mechanisms for analyzing collected job information and extracting and identifying tasks that can be mechanized or automated.

[0008] "Means for screening identified companies" refers to a system for evaluating and ranking companies with identified business operations based on financial data and intentions to introduce technology.

[0009] The "means for generating a mechanization plan for each screened company" is an element that has the function of generating specific mechanization solutions and their implementation procedures for the screened companies.

[0010] "Means of notifying companies of the generated automation plan" refers to a mechanism for sending the generated automation plan to the person in charge at the target company via email or the notification function on the platform. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0012] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0013] First, the terms used in the following description will be explained.

[0014] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0015] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0016] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0017] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0024] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0031] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0032] The present invention relates to a system for collecting, analyzing, screening, and generating and notifying job information automation plans. This system is composed of a server, a terminal, and a user, and each component functions as follows.

[0033] overview

[0034] The server periodically collects job information, analyzes the data, and identifies tasks that can be automated. It then screens the identified companies and generates an optimal automation plan for each company based on the results. Finally, the plan is notified to the company's representative.

[0035] Data collection

[0036] The server collects job information from websites that publish job postings using scraping technology or APIs. The collected data is analyzed by fields such as company name, job type, required skills, and salary information, and then stored in a database.

[0037] Examples:

[0038] Every day at 2 a.m., the server retrieves data from multiple websites that publish job listings. For example, if "Company X" is hiring a "cashier," the server stores that information in a database.

[0039] Company specific

[0040] The server analyzes the collected data and filters job listings that contain specific keywords (e.g., "cashier operator" or "data entry"), thereby identifying companies with jobs that can be automated.

[0041] Examples:

[0042] "Company Y" is identified based on keywords such as "cashier operation" and "data entry." The server retrieves and analyzes job information for "Company Y" from the database.

[0043] screening

[0044] The server evaluates the identified companies based on financial data, intentions to introduce technology, industry trends, etc., and screens them based on their future potential. The screening results are then ranked.

[0045] Examples:

[0046] The financial data and technology adoption intentions of "Company Y" are obtained from an external database, and the server uses that information to rank "Company Y." For example, "Company Y" can receive a relatively high score.

[0047] Mechanization plan generation

[0048] The server generates a mechanization plan for each selected company based on the screening results. The plan includes the technology to be introduced, the expected costs, and the effects after introduction. The plan is generated in report format and saved on the server.

[0049] Examples:

[0050] The server generates a plan proposing the introduction of an automated cash register system for Company Y's cash register operations. This plan details the introduction costs, predicted benefits, and specific implementation procedures.

[0051] notification

[0052] The server notifies the target company's personnel of the generated automation plan. This notification is done via email or the platform's notification function. The user (company personnel) receives the notification, checks the proposal, and sends feedback to the server if necessary.

[0053] Examples:

[0054] The server sends an email with the automated cash register system implementation plan to the person in charge at Company Y. The person in charge (user) receives the email and reviews the plan in detail.

[0055] This system will enable small and medium-sized enterprises to efficiently promote digital transformation by consistently analyzing job information and providing specific mechanization plans.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The server accesses websites and APIs where job information is published based on a regular schedule, and retrieves job information using scraping technology and APIs.

[0059] Step 2:

[0060] The server parses the job postings, which includes extracting the necessary data fields (company name, job title, required skills, salary information, etc.) from the JSON or HTML format.

[0061] Step 3:

[0062] The server stores the analyzed job information in a database, including company names, job titles, required skills, salary information, etc.

[0063] Step 4:

[0064] The server queries and retrieves job data from a database, filtering the data to see if it contains specific keywords (e.g., "cashier clerk" or "data entry").

[0065] Step 5:

[0066] The server lists companies that have mechanizable processes based on specific keywords, and these companies are then subject to screening.

[0067] Step 6:

[0068] The server refers to external databases and survey results to conduct financial data and technology adoption intention surveys for the listed companies, and evaluates each company based on this data.

[0069] Step 7:

[0070] The server scores each company based on the evaluation results and generates a ranking based on future potential. Companies with high scores are given priority in generating automation plans.

[0071] Step 8:

[0072] The server generates a mechanization plan for each high-scoring company, which includes the technology to be implemented, the expected costs, and the effects of implementation.

[0073] Step 9:

[0074] The server compiles the generated mechanization plan in a report format that is easy for company personnel to understand and is stored in a database.

[0075] Step 10:

[0076] The server generates an email or platform notification to notify the target company's personnel of the automation plan, which includes details of the plan.

[0077] Step 11:

[0078] The user (company representative) checks the notification and reviews the proposal. If necessary, the user can submit feedback or additional questions to the server through a dedicated web form.

[0079] Step 12:

[0080] The server analyzes the received feedback, modifies the mechanization plan as necessary, generates a final proposal after the modifications, and notifies the company representative again.

[0081] Step 13:

[0082] The user (company representative) receives the final proposal and initiates the internal approval process. The server tracks the company's progress in implementing DX and sends notifications if additional support is required.

[0083] Example 1

[0084] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0085] Currently, for small and medium-sized enterprises to efficiently promote digital transformation (DX), advanced technical knowledge and a great deal of effort are required. As a result, many small and medium-sized enterprises are unable to implement effective DX, making it difficult to improve operational efficiency and reduce costs. If we could identify mechanizable tasks from job information and provide companies with appropriate mechanization plans, we could support the promotion of DX in small and medium-sized enterprises. However, doing this manually is extremely labor-intensive and difficult to describe as efficient. To solve this issue, it is necessary to automate the system and perform all processes from collecting job information to generating and notifying mechanization plans.

[0086] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0087] In this invention, the server includes: means for collecting job information; means for analyzing the collected job information to identify mechanizable tasks; means for screening identified companies; means for generating a mechanization plan for each screened company; means for notifying the companies of the generated mechanization plan; means for using web scraping technology or a public API to collect job information; means for parsing the collected data into company names, job duties, required skills, and compensation information and storing them in a database; means for analyzing the job information using natural language processing and filtering the job information based on specific keywords to identify mechanizable tasks; means for evaluating and screening companies based on financial data, technology adoption intentions, and industry trends; means for generating a mechanization plan based on the evaluated screening results, including the technology to be introduced, expected costs, and post-implementation effects; means for notifying company representatives of the generated mechanization plan via email or platform notification function; and means for receiving user feedback. This automates the entire process from collecting job information to analyzing, filtering, screening, and generating and notifying mechanization plans, enabling small and medium-sized enterprises to efficiently promote digital transformation.

[0088] "Means of collecting job information" refers to the function of automatically obtaining data from websites where job information is published using web scraping technology or public APIs.

[0089] "Means of analyzing collected job information to identify tasks that can be automated" refers to the function of analyzing the text of collected job information using natural language processing (NLP) technology and filtering tasks that can be automated based on specific keywords.

[0090] "Means for screening identified companies" refers to the function of evaluating companies identified as having operations that can be mechanized based on information such as financial data, intentions to introduce technology, and industry trends, and then screening and ranking the companies.

[0091] "Means for generating mechanization plans for each screened company" refers to the function of generating mechanization plans for selected companies based on the screening results, including the technology to be introduced, expected costs, and post-implementation effects.

[0092] "Means for notifying the enterprise of the generated mechanization plan" refers to the function of sending the generated mechanization plan to the enterprise's personnel via email or platform notification.

[0093] "Methods of using web scraping technology or public APIs to collect job information" refers to the function of automatically collecting data from websites where job information is published using web scraping technology or public APIs.

[0094] "Means for analyzing collected data into company name, job position, required skills, and compensation information and storing it in a database" refers to the function of analyzing collected job information into fields such as company name, job position, required skills, and compensation information, and storing it appropriately in a database.

[0095] "Means of analyzing job postings using natural language processing, filtering job postings based on specific keywords, and identifying jobs that can be mechanized" refers to a function that uses natural language processing technology to analyze the text of job postings, filtering job postings based on specific keywords such as "cash register" or "data entry," and identifying job postings that have tasks that can be mechanized.

[0096] "Means of evaluating and screening companies based on financial data, intentions to introduce technology, and industry trends" refers to the function of collecting information such as financial data, intentions to introduce technology, and industry trends of identified companies, and evaluating and screening companies based on this data.

[0097] "Means for generating a mechanization plan including the technology to be introduced, the expected cost, and the effects after introduction based on the evaluated screening results" refers to the function of generating a mechanization plan that specifies the technology to be introduced, the expected cost of introduction, and the effects after introduction based on the company's screening results.

[0098] "Means for notifying company personnel of the generated automation plan by email or platform notification function" refers to the function of sending the generated automation plan to company personnel via email or platform notification, allowing the personnel to review the plan.

[0099] "Means for receiving feedback from users" refers to a function that allows a company representative to send feedback on a proposed mechanization plan to the server and receive that feedback.

[0100] The present invention relates to a system for collecting, analyzing, screening, and generating and notifying job information automation plans. This system is composed of a server, terminals, and users, and each component functions in cooperation with the others.

[0101] Data collection

[0102] The server periodically collects job information from websites that publish job postings. This collection process uses web scraping technology and public APIs. Specifically, data is extracted using Python libraries such as BeautifulSoup and Selenium. The collected data is analyzed into fields such as company name, job position, required skills, and compensation information, and then stored in a database such as MySQL or PostgreSQL.

[0103] As a concrete example, the server retrieves data from "job site A" and "job site B" every day at 2:00 a.m. For example, if "company A" is hiring a "cashier clerk," that information is stored in the database as the company name, job title, required skills, and compensation information.

[0104] Keyword Analysis

[0105] The server periodically analyzes the collected data and filters out job postings that contain specific keywords (e.g., "cashier operator" or "data entry"). This analysis is performed using natural language processing (NLP) technology. Specifically, NLP libraries such as NLTK and spaCy are used. Based on the results of this filtering, companies with tasks that can be automated are identified.

[0106] As a specific example, the server analyzes the text of the collected job postings and extracts job postings that contain keywords such as "cashier operator" and "data entry." For example, "Company B" is identified, and its job posting information is retrieved from the database and analyzed.

[0107] screening

[0108] The server evaluates and screens the identified companies based on financial data, technology adoption intentions, industry trends, etc. This evaluation process uses data obtained from external databases such as D&B Hoovers and Crunchbase. The server scores companies based on this data and stores the evaluation results in a new database table.

[0109] As a specific example, the server obtains financial data and technology adoption intentions of "Company B" from an external database and evaluates "Company B" based on that information. Company B can receive a relatively high score.

[0110] Mechanization plan generation

[0111] Based on the screening results, the server generates a mechanization plan for each selected company, which includes the technology to be introduced, the expected costs, and the effects after introduction. The generated plan is saved as a PDF report.

[0112] As a specific example, the server generates a mechanization plan proposing the introduction of an automated cash register system for the cash register operations of "Company B." This plan details the introduction costs, predicted benefits, and specific implementation procedures.

[0113] notification

[0114] The server notifies the company representative (user) of the generated mechanization plan via email or the platform notification function. The user receives the notification and checks the proposal. If necessary, the user can send feedback to the server.

[0115] As a concrete example, the server sends an automated cash register system implementation plan by email to the person in charge (user) of "Company B." The user receives the email and reviews the plan in detail.

[0116] Prompt Sentence Examples

[0117] Here are some example prompts for a generative AI model:

[0118] Analyze the job postings of the following companies, identify the tasks that can be automated, and then create a mechanization plan based on that. Company Name: Company C

[0119] This system will enable small and medium-sized enterprises to efficiently promote digital transformation by consistently analyzing job information and providing specific mechanization plans.

[0120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0121] Step 1: Data collection

[0122] The device periodically sends a request to the server to collect job information. The server uses Python's BeautifulSoup and Selenium to scrape job information from websites. The job data is parsed into company names, job roles, required skills, and compensation information, and stored in a MySQL or PostgreSQL database.

[0123] Specific behavior:

[0124] The device sends a job information collection request to the server at 2:00 AM.

[0125] The server scrapes job information from "job site A" and "job site B" and obtains the HTML data.

[0126] The server uses BeautifulSoup to parse the HTML data and categorize it into company names, job roles, required skills, compensation information, etc.

[0127] The server stores the classified data in a database.

[0128] Input: Request from the device, HTML data of the job site

[0129] Output: A database containing company names, jobs, required skills, and compensation information

[0130] Step 2: Keyword analysis

[0131] The server periodically retrieves collected data from the database and filters job postings that contain specific keywords. It analyzes the text using natural language processing techniques such as NLTK and spaCy.

[0132] Specific behavior:

[0133] The server retrieves all jobs from the database.

[0134] The server uses NLTK to analyze the text of the job posting and detect keywords such as "cashier operator" and "data entry."

[0135] The server filters job listings based on keywords to identify job listings that include tasks that can be mechanized.

[0136] Store the filtered job listings in a new database table.

[0137] Input: Jobs in the database

[0138] Output: A new database table with filtered job listings

[0139] Step 3: Identify the company

[0140] The server identifies companies with work that can be automated based on the filtered job information. The information about the identified companies is recorded in a separate database table.

[0141] Specific behavior:

[0142] The server extracts company names from the filtered job listings.

[0143] The server stores the extracted company names in a new database table.

[0144] Input: Filtered Jobs

[0145] Output: A database table containing the identified company names

[0146] Step 4: Screening

[0147] The server evaluates companies based on their financial data, intentions to adopt technology, industry trends, etc. It obtains the necessary information from external databases such as D&B Hoovers and Crunchbase, scores companies, and stores the results in a new database table.

[0148] Specific behavior:

[0149] The server uses an external API to obtain financial data and technology adoption intentions of the identified companies.

[0150] Based on the data acquired by the server, companies are screened using a specified algorithm.

[0151] The screening results are stored in a new database table.

[0152] Input: Company information obtained from an external database

[0153] Output: Database table containing screening results (scores)

[0154] Step 5: Mechanization plan generation

[0155] Based on the screening results, the server generates a mechanization plan for each company. This plan includes the technology to be implemented, the expected costs, and the effects after implementation. The plan is compiled into a PDF report.

[0156] Specific behavior:

[0157] The server obtains the screening results and generates a mechanization plan suitable for each company.

[0158] The generated plan is saved as a PDF report.

[0159] Input: Screening results

[0160] Output: Mechanized plan in PDF format

[0161] Step 6: Notification

[0162] The server sends the generated mechanized plan to the company representative (user) via email or platform notification function.

[0163] Specific behavior:

[0164] The server obtains the email address of the company contact person.

[0165] The server sends the generated mechanized plan as an attachment to an email.

[0166] The user receives an email confirming the plan.

[0167] Input: Mechanization plan in PDF format, email address of company contact person

[0168] Output: Email sent to company contact

[0169] Prompt Sentence Examples

[0170] Here are some example prompts for a generative AI model:

[0171] Analyze the job postings of the following companies, identify the tasks that can be automated, and then create a mechanization plan based on that. Company Name: Company C

[0172] (Application example 1)

[0173] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0174] In modern factories, labor shortages and streamlining operations are major challenges. However, determining which operations are suitable for mechanization and creating specific plans for doing so requires a great deal of time and specialized knowledge. Furthermore, there is a lack of ways for company personnel to quickly understand and implement implementation plans. Given these circumstances, there is a need for a system that allows companies to mechanize operations quickly and efficiently.

[0175] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0176] In this invention, the server includes means for collecting job information, means for analyzing the collected job information to identify tasks that can be mechanized, means for screening the identified companies, means for generating a mechanization plan for each screened company, means for notifying the companies of the generated mechanization plan, means for generating a factory robot introduction plan based on the collected job information, and means for notifying the company's smartphone application of the generated introduction plan. This allows companies to quickly and efficiently obtain a mechanization plan and proceed with the introduction of appropriate factory robots.

[0177] "Job information" refers to information about the job duties, required skills, salary conditions, etc., of the personnel that companies are looking for.

[0178] The "means of collection" refers to the mechanism by which job information is obtained from websites via scraping or API.

[0179] "Means of analyzing and identifying tasks that can be mechanized" refers to a method of analyzing collected job information and finding tasks that can be replaced by machines.

[0180] "Means for screening identified companies" refers to a method of evaluating companies that are deemed capable of mechanizing their operations based on financial data, intentions to introduce technology, etc.

[0181] The "means of generating a mechanization plan" is a method of creating the optimal mechanization plan for each company and creating a report that includes implementation costs, effects, implementation procedures, etc.

[0182] The "means of notification" refers to a mechanism for communicating the generated mechanization plan to company personnel via email or on the platform.

[0183] A "factory robot" is a mechanical device introduced to automate manufacturing work.

[0184] A "smartphone application" is software installed on a smartphone and is a program with notification and data processing functions.

[0185] A "prompt" is a textual input given to a generative AI model to generate a specific output.

[0186] A "generative AI model" is an artificial intelligence system that uses machine learning and deep learning to generate specific outputs from input data.

[0187] The present invention relates to a system in which a server collects, analyzes, screens, generates and notifies job information. A specific embodiment of this system is described below.

[0188] Collecting job information

[0189] The server periodically collects job information from websites that publish job postings using scraping technology or APIs. This information is stored in a database and categorized by fields such as company name, job type, required skills, salary information, etc. For example, if a "company" is hiring an "assembly line worker," that information will be retrieved by the server.

[0190] Data analysis and company identification

[0191] Next, the server analyzes the collected job information and filters job postings containing specific keywords (e.g., "assembly," "inspection," etc.) to identify tasks that can be automated. This step extracts companies that are suitable for introducing factory robots. For example, if a "certain factory" is hiring someone for assembly work, that company will be identified.

[0192] screening

[0193] The server collects and evaluates external data on identified companies, such as financial data, technology adoption intentions, and industry trends. This allows the companies to be ranked based on their future prospects. For example, the server evaluates the financial data and technology adoption intentions of a "certain factory," and assigns a certain score based on the results.

[0194] Generating mechanization plans

[0195] Based on the screening results, the server generates a mechanization plan for each company. This plan includes the factory robots to be introduced, the estimated costs, and the introduction procedure. The generated plan is saved in the form of a report. For example, for the assembly line operations of a "certain factory," the server generates a plan proposing the introduction of XYZ robots, and the details are provided in a report.

[0196] notification

[0197] The generated mechanization plan is notified from the server to the company's employee's smartphone application. This notification is sent via email or push notification. The user (company employee) receives the notification, checks the proposal, and sends feedback to the server if necessary. For example, the server can send an automation plan to the employee of a "certain factory" via a smartphone application.

[0198] Hardware and software used

[0199] The system consists of a server, database, network infrastructure, and a user's smartphone application. Tools such as BeautifulSoup and Selenium are used for scraping, and the Requests library is used for API communication. Server-side processing is implemented using frameworks such as Flask and Django. Machine learning models and condition-based filtering are used for data analysis and company identification.

[0200] Examples of concrete examples and prompts

[0201] For example, if the server finds a job opening for an assembly line worker in a "certain factory" and determines that the job is suitable for mechanization, it will generate a plan to introduce XYZ robots. The plan is provided in the following format:

[0202] Example prompt sentence:

[0203] Company Name: A Factory

[0204] Position: Assembly Line Worker

[0205] Skills: Basic assembly work

[0206] Salary: 3 million yen / year

[0207] Please propose an appropriate automation plan for this company, particularly the type of robots to be implemented, the estimated costs, and the expected benefits after implementation.

[0208] In this way, companies can obtain an efficient and specific mechanization plan and proceed with the introduction of appropriate factory robots.

[0209] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0210] Step 1:

[0211] The server collects job information.

[0212] Input: URLs of multiple websites where job postings are published.

[0213] What it does: The server uses BeautifulSoup and Selenium to scrape job listings from the specified website, and if a specific API is provided, it uses the Requests library to collect data via the API.

[0214] Output: Collected job information (company name, job title, required skills, salary information, etc.).

[0215] Step 2:

[0216] The server analyzes the collected job information and identifies tasks that can be automated.

[0217] Input: The collected job posting dataset.

[0218] How it works: The server uses natural language processing (NLP) technology to analyze the text data of job postings, checking whether specific keywords (e.g., "assembly," "inspection," etc.) are included, and filtering out tasks that can be automated.

[0219] Output: Job postings and a list of companies with mechanizable tasks.

[0220] Step 3:

[0221] Screening companies whose servers have been identified.

[0222] Input: List of companies with mechanizable operations.

[0223] What it does: The server collects external data such as company financial data, technology adoption intentions, and industry trends. This includes API access to external databases (e.g., financial databases). Based on the collected data, it evaluates and scores each company.

[0224] Output: A ranked list of highly rated companies.

[0225] Step 4:

[0226] The server generates a mechanized plan for each company screened.

[0227] Input: A ranked list of highly rated companies.

[0228] How it works: The server uses a generative AI model to generate an optimal mechanization plan for each company. It prompts users to enter information about the company, the position being filled, the required skills, and salary information, and generates a report that includes the type of robot to be introduced, the estimated cost, and the effects after introduction.

[0229] Output: Mechanization plan report for each company.

[0230] Step 5:

[0231] The server notifies the generated mechanization plan to the company representative's smartphone application.

[0232] Input: Mechanization plan report and company contact information.

[0233] Specific operation: The server uses an SMTP server to generate a notification email and send it to the company's representative. It also uses a push notification service (e.g., Firebase Cloud Messaging) to send a push notification to a smartphone application.

[0234] Output: A notification message to the company contact who received the plan notification.

[0235] By performing the above steps, the server can consistently perform the process from collecting job information to generating and notifying a mechanized plan.

[0236] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0237] This invention combines an emotion engine with a system that collects, analyzes, screens, and generates and notifies job information mechanized plans. This system consists of a server, a terminal, a user, and an emotion engine, and each component functions as follows:

[0238] overview

[0239] The server periodically collects job information, analyzes the data, and identifies tasks that can be automated. It then screens the identified companies and generates an optimal automation plan for each company based on the results. The generated plan is notified to the company's representative, and an emotion engine analyzes user feedback and emotions to further optimize the plan.

[0240] Data collection

[0241] The server periodically retrieves data from websites and APIs where job information is published. Using scraping technology and APIs, the server collects job information, analyzes it into company names, job types, required skills, salary information, etc., and stores the information in a database.

[0242] Examples:

[0243] Every day at 2 a.m., the server retrieves data from multiple websites that publish job information. For example, if "Company A" is hiring a "cashier," the server stores that information in a database.

[0244] Company specific

[0245] The server queries and retrieves job data from a database, analyzes the data, and filters it based on specific keywords (e.g., "cashier operation" or "data entry") to identify companies with tasks that can be automated.

[0246] Examples:

[0247] "Company B" is identified based on keywords such as "cashier operation" and "data entry." The server retrieves and analyzes the job information for "Company B" from the database.

[0248] screening

[0249] The server then refers to external databases and survey results to obtain financial data and technology adoption intentions for the identified companies. The server then evaluates each company based on this data and ranks the companies with the highest scores.

[0250] Examples:

[0251] The financial data and technology adoption intentions of "Company B" are obtained from an external database, and the server uses that information to rank "Company B." For example, "Company B" can receive a relatively high score.

[0252] Mechanization plan generation

[0253] The server generates a mechanization plan for each high-ranking company, detailing the technology to be implemented, the expected costs, and the effects after implementation. The generated plan is compiled in a report format and saved on the server.

[0254] Examples:

[0255] The server generates a plan proposing the introduction of an automated cash register system for Company B's cash register operations. This plan details the introduction costs, predicted benefits, and specific implementation procedures.

[0256] notification

[0257] The server sends the generated mechanization plan to the person in charge of the target company via email or the platform's notification function. The user (company person in charge) receives the notification and confirms the proposal.

[0258] Examples:

[0259] The server sends an email with the automated cash register system implementation plan to the person in charge at Company B. The person in charge (user) receives the email and reviews the plan in detail.

[0260] Emotion engine integration

[0261] The emotion engine analyzes the user's feedback and reactions, analyzing the text entered by the user through the feedback form, as well as facial expressions and voice when confirming the plan, to obtain emotional data.

[0262] Examples:

[0263] When a company representative provides feedback while reviewing the plan, the emotion engine analyzes the user's input text, facial expressions, and voice. For example, if the user is worried about the implementation cost, the emotion engine analyzes that information and provides it to the server.

[0264] Modifying the plan

[0265] The server modifies the mechanized plan based on the emotion data obtained from the emotion engine, and the modified plan is notified to the user again.

[0266] Examples:

[0267] Based on the information obtained from the emotion engine, the server regenerates a correction plan that includes a detailed breakdown of implementation costs and options for cost reduction. The correction plan is then sent again to the company's representative via email.

[0268] This system not only provides mechanized plans, but also provides optimized plans that take into account user emotions and feedback, making it possible to effectively support companies in promoting digital transformation.

[0269] The processing flow will be explained below.

[0270] Step 1:

[0271] The server accesses websites and APIs where job information is published based on a regular schedule, and retrieves job information using scraping technology and APIs.

[0272] Step 2:

[0273] The server parses the job postings, which includes extracting the necessary data fields (company name, job title, required skills, salary information, etc.) from the JSON or HTML format.

[0274] Step 3:

[0275] The server stores the analyzed job information in a database, including company names, job titles, required skills, salary information, etc.

[0276] Step 4:

[0277] The server queries and retrieves job data from a database, filtering the data for specific keywords (e.g., "cashier clerk" or "data entry").

[0278] Step 5:

[0279] The server identifies companies with mechanizable tasks based on the filtered job listings, and adds the identified companies to a list.

[0280] Step 6:

[0281] Based on the list of identified companies, the server obtains external data for evaluation (e.g., financial data, intention to introduce technology, etc.) and uses this data to evaluate each company and assign a score.

[0282] Step 7:

[0283] The server ranks each company based on the evaluation results, and companies with higher scores are given priority when generating mechanization plans.

[0284] Step 8:

[0285] The server generates a mechanization plan for each high-scoring company, which includes the technology to be implemented, the expected costs, and the benefits of implementation.

[0286] Step 9:

[0287] The server compiles the generated mechanization plan in the form of a report and stores it in a database.

[0288] Step 10:

[0289] The server sends the generated mechanized plan to the person in charge of the target company via email or the notification function on the platform, which includes details of the plan.

[0290] Step 11:

[0291] The user (company representative) checks the notification and reviews the proposal, and then submits feedback or additional questions to the server via a dedicated web form.

[0292] Step 12:

[0293] The emotion engine analyzes the user's feedback and facial expressions and voice when confirming the plan, and the analysis results are provided to the server as emotion data.

[0294] Step 13:

[0295] The server modifies the mechanized plan based on the emotion data and regenerates an optimized plan, which is then stored in the database.

[0296] Step 14:

[0297] The server then notifies the user of the optimized plan, who then reviews the plan and provides final feedback and approval.

[0298] Step 15:

[0299] The user (company representative) initiates the internal approval process based on the final proposal. The server tracks the progress of the company's DX implementation and sends notifications if additional support is required.

[0300] Example 2

[0301] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0302] Conventional recruitment information collection systems are capable of collecting and analyzing recruitment information and generating automation plans, but they are not optimized to take into account the feelings and feedback of company representatives. As a result, it is difficult for the proposed automation plans to fully meet the needs of company representatives, and actual implementation may not progress.

[0303] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0304] In this invention, the server includes means for collecting job information, means for analyzing the collected job information to identify tasks that can be mechanized, means for screening the identified organizations, means for generating a mechanization plan for each screened organization, means for notifying the organizations of the generated mechanization plan, means including an emotion engine for collecting and analyzing feedback from organizational personnel, and means for modifying the mechanization plan based on the emotion engine. This makes it possible to provide more practical and easy-to-implement mechanization plans that reflect the emotions and feedback of company personnel.

[0305] "Methods of collecting job information" refers to technologies for obtaining job data from websites and APIs, including scraping technologies and API integration.

[0306] "Means for analyzing job information to identify tasks that can be automated" refers to technology that analyzes collected job data and identifies tasks that can be automated based on specific keywords or patterns.

[0307] The "means for screening the identified organizations" refers to techniques for investigating and evaluating the financial data and intentions to introduce technology of the identified organizations.

[0308] The "means for generating a mechanization plan" is a technique for designing an optimal mechanization plan for each evaluated organization, detailing the implementation technology, costs, effects, etc.

[0309] "Means for notifying the organization of the generated mechanization plan" refers to a technology for sending the generated mechanization plan to the person in charge at the target organization via email or a notification function on the platform.

[0310] The "means including an emotion engine for collecting and analyzing feedback from organizational personnel" is a technology for collecting feedback provided by personnel and analyzing text, facial expressions, and voice.

[0311] The "means for modifying a mechanization plan based on an emotion engine" is a technology that identifies areas for improvement in a mechanization plan based on emotion data obtained from an emotion engine and redesigns the plan.

[0312] This invention combines an emotion engine with a system that collects, analyzes, screens, and generates and notifies job information mechanization plans. This system consists of a server, terminals, users, and an emotion engine. The detailed configuration and operation are described below.

[0313] First, the server collects job information. To do this, it uses scraping technologies such as Python's Beautiful Soup and Scrapy, as well as RESTful APIs. Every day at 2:00 AM, the server retrieves data from websites and APIs that list multiple job listings, parses it into information such as company name, job type, required skills, and salary information, and then stores it in a database (such as MySQL or PostgreSQL).

[0314] For example, the server periodically retrieves job information for "cashier staff" from "XYZ job site" every day and stores it in a MySQL database. This collected data is used in subsequent processing.

[0315] Next, the server identifies companies. It uses specific keywords (e.g., "cashier operation" or "data entry") to filter out companies with tasks that can be automated for the job data retrieved from the database. For example, the server identifies a company based on the keywords "cashier operation" or "data entry."

[0316] The server then screens the identified companies. This involves using external databases such as the Google Finance API to obtain financial data and evaluating the companies' intentions to adopt technology. Companies with high scores are then ranked. For example, the server evaluates the financial data and intentions to adopt technology of "Company B" and gives it a high score.

[0317] Next, the server generates an automation plan for each highly rated company. It creates a plan in the form of a report that includes implementation costs, effects, and implementation procedures, such as an automated cash register system implementation plan. This generated plan is saved in a database. For example, it generates an automated cash register system implementation plan for Company B's cash register operations and compiles it into a PDF report.

[0318] The server notifies the person in charge (user) of the target company of the generated plan. The notification method is an email service such as SendGrid. For example, the server sends an email with the implementation plan for the automated cash register system to the person in charge at "Company B," who then receives the email and checks the contents.

[0319] Additionally, users can provide feedback on the plan. Emotional data is collected through the analysis of user-entered text, facial expressions, and voice using an emotion engine (powered by IBM Watson and Google Cloud Natural Language API). For example, users can enter their concerns about the implementation cost into a feedback form, while their facial expressions are captured with a webcam.

[0320] The server then modifies the automation plan based on the emotion data obtained from the emotion engine. Specifically, it regenerates the plan by adding cost-saving options and detailed breakdowns, and notifies the user again. For example, the server may send the modified automated cash register system implementation plan to the person in charge at "Company B" again by email.

[0321] By following these steps, the system can manage a series of processes, from collecting and analyzing job information, notifying companies, and analyzing user feedback, effectively supporting companies in promoting digital transformation (DX).

[0322] Specific examples of prompts include:

[0323] "Please review Company B's plan to implement an automated cash register system for cash register operations and provide your opinion on the implementation costs."

[0324] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0325] Step 1:

[0326] The server collects job information.

[0327] Input: URL of website or API.

[0328] How it works: It uses Python's Beautiful Soup and Scrapy to scrape job information, retrieves it using a RESTful API, and sets up a scheduler to run it periodically.

[0329] Output: Job listings in raw data format.

[0330] Specific operation: The server retrieves job information for "cashier staff" from "job site A" and saves it in raw data format.

[0331] Step 2:

[0332] The server analyzes the collected job information.

[0333] Input: Job information collected in step 1 (raw data format).

[0334] How it works: Uses regular expressions and natural language processing (NLP) to extract company names, job titles, required skills, salary information, and more.

[0335] Output: Parsed job listings.

[0336] Specific operation: The server analyzes the job information obtained from "job site A" and extracts information such as "Company B," "cashier staff," and "monthly salary of 200,000 yen."

[0337] Step 3:

[0338] The server stores the analysis results in a database.

[0339] Input: The job information parsed in step 2.

[0340] What it does: Generates and executes an insert statement to save to a database such as MySQL or PostgreSQL.

[0341] Output: Job information stored in a database.

[0342] Specific operation: The server creates the analysis results as an insert statement and stores information such as "Company B," "cashier staff," and "monthly salary of 200,000 yen" in the MySQL database.

[0343] Step 4:

[0344] The server queries the database.

[0345] Input: Keywords for filtering (e.g., "cashier" or "data entry").

[0346] What it does: Retrieves relevant job listings from the database using an SQL query.

[0347] Output: Filtered job listings.

[0348] Specific operation: The server queries job information from the database based on keywords such as "cashier operation" and "data entry" and identifies "Company B."

[0349] Step 5:

[0350] The server performs company identification.

[0351] Input: Job listings filtered in step 4.

[0352] How it works: It uses machine learning algorithms to identify companies with jobs that can be automated from job postings.

[0353] Output: A list of identified companies.

[0354] Specific operation: The server identifies "Company B" based on keywords such as "cashier operation" and "data entry."

[0355] Step 6:

[0356] The server performs screening for the identified companies.

[0357] Input: List of identified companies.

[0358] How it works: Evaluates companies by retrieving financial data and technology adoption intentions from external databases, using Google Finance APIs and other similar tools.

[0359] Output: Ranking of assessed companies.

[0360] Specific operation: The server retrieves the financial data of "Company B" from the Google Finance API, evaluates its intention to adopt technology, and assigns it a high score.

[0361] Step 7:

[0362] The server generates a mechanized plan.

[0363] Enter: a list of highly rated companies.

[0364] How it works: Generates an optimal mechanization plan including the required technology, costs, and post-implementation effects, and summarizes it in a report format.

[0365] Output: Mechanization plan report.

[0366] Specific operation: The server generates an implementation plan for an automated cash register system for Company B and compiles it into a PDF report.

[0367] Step 8:

[0368] The server notifies the generated mechanization plan.

[0369] Input: Mechanization plan report.

[0370] How it works: Sent via email or in-platform notification. Use an email service like SendGrid.

[0371] Output: Notification to company personnel.

[0372] Specific operation: The server sends the generated implementation plan for the automated cash register system to the person in charge at Company B via email.

[0373] Step 9:

[0374] Users provide feedback on the plan.

[0375] Input: Notified mechanization plan.

[0376] How it works: Enter your thoughts and opinions through a feedback form and capture your facial expressions with a webcam.

[0377] Output: Feedback information and emotion data.

[0378] Specific operation: The user enters "The implementation cost is high" in the feedback form and captures their facial expression with a webcam.

[0379] Step 10:

[0380] The emotion engine analyzes the feedback.

[0381] Input: User feedback and emotional data.

[0382] How it works: Analyzes user emotions and opinions using natural language processing and facial expression analysis technology. Uses IBM Watson and Google Cloud Natural Language APIs.

[0383] Output: Parsed emotion data and feedback information.

[0384] Specific operation: The emotion engine analyzes the text "The implementation cost is high" and the anxious facial expression, and provides this information to the server.

[0385] Step 11:

[0386] The server modifies the plan based on the emotional data.

[0387] Input: Parsed emotion data and feedback information.

[0388] Action: Identify corrections and regenerate revised mechanization plans.

[0389] Output: Revised mechanization plan.

[0390] What it does: The server takes the user's concerns and generates a remediation plan with a detailed breakdown of implementation costs and cost-saving options.

[0391] Step 12:

[0392] The server notifies the modified plan.

[0393] Input: Revised mechanization plan.

[0394] Action: Re-inform the user about the remediation plan.

[0395] Output: Re-notification to company representative.

[0396] Specific operation: The server sends the revised automated cash register system implementation plan again to the person in charge at "Company B" by email.

[0397] This allows the system to manage a series of processes, from collecting job information and analyzing it, to notifying companies and analyzing user feedback, effectively supporting companies in promoting digital transformation (DX).

[0398] (Application example 2)

[0399] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0400] When mechanizing factory operations, it is difficult to allocate personnel efficiently and optimally allocate machines. There is also the problem of not being able to properly reflect the feelings and feedback of factory managers regarding mechanization plans. This can lead to delays in implementing mechanization plans and the failure to create an optimized working environment.

[0401] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting job information and in-factory personnel allocation data, means for analyzing the collected data to identify tasks that can be mechanized, means for screening identified companies, means for generating a mechanization plan for each screened company, means for notifying company and factory managers of the generated mechanization plan, means for collecting feedback and emotion data from company personnel, and means for analyzing the collected feedback and emotion data to revise the mechanization plan. This enables efficient mechanization of tasks within a factory and the provision of an optimal plan that reflects managerial feedback.

[0402] "Job information" refers to detailed information such as job type, required skills, salary, and work location that is published by a company when recruiting personnel.

[0403] "Feedback" is information provided by company representatives and factory managers that indicates responses such as areas for improvement, opinions, and satisfaction.

[0404] "Emotion data" is data that indicates the emotional state of a user extracted from facial expressions, voice, input text, etc.

[0405] A "mechanization plan" is a plan that includes specific procedures, implementation costs, and effects for automating specific tasks using machines or robots.

[0406] "Screening" is the process of evaluating and selecting the suitability of companies and businesses based on collected data.

[0407] "Analysis" is the process of processing collected data to extract and understand information suitable for a specific purpose.

[0408] "Revise" means adjusting and improving the initially generated plan or initiative based on feedback and sentiment data.

[0409] "Notification" is the process of communicating plans and information to relevant personnel and users.

[0410] This invention is a system that mechanizes factory operations and realizes optimal robot placement. This system is composed of a server, terminals, users, and an emotion engine.

[0411] server

[0412] The server operates this system using the following methods:

[0413] 1. Data collection methods:

[0414] The server collects job information and factory staffing data via websites and APIs and stores it in a database using scraping technology and APIs, specifically Python, BeautifulSoup, and an SQL database.

[0415] 2. Analysis method:

[0416] Machine learning algorithms (such as scikit-learn) are used to analyze collected data and identify tasks that can be automated. For example, collected data such as "machine operation" and "logistics management" can be classified and tasks that can be automated can be extracted.

[0417] 3. Screening measures:

[0418] The screening method evaluates companies' financial data and intentions to adopt technology based on the analyzed data, and identifies companies with high scores. In this process, APIs are used to obtain information from external databases.

[0419] 4. Mechanized plan generation means:

[0420] A mechanization plan is generated for each high-scoring company. This plan includes implementation costs, benefits, and implementation procedures. The plan is compiled into a report using Python and saved on the server.

[0421] 5. Means of notification:

[0422] The mechanization plan generated using the notification function is sent to the factory manager via email or push notification. Notifications are sent using email service APIs (e.g., SendGrid) or push notification mechanisms (e.g., Firebase).

[0423] 6. Emotional data collection methods:

[0424] To collect feedback and emotional data from factory managers, cameras and microphones for emotion analysis are used. The emotion engine (Emotion API) analyzes facial expressions and voice data to obtain the content of the feedback.

[0425] 7. Sentiment data analysis methods:

[0426] The collected emotional data is analyzed to help refine the mechanized plan, using an emotional analysis engine to optimize the plan according to the emotions expressed by the user.

[0427] 8. Plan Modification Methods:

[0428] The plan is revised based on the sentiment data and notified to the user again. The revised plan includes new cost-saving ideas and implementation steps, and is sent via email and push notifications.

[0429] Terminal

[0430] The factory manager's device (smartphone or tablet) is used to input feedback and collect sentiment data, allowing the manager to review the proposed mechanization plan and provide feedback.

[0431] User

[0432] The user, the factory manager, can review the notified plan and provide feedback and emotions, which will be used to optimize the plan.

[0433] Specific examples

[0434] For example, the server may identify from collected data that mechanization of "logistics management" tasks is possible and generate a plan proposing the introduction of automated transport robots. This plan is then notified to the factory manager, and if the manager mentions "the introduction cost is high" as emotional feedback, the server will regenerate a revised plan including cost reduction proposals and notify the manager again.

[0435] Example prompt sentence:

[0436] This email is to inform you about your factory's mechanization plan. Please review the plan below and let us know your opinions and feedback.

[0437] Plan details:

[0438] Operations to be mechanized: Logistics management

[0439] Proposed technology: Automatic transport robot deployment

[0440] Estimated cost: 5 million yen

[0441] Introduction effect: Reduction of work time, improvement of labor efficiency

[0442] Please leave your comments and feedback here: [Link]

[0443] Thank you for your cooperation.

[0444] This invention allows for efficient mechanization and optimal allocation of work within a factory, and makes it possible to provide optimal plans that take into account the opinions and feelings of managers.

[0445] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0446] Step 1: Data collection

[0447] The server collects job information and factory staffing data from websites and APIs. Specifically, it uses scraping technology (e.g., Python's BeautifulSoup) and APIs (e.g., the API of a job information service) to collect data such as "machine operation" and "logistics management." The collected data is then stored in a database (e.g., an SQL database).

[0448] Input: Job postings and staffing data.

[0449] Data processing: Convert data into structured data using scraping technology or APIs.

[0450] Output: Information stored in a database.

[0451] Step 2: Data analysis

[0452] The server analyzes the collected data and identifies tasks that can be automated. It uses machine learning algorithms (e.g., scikit-learn) to classify the data based on specific keywords. For example, based on data on "logistics management," it identifies tasks for which automated transport robots can be introduced.

[0453] Input: Job postings and placement data from the database.

[0454] Data computation: analysis using machine learning algorithms.

[0455] Output: A list of tasks that can be automated.

[0456] Step 3: Screening

[0457] The server screens companies for the identified business, scores them by referencing external databases and survey results (e.g., company financial data and technology adoption intentions), and ranks and prioritizes companies with high scores.

[0458] Input: Parsed business data and information from external databases.

[0459] Data calculations: scoring algorithms.

[0460] Output: A ranked list of the highest scoring companies.

[0461] Step 4: Generate a mechanization plan

[0462] The server generates a mechanization plan for each top-ranked company, including implementation costs, benefits, and implementation procedures, and compiles the plan into a report using Python.

[0463] Input: Ranking list and information on mechanizable tasks.

[0464] Data Processing: Generating plans and converting them into report formats.

[0465] Output: Mechanized plan in report format.

[0466] Step 5: Notification

[0467] The server sends the generated mechanization plan to the factory manager via email or push notification, using an email service API (e.g., SendGrid) or a push notification function (e.g., Firebase).

[0468] Input: Mechanized plan in report format.

[0469] Data processing: Convert into email or push notification.

[0470] Output: Notification to factory manager.

[0471] Step 6: Collect feedback and sentiment data

[0472] Through the terminal, the factory manager provides feedback on the received plan and emotional data (e.g., facial expressions, voice). The data is analyzed by an emotion engine (e.g., Emotion API) using an emotion analysis camera and microphone.

[0473] Input: Feedback and sentiment data from factory managers.

[0474] Data Computing: Text and Sentiment Analysis.

[0475] Output: Parsed emotion data.

[0476] Step 7: Modify the plan

[0477] The server then uses the feedback and sentiment data to revise the original mechanisation plan, including new cost-saving ideas and detailed implementation steps, and compiles the results in a report.

[0478] Input: Emotion data and feedback.

[0479] Data processing: Modifying the plan and converting it back into a report format.

[0480] Output: Revised mechanization plan.

[0481] Step 8: Snooze

[0482] The server again notifies the factory manager of the revised mechanization plan.

[0483] Input: Revised mechanization plan.

[0484] Data processing: Reconvert to email or push notification.

[0485] Output: Re-notify factory manager.

[0486] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0487] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0488] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0489] [Second embodiment]

[0490] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0491] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0492] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0493] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0494] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0495] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0496] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0497] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0498] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0499] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0500] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0501] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0502] The present invention relates to a system for collecting, analyzing, screening, and generating and notifying job information automation plans. This system is composed of a server, a terminal, and a user, and each component functions as follows.

[0503] overview

[0504] The server periodically collects job information, analyzes the data, and identifies tasks that can be automated. It then screens the identified companies and generates an optimal automation plan for each company based on the results. Finally, the plan is notified to the company's representative.

[0505] Data collection

[0506] The server collects job information from websites that publish job postings using scraping technology or APIs. The collected data is analyzed by fields such as company name, job type, required skills, and salary information, and then stored in a database.

[0507] Examples:

[0508] Every day at 2 a.m., the server retrieves data from multiple websites that publish job listings. For example, if "Company X" is hiring a "cashier," the server stores that information in a database.

[0509] Company specific

[0510] The server analyzes the collected data and filters job listings that contain specific keywords (e.g., "cashier operator" or "data entry"), thereby identifying companies with jobs that can be automated.

[0511] Examples:

[0512] "Company Y" is identified based on keywords such as "cashier operation" and "data entry." The server retrieves and analyzes job information for "Company Y" from the database.

[0513] screening

[0514] The server evaluates the identified companies based on financial data, intentions to introduce technology, industry trends, etc., and screens them based on their future potential. The screening results are then ranked.

[0515] Examples:

[0516] The financial data and technology adoption intentions of "Company Y" are obtained from an external database, and the server uses that information to rank "Company Y." For example, "Company Y" can receive a relatively high score.

[0517] Mechanization plan generation

[0518] The server generates a mechanization plan for each selected company based on the screening results. The plan includes the technology to be introduced, the expected costs, and the effects after introduction. The plan is generated in report format and saved on the server.

[0519] Examples:

[0520] The server generates a plan proposing the introduction of an automated cash register system for Company Y's cash register operations. This plan details the introduction costs, predicted benefits, and specific implementation procedures.

[0521] notification

[0522] The server notifies the target company's personnel of the generated automation plan. This notification is done via email or the platform's notification function. The user (company personnel) receives the notification, checks the proposal, and sends feedback to the server if necessary.

[0523] Examples:

[0524] The server sends an email with the automated cash register system implementation plan to the person in charge at Company Y. The person in charge (user) receives the email and reviews the plan in detail.

[0525] This system will enable small and medium-sized enterprises to efficiently promote digital transformation by consistently analyzing job information and providing specific mechanization plans.

[0526] The processing flow will be explained below.

[0527] Step 1:

[0528] The server accesses websites and APIs where job information is published based on a regular schedule, and retrieves job information using scraping technology and APIs.

[0529] Step 2:

[0530] The server parses the job postings, which includes extracting the necessary data fields (company name, job title, required skills, salary information, etc.) from the JSON or HTML format.

[0531] Step 3:

[0532] The server stores the analyzed job information in a database, including company names, job titles, required skills, salary information, etc.

[0533] Step 4:

[0534] The server queries and retrieves job data from a database, filtering the data to see if it contains specific keywords (e.g., "cashier clerk" or "data entry").

[0535] Step 5:

[0536] The server lists companies that have mechanizable processes based on specific keywords, and these companies are then subject to screening.

[0537] Step 6:

[0538] The server refers to external databases and survey results to conduct financial data and technology adoption intention surveys for the listed companies, and evaluates each company based on this data.

[0539] Step 7:

[0540] The server scores each company based on the evaluation results and generates a ranking based on future potential. Companies with high scores are given priority in generating automation plans.

[0541] Step 8:

[0542] The server generates a mechanization plan for each high-scoring company, which includes the technology to be implemented, the expected costs, and the effects of implementation.

[0543] Step 9:

[0544] The server compiles the generated mechanization plan in a report format that is easy for company personnel to understand and is stored in a database.

[0545] Step 10:

[0546] The server generates an email or platform notification to notify the target company's personnel of the automation plan, which includes details of the plan.

[0547] Step 11:

[0548] The user (company representative) checks the notification and reviews the proposal. If necessary, the user can submit feedback or additional questions to the server through a dedicated web form.

[0549] Step 12:

[0550] The server analyzes the received feedback, modifies the mechanization plan as necessary, generates a final proposal after the modifications, and notifies the company representative again.

[0551] Step 13:

[0552] The user (company representative) receives the final proposal and initiates the internal approval process. The server tracks the company's progress in implementing DX and sends notifications if additional support is required.

[0553] Example 1

[0554] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0555] Currently, for small and medium-sized enterprises to efficiently promote digital transformation (DX), advanced technical knowledge and a great deal of effort are required. As a result, many small and medium-sized enterprises are unable to implement effective DX, making it difficult to improve operational efficiency and reduce costs. If we could identify mechanizable tasks from job information and provide companies with appropriate mechanization plans, we could support the promotion of DX in small and medium-sized enterprises. However, doing this manually is extremely labor-intensive and difficult to describe as efficient. To solve this issue, it is necessary to automate the system and perform all processes from collecting job information to generating and notifying mechanization plans.

[0556] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0557] In this invention, the server includes: means for collecting job information; means for analyzing the collected job information to identify mechanizable tasks; means for screening identified companies; means for generating a mechanization plan for each screened company; means for notifying the companies of the generated mechanization plan; means for using web scraping technology or a public API to collect job information; means for parsing the collected data into company names, job duties, required skills, and compensation information and storing them in a database; means for analyzing the job information using natural language processing and filtering the job information based on specific keywords to identify mechanizable tasks; means for evaluating and screening companies based on financial data, technology adoption intentions, and industry trends; means for generating a mechanization plan based on the evaluated screening results, including the technology to be introduced, expected costs, and post-implementation effects; means for notifying company representatives of the generated mechanization plan via email or platform notification function; and means for receiving user feedback. This automates the entire process from collecting job information to analyzing, filtering, screening, and generating and notifying mechanization plans, enabling small and medium-sized enterprises to efficiently promote digital transformation.

[0558] "Means of collecting job information" refers to the function of automatically obtaining data from websites where job information is published using web scraping technology or public APIs.

[0559] "Means of analyzing collected job information to identify tasks that can be automated" refers to the function of analyzing the text of collected job information using natural language processing (NLP) technology and filtering tasks that can be automated based on specific keywords.

[0560] "Means for screening identified companies" refers to the function of evaluating companies identified as having operations that can be mechanized based on information such as financial data, intentions to introduce technology, and industry trends, and then screening and ranking the companies.

[0561] "Means for generating mechanization plans for each screened company" refers to the function of generating mechanization plans for selected companies based on the screening results, including the technology to be introduced, expected costs, and post-implementation effects.

[0562] "Means for notifying the enterprise of the generated mechanization plan" refers to the function of sending the generated mechanization plan to the enterprise's personnel via email or platform notification.

[0563] "Methods of using web scraping technology or public APIs to collect job information" refers to the function of automatically collecting data from websites where job information is published using web scraping technology or public APIs.

[0564] "Means for analyzing collected data into company name, job position, required skills, and compensation information and storing it in a database" refers to the function of analyzing collected job information into fields such as company name, job position, required skills, and compensation information, and storing it appropriately in a database.

[0565] "Means of analyzing job postings using natural language processing, filtering job postings based on specific keywords, and identifying jobs that can be mechanized" refers to a function that uses natural language processing technology to analyze the text of job postings, filtering job postings based on specific keywords such as "cash register" or "data entry," and identifying job postings that have tasks that can be mechanized.

[0566] "Means of evaluating and screening companies based on financial data, intentions to introduce technology, and industry trends" refers to the function of collecting information such as financial data, intentions to introduce technology, and industry trends of identified companies, and evaluating and screening companies based on this data.

[0567] "Means for generating a mechanization plan including the technology to be introduced, the expected cost, and the effects after introduction based on the evaluated screening results" refers to the function of generating a mechanization plan that specifies the technology to be introduced, the expected cost of introduction, and the effects after introduction based on the company's screening results.

[0568] "Means for notifying company personnel of the generated automation plan by email or platform notification function" refers to the function of sending the generated automation plan to company personnel via email or platform notification, allowing the personnel to review the plan.

[0569] "Means for receiving feedback from users" refers to a function that allows a company representative to send feedback on a proposed mechanization plan to the server and receive that feedback.

[0570] The present invention relates to a system for collecting, analyzing, screening, and generating and notifying job information automation plans. This system is composed of a server, terminals, and users, and each component functions in cooperation with the others.

[0571] Data collection

[0572] The server periodically collects job information from websites that publish job postings. This collection process uses web scraping technology and public APIs. Specifically, data is extracted using Python libraries such as BeautifulSoup and Selenium. The collected data is analyzed into fields such as company name, job position, required skills, and compensation information, and then stored in a database such as MySQL or PostgreSQL.

[0573] As a concrete example, the server retrieves data from "job site A" and "job site B" every day at 2:00 a.m. For example, if "company A" is hiring a "cashier clerk," that information is stored in the database as the company name, job title, required skills, and compensation information.

[0574] Keyword Analysis

[0575] The server periodically analyzes the collected data and filters out job postings that contain specific keywords (e.g., "cashier operator" or "data entry"). This analysis is performed using natural language processing (NLP) technology. Specifically, NLP libraries such as NLTK and spaCy are used. Based on the results of this filtering, companies with tasks that can be automated are identified.

[0576] As a specific example, the server analyzes the text of the collected job postings and extracts job postings that contain keywords such as "cashier operator" and "data entry." For example, "Company B" is identified, and its job posting information is retrieved from the database and analyzed.

[0577] screening

[0578] The server evaluates and screens the identified companies based on financial data, technology adoption intentions, industry trends, etc. This evaluation process uses data obtained from external databases such as D&B Hoovers and Crunchbase. The server scores companies based on this data and stores the evaluation results in a new database table.

[0579] As a specific example, the server obtains financial data and technology adoption intentions of "Company B" from an external database and evaluates "Company B" based on that information. Company B can receive a relatively high score.

[0580] Mechanization plan generation

[0581] Based on the screening results, the server generates a mechanization plan for each selected company, which includes the technology to be introduced, the expected costs, and the effects after introduction. The generated plan is saved as a PDF report.

[0582] As a specific example, the server generates a mechanization plan proposing the introduction of an automated cash register system for the cash register operations of "Company B." This plan details the introduction costs, predicted benefits, and specific implementation procedures.

[0583] notification

[0584] The server notifies the company representative (user) of the generated mechanization plan via email or the platform notification function. The user receives the notification and checks the proposal. If necessary, the user can send feedback to the server.

[0585] As a concrete example, the server sends an automated cash register system implementation plan by email to the person in charge (user) of "Company B." The user receives the email and reviews the plan in detail.

[0586] Prompt Sentence Examples

[0587] Here are some example prompts for a generative AI model:

[0588] Analyze the job postings of the following companies, identify the tasks that can be automated, and then create a mechanization plan based on that. Company Name: Company C

[0589] This system will enable small and medium-sized enterprises to efficiently promote digital transformation by consistently analyzing job information and providing specific mechanization plans.

[0590] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0591] Step 1: Data collection

[0592] The device periodically sends a request to the server to collect job information. The server uses Python's BeautifulSoup and Selenium to scrape job information from websites. The job data is parsed into company names, job roles, required skills, and compensation information, and stored in a MySQL or PostgreSQL database.

[0593] Specific behavior:

[0594] The device sends a job information collection request to the server at 2:00 AM.

[0595] The server scrapes job information from "job site A" and "job site B" and obtains the HTML data.

[0596] The server uses BeautifulSoup to parse the HTML data and categorize it into company names, job roles, required skills, compensation information, etc.

[0597] The server stores the classified data in a database.

[0598] Input: Request from the device, HTML data of the job site

[0599] Output: A database containing company names, jobs, required skills, and compensation information

[0600] Step 2: Keyword analysis

[0601] The server periodically retrieves collected data from the database and filters job postings that contain specific keywords. It analyzes the text using natural language processing techniques such as NLTK and spaCy.

[0602] Specific behavior:

[0603] The server retrieves all jobs from the database.

[0604] The server uses NLTK to analyze the text of the job posting and detect keywords such as "cashier operator" and "data entry."

[0605] The server filters job listings based on keywords to identify job listings that include tasks that can be mechanized.

[0606] Store the filtered job listings in a new database table.

[0607] Input: Jobs in the database

[0608] Output: A new database table with filtered job listings

[0609] Step 3: Identify the company

[0610] The server identifies companies with work that can be automated based on the filtered job information. The information about the identified companies is recorded in a separate database table.

[0611] Specific behavior:

[0612] The server extracts company names from the filtered job listings.

[0613] The server stores the extracted company names in a new database table.

[0614] Input: Filtered Jobs

[0615] Output: A database table containing the identified company names

[0616] Step 4: Screening

[0617] The server evaluates companies based on their financial data, intentions to adopt technology, industry trends, etc. It obtains the necessary information from external databases such as D&B Hoovers and Crunchbase, scores companies, and stores the results in a new database table.

[0618] Specific behavior:

[0619] The server uses an external API to obtain financial data and technology adoption intentions of the identified companies.

[0620] Based on the data acquired by the server, companies are screened using a specified algorithm.

[0621] The screening results are stored in a new database table.

[0622] Input: Company information obtained from an external database

[0623] Output: Database table containing screening results (scores)

[0624] Step 5: Mechanization plan generation

[0625] Based on the screening results, the server generates a mechanization plan for each company. This plan includes the technology to be implemented, the expected costs, and the effects after implementation. The plan is compiled into a PDF report.

[0626] Specific behavior:

[0627] The server obtains the screening results and generates a mechanization plan suitable for each company.

[0628] The generated plan is saved as a PDF report.

[0629] Input: Screening results

[0630] Output: Mechanized plan in PDF format

[0631] Step 6: Notification

[0632] The server sends the generated mechanized plan to the company representative (user) via email or platform notification function.

[0633] Specific behavior:

[0634] The server obtains the email address of the company contact person.

[0635] The server sends the generated mechanized plan as an attachment to an email.

[0636] The user receives an email confirming the plan.

[0637] Input: Mechanization plan in PDF format, email address of company contact person

[0638] Output: Email sent to company contact

[0639] Prompt Sentence Examples

[0640] Here are some example prompts for a generative AI model:

[0641] Analyze the job postings of the following companies, identify the tasks that can be automated, and then create a mechanization plan based on that. Company Name: Company C

[0642] (Application example 1)

[0643] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0644] In modern factories, labor shortages and streamlining operations are major challenges. However, determining which operations are suitable for mechanization and creating specific plans for doing so requires a great deal of time and specialized knowledge. Furthermore, there is a lack of ways for company personnel to quickly understand and implement implementation plans. Given these circumstances, there is a need for a system that allows companies to mechanize operations quickly and efficiently.

[0645] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0646] In this invention, the server includes means for collecting job information, means for analyzing the collected job information to identify tasks that can be mechanized, means for screening the identified companies, means for generating a mechanization plan for each screened company, means for notifying the companies of the generated mechanization plan, means for generating a factory robot introduction plan based on the collected job information, and means for notifying the company's smartphone application of the generated introduction plan. This allows companies to quickly and efficiently obtain a mechanization plan and proceed with the introduction of appropriate factory robots.

[0647] "Job information" refers to information about the job duties, required skills, salary conditions, etc., of the personnel that companies are looking for.

[0648] The "means of collection" refers to the mechanism by which job information is obtained from websites via scraping or API.

[0649] "Means of analyzing and identifying tasks that can be mechanized" refers to a method of analyzing collected job information and finding tasks that can be replaced by machines.

[0650] "Means for screening identified companies" refers to a method of evaluating companies that are deemed capable of mechanizing their operations based on financial data, intentions to introduce technology, etc.

[0651] The "means of generating a mechanization plan" is a method of creating the optimal mechanization plan for each company and creating a report that includes implementation costs, effects, implementation procedures, etc.

[0652] The "means of notification" refers to a mechanism for communicating the generated mechanization plan to company personnel via email or on the platform.

[0653] A "factory robot" is a mechanical device introduced to automate manufacturing work.

[0654] A "smartphone application" is software installed on a smartphone and is a program with notification and data processing functions.

[0655] A "prompt" is a textual input given to a generative AI model to generate a specific output.

[0656] A "generative AI model" is an artificial intelligence system that uses machine learning and deep learning to generate specific outputs from input data.

[0657] The present invention relates to a system in which a server collects, analyzes, screens, generates and notifies job information. A specific embodiment of this system is described below.

[0658] Collecting job information

[0659] The server periodically collects job information from websites that publish job postings using scraping technology or APIs. This information is stored in a database and categorized by fields such as company name, job type, required skills, salary information, etc. For example, if a "company" is hiring an "assembly line worker," that information will be retrieved by the server.

[0660] Data analysis and company identification

[0661] Next, the server analyzes the collected job information and filters job postings containing specific keywords (e.g., "assembly," "inspection," etc.) to identify tasks that can be automated. This step extracts companies that are suitable for introducing factory robots. For example, if a "certain factory" is hiring someone for assembly work, that company will be identified.

[0662] screening

[0663] The server collects and evaluates external data on identified companies, such as financial data, technology adoption intentions, and industry trends. This allows the companies to be ranked based on their future prospects. For example, the server evaluates the financial data and technology adoption intentions of a "certain factory," and assigns a certain score based on the results.

[0664] Generating mechanization plans

[0665] Based on the screening results, the server generates a mechanization plan for each company. This plan includes the factory robots to be introduced, the estimated costs, and the introduction procedure. The generated plan is saved in the form of a report. For example, for the assembly line operations of a "certain factory," the server generates a plan proposing the introduction of XYZ robots, and the details are provided in a report.

[0666] notification

[0667] The generated mechanization plan is notified from the server to the company's employee's smartphone application. This notification is sent via email or push notification. The user (company employee) receives the notification, checks the proposal, and sends feedback to the server if necessary. For example, the server can send an automation plan to the employee of a "certain factory" via a smartphone application.

[0668] Hardware and software used

[0669] The system consists of a server, database, network infrastructure, and a user's smartphone application. Tools such as BeautifulSoup and Selenium are used for scraping, and the Requests library is used for API communication. Server-side processing is implemented using frameworks such as Flask and Django. Machine learning models and condition-based filtering are used for data analysis and company identification.

[0670] Examples of concrete examples and prompts

[0671] For example, if the server finds a job opening for an assembly line worker in a "certain factory" and determines that the job is suitable for mechanization, it will generate a plan to introduce XYZ robots. The plan is provided in the following format:

[0672] Example prompt sentence:

[0673] Company Name: A Factory

[0674] Position: Assembly Line Worker

[0675] Skills: Basic assembly work

[0676] Salary: 3 million yen / year

[0677] Please propose an appropriate automation plan for this company, particularly the type of robots to be implemented, the estimated costs, and the expected benefits after implementation.

[0678] In this way, companies can obtain an efficient and specific mechanization plan and proceed with the introduction of appropriate factory robots.

[0679] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0680] Step 1:

[0681] The server collects job information.

[0682] Input: URLs of multiple websites where job postings are published.

[0683] What it does: The server uses BeautifulSoup and Selenium to scrape job listings from the specified website, and if a specific API is provided, it uses the Requests library to collect data via the API.

[0684] Output: Collected job information (company name, job title, required skills, salary information, etc.).

[0685] Step 2:

[0686] The server analyzes the collected job information and identifies tasks that can be automated.

[0687] Input: The collected job posting dataset.

[0688] How it works: The server uses natural language processing (NLP) technology to analyze the text data of job postings, checking whether specific keywords (e.g., "assembly," "inspection," etc.) are included, and filtering out tasks that can be automated.

[0689] Output: Job postings and a list of companies with mechanizable tasks.

[0690] Step 3:

[0691] Screening companies whose servers have been identified.

[0692] Input: List of companies with mechanizable operations.

[0693] What it does: The server collects external data such as company financial data, technology adoption intentions, and industry trends. This includes API access to external databases (e.g., financial databases). Based on the collected data, it evaluates and scores each company.

[0694] Output: A ranked list of highly rated companies.

[0695] Step 4:

[0696] The server generates a mechanized plan for each company screened.

[0697] Input: A ranked list of highly rated companies.

[0698] How it works: The server uses a generative AI model to generate an optimal mechanization plan for each company. It prompts users to enter information about the company, the position being filled, the required skills, and salary information, and generates a report that includes the type of robot to be introduced, the estimated cost, and the effects after introduction.

[0699] Output: Mechanization plan report for each company.

[0700] Step 5:

[0701] The server notifies the generated mechanization plan to the company representative's smartphone application.

[0702] Input: Mechanization plan report and company contact information.

[0703] Specific operation: The server uses an SMTP server to generate a notification email and send it to the company's representative. It also uses a push notification service (e.g., Firebase Cloud Messaging) to send a push notification to a smartphone application.

[0704] Output: A notification message to the company contact who received the plan notification.

[0705] By performing the above steps, the server can consistently perform the process from collecting job information to generating and notifying a mechanized plan.

[0706] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0707] This invention combines an emotion engine with a system that collects, analyzes, screens, and generates and notifies job information mechanized plans. This system consists of a server, a terminal, a user, and an emotion engine, and each component functions as follows:

[0708] overview

[0709] The server periodically collects job information, analyzes the data, and identifies tasks that can be automated. It then screens the identified companies and generates an optimal automation plan for each company based on the results. The generated plan is notified to the company's representative, and an emotion engine analyzes user feedback and emotions to further optimize the plan.

[0710] Data collection

[0711] The server periodically retrieves data from websites and APIs where job information is published. Using scraping technology and APIs, the server collects job information, analyzes it into company names, job types, required skills, salary information, etc., and stores the information in a database.

[0712] Examples:

[0713] Every day at 2 a.m., the server retrieves data from multiple websites that publish job information. For example, if "Company A" is hiring a "cashier," the server stores that information in a database.

[0714] Company specific

[0715] The server queries and retrieves job data from a database, analyzes the data, and filters it based on specific keywords (e.g., "cashier operation" or "data entry") to identify companies with tasks that can be automated.

[0716] Examples:

[0717] "Company B" is identified based on keywords such as "cashier operation" and "data entry." The server retrieves and analyzes the job information for "Company B" from the database.

[0718] screening

[0719] The server then refers to external databases and survey results to obtain financial data and technology adoption intentions for the identified companies. The server then evaluates each company based on this data and ranks the companies with the highest scores.

[0720] Examples:

[0721] The financial data and technology adoption intentions of "Company B" are obtained from an external database, and the server uses that information to rank "Company B." For example, "Company B" can receive a relatively high score.

[0722] Mechanization plan generation

[0723] The server generates a mechanization plan for each high-ranking company, detailing the technology to be implemented, the expected costs, and the effects after implementation. The generated plan is compiled in a report format and saved on the server.

[0724] Examples:

[0725] The server generates a plan proposing the introduction of an automated cash register system for Company B's cash register operations. This plan details the introduction costs, predicted benefits, and specific implementation procedures.

[0726] notification

[0727] The server sends the generated mechanization plan to the person in charge of the target company via email or the platform's notification function. The user (company person in charge) receives the notification and confirms the proposal.

[0728] Examples:

[0729] The server sends an email with the automated cash register system implementation plan to the person in charge at Company B. The person in charge (user) receives the email and reviews the plan in detail.

[0730] Emotion engine integration

[0731] The emotion engine analyzes the user's feedback and reactions, analyzing the text entered by the user through the feedback form, as well as facial expressions and voice when confirming the plan, to obtain emotional data.

[0732] Examples:

[0733] When a company representative provides feedback while reviewing the plan, the emotion engine analyzes the user's input text, facial expressions, and voice. For example, if the user is worried about the implementation cost, the emotion engine analyzes that information and provides it to the server.

[0734] Modifying the plan

[0735] The server modifies the mechanized plan based on the emotion data obtained from the emotion engine, and the modified plan is notified to the user again.

[0736] Examples:

[0737] Based on the information obtained from the emotion engine, the server regenerates a correction plan that includes a detailed breakdown of implementation costs and options for cost reduction. The correction plan is then sent again to the company's representative via email.

[0738] This system not only provides mechanized plans, but also provides optimized plans that take into account user emotions and feedback, making it possible to effectively support companies in promoting digital transformation.

[0739] The processing flow will be explained below.

[0740] Step 1:

[0741] The server accesses websites and APIs where job information is published based on a regular schedule, and retrieves job information using scraping technology and APIs.

[0742] Step 2:

[0743] The server parses the job postings, which includes extracting the necessary data fields (company name, job title, required skills, salary information, etc.) from the JSON or HTML format.

[0744] Step 3:

[0745] The server stores the analyzed job information in a database, including company names, job titles, required skills, salary information, etc.

[0746] Step 4:

[0747] The server queries and retrieves job data from a database, filtering the data for specific keywords (e.g., "cashier clerk" or "data entry").

[0748] Step 5:

[0749] The server identifies companies with mechanizable tasks based on the filtered job listings, and adds the identified companies to a list.

[0750] Step 6:

[0751] Based on the list of identified companies, the server obtains external data for evaluation (e.g., financial data, intention to introduce technology, etc.) and uses this data to evaluate each company and assign a score.

[0752] Step 7:

[0753] The server ranks each company based on the evaluation results, and companies with higher scores are given priority when generating mechanization plans.

[0754] Step 8:

[0755] The server generates a mechanization plan for each high-scoring company, which includes the technology to be implemented, the expected costs, and the benefits of implementation.

[0756] Step 9:

[0757] The server compiles the generated mechanization plan in the form of a report and stores it in a database.

[0758] Step 10:

[0759] The server sends the generated mechanized plan to the person in charge of the target company via email or the notification function on the platform, which includes details of the plan.

[0760] Step 11:

[0761] The user (company representative) checks the notification and reviews the proposal, and then submits feedback or additional questions to the server via a dedicated web form.

[0762] Step 12:

[0763] The emotion engine analyzes the user's feedback and facial expressions and voice when confirming the plan, and the analysis results are provided to the server as emotion data.

[0764] Step 13:

[0765] The server modifies the mechanized plan based on the emotion data and regenerates an optimized plan, which is then stored in the database.

[0766] Step 14:

[0767] The server then notifies the user of the optimized plan, who then reviews the plan and provides final feedback and approval.

[0768] Step 15:

[0769] The user (company representative) initiates the internal approval process based on the final proposal. The server tracks the progress of the company's DX implementation and sends notifications if additional support is required.

[0770] Example 2

[0771] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0772] Conventional recruitment information collection systems are capable of collecting and analyzing recruitment information and generating automation plans, but they are not optimized to take into account the feelings and feedback of company representatives. As a result, it is difficult for the proposed automation plans to fully meet the needs of company representatives, and actual implementation may not progress.

[0773] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0774] In this invention, the server includes means for collecting job information, means for analyzing the collected job information to identify tasks that can be mechanized, means for screening the identified organizations, means for generating a mechanization plan for each screened organization, means for notifying the organizations of the generated mechanization plan, means including an emotion engine for collecting and analyzing feedback from organizational personnel, and means for modifying the mechanization plan based on the emotion engine. This makes it possible to provide more practical and easy-to-implement mechanization plans that reflect the emotions and feedback of company personnel.

[0775] "Methods of collecting job information" refers to technologies for obtaining job data from websites and APIs, including scraping technologies and API integration.

[0776] "Means for analyzing job information to identify tasks that can be automated" refers to technology that analyzes collected job data and identifies tasks that can be automated based on specific keywords or patterns.

[0777] The "means for screening the identified organizations" refers to techniques for investigating and evaluating the financial data and intentions to introduce technology of the identified organizations.

[0778] The "means for generating a mechanization plan" is a technique for designing an optimal mechanization plan for each evaluated organization, detailing the implementation technology, costs, effects, etc.

[0779] "Means for notifying the organization of the generated mechanization plan" refers to a technology for sending the generated mechanization plan to the person in charge at the target organization via email or a notification function on the platform.

[0780] The "means including an emotion engine for collecting and analyzing feedback from organizational personnel" is a technology for collecting feedback provided by personnel and analyzing text, facial expressions, and voice.

[0781] The "means for modifying a mechanization plan based on an emotion engine" is a technology that identifies areas for improvement in a mechanization plan based on emotion data obtained from an emotion engine and redesigns the plan.

[0782] This invention combines an emotion engine with a system that collects, analyzes, screens, and generates and notifies job information mechanization plans. This system consists of a server, terminals, users, and an emotion engine. The detailed configuration and operation are described below.

[0783] First, the server collects job information. To do this, it uses scraping technologies such as Python's Beautiful Soup and Scrapy, as well as RESTful APIs. Every day at 2:00 AM, the server retrieves data from websites and APIs that list multiple job listings, parses it into information such as company name, job type, required skills, and salary information, and then stores it in a database (such as MySQL or PostgreSQL).

[0784] For example, the server periodically retrieves job information for "cashier staff" from "XYZ job site" every day and stores it in a MySQL database. This collected data is used in subsequent processing.

[0785] Next, the server identifies companies. It uses specific keywords (e.g., "cashier operation" or "data entry") to filter out companies with tasks that can be automated for the job data retrieved from the database. For example, the server identifies a company based on the keywords "cashier operation" or "data entry."

[0786] The server then screens the identified companies. This involves using external databases such as the Google Finance API to obtain financial data and evaluating the companies' intentions to adopt technology. Companies with high scores are then ranked. For example, the server evaluates the financial data and intentions to adopt technology of "Company B" and gives it a high score.

[0787] Next, the server generates an automation plan for each highly rated company. It creates a plan in the form of a report that includes implementation costs, effects, and implementation procedures, such as an automated cash register system implementation plan. This generated plan is saved in a database. For example, it generates an automated cash register system implementation plan for Company B's cash register operations and compiles it into a PDF report.

[0788] The server notifies the person in charge (user) of the target company of the generated plan. The notification method is an email service such as SendGrid. For example, the server sends an email with the implementation plan for the automated cash register system to the person in charge at "Company B," who then receives the email and checks the contents.

[0789] Additionally, users can provide feedback on the plan. Emotional data is collected through the analysis of user-entered text, facial expressions, and voice using an emotion engine (powered by IBM Watson and Google Cloud Natural Language API). For example, users can enter their concerns about the implementation cost into a feedback form, while their facial expressions are captured with a webcam.

[0790] The server then modifies the automation plan based on the emotion data obtained from the emotion engine. Specifically, it regenerates the plan by adding cost-saving options and detailed breakdowns, and notifies the user again. For example, the server may send the modified automated cash register system implementation plan to the person in charge at "Company B" again by email.

[0791] By following these steps, the system can manage a series of processes, from collecting and analyzing job information, notifying companies, and analyzing user feedback, effectively supporting companies in promoting digital transformation (DX).

[0792] Specific examples of prompts include:

[0793] "Please review Company B's plan to implement an automated cash register system for cash register operations and provide your opinion on the implementation costs."

[0794] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0795] Step 1:

[0796] The server collects job information.

[0797] Input: URL of website or API.

[0798] How it works: It uses Python's Beautiful Soup and Scrapy to scrape job information, retrieves it using a RESTful API, and sets up a scheduler to run it periodically.

[0799] Output: Job listings in raw data format.

[0800] Specific operation: The server retrieves job information for "cashier staff" from "job site A" and saves it in raw data format.

[0801] Step 2:

[0802] The server analyzes the collected job information.

[0803] Input: Job information collected in step 1 (raw data format).

[0804] How it works: Uses regular expressions and natural language processing (NLP) to extract company names, job titles, required skills, salary information, and more.

[0805] Output: Parsed job listings.

[0806] Specific operation: The server analyzes the job information obtained from "job site A" and extracts information such as "Company B," "cashier staff," and "monthly salary of 200,000 yen."

[0807] Step 3:

[0808] The server stores the analysis results in a database.

[0809] Input: The job information parsed in step 2.

[0810] What it does: Generates and executes an insert statement to save to a database such as MySQL or PostgreSQL.

[0811] Output: Job information stored in a database.

[0812] Specific operation: The server creates the analysis results as an insert statement and stores information such as "Company B," "cashier staff," and "monthly salary of 200,000 yen" in the MySQL database.

[0813] Step 4:

[0814] The server queries the database.

[0815] Input: Keywords for filtering (e.g., "cashier" or "data entry").

[0816] What it does: Retrieves relevant job listings from the database using an SQL query.

[0817] Output: Filtered job listings.

[0818] Specific operation: The server queries job information from the database based on keywords such as "cashier operation" and "data entry" and identifies "Company B."

[0819] Step 5:

[0820] The server performs company identification.

[0821] Input: Job listings filtered in step 4.

[0822] How it works: It uses machine learning algorithms to identify companies with jobs that can be automated from job postings.

[0823] Output: A list of identified companies.

[0824] Specific operation: The server identifies "Company B" based on keywords such as "cashier operation" and "data entry."

[0825] Step 6:

[0826] The server performs screening for the identified companies.

[0827] Input: List of identified companies.

[0828] How it works: Evaluates companies by retrieving financial data and technology adoption intentions from external databases, using Google Finance APIs and other similar tools.

[0829] Output: Ranking of assessed companies.

[0830] Specific operation: The server retrieves the financial data of "Company B" from the Google Finance API, evaluates its intention to adopt technology, and assigns it a high score.

[0831] Step 7:

[0832] The server generates a mechanized plan.

[0833] Enter: a list of highly rated companies.

[0834] How it works: Generates an optimal mechanization plan including the required technology, costs, and post-implementation effects, and summarizes it in a report format.

[0835] Output: Mechanization plan report.

[0836] Specific operation: The server generates an implementation plan for an automated cash register system for Company B and compiles it into a PDF report.

[0837] Step 8:

[0838] The server notifies the generated mechanization plan.

[0839] Input: Mechanization plan report.

[0840] How it works: Sent via email or in-platform notification. Use an email service like SendGrid.

[0841] Output: Notification to company personnel.

[0842] Specific operation: The server sends the generated implementation plan for the automated cash register system to the person in charge at Company B via email.

[0843] Step 9:

[0844] Users provide feedback on the plan.

[0845] Input: Notified mechanization plan.

[0846] How it works: Enter your thoughts and opinions through a feedback form and capture your facial expressions with a webcam.

[0847] Output: Feedback information and emotion data.

[0848] Specific operation: The user enters "The implementation cost is high" in the feedback form and captures their facial expression with a webcam.

[0849] Step 10:

[0850] The emotion engine analyzes the feedback.

[0851] Input: User feedback and emotional data.

[0852] How it works: Analyzes user emotions and opinions using natural language processing and facial expression analysis technology. Uses IBM Watson and Google Cloud Natural Language APIs.

[0853] Output: Parsed emotion data and feedback information.

[0854] Specific operation: The emotion engine analyzes the text "The implementation cost is high" and the anxious facial expression, and provides this information to the server.

[0855] Step 11:

[0856] The server modifies the plan based on the emotional data.

[0857] Input: Parsed emotion data and feedback information.

[0858] Action: Identify corrections and regenerate revised mechanization plans.

[0859] Output: Revised mechanization plan.

[0860] What it does: The server takes the user's concerns and generates a remediation plan with a detailed breakdown of implementation costs and cost-saving options.

[0861] Step 12:

[0862] The server notifies the modified plan.

[0863] Input: Revised mechanization plan.

[0864] Action: Re-inform the user about the remediation plan.

[0865] Output: Re-notification to company representative.

[0866] Specific operation: The server sends the revised automated cash register system implementation plan again to the person in charge at "Company B" by email.

[0867] This allows the system to manage a series of processes, from collecting job information and analyzing it, to notifying companies and analyzing user feedback, effectively supporting companies in promoting digital transformation (DX).

[0868] (Application example 2)

[0869] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0870] When mechanizing factory operations, it is difficult to allocate personnel efficiently and optimally allocate machines. There is also the problem of not being able to properly reflect the feelings and feedback of factory managers regarding mechanization plans. This can lead to delays in implementing mechanization plans and the failure to create an optimized working environment.

[0871] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting job information and in-factory personnel allocation data, means for analyzing the collected data to identify tasks that can be mechanized, means for screening identified companies, means for generating a mechanization plan for each screened company, means for notifying company and factory managers of the generated mechanization plan, means for collecting feedback and emotion data from company personnel, and means for analyzing the collected feedback and emotion data to revise the mechanization plan. This enables efficient mechanization of tasks within a factory and the provision of an optimal plan that reflects managerial feedback.

[0872] "Job information" refers to detailed information such as job type, required skills, salary, and work location that is published by a company when recruiting personnel.

[0873] "Feedback" is information provided by company representatives and factory managers that indicates responses such as areas for improvement, opinions, and satisfaction.

[0874] "Emotion data" is data that indicates the emotional state of a user extracted from facial expressions, voice, input text, etc.

[0875] A "mechanization plan" is a plan that includes specific procedures, implementation costs, and effects for automating specific tasks using machines or robots.

[0876] "Screening" is the process of evaluating and selecting the suitability of companies and businesses based on collected data.

[0877] "Analysis" is the process of processing collected data to extract and understand information suitable for a specific purpose.

[0878] "Revise" means adjusting and improving the initially generated plan or initiative based on feedback and sentiment data.

[0879] "Notification" is the process of communicating plans and information to relevant personnel and users.

[0880] This invention is a system that mechanizes factory operations and realizes optimal robot placement. This system is composed of a server, terminals, users, and an emotion engine.

[0881] server

[0882] The server operates this system using the following methods:

[0883] 1. Data collection methods:

[0884] The server collects job information and factory staffing data via websites and APIs and stores it in a database using scraping technology and APIs, specifically Python, BeautifulSoup, and an SQL database.

[0885] 2. Analysis method:

[0886] Machine learning algorithms (such as scikit-learn) are used to analyze collected data and identify tasks that can be automated. For example, collected data such as "machine operation" and "logistics management" can be classified and tasks that can be automated can be extracted.

[0887] 3. Screening measures:

[0888] The screening method evaluates companies' financial data and intentions to adopt technology based on the analyzed data, and identifies companies with high scores. In this process, APIs are used to obtain information from external databases.

[0889] 4. Mechanized plan generation means:

[0890] A mechanization plan is generated for each high-scoring company. This plan includes implementation costs, benefits, and implementation procedures. The plan is compiled into a report using Python and saved on the server.

[0891] 5. Means of notification:

[0892] The mechanization plan generated using the notification function is sent to the factory manager via email or push notification. Notifications are sent using email service APIs (e.g., SendGrid) or push notification mechanisms (e.g., Firebase).

[0893] 6. Emotional data collection methods:

[0894] To collect feedback and emotional data from factory managers, cameras and microphones for emotion analysis are used. The emotion engine (Emotion API) analyzes facial expressions and voice data to obtain the content of the feedback.

[0895] 7. Sentiment data analysis methods:

[0896] The collected emotional data is analyzed to help refine the mechanized plan, using an emotional analysis engine to optimize the plan according to the emotions expressed by the user.

[0897] 8. Plan Modification Methods:

[0898] The plan is revised based on the sentiment data and notified to the user again. The revised plan includes new cost-saving ideas and implementation steps, and is sent via email and push notifications.

[0899] Terminal

[0900] The factory manager's device (smartphone or tablet) is used to input feedback and collect sentiment data, allowing the manager to review the proposed mechanization plan and provide feedback.

[0901] User

[0902] The user, the factory manager, can review the notified plan and provide feedback and emotions, which will be used to optimize the plan.

[0903] Specific examples

[0904] For example, the server may identify from collected data that mechanization of "logistics management" tasks is possible and generate a plan proposing the introduction of automated transport robots. This plan is then notified to the factory manager, and if the manager mentions "the introduction cost is high" as emotional feedback, the server will regenerate a revised plan including cost reduction proposals and notify the manager again.

[0905] Example prompt sentence:

[0906] This email is to inform you about your factory's mechanization plan. Please review the plan below and let us know your opinions and feedback.

[0907] Plan details:

[0908] Operations to be mechanized: Logistics management

[0909] Proposed technology: Automatic transport robot deployment

[0910] Estimated cost: 5 million yen

[0911] Introduction effect: Reduction of work time, improvement of labor efficiency

[0912] Please leave your comments and feedback here: [Link]

[0913] Thank you for your cooperation.

[0914] This invention allows for efficient mechanization and optimal allocation of work within a factory, and makes it possible to provide optimal plans that take into account the opinions and feelings of managers.

[0915] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0916] Step 1: Data collection

[0917] The server collects job information and factory staffing data from websites and APIs. Specifically, it uses scraping technology (e.g., Python's BeautifulSoup) and APIs (e.g., the API of a job information service) to collect data such as "machine operation" and "logistics management." The collected data is then stored in a database (e.g., an SQL database).

[0918] Input: Job postings and staffing data.

[0919] Data processing: Convert data into structured data using scraping technology or APIs.

[0920] Output: Information stored in a database.

[0921] Step 2: Data analysis

[0922] The server analyzes the collected data and identifies tasks that can be automated. It uses machine learning algorithms (e.g., scikit-learn) to classify the data based on specific keywords. For example, based on data on "logistics management," it identifies tasks for which automated transport robots can be introduced.

[0923] Input: Job postings and placement data from the database.

[0924] Data computation: analysis using machine learning algorithms.

[0925] Output: A list of tasks that can be automated.

[0926] Step 3: Screening

[0927] The server screens companies for the identified business, scores them by referencing external databases and survey results (e.g., company financial data and technology adoption intentions), and ranks and prioritizes companies with high scores.

[0928] Input: Parsed business data and information from external databases.

[0929] Data calculations: scoring algorithms.

[0930] Output: A ranked list of the highest scoring companies.

[0931] Step 4: Generate a mechanization plan

[0932] The server generates a mechanization plan for each top-ranked company, including implementation costs, benefits, and implementation procedures, and compiles the plan into a report using Python.

[0933] Input: Ranking list and information on mechanizable tasks.

[0934] Data Processing: Generating plans and converting them into report formats.

[0935] Output: Mechanized plan in report format.

[0936] Step 5: Notification

[0937] The server sends the generated mechanization plan to the factory manager via email or push notification, using an email service API (e.g., SendGrid) or a push notification function (e.g., Firebase).

[0938] Input: Mechanized plan in report format.

[0939] Data processing: Convert into email or push notification.

[0940] Output: Notification to factory manager.

[0941] Step 6: Collect feedback and sentiment data

[0942] Through the terminal, the factory manager provides feedback on the received plan and emotional data (e.g., facial expressions, voice). The data is analyzed by an emotion engine (e.g., Emotion API) using an emotion analysis camera and microphone.

[0943] Input: Feedback and sentiment data from factory managers.

[0944] Data Computing: Text and Sentiment Analysis.

[0945] Output: Parsed emotion data.

[0946] Step 7: Modify the plan

[0947] The server then uses the feedback and sentiment data to revise the original mechanisation plan, including new cost-saving ideas and detailed implementation steps, and compiles the results in a report.

[0948] Input: Emotion data and feedback.

[0949] Data processing: Modifying the plan and converting it back into a report format.

[0950] Output: Revised mechanization plan.

[0951] Step 8: Snooze

[0952] The server again notifies the factory manager of the revised mechanization plan.

[0953] Input: Revised mechanization plan.

[0954] Data processing: Reconvert to email or push notification.

[0955] Output: Re-notify factory manager.

[0956] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0957] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0958] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0959] [Third embodiment]

[0960] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0961] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0962] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0963] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0964] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0965] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0966] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0967] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0968] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0969] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0970] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0971] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0972] The present invention relates to a system for collecting, analyzing, screening, and generating and notifying job information automation plans. This system is composed of a server, a terminal, and a user, and each component functions as follows.

[0973] overview

[0974] The server periodically collects job information, analyzes the data, and identifies tasks that can be automated. It then screens the identified companies and generates an optimal automation plan for each company based on the results. Finally, the plan is notified to the company's representative.

[0975] Data collection

[0976] The server collects job information from websites that publish job postings using scraping technology or APIs. The collected data is analyzed by fields such as company name, job type, required skills, and salary information, and then stored in a database.

[0977] Examples:

[0978] Every day at 2 a.m., the server retrieves data from multiple websites that publish job listings. For example, if "Company X" is hiring a "cashier," the server stores that information in a database.

[0979] Company specific

[0980] The server analyzes the collected data and filters job listings that contain specific keywords (e.g., "cashier operator" or "data entry"), thereby identifying companies with jobs that can be automated.

[0981] Examples:

[0982] "Company Y" is identified based on keywords such as "cashier operation" and "data entry." The server retrieves and analyzes job information for "Company Y" from the database.

[0983] screening

[0984] The server evaluates the identified companies based on financial data, intentions to introduce technology, industry trends, etc., and screens them based on their future potential. The screening results are then ranked.

[0985] Examples:

[0986] The financial data and technology adoption intentions of "Company Y" are obtained from an external database, and the server uses that information to rank "Company Y." For example, "Company Y" can receive a relatively high score.

[0987] Mechanization plan generation

[0988] The server generates a mechanization plan for each selected company based on the screening results. The plan includes the technology to be introduced, the expected costs, and the effects after introduction. The plan is generated in report format and saved on the server.

[0989] Examples:

[0990] The server generates a plan proposing the introduction of an automated cash register system for Company Y's cash register operations. This plan details the introduction costs, predicted benefits, and specific implementation procedures.

[0991] notification

[0992] The server notifies the target company's personnel of the generated automation plan. This notification is done via email or the platform's notification function. The user (company personnel) receives the notification, checks the proposal, and sends feedback to the server if necessary.

[0993] Examples:

[0994] The server sends an email with the automated cash register system implementation plan to the person in charge at Company Y. The person in charge (user) receives the email and reviews the plan in detail.

[0995] This system will enable small and medium-sized enterprises to efficiently promote digital transformation by consistently analyzing job information and providing specific mechanization plans.

[0996] The processing flow will be explained below.

[0997] Step 1:

[0998] The server accesses websites and APIs where job information is published based on a regular schedule, and retrieves job information using scraping technology and APIs.

[0999] Step 2:

[1000] The server parses the job postings, which includes extracting the necessary data fields (company name, job title, required skills, salary information, etc.) from the JSON or HTML format.

[1001] Step 3:

[1002] The server stores the analyzed job information in a database, including company names, job titles, required skills, salary information, etc.

[1003] Step 4:

[1004] The server queries and retrieves job data from a database, filtering the data to see if it contains specific keywords (e.g., "cashier clerk" or "data entry").

[1005] Step 5:

[1006] The server lists companies that have mechanizable processes based on specific keywords, and these companies are then subject to screening.

[1007] Step 6:

[1008] The server refers to external databases and survey results to conduct financial data and technology adoption intention surveys for the listed companies, and evaluates each company based on this data.

[1009] Step 7:

[1010] The server scores each company based on the evaluation results and generates a ranking based on future potential. Companies with high scores are given priority in generating automation plans.

[1011] Step 8:

[1012] The server generates a mechanization plan for each high-scoring company, which includes the technology to be implemented, the expected costs, and the effects of implementation.

[1013] Step 9:

[1014] The server compiles the generated mechanization plan in a report format that is easy for company personnel to understand and is stored in a database.

[1015] Step 10:

[1016] The server generates an email or platform notification to notify the target company's personnel of the automation plan, which includes details of the plan.

[1017] Step 11:

[1018] The user (company representative) checks the notification and reviews the proposal. If necessary, the user can submit feedback or additional questions to the server through a dedicated web form.

[1019] Step 12:

[1020] The server analyzes the received feedback, modifies the mechanization plan as necessary, generates a final proposal after the modifications, and notifies the company representative again.

[1021] Step 13:

[1022] The user (company representative) receives the final proposal and initiates the internal approval process. The server tracks the company's progress in implementing DX and sends notifications if additional support is required.

[1023] Example 1

[1024] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1025] Currently, for small and medium-sized enterprises to efficiently promote digital transformation (DX), advanced technical knowledge and a great deal of effort are required. As a result, many small and medium-sized enterprises are unable to implement effective DX, making it difficult to improve operational efficiency and reduce costs. If we could identify mechanizable tasks from job information and provide companies with appropriate mechanization plans, we could support the promotion of DX in small and medium-sized enterprises. However, doing this manually is extremely labor-intensive and difficult to describe as efficient. To solve this issue, it is necessary to automate the system and perform all processes from collecting job information to generating and notifying mechanization plans.

[1026] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1027] In this invention, the server includes: means for collecting job information; means for analyzing the collected job information to identify mechanizable tasks; means for screening identified companies; means for generating a mechanization plan for each screened company; means for notifying the companies of the generated mechanization plan; means for using web scraping technology or a public API to collect job information; means for parsing the collected data into company names, job duties, required skills, and compensation information and storing them in a database; means for analyzing the job information using natural language processing and filtering the job information based on specific keywords to identify mechanizable tasks; means for evaluating and screening companies based on financial data, technology adoption intentions, and industry trends; means for generating a mechanization plan based on the evaluated screening results, including the technology to be introduced, expected costs, and post-implementation effects; means for notifying company representatives of the generated mechanization plan via email or platform notification function; and means for receiving user feedback. This automates the entire process from collecting job information to analyzing, filtering, screening, and generating and notifying mechanization plans, enabling small and medium-sized enterprises to efficiently promote digital transformation.

[1028] "Means of collecting job information" refers to the function of automatically obtaining data from websites where job information is published using web scraping technology or public APIs.

[1029] "Means of analyzing collected job information to identify tasks that can be automated" refers to the function of analyzing the text of collected job information using natural language processing (NLP) technology and filtering tasks that can be automated based on specific keywords.

[1030] "Means for screening identified companies" refers to the function of evaluating companies identified as having operations that can be mechanized based on information such as financial data, intentions to introduce technology, and industry trends, and then screening and ranking the companies.

[1031] "Means for generating mechanization plans for each screened company" refers to the function of generating mechanization plans for selected companies based on the screening results, including the technology to be introduced, expected costs, and post-implementation effects.

[1032] "Means for notifying the enterprise of the generated mechanization plan" refers to the function of sending the generated mechanization plan to the enterprise's personnel via email or platform notification.

[1033] "Methods of using web scraping technology or public APIs to collect job information" refers to the function of automatically collecting data from websites where job information is published using web scraping technology or public APIs.

[1034] "Means for analyzing collected data into company name, job position, required skills, and compensation information and storing it in a database" refers to the function of analyzing collected job information into fields such as company name, job position, required skills, and compensation information, and storing it appropriately in a database.

[1035] "Means of analyzing job postings using natural language processing, filtering job postings based on specific keywords, and identifying jobs that can be mechanized" refers to a function that uses natural language processing technology to analyze the text of job postings, filtering job postings based on specific keywords such as "cash register" or "data entry," and identifying job postings that have tasks that can be mechanized.

[1036] "Means of evaluating and screening companies based on financial data, intentions to introduce technology, and industry trends" refers to the function of collecting information such as financial data, intentions to introduce technology, and industry trends of identified companies, and evaluating and screening companies based on this data.

[1037] "Means for generating a mechanization plan including the technology to be introduced, the expected cost, and the effects after introduction based on the evaluated screening results" refers to the function of generating a mechanization plan that specifies the technology to be introduced, the expected cost of introduction, and the effects after introduction based on the company's screening results.

[1038] "Means for notifying company personnel of the generated automation plan by email or platform notification function" refers to the function of sending the generated automation plan to company personnel via email or platform notification, allowing the personnel to review the plan.

[1039] "Means for receiving feedback from users" refers to a function that allows a company representative to send feedback on a proposed mechanization plan to the server and receive that feedback.

[1040] The present invention relates to a system for collecting, analyzing, screening, and generating and notifying job information automation plans. This system is composed of a server, terminals, and users, and each component functions in cooperation with the others.

[1041] Data collection

[1042] The server periodically collects job information from websites that publish job postings. This collection process uses web scraping technology and public APIs. Specifically, data is extracted using Python libraries such as BeautifulSoup and Selenium. The collected data is analyzed into fields such as company name, job position, required skills, and compensation information, and then stored in a database such as MySQL or PostgreSQL.

[1043] As a concrete example, the server retrieves data from "job site A" and "job site B" every day at 2:00 a.m. For example, if "company A" is hiring a "cashier clerk," that information is stored in the database as the company name, job title, required skills, and compensation information.

[1044] Keyword Analysis

[1045] The server periodically analyzes the collected data and filters out job postings that contain specific keywords (e.g., "cashier operator" or "data entry"). This analysis is performed using natural language processing (NLP) technology. Specifically, NLP libraries such as NLTK and spaCy are used. Based on the results of this filtering, companies with tasks that can be automated are identified.

[1046] As a specific example, the server analyzes the text of the collected job postings and extracts job postings that contain keywords such as "cashier operator" and "data entry." For example, "Company B" is identified, and its job posting information is retrieved from the database and analyzed.

[1047] screening

[1048] The server evaluates and screens the identified companies based on financial data, technology adoption intentions, industry trends, etc. This evaluation process uses data obtained from external databases such as D&B Hoovers and Crunchbase. The server scores companies based on this data and stores the evaluation results in a new database table.

[1049] As a specific example, the server obtains financial data and technology adoption intentions of "Company B" from an external database and evaluates "Company B" based on that information. Company B can receive a relatively high score.

[1050] Mechanization plan generation

[1051] Based on the screening results, the server generates a mechanization plan for each selected company, which includes the technology to be introduced, the expected costs, and the effects after introduction. The generated plan is saved as a PDF report.

[1052] As a specific example, the server generates a mechanization plan proposing the introduction of an automated cash register system for the cash register operations of "Company B." This plan details the introduction costs, predicted benefits, and specific implementation procedures.

[1053] notification

[1054] The server notifies the company representative (user) of the generated mechanization plan via email or the platform notification function. The user receives the notification and checks the proposal. If necessary, the user can send feedback to the server.

[1055] As a concrete example, the server sends an automated cash register system implementation plan by email to the person in charge (user) of "Company B." The user receives the email and reviews the plan in detail.

[1056] Prompt Sentence Examples

[1057] Here are some example prompts for a generative AI model:

[1058] Analyze the job postings of the following companies, identify the tasks that can be automated, and then create a mechanization plan based on that. Company Name: Company C

[1059] This system will enable small and medium-sized enterprises to efficiently promote digital transformation by consistently analyzing job information and providing specific mechanization plans.

[1060] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1061] Step 1: Data collection

[1062] The device periodically sends a request to the server to collect job information. The server uses Python's BeautifulSoup and Selenium to scrape job information from websites. The job data is parsed into company names, job roles, required skills, and compensation information, and stored in a MySQL or PostgreSQL database.

[1063] Specific behavior:

[1064] The device sends a job information collection request to the server at 2:00 AM.

[1065] The server scrapes job information from "job site A" and "job site B" and obtains the HTML data.

[1066] The server uses BeautifulSoup to parse the HTML data and categorize it into company names, job roles, required skills, compensation information, etc.

[1067] The server stores the classified data in a database.

[1068] Input: Request from the device, HTML data of the job site

[1069] Output: A database containing company names, jobs, required skills, and compensation information

[1070] Step 2: Keyword analysis

[1071] The server periodically retrieves collected data from the database and filters job postings that contain specific keywords. It analyzes the text using natural language processing techniques such as NLTK and spaCy.

[1072] Specific behavior:

[1073] The server retrieves all jobs from the database.

[1074] The server uses NLTK to analyze the text of the job posting and detect keywords such as "cashier operator" and "data entry."

[1075] The server filters job listings based on keywords to identify job listings that include tasks that can be mechanized.

[1076] Store the filtered job listings in a new database table.

[1077] Input: Jobs in the database

[1078] Output: A new database table with filtered job listings

[1079] Step 3: Identify the company

[1080] The server identifies companies with work that can be automated based on the filtered job information. The information about the identified companies is recorded in a separate database table.

[1081] Specific behavior:

[1082] The server extracts company names from the filtered job listings.

[1083] The server stores the extracted company names in a new database table.

[1084] Input: Filtered Jobs

[1085] Output: A database table containing the identified company names

[1086] Step 4: Screening

[1087] The server evaluates companies based on their financial data, intentions to adopt technology, industry trends, etc. It obtains the necessary information from external databases such as D&B Hoovers and Crunchbase, scores companies, and stores the results in a new database table.

[1088] Specific behavior:

[1089] The server uses an external API to obtain financial data and technology adoption intentions of the identified companies.

[1090] Based on the data acquired by the server, companies are screened using a specified algorithm.

[1091] The screening results are stored in a new database table.

[1092] Input: Company information obtained from an external database

[1093] Output: Database table containing screening results (scores)

[1094] Step 5: Mechanization plan generation

[1095] Based on the screening results, the server generates a mechanization plan for each company. This plan includes the technology to be implemented, the expected costs, and the effects after implementation. The plan is compiled into a PDF report.

[1096] Specific behavior:

[1097] The server obtains the screening results and generates a mechanization plan suitable for each company.

[1098] The generated plan is saved as a PDF report.

[1099] Input: Screening results

[1100] Output: Mechanized plan in PDF format

[1101] Step 6: Notification

[1102] The server sends the generated mechanized plan to the company representative (user) via email or platform notification function.

[1103] Specific behavior:

[1104] The server obtains the email address of the company contact person.

[1105] The server sends the generated mechanized plan as an attachment to an email.

[1106] The user receives an email confirming the plan.

[1107] Input: Mechanization plan in PDF format, email address of company contact person

[1108] Output: Email sent to company contact

[1109] Prompt Sentence Examples

[1110] Here are some example prompts for a generative AI model:

[1111] Analyze the job postings of the following companies, identify the tasks that can be automated, and then create a mechanization plan based on that. Company Name: Company C

[1112] (Application example 1)

[1113] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1114] In modern factories, labor shortages and streamlining operations are major challenges. However, determining which operations are suitable for mechanization and creating specific plans for doing so requires a great deal of time and specialized knowledge. Furthermore, there is a lack of ways for company personnel to quickly understand and implement implementation plans. Given these circumstances, there is a need for a system that allows companies to mechanize operations quickly and efficiently.

[1115] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1116] In this invention, the server includes means for collecting job information, means for analyzing the collected job information to identify tasks that can be mechanized, means for screening the identified companies, means for generating a mechanization plan for each screened company, means for notifying the companies of the generated mechanization plan, means for generating a factory robot introduction plan based on the collected job information, and means for notifying the company's smartphone application of the generated introduction plan. This allows companies to quickly and efficiently obtain a mechanization plan and proceed with the introduction of appropriate factory robots.

[1117] "Job information" refers to information about the job duties, required skills, salary conditions, etc., of the personnel that companies are looking for.

[1118] The "means of collection" refers to the mechanism by which job information is obtained from websites via scraping or API.

[1119] "Means of analyzing and identifying tasks that can be mechanized" refers to a method of analyzing collected job information and finding tasks that can be replaced by machines.

[1120] "Means for screening identified companies" refers to a method of evaluating companies that are deemed capable of mechanizing their operations based on financial data, intentions to introduce technology, etc.

[1121] The "means of generating a mechanization plan" is a method of creating the optimal mechanization plan for each company and creating a report that includes implementation costs, effects, implementation procedures, etc.

[1122] The "means of notification" refers to a mechanism for communicating the generated mechanization plan to company personnel via email or on the platform.

[1123] A "factory robot" is a mechanical device introduced to automate manufacturing work.

[1124] A "smartphone application" is software installed on a smartphone and is a program with notification and data processing functions.

[1125] A "prompt" is a textual input given to a generative AI model to generate a specific output.

[1126] A "generative AI model" is an artificial intelligence system that uses machine learning and deep learning to generate specific outputs from input data.

[1127] The present invention relates to a system in which a server collects, analyzes, screens, generates and notifies job information. A specific embodiment of this system is described below.

[1128] Collecting job information

[1129] The server periodically collects job information from websites that publish job postings using scraping technology or APIs. This information is stored in a database and categorized by fields such as company name, job type, required skills, salary information, etc. For example, if a "company" is hiring an "assembly line worker," that information will be retrieved by the server.

[1130] Data analysis and company identification

[1131] Next, the server analyzes the collected job information and filters job postings containing specific keywords (e.g., "assembly," "inspection," etc.) to identify tasks that can be automated. This step extracts companies that are suitable for introducing factory robots. For example, if a "certain factory" is hiring someone for assembly work, that company will be identified.

[1132] screening

[1133] The server collects and evaluates external data on identified companies, such as financial data, technology adoption intentions, and industry trends. This allows the companies to be ranked based on their future prospects. For example, the server evaluates the financial data and technology adoption intentions of a "certain factory," and assigns a certain score based on the results.

[1134] Generating mechanization plans

[1135] Based on the screening results, the server generates a mechanization plan for each company. This plan includes the factory robots to be introduced, the estimated costs, and the introduction procedure. The generated plan is saved in the form of a report. For example, for the assembly line operations of a "certain factory," the server generates a plan proposing the introduction of XYZ robots, and the details are provided in a report.

[1136] notification

[1137] The generated mechanization plan is notified from the server to the company's employee's smartphone application. This notification is sent via email or push notification. The user (company employee) receives the notification, checks the proposal, and sends feedback to the server if necessary. For example, the server can send an automation plan to the employee of a "certain factory" via a smartphone application.

[1138] Hardware and software used

[1139] The system consists of a server, database, network infrastructure, and a user's smartphone application. Tools such as BeautifulSoup and Selenium are used for scraping, and the Requests library is used for API communication. Server-side processing is implemented using frameworks such as Flask and Django. Machine learning models and condition-based filtering are used for data analysis and company identification.

[1140] Examples of concrete examples and prompts

[1141] For example, if the server finds a job opening for an assembly line worker in a "certain factory" and determines that the job is suitable for mechanization, it will generate a plan to introduce XYZ robots. The plan is provided in the following format:

[1142] Example prompt sentence:

[1143] Company Name: A Factory

[1144] Position: Assembly Line Worker

[1145] Skills: Basic assembly work

[1146] Salary: 3 million yen / year

[1147] Please propose an appropriate automation plan for this company, particularly the type of robots to be implemented, the estimated costs, and the expected benefits after implementation.

[1148] In this way, companies can obtain an efficient and specific mechanization plan and proceed with the introduction of appropriate factory robots.

[1149] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1150] Step 1:

[1151] The server collects job information.

[1152] Input: URLs of multiple websites where job postings are published.

[1153] What it does: The server uses BeautifulSoup and Selenium to scrape job listings from the specified website, and if a specific API is provided, it uses the Requests library to collect data via the API.

[1154] Output: Collected job information (company name, job title, required skills, salary information, etc.).

[1155] Step 2:

[1156] The server analyzes the collected job information and identifies tasks that can be automated.

[1157] Input: The collected job posting dataset.

[1158] How it works: The server uses natural language processing (NLP) technology to analyze the text data of job postings, checking whether specific keywords (e.g., "assembly," "inspection," etc.) are included, and filtering out tasks that can be automated.

[1159] Output: Job postings and a list of companies with mechanizable tasks.

[1160] Step 3:

[1161] Screening companies whose servers have been identified.

[1162] Input: List of companies with mechanizable operations.

[1163] What it does: The server collects external data such as company financial data, technology adoption intentions, and industry trends. This includes API access to external databases (e.g., financial databases). Based on the collected data, it evaluates and scores each company.

[1164] Output: A ranked list of highly rated companies.

[1165] Step 4:

[1166] The server generates a mechanized plan for each company screened.

[1167] Input: A ranked list of highly rated companies.

[1168] How it works: The server uses a generative AI model to generate an optimal mechanization plan for each company. It prompts users to enter information about the company, the position being filled, the required skills, and salary information, and generates a report that includes the type of robot to be introduced, the estimated cost, and the effects after introduction.

[1169] Output: Mechanization plan report for each company.

[1170] Step 5:

[1171] The server notifies the generated mechanization plan to the company representative's smartphone application.

[1172] Input: Mechanization plan report and company contact information.

[1173] Specific operation: The server uses an SMTP server to generate a notification email and send it to the company's representative. It also uses a push notification service (e.g., Firebase Cloud Messaging) to send a push notification to a smartphone application.

[1174] Output: A notification message to the company contact who received the plan notification.

[1175] By performing the above steps, the server can consistently perform the process from collecting job information to generating and notifying a mechanized plan.

[1176] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1177] This invention combines an emotion engine with a system that collects, analyzes, screens, and generates and notifies job information mechanized plans. This system consists of a server, a terminal, a user, and an emotion engine, and each component functions as follows:

[1178] overview

[1179] The server periodically collects job information, analyzes the data, and identifies tasks that can be automated. It then screens the identified companies and generates an optimal automation plan for each company based on the results. The generated plan is notified to the company's representative, and an emotion engine analyzes user feedback and emotions to further optimize the plan.

[1180] Data collection

[1181] The server periodically retrieves data from websites and APIs where job information is published. Using scraping technology and APIs, the server collects job information, analyzes it into company names, job types, required skills, salary information, etc., and stores the information in a database.

[1182] Examples:

[1183] Every day at 2 a.m., the server retrieves data from multiple websites that publish job information. For example, if "Company A" is hiring a "cashier," the server stores that information in a database.

[1184] Company specific

[1185] The server queries and retrieves job data from a database, analyzes the data, and filters it based on specific keywords (e.g., "cashier operation" or "data entry") to identify companies with tasks that can be automated.

[1186] Examples:

[1187] "Company B" is identified based on keywords such as "cashier operation" and "data entry." The server retrieves and analyzes the job information for "Company B" from the database.

[1188] screening

[1189] The server then refers to external databases and survey results to obtain financial data and technology adoption intentions for the identified companies. The server then evaluates each company based on this data and ranks the companies with the highest scores.

[1190] Examples:

[1191] The financial data and technology adoption intentions of "Company B" are obtained from an external database, and the server uses that information to rank "Company B." For example, "Company B" can receive a relatively high score.

[1192] Mechanization plan generation

[1193] The server generates a mechanization plan for each high-ranking company, detailing the technology to be implemented, the expected costs, and the effects after implementation. The generated plan is compiled in a report format and saved on the server.

[1194] Examples:

[1195] The server generates a plan proposing the introduction of an automated cash register system for Company B's cash register operations. This plan details the introduction costs, predicted benefits, and specific implementation procedures.

[1196] notification

[1197] The server sends the generated mechanization plan to the person in charge of the target company via email or the platform's notification function. The user (company person in charge) receives the notification and confirms the proposal.

[1198] Examples:

[1199] The server sends an email with the automated cash register system implementation plan to the person in charge at Company B. The person in charge (user) receives the email and reviews the plan in detail.

[1200] Emotion engine integration

[1201] The emotion engine analyzes the user's feedback and reactions, analyzing the text entered by the user through the feedback form, as well as facial expressions and voice when confirming the plan, to obtain emotional data.

[1202] Examples:

[1203] When a company representative provides feedback while reviewing the plan, the emotion engine analyzes the user's input text, facial expressions, and voice. For example, if the user is worried about the implementation cost, the emotion engine analyzes that information and provides it to the server.

[1204] Modifying the plan

[1205] The server modifies the mechanized plan based on the emotion data obtained from the emotion engine, and the modified plan is notified to the user again.

[1206] Examples:

[1207] Based on the information obtained from the emotion engine, the server regenerates a correction plan that includes a detailed breakdown of implementation costs and options for cost reduction. The correction plan is then sent again to the company's representative via email.

[1208] This system not only provides mechanized plans, but also provides optimized plans that take into account user emotions and feedback, making it possible to effectively support companies in promoting digital transformation.

[1209] The processing flow will be explained below.

[1210] Step 1:

[1211] The server accesses websites and APIs where job information is published based on a regular schedule, and retrieves job information using scraping technology and APIs.

[1212] Step 2:

[1213] The server parses the job postings, which includes extracting the necessary data fields (company name, job title, required skills, salary information, etc.) from the JSON or HTML format.

[1214] Step 3:

[1215] The server stores the analyzed job information in a database, including company names, job titles, required skills, salary information, etc.

[1216] Step 4:

[1217] The server queries and retrieves job data from a database, filtering the data for specific keywords (e.g., "cashier clerk" or "data entry").

[1218] Step 5:

[1219] The server identifies companies with mechanizable tasks based on the filtered job listings, and adds the identified companies to a list.

[1220] Step 6:

[1221] Based on the list of identified companies, the server obtains external data for evaluation (e.g., financial data, intention to introduce technology, etc.) and uses this data to evaluate each company and assign a score.

[1222] Step 7:

[1223] The server ranks each company based on the evaluation results, and companies with higher scores are given priority when generating mechanization plans.

[1224] Step 8:

[1225] The server generates a mechanization plan for each high-scoring company, which includes the technology to be implemented, the expected costs, and the benefits of implementation.

[1226] Step 9:

[1227] The server compiles the generated mechanization plan in the form of a report and stores it in a database.

[1228] Step 10:

[1229] The server sends the generated mechanized plan to the person in charge of the target company via email or the notification function on the platform, which includes details of the plan.

[1230] Step 11:

[1231] The user (company representative) checks the notification and reviews the proposal, and then submits feedback or additional questions to the server via a dedicated web form.

[1232] Step 12:

[1233] The emotion engine analyzes the user's feedback and facial expressions and voice when confirming the plan, and the analysis results are provided to the server as emotion data.

[1234] Step 13:

[1235] The server modifies the mechanized plan based on the emotion data and regenerates an optimized plan, which is then stored in the database.

[1236] Step 14:

[1237] The server then notifies the user of the optimized plan, who then reviews the plan and provides final feedback and approval.

[1238] Step 15:

[1239] The user (company representative) initiates the internal approval process based on the final proposal. The server tracks the progress of the company's DX implementation and sends notifications if additional support is required.

[1240] Example 2

[1241] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1242] Conventional recruitment information collection systems are capable of collecting and analyzing recruitment information and generating automation plans, but they are not optimized to take into account the feelings and feedback of company representatives. As a result, it is difficult for the proposed automation plans to fully meet the needs of company representatives, and actual implementation may not progress.

[1243] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1244] In this invention, the server includes means for collecting job information, means for analyzing the collected job information to identify tasks that can be mechanized, means for screening the identified organizations, means for generating a mechanization plan for each screened organization, means for notifying the organizations of the generated mechanization plan, means including an emotion engine for collecting and analyzing feedback from organizational personnel, and means for modifying the mechanization plan based on the emotion engine. This makes it possible to provide more practical and easy-to-implement mechanization plans that reflect the emotions and feedback of company personnel.

[1245] "Methods of collecting job information" refers to technologies for obtaining job data from websites and APIs, including scraping technologies and API integration.

[1246] "Means for analyzing job information to identify tasks that can be automated" refers to technology that analyzes collected job data and identifies tasks that can be automated based on specific keywords or patterns.

[1247] The "means for screening the identified organizations" refers to techniques for investigating and evaluating the financial data and intentions to introduce technology of the identified organizations.

[1248] The "means for generating a mechanization plan" is a technique for designing an optimal mechanization plan for each evaluated organization, detailing the implementation technology, costs, effects, etc.

[1249] "Means for notifying the organization of the generated mechanization plan" refers to a technology for sending the generated mechanization plan to the person in charge at the target organization via email or a notification function on the platform.

[1250] The "means including an emotion engine for collecting and analyzing feedback from organizational personnel" is a technology for collecting feedback provided by personnel and analyzing text, facial expressions, and voice.

[1251] The "means for modifying a mechanization plan based on an emotion engine" is a technology that identifies areas for improvement in a mechanization plan based on emotion data obtained from an emotion engine and redesigns the plan.

[1252] This invention combines an emotion engine with a system that collects, analyzes, screens, and generates and notifies job information mechanization plans. This system consists of a server, terminals, users, and an emotion engine. The detailed configuration and operation are described below.

[1253] First, the server collects job information. To do this, it uses scraping technologies such as Python's Beautiful Soup and Scrapy, as well as RESTful APIs. Every day at 2:00 AM, the server retrieves data from websites and APIs that list multiple job listings, parses it into information such as company name, job type, required skills, and salary information, and then stores it in a database (such as MySQL or PostgreSQL).

[1254] For example, the server periodically retrieves job information for "cashier staff" from "XYZ job site" every day and stores it in a MySQL database. This collected data is used in subsequent processing.

[1255] Next, the server identifies companies. It uses specific keywords (e.g., "cashier operation" or "data entry") to filter out companies with tasks that can be automated for the job data retrieved from the database. For example, the server identifies a company based on the keywords "cashier operation" or "data entry."

[1256] The server then screens the identified companies. This involves using external databases such as the Google Finance API to obtain financial data and evaluating the companies' intentions to adopt technology. Companies with high scores are then ranked. For example, the server evaluates the financial data and intentions to adopt technology of "Company B" and gives it a high score.

[1257] Next, the server generates an automation plan for each highly rated company. It creates a plan in the form of a report that includes implementation costs, effects, and implementation procedures, such as an automated cash register system implementation plan. This generated plan is saved in a database. For example, it generates an automated cash register system implementation plan for Company B's cash register operations and compiles it into a PDF report.

[1258] The server notifies the person in charge (user) of the target company of the generated plan. The notification method is an email service such as SendGrid. For example, the server sends an email with the implementation plan for the automated cash register system to the person in charge at "Company B," who then receives the email and checks the contents.

[1259] Additionally, users can provide feedback on the plan. Emotional data is collected through the analysis of user-entered text, facial expressions, and voice using an emotion engine (powered by IBM Watson and Google Cloud Natural Language API). For example, users can enter their concerns about the implementation cost into a feedback form, while their facial expressions are captured with a webcam.

[1260] The server then modifies the automation plan based on the emotion data obtained from the emotion engine. Specifically, it regenerates the plan by adding cost-saving options and detailed breakdowns, and notifies the user again. For example, the server may send the modified automated cash register system implementation plan to the person in charge at "Company B" again by email.

[1261] By following these steps, the system can manage a series of processes, from collecting and analyzing job information, notifying companies, and analyzing user feedback, effectively supporting companies in promoting digital transformation (DX).

[1262] Specific examples of prompts include:

[1263] "Please review Company B's plan to implement an automated cash register system for cash register operations and provide your opinion on the implementation costs."

[1264] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1265] Step 1:

[1266] The server collects job information.

[1267] Input: URL of website or API.

[1268] How it works: It uses Python's Beautiful Soup and Scrapy to scrape job information, retrieves it using a RESTful API, and sets up a scheduler to run it periodically.

[1269] Output: Job listings in raw data format.

[1270] Specific operation: The server retrieves job information for "cashier staff" from "job site A" and saves it in raw data format.

[1271] Step 2:

[1272] The server analyzes the collected job information.

[1273] Input: Job information collected in step 1 (raw data format).

[1274] How it works: Uses regular expressions and natural language processing (NLP) to extract company names, job titles, required skills, salary information, and more.

[1275] Output: Parsed job listings.

[1276] Specific operation: The server analyzes the job information obtained from "job site A" and extracts information such as "Company B," "cashier staff," and "monthly salary of 200,000 yen."

[1277] Step 3:

[1278] The server stores the analysis results in a database.

[1279] Input: The job information parsed in step 2.

[1280] What it does: Generates and executes an insert statement to save to a database such as MySQL or PostgreSQL.

[1281] Output: Job information stored in a database.

[1282] Specific operation: The server creates the analysis results as an insert statement and stores information such as "Company B," "cashier staff," and "monthly salary of 200,000 yen" in the MySQL database.

[1283] Step 4:

[1284] The server queries the database.

[1285] Input: Keywords for filtering (e.g., "cashier" or "data entry").

[1286] What it does: Retrieves relevant job listings from the database using an SQL query.

[1287] Output: Filtered job listings.

[1288] Specific operation: The server queries job information from the database based on keywords such as "cashier operation" and "data entry" and identifies "Company B."

[1289] Step 5:

[1290] The server performs company identification.

[1291] Input: Job listings filtered in step 4.

[1292] How it works: It uses machine learning algorithms to identify companies with jobs that can be automated from job postings.

[1293] Output: A list of identified companies.

[1294] Specific operation: The server identifies "Company B" based on keywords such as "cashier operation" and "data entry."

[1295] Step 6:

[1296] The server performs screening for the identified companies.

[1297] Input: List of identified companies.

[1298] How it works: Evaluates companies by retrieving financial data and technology adoption intentions from external databases, using Google Finance APIs and other similar tools.

[1299] Output: Ranking of assessed companies.

[1300] Specific operation: The server retrieves the financial data of "Company B" from the Google Finance API, evaluates its intention to adopt technology, and assigns it a high score.

[1301] Step 7:

[1302] The server generates a mechanized plan.

[1303] Enter: a list of highly rated companies.

[1304] How it works: Generates an optimal mechanization plan including the required technology, costs, and post-implementation effects, and summarizes it in a report format.

[1305] Output: Mechanization plan report.

[1306] Specific operation: The server generates an implementation plan for an automated cash register system for Company B and compiles it into a PDF report.

[1307] Step 8:

[1308] The server notifies the generated mechanization plan.

[1309] Input: Mechanization plan report.

[1310] How it works: Sent via email or in-platform notification. Use an email service like SendGrid.

[1311] Output: Notification to company personnel.

[1312] Specific operation: The server sends the generated implementation plan for the automated cash register system to the person in charge at Company B via email.

[1313] Step 9:

[1314] Users provide feedback on the plan.

[1315] Input: Notified mechanization plan.

[1316] How it works: Enter your thoughts and opinions through a feedback form and capture your facial expressions with a webcam.

[1317] Output: Feedback information and emotion data.

[1318] Specific operation: The user enters "The implementation cost is high" in the feedback form and captures their facial expression with a webcam.

[1319] Step 10:

[1320] The emotion engine analyzes the feedback.

[1321] Input: User feedback and emotional data.

[1322] How it works: Analyzes user emotions and opinions using natural language processing and facial expression analysis technology. Uses IBM Watson and Google Cloud Natural Language APIs.

[1323] Output: Parsed emotion data and feedback information.

[1324] Specific operation: The emotion engine analyzes the text "The implementation cost is high" and the anxious facial expression, and provides this information to the server.

[1325] Step 11:

[1326] The server modifies the plan based on the emotional data.

[1327] Input: Parsed emotion data and feedback information.

[1328] Action: Identify corrections and regenerate revised mechanization plans.

[1329] Output: Revised mechanization plan.

[1330] What it does: The server takes the user's concerns and generates a remediation plan with a detailed breakdown of implementation costs and cost-saving options.

[1331] Step 12:

[1332] The server notifies the modified plan.

[1333] Input: Revised mechanization plan.

[1334] Action: Re-inform the user about the remediation plan.

[1335] Output: Re-notification to company representative.

[1336] Specific operation: The server sends the revised automated cash register system implementation plan again to the person in charge at "Company B" by email.

[1337] This allows the system to manage a series of processes, from collecting job information and analyzing it, to notifying companies and analyzing user feedback, effectively supporting companies in promoting digital transformation (DX).

[1338] (Application example 2)

[1339] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1340] When mechanizing factory operations, it is difficult to allocate personnel efficiently and optimally allocate machines. There is also the problem of not being able to properly reflect the feelings and feedback of factory managers regarding mechanization plans. This can lead to delays in implementing mechanization plans and the failure to create an optimized working environment.

[1341] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting job information and in-factory personnel allocation data, means for analyzing the collected data to identify tasks that can be mechanized, means for screening identified companies, means for generating a mechanization plan for each screened company, means for notifying company and factory managers of the generated mechanization plan, means for collecting feedback and emotion data from company personnel, and means for analyzing the collected feedback and emotion data to revise the mechanization plan. This enables efficient mechanization of tasks within a factory and the provision of an optimal plan that reflects managerial feedback.

[1342] "Job information" refers to detailed information such as job type, required skills, salary, and work location that is published by a company when recruiting personnel.

[1343] "Feedback" is information provided by company representatives and factory managers that indicates responses such as areas for improvement, opinions, and satisfaction.

[1344] "Emotion data" is data that indicates the emotional state of a user extracted from facial expressions, voice, input text, etc.

[1345] A "mechanization plan" is a plan that includes specific procedures, implementation costs, and effects for automating specific tasks using machines or robots.

[1346] "Screening" is the process of evaluating and selecting the suitability of companies and businesses based on collected data.

[1347] "Analysis" is the process of processing collected data to extract and understand information suitable for a specific purpose.

[1348] "Revise" means adjusting and improving the initially generated plan or initiative based on feedback and sentiment data.

[1349] "Notification" is the process of communicating plans and information to relevant personnel and users.

[1350] This invention is a system that mechanizes factory operations and realizes optimal robot placement. This system is composed of a server, terminals, users, and an emotion engine.

[1351] server

[1352] The server operates this system using the following methods:

[1353] 1. Data collection methods:

[1354] The server collects job information and factory staffing data via websites and APIs and stores it in a database using scraping technology and APIs, specifically Python, BeautifulSoup, and an SQL database.

[1355] 2. Analysis method:

[1356] Machine learning algorithms (such as scikit-learn) are used to analyze collected data and identify tasks that can be automated. For example, collected data such as "machine operation" and "logistics management" can be classified and tasks that can be automated can be extracted.

[1357] 3. Screening measures:

[1358] The screening method evaluates companies' financial data and intentions to adopt technology based on the analyzed data, and identifies companies with high scores. In this process, APIs are used to obtain information from external databases.

[1359] 4. Mechanized plan generation means:

[1360] A mechanization plan is generated for each high-scoring company. This plan includes implementation costs, benefits, and implementation procedures. The plan is compiled into a report using Python and saved on the server.

[1361] 5. Means of notification:

[1362] The mechanization plan generated using the notification function is sent to the factory manager via email or push notification. Notifications are sent using email service APIs (e.g., SendGrid) or push notification mechanisms (e.g., Firebase).

[1363] 6. Emotional data collection methods:

[1364] To collect feedback and emotional data from factory managers, cameras and microphones for emotion analysis are used. The emotion engine (Emotion API) analyzes facial expressions and voice data to obtain the content of the feedback.

[1365] 7. Sentiment data analysis methods:

[1366] The collected emotional data is analyzed to help refine the mechanized plan, using an emotional analysis engine to optimize the plan according to the emotions expressed by the user.

[1367] 8. Plan Modification Methods:

[1368] The plan is revised based on the sentiment data and notified to the user again. The revised plan includes new cost-saving ideas and implementation steps, and is sent via email and push notifications.

[1369] Terminal

[1370] The factory manager's device (smartphone or tablet) is used to input feedback and collect sentiment data, allowing the manager to review the proposed mechanization plan and provide feedback.

[1371] User

[1372] The user, the factory manager, can review the notified plan and provide feedback and emotions, which will be used to optimize the plan.

[1373] Specific examples

[1374] For example, the server may identify from collected data that mechanization of "logistics management" tasks is possible and generate a plan proposing the introduction of automated transport robots. This plan is then notified to the factory manager, and if the manager mentions "the introduction cost is high" as emotional feedback, the server will regenerate a revised plan including cost reduction proposals and notify the manager again.

[1375] Example prompt sentence:

[1376] This email is to inform you about your factory's mechanization plan. Please review the plan below and let us know your opinions and feedback.

[1377] Plan details:

[1378] Operations to be mechanized: Logistics management

[1379] Proposed technology: Automatic transport robot deployment

[1380] Estimated cost: 5 million yen

[1381] Introduction effect: Reduction of work time, improvement of labor efficiency

[1382] Please leave your comments and feedback here: [Link]

[1383] Thank you for your cooperation.

[1384] This invention allows for efficient mechanization and optimal allocation of work within a factory, and makes it possible to provide optimal plans that take into account the opinions and feelings of managers.

[1385] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1386] Step 1: Data collection

[1387] The server collects job information and factory staffing data from websites and APIs. Specifically, it uses scraping technology (e.g., Python's BeautifulSoup) and APIs (e.g., the API of a job information service) to collect data such as "machine operation" and "logistics management." The collected data is then stored in a database (e.g., an SQL database).

[1388] Input: Job postings and staffing data.

[1389] Data processing: Convert data into structured data using scraping technology or APIs.

[1390] Output: Information stored in a database.

[1391] Step 2: Data analysis

[1392] The server analyzes the collected data and identifies tasks that can be automated. It uses machine learning algorithms (e.g., scikit-learn) to classify the data based on specific keywords. For example, based on data on "logistics management," it identifies tasks for which automated transport robots can be introduced.

[1393] Input: Job postings and placement data from the database.

[1394] Data computation: analysis using machine learning algorithms.

[1395] Output: A list of tasks that can be automated.

[1396] Step 3: Screening

[1397] The server screens companies for the identified business, scores them by referencing external databases and survey results (e.g., company financial data and technology adoption intentions), and ranks and prioritizes companies with high scores.

[1398] Input: Parsed business data and information from external databases.

[1399] Data calculations: scoring algorithms.

[1400] Output: A ranked list of the highest scoring companies.

[1401] Step 4: Generate a mechanization plan

[1402] The server generates a mechanization plan for each top-ranked company, including implementation costs, benefits, and implementation procedures, and compiles the plan into a report using Python.

[1403] Input: Ranking list and information on mechanizable tasks.

[1404] Data Processing: Generating plans and converting them into report formats.

[1405] Output: Mechanized plan in report format.

[1406] Step 5: Notification

[1407] The server sends the generated mechanization plan to the factory manager via email or push notification, using an email service API (e.g., SendGrid) or a push notification function (e.g., Firebase).

[1408] Input: Mechanized plan in report format.

[1409] Data processing: Convert into email or push notification.

[1410] Output: Notification to factory manager.

[1411] Step 6: Collect feedback and sentiment data

[1412] Through the terminal, the factory manager provides feedback on the received plan and emotional data (e.g., facial expressions, voice). The data is analyzed by an emotion engine (e.g., Emotion API) using an emotion analysis camera and microphone.

[1413] Input: Feedback and sentiment data from factory managers.

[1414] Data Computing: Text and Sentiment Analysis.

[1415] Output: Parsed emotion data.

[1416] Step 7: Modify the plan

[1417] The server then uses the feedback and sentiment data to revise the original mechanisation plan, including new cost-saving ideas and detailed implementation steps, and compiles the results in a report.

[1418] Input: Emotion data and feedback.

[1419] Data processing: Modifying the plan and converting it back into a report format.

[1420] Output: Revised mechanization plan.

[1421] Step 8: Snooze

[1422] The server again notifies the factory manager of the revised mechanization plan.

[1423] Input: Revised mechanization plan.

[1424] Data processing: Reconvert to email or push notification.

[1425] Output: Re-notify factory manager.

[1426] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1427] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1428] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1429] [Fourth embodiment]

[1430] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1431] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1432] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1433] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1434] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1435] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1436] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1437] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1438] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1439] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1440] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1441] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1442] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1443] The present invention relates to a system for collecting, analyzing, screening, and generating and notifying job information automation plans. This system is composed of a server, a terminal, and a user, and each component functions as follows.

[1444] overview

[1445] The server periodically collects job information, analyzes the data, and identifies tasks that can be automated. It then screens the identified companies and generates an optimal automation plan for each company based on the results. Finally, the plan is notified to the company's representative.

[1446] Data collection

[1447] The server collects job information from websites that publish job postings using scraping technology or APIs. The collected data is analyzed by fields such as company name, job type, required skills, and salary information, and then stored in a database.

[1448] Examples:

[1449] Every day at 2 a.m., the server retrieves data from multiple websites that publish job listings. For example, if "Company X" is hiring a "cashier," the server stores that information in a database.

[1450] Company specific

[1451] The server analyzes the collected data and filters job listings that contain specific keywords (e.g., "cashier operator" or "data entry"), thereby identifying companies with jobs that can be automated.

[1452] Examples:

[1453] "Company Y" is identified based on keywords such as "cashier operation" and "data entry." The server retrieves and analyzes job information for "Company Y" from the database.

[1454] screening

[1455] The server evaluates the identified companies based on financial data, intentions to introduce technology, industry trends, etc., and screens them based on their future potential. The screening results are then ranked.

[1456] Examples:

[1457] The financial data and technology adoption intentions of "Company Y" are obtained from an external database, and the server uses that information to rank "Company Y." For example, "Company Y" can receive a relatively high score.

[1458] Mechanization plan generation

[1459] The server generates a mechanization plan for each selected company based on the screening results. The plan includes the technology to be introduced, the expected costs, and the effects after introduction. The plan is generated in report format and saved on the server.

[1460] Examples:

[1461] The server generates a plan proposing the introduction of an automated cash register system for Company Y's cash register operations. This plan details the introduction costs, predicted benefits, and specific implementation procedures.

[1462] notification

[1463] The server notifies the target company's personnel of the generated automation plan. This notification is done via email or the platform's notification function. The user (company personnel) receives the notification, checks the proposal, and sends feedback to the server if necessary.

[1464] Examples:

[1465] The server sends an email with the automated cash register system implementation plan to the person in charge at Company Y. The person in charge (user) receives the email and reviews the plan in detail.

[1466] This system will enable small and medium-sized enterprises to efficiently promote digital transformation by consistently analyzing job information and providing specific mechanization plans.

[1467] The processing flow will be explained below.

[1468] Step 1:

[1469] The server accesses websites and APIs where job information is published based on a regular schedule, and retrieves job information using scraping technology and APIs.

[1470] Step 2:

[1471] The server parses the job postings, which includes extracting the necessary data fields (company name, job title, required skills, salary information, etc.) from the JSON or HTML format.

[1472] Step 3:

[1473] The server stores the analyzed job information in a database, including company names, job titles, required skills, salary information, etc.

[1474] Step 4:

[1475] The server queries and retrieves job data from a database, filtering the data to see if it contains specific keywords (e.g., "cashier clerk" or "data entry").

[1476] Step 5:

[1477] The server lists companies that have mechanizable processes based on specific keywords, and these companies are then subject to screening.

[1478] Step 6:

[1479] The server refers to external databases and survey results to conduct financial data and technology adoption intention surveys for the listed companies, and evaluates each company based on this data.

[1480] Step 7:

[1481] The server scores each company based on the evaluation results and generates a ranking based on future potential. Companies with high scores are given priority in generating automation plans.

[1482] Step 8:

[1483] The server generates a mechanization plan for each high-scoring company, which includes the technology to be implemented, the expected costs, and the effects of implementation.

[1484] Step 9:

[1485] The server compiles the generated mechanization plan in a report format that is easy for company personnel to understand and is stored in a database.

[1486] Step 10:

[1487] The server generates an email or platform notification to notify the target company's personnel of the automation plan, which includes details of the plan.

[1488] Step 11:

[1489] The user (company representative) checks the notification and reviews the proposal. If necessary, the user can submit feedback or additional questions to the server through a dedicated web form.

[1490] Step 12:

[1491] The server analyzes the received feedback, modifies the mechanization plan as necessary, generates a final proposal after the modifications, and notifies the company representative again.

[1492] Step 13:

[1493] The user (company representative) receives the final proposal and initiates the internal approval process. The server tracks the company's progress in implementing DX and sends notifications if additional support is required.

[1494] Example 1

[1495] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1496] Currently, for small and medium-sized enterprises to efficiently promote digital transformation (DX), advanced technical knowledge and a great deal of effort are required. As a result, many small and medium-sized enterprises are unable to implement effective DX, making it difficult to improve operational efficiency and reduce costs. If we could identify mechanizable tasks from job information and provide companies with appropriate mechanization plans, we could support the promotion of DX in small and medium-sized enterprises. However, doing this manually is extremely labor-intensive and difficult to describe as efficient. To solve this issue, it is necessary to automate the system and perform all processes from collecting job information to generating and notifying mechanization plans.

[1497] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1498] In this invention, the server includes: means for collecting job information; means for analyzing the collected job information to identify mechanizable tasks; means for screening identified companies; means for generating a mechanization plan for each screened company; means for notifying the companies of the generated mechanization plan; means for using web scraping technology or a public API to collect job information; means for parsing the collected data into company names, job duties, required skills, and compensation information and storing them in a database; means for analyzing the job information using natural language processing and filtering the job information based on specific keywords to identify mechanizable tasks; means for evaluating and screening companies based on financial data, technology adoption intentions, and industry trends; means for generating a mechanization plan based on the evaluated screening results, including the technology to be introduced, expected costs, and post-implementation effects; means for notifying company representatives of the generated mechanization plan via email or platform notification function; and means for receiving user feedback. This automates the entire process from collecting job information to analyzing, filtering, screening, and generating and notifying mechanization plans, enabling small and medium-sized enterprises to efficiently promote digital transformation.

[1499] "Means of collecting job information" refers to the function of automatically obtaining data from websites where job information is published using web scraping technology or public APIs.

[1500] "Means of analyzing collected job information to identify tasks that can be automated" refers to the function of analyzing the text of collected job information using natural language processing (NLP) technology and filtering tasks that can be automated based on specific keywords.

[1501] "Means for screening identified companies" refers to the function of evaluating companies identified as having operations that can be mechanized based on information such as financial data, intentions to introduce technology, and industry trends, and then screening and ranking the companies.

[1502] "Means for generating mechanization plans for each screened company" refers to the function of generating mechanization plans for selected companies based on the screening results, including the technology to be introduced, expected costs, and post-implementation effects.

[1503] "Means for notifying the enterprise of the generated mechanization plan" refers to the function of sending the generated mechanization plan to the enterprise's personnel via email or platform notification.

[1504] "Methods of using web scraping technology or public APIs to collect job information" refers to the function of automatically collecting data from websites where job information is published using web scraping technology or public APIs.

[1505] "Means for analyzing collected data into company name, job position, required skills, and compensation information and storing it in a database" refers to the function of analyzing collected job information into fields such as company name, job position, required skills, and compensation information, and storing it appropriately in a database.

[1506] "Means of analyzing job postings using natural language processing, filtering job postings based on specific keywords, and identifying jobs that can be mechanized" refers to a function that uses natural language processing technology to analyze the text of job postings, filtering job postings based on specific keywords such as "cash register" or "data entry," and identifying job postings that have tasks that can be mechanized.

[1507] "Means of evaluating and screening companies based on financial data, intentions to introduce technology, and industry trends" refers to the function of collecting information such as financial data, intentions to introduce technology, and industry trends of identified companies, and evaluating and screening companies based on this data.

[1508] "Means for generating a mechanization plan including the technology to be introduced, the expected cost, and the effects after introduction based on the evaluated screening results" refers to the function of generating a mechanization plan that specifies the technology to be introduced, the expected cost of introduction, and the effects after introduction based on the company's screening results.

[1509] "Means for notifying company personnel of the generated automation plan by email or platform notification function" refers to the function of sending the generated automation plan to company personnel via email or platform notification, allowing the personnel to review the plan.

[1510] "Means for receiving feedback from users" refers to a function that allows a company representative to send feedback on a proposed mechanization plan to the server and receive that feedback.

[1511] The present invention relates to a system for collecting, analyzing, screening, and generating and notifying job information automation plans. This system is composed of a server, terminals, and users, and each component functions in cooperation with the others.

[1512] Data collection

[1513] The server periodically collects job information from websites that publish job postings. This collection process uses web scraping technology and public APIs. Specifically, data is extracted using Python libraries such as BeautifulSoup and Selenium. The collected data is analyzed into fields such as company name, job position, required skills, and compensation information, and then stored in a database such as MySQL or PostgreSQL.

[1514] As a concrete example, the server retrieves data from "job site A" and "job site B" every day at 2:00 a.m. For example, if "company A" is hiring a "cashier clerk," that information is stored in the database as the company name, job title, required skills, and compensation information.

[1515] Keyword Analysis

[1516] The server periodically analyzes the collected data and filters out job postings that contain specific keywords (e.g., "cashier operator" or "data entry"). This analysis is performed using natural language processing (NLP) technology. Specifically, NLP libraries such as NLTK and spaCy are used. Based on the results of this filtering, companies with tasks that can be automated are identified.

[1517] As a specific example, the server analyzes the text of the collected job postings and extracts job postings that contain keywords such as "cashier operator" and "data entry." For example, "Company B" is identified, and its job posting information is retrieved from the database and analyzed.

[1518] screening

[1519] The server evaluates and screens the identified companies based on financial data, technology adoption intentions, industry trends, etc. This evaluation process uses data obtained from external databases such as D&B Hoovers and Crunchbase. The server scores companies based on this data and stores the evaluation results in a new database table.

[1520] As a specific example, the server obtains financial data and technology adoption intentions of "Company B" from an external database and evaluates "Company B" based on that information. Company B can receive a relatively high score.

[1521] Mechanization plan generation

[1522] Based on the screening results, the server generates a mechanization plan for each selected company, which includes the technology to be introduced, the expected costs, and the effects after introduction. The generated plan is saved as a PDF report.

[1523] As a specific example, the server generates a mechanization plan proposing the introduction of an automated cash register system for the cash register operations of "Company B." This plan details the introduction costs, predicted benefits, and specific implementation procedures.

[1524] notification

[1525] The server notifies the company representative (user) of the generated mechanization plan via email or the platform notification function. The user receives the notification and checks the proposal. If necessary, the user can send feedback to the server.

[1526] As a concrete example, the server sends an automated cash register system implementation plan by email to the person in charge (user) of "Company B." The user receives the email and reviews the plan in detail.

[1527] Prompt Sentence Examples

[1528] Here are some example prompts for a generative AI model:

[1529] Analyze the job postings of the following companies, identify the tasks that can be automated, and then create a mechanization plan based on that. Company Name: Company C

[1530] This system will enable small and medium-sized enterprises to efficiently promote digital transformation by consistently analyzing job information and providing specific mechanization plans.

[1531] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1532] Step 1: Data collection

[1533] The device periodically sends a request to the server to collect job information. The server uses Python's BeautifulSoup and Selenium to scrape job information from websites. The job data is parsed into company names, job roles, required skills, and compensation information, and stored in a MySQL or PostgreSQL database.

[1534] Specific behavior:

[1535] The device sends a job information collection request to the server at 2:00 AM.

[1536] The server scrapes job information from "job site A" and "job site B" and obtains the HTML data.

[1537] The server uses BeautifulSoup to parse the HTML data and categorize it into company names, job roles, required skills, compensation information, etc.

[1538] The server stores the classified data in a database.

[1539] Input: Request from the device, HTML data of the job site

[1540] Output: A database containing company names, jobs, required skills, and compensation information

[1541] Step 2: Keyword analysis

[1542] The server periodically retrieves collected data from the database and filters job postings that contain specific keywords. It analyzes the text using natural language processing techniques such as NLTK and spaCy.

[1543] Specific behavior:

[1544] The server retrieves all jobs from the database.

[1545] The server uses NLTK to analyze the text of the job posting and detect keywords such as "cashier operator" and "data entry."

[1546] The server filters job listings based on keywords to identify job listings that include tasks that can be mechanized.

[1547] Store the filtered job listings in a new database table.

[1548] Input: Jobs in the database

[1549] Output: A new database table with filtered job listings

[1550] Step 3: Identify the company

[1551] The server identifies companies with work that can be automated based on the filtered job information. The information about the identified companies is recorded in a separate database table.

[1552] Specific behavior:

[1553] The server extracts company names from the filtered job listings.

[1554] The server stores the extracted company names in a new database table.

[1555] Input: Filtered Jobs

[1556] Output: A database table containing the identified company names

[1557] Step 4: Screening

[1558] The server evaluates companies based on their financial data, intentions to adopt technology, industry trends, etc. It obtains the necessary information from external databases such as D&B Hoovers and Crunchbase, scores companies, and stores the results in a new database table.

[1559] Specific behavior:

[1560] The server uses an external API to obtain financial data and technology adoption intentions of the identified companies.

[1561] Based on the data acquired by the server, companies are screened using a specified algorithm.

[1562] The screening results are stored in a new database table.

[1563] Input: Company information obtained from an external database

[1564] Output: Database table containing screening results (scores)

[1565] Step 5: Mechanization plan generation

[1566] Based on the screening results, the server generates a mechanization plan for each company. This plan includes the technology to be implemented, the expected costs, and the effects after implementation. The plan is compiled into a PDF report.

[1567] Specific behavior:

[1568] The server obtains the screening results and generates a mechanization plan suitable for each company.

[1569] The generated plan is saved as a PDF report.

[1570] Input: Screening results

[1571] Output: Mechanized plan in PDF format

[1572] Step 6: Notification

[1573] The server sends the generated mechanized plan to the company representative (user) via email or platform notification function.

[1574] Specific behavior:

[1575] The server obtains the email address of the company contact person.

[1576] The server sends the generated mechanized plan as an attachment to an email.

[1577] The user receives an email confirming the plan.

[1578] Input: Mechanization plan in PDF format, email address of company contact person

[1579] Output: Email sent to company contact

[1580] Prompt Sentence Examples

[1581] Here are some example prompts for a generative AI model:

[1582] Analyze the job postings of the following companies, identify the tasks that can be automated, and then create a mechanization plan based on that. Company Name: Company C

[1583] (Application example 1)

[1584] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1585] In modern factories, labor shortages and streamlining operations are major challenges. However, determining which operations are suitable for mechanization and creating specific plans for doing so requires a great deal of time and specialized knowledge. Furthermore, there is a lack of ways for company personnel to quickly understand and implement implementation plans. Given these circumstances, there is a need for a system that allows companies to mechanize operations quickly and efficiently.

[1586] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1587] In this invention, the server includes means for collecting job information, means for analyzing the collected job information to identify tasks that can be mechanized, means for screening the identified companies, means for generating a mechanization plan for each screened company, means for notifying the companies of the generated mechanization plan, means for generating a factory robot introduction plan based on the collected job information, and means for notifying the company's smartphone application of the generated introduction plan. This allows companies to quickly and efficiently obtain a mechanization plan and proceed with the introduction of appropriate factory robots.

[1588] "Job information" refers to information about the job duties, required skills, salary conditions, etc., of the personnel that companies are looking for.

[1589] The "means of collection" refers to the mechanism by which job information is obtained from websites via scraping or API.

[1590] "Means of analyzing and identifying tasks that can be mechanized" refers to a method of analyzing collected job information and finding tasks that can be replaced by machines.

[1591] "Means for screening identified companies" refers to a method of evaluating companies that are deemed capable of mechanizing their operations based on financial data, intentions to introduce technology, etc.

[1592] The "means of generating a mechanization plan" is a method of creating the optimal mechanization plan for each company and creating a report that includes implementation costs, effects, implementation procedures, etc.

[1593] The "means of notification" refers to a mechanism for communicating the generated mechanization plan to company personnel via email or on the platform.

[1594] A "factory robot" is a mechanical device introduced to automate manufacturing work.

[1595] A "smartphone application" is software installed on a smartphone and is a program with notification and data processing functions.

[1596] A "prompt" is a textual input given to a generative AI model to generate a specific output.

[1597] A "generative AI model" is an artificial intelligence system that uses machine learning and deep learning to generate specific outputs from input data.

[1598] The present invention relates to a system in which a server collects, analyzes, screens, generates and notifies job information. A specific embodiment of this system is described below.

[1599] Collecting job information

[1600] The server periodically collects job information from websites that publish job postings using scraping technology or APIs. This information is stored in a database and categorized by fields such as company name, job type, required skills, salary information, etc. For example, if a "company" is hiring an "assembly line worker," that information will be retrieved by the server.

[1601] Data analysis and company identification

[1602] Next, the server analyzes the collected job information and filters job postings containing specific keywords (e.g., "assembly," "inspection," etc.) to identify tasks that can be automated. This step extracts companies that are suitable for introducing factory robots. For example, if a "certain factory" is hiring someone for assembly work, that company will be identified.

[1603] screening

[1604] The server collects and evaluates external data on identified companies, such as financial data, technology adoption intentions, and industry trends. This allows the companies to be ranked based on their future prospects. For example, the server evaluates the financial data and technology adoption intentions of a "certain factory," and assigns a certain score based on the results.

[1605] Generating mechanization plans

[1606] Based on the screening results, the server generates a mechanization plan for each company. This plan includes the factory robots to be introduced, the estimated costs, and the introduction procedure. The generated plan is saved in the form of a report. For example, for the assembly line operations of a "certain factory," the server generates a plan proposing the introduction of XYZ robots, and the details are provided in a report.

[1607] notification

[1608] The generated mechanization plan is notified from the server to the company's employee's smartphone application. This notification is sent via email or push notification. The user (company employee) receives the notification, checks the proposal, and sends feedback to the server if necessary. For example, the server can send an automation plan to the employee of a "certain factory" via a smartphone application.

[1609] Hardware and software used

[1610] The system consists of a server, database, network infrastructure, and a user's smartphone application. Tools such as BeautifulSoup and Selenium are used for scraping, and the Requests library is used for API communication. Server-side processing is implemented using frameworks such as Flask and Django. Machine learning models and condition-based filtering are used for data analysis and company identification.

[1611] Examples of concrete examples and prompts

[1612] For example, if the server finds a job opening for an assembly line worker in a "certain factory" and determines that the job is suitable for mechanization, it will generate a plan to introduce XYZ robots. The plan is provided in the following format:

[1613] Example prompt sentence:

[1614] Company Name: A Factory

[1615] Position: Assembly Line Worker

[1616] Skills: Basic assembly work

[1617] Salary: 3 million yen / year

[1618] Please propose an appropriate automation plan for this company, particularly the type of robots to be implemented, the estimated costs, and the expected benefits after implementation.

[1619] In this way, companies can obtain an efficient and specific mechanization plan and proceed with the introduction of appropriate factory robots.

[1620] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1621] Step 1:

[1622] The server collects job information.

[1623] Input: URLs of multiple websites where job postings are published.

[1624] What it does: The server uses BeautifulSoup and Selenium to scrape job listings from the specified website, and if a specific API is provided, it uses the Requests library to collect data via the API.

[1625] Output: Collected job information (company name, job title, required skills, salary information, etc.).

[1626] Step 2:

[1627] The server analyzes the collected job information and identifies tasks that can be automated.

[1628] Input: The collected job posting dataset.

[1629] How it works: The server uses natural language processing (NLP) technology to analyze the text data of job postings, checking whether specific keywords (e.g., "assembly," "inspection," etc.) are included, and filtering out tasks that can be automated.

[1630] Output: Job postings and a list of companies with mechanizable tasks.

[1631] Step 3:

[1632] Screening companies whose servers have been identified.

[1633] Input: List of companies with mechanizable operations.

[1634] What it does: The server collects external data such as company financial data, technology adoption intentions, and industry trends. This includes API access to external databases (e.g., financial databases). Based on the collected data, it evaluates and scores each company.

[1635] Output: A ranked list of highly rated companies.

[1636] Step 4:

[1637] The server generates a mechanized plan for each company screened.

[1638] Input: A ranked list of highly rated companies.

[1639] How it works: The server uses a generative AI model to generate an optimal mechanization plan for each company. It prompts users to enter information about the company, the position being filled, the required skills, and salary information, and generates a report that includes the type of robot to be introduced, the estimated cost, and the effects after introduction.

[1640] Output: Mechanization plan report for each company.

[1641] Step 5:

[1642] The server notifies the generated mechanization plan to the company representative's smartphone application.

[1643] Input: Mechanization plan report and company contact information.

[1644] Specific operation: The server uses an SMTP server to generate a notification email and send it to the company's representative. It also uses a push notification service (e.g., Firebase Cloud Messaging) to send a push notification to a smartphone application.

[1645] Output: A notification message to the company contact who received the plan notification.

[1646] By performing the above steps, the server can consistently perform the process from collecting job information to generating and notifying a mechanized plan.

[1647] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1648] This invention combines an emotion engine with a system that collects, analyzes, screens, and generates and notifies job information mechanized plans. This system consists of a server, a terminal, a user, and an emotion engine, and each component functions as follows:

[1649] overview

[1650] The server periodically collects job information, analyzes the data, and identifies tasks that can be automated. It then screens the identified companies and generates an optimal automation plan for each company based on the results. The generated plan is notified to the company's representative, and an emotion engine analyzes user feedback and emotions to further optimize the plan.

[1651] Data collection

[1652] The server periodically retrieves data from websites and APIs where job information is published. Using scraping technology and APIs, the server collects job information, analyzes it into company names, job types, required skills, salary information, etc., and stores the information in a database.

[1653] Examples:

[1654] Every day at 2 a.m., the server retrieves data from multiple websites that publish job information. For example, if "Company A" is hiring a "cashier," the server stores that information in a database.

[1655] Company specific

[1656] The server queries and retrieves job data from a database, analyzes the data, and filters it based on specific keywords (e.g., "cashier operation" or "data entry") to identify companies with tasks that can be automated.

[1657] Examples:

[1658] "Company B" is identified based on keywords such as "cashier operation" and "data entry." The server retrieves and analyzes the job information for "Company B" from the database.

[1659] screening

[1660] The server then refers to external databases and survey results to obtain financial data and technology adoption intentions for the identified companies. The server then evaluates each company based on this data and ranks the companies with the highest scores.

[1661] Examples:

[1662] The financial data and technology adoption intentions of "Company B" are obtained from an external database, and the server uses that information to rank "Company B." For example, "Company B" can receive a relatively high score.

[1663] Mechanization plan generation

[1664] The server generates a mechanization plan for each high-ranking company, detailing the technology to be implemented, the expected costs, and the effects after implementation. The generated plan is compiled in a report format and saved on the server.

[1665] Examples:

[1666] The server generates a plan proposing the introduction of an automated cash register system for Company B's cash register operations. This plan details the introduction costs, predicted benefits, and specific implementation procedures.

[1667] notification

[1668] The server sends the generated mechanization plan to the person in charge of the target company via email or the platform's notification function. The user (company person in charge) receives the notification and confirms the proposal.

[1669] Examples:

[1670] The server sends an email with the automated cash register system implementation plan to the person in charge at Company B. The person in charge (user) receives the email and reviews the plan in detail.

[1671] Emotion engine integration

[1672] The emotion engine analyzes the user's feedback and reactions, analyzing the text entered by the user through the feedback form, as well as facial expressions and voice when confirming the plan, to obtain emotional data.

[1673] Examples:

[1674] When a company representative provides feedback while reviewing the plan, the emotion engine analyzes the user's input text, facial expressions, and voice. For example, if the user is worried about the implementation cost, the emotion engine analyzes that information and provides it to the server.

[1675] Modifying the plan

[1676] The server modifies the mechanized plan based on the emotion data obtained from the emotion engine, and the modified plan is notified to the user again.

[1677] Examples:

[1678] Based on the information obtained from the emotion engine, the server regenerates a correction plan that includes a detailed breakdown of implementation costs and options for cost reduction. The correction plan is then sent again to the company's representative via email.

[1679] This system not only provides mechanized plans, but also provides optimized plans that take into account user emotions and feedback, making it possible to effectively support companies in promoting digital transformation.

[1680] The processing flow will be explained below.

[1681] Step 1:

[1682] The server accesses websites and APIs where job information is published based on a regular schedule, and retrieves job information using scraping technology and APIs.

[1683] Step 2:

[1684] The server parses the job postings, which includes extracting the necessary data fields (company name, job title, required skills, salary information, etc.) from the JSON or HTML format.

[1685] Step 3:

[1686] The server stores the analyzed job information in a database, including company names, job titles, required skills, salary information, etc.

[1687] Step 4:

[1688] The server queries and retrieves job data from a database, filtering the data for specific keywords (e.g., "cashier clerk" or "data entry").

[1689] Step 5:

[1690] The server identifies companies with mechanizable tasks based on the filtered job listings, and adds the identified companies to a list.

[1691] Step 6:

[1692] Based on the list of identified companies, the server obtains external data for evaluation (e.g., financial data, intention to introduce technology, etc.) and uses this data to evaluate each company and assign a score.

[1693] Step 7:

[1694] The server ranks each company based on the evaluation results, and companies with higher scores are given priority when generating mechanization plans.

[1695] Step 8:

[1696] The server generates a mechanization plan for each high-scoring company, which includes the technology to be implemented, the expected costs, and the benefits of implementation.

[1697] Step 9:

[1698] The server compiles the generated mechanization plan in the form of a report and stores it in a database.

[1699] Step 10:

[1700] The server sends the generated mechanized plan to the person in charge of the target company via email or the notification function on the platform, which includes details of the plan.

[1701] Step 11:

[1702] The user (company representative) checks the notification and reviews the proposal, and then submits feedback or additional questions to the server via a dedicated web form.

[1703] Step 12:

[1704] The emotion engine analyzes the user's feedback and facial expressions and voice when confirming the plan, and the analysis results are provided to the server as emotion data.

[1705] Step 13:

[1706] The server modifies the mechanized plan based on the emotion data and regenerates an optimized plan, which is then stored in the database.

[1707] Step 14:

[1708] The server then notifies the user of the optimized plan, who then reviews the plan and provides final feedback and approval.

[1709] Step 15:

[1710] The user (company representative) initiates the internal approval process based on the final proposal. The server tracks the progress of the company's DX implementation and sends notifications if additional support is required.

[1711] Example 2

[1712] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1713] Conventional recruitment information collection systems are capable of collecting and analyzing recruitment information and generating automation plans, but they are not optimized to take into account the feelings and feedback of company representatives. As a result, it is difficult for the proposed automation plans to fully meet the needs of company representatives, and actual implementation may not progress.

[1714] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1715] In this invention, the server includes means for collecting job information, means for analyzing the collected job information to identify tasks that can be mechanized, means for screening the identified organizations, means for generating a mechanization plan for each screened organization, means for notifying the organizations of the generated mechanization plan, means including an emotion engine for collecting and analyzing feedback from organizational personnel, and means for modifying the mechanization plan based on the emotion engine. This makes it possible to provide more practical and easy-to-implement mechanization plans that reflect the emotions and feedback of company personnel.

[1716] "Methods of collecting job information" refers to technologies for obtaining job data from websites and APIs, including scraping technologies and API integration.

[1717] "Means for analyzing job information to identify tasks that can be automated" refers to technology that analyzes collected job data and identifies tasks that can be automated based on specific keywords or patterns.

[1718] The "means for screening the identified organizations" refers to techniques for investigating and evaluating the financial data and intentions to introduce technology of the identified organizations.

[1719] The "means for generating a mechanization plan" is a technique for designing an optimal mechanization plan for each evaluated organization, detailing the implementation technology, costs, effects, etc.

[1720] "Means for notifying the organization of the generated mechanization plan" refers to a technology for sending the generated mechanization plan to the person in charge at the target organization via email or a notification function on the platform.

[1721] The "means including an emotion engine for collecting and analyzing feedback from organizational personnel" is a technology for collecting feedback provided by personnel and analyzing text, facial expressions, and voice.

[1722] The "means for modifying a mechanization plan based on an emotion engine" is a technology that identifies areas for improvement in a mechanization plan based on emotion data obtained from an emotion engine and redesigns the plan.

[1723] This invention combines an emotion engine with a system that collects, analyzes, screens, and generates and notifies job information mechanization plans. This system consists of a server, terminals, users, and an emotion engine. The detailed configuration and operation are described below.

[1724] First, the server collects job information. To do this, it uses scraping technologies such as Python's Beautiful Soup and Scrapy, as well as RESTful APIs. Every day at 2:00 AM, the server retrieves data from websites and APIs that list multiple job listings, parses it into information such as company name, job type, required skills, and salary information, and then stores it in a database (such as MySQL or PostgreSQL).

[1725] For example, the server periodically retrieves job information for "cashier staff" from "XYZ job site" every day and stores it in a MySQL database. This collected data is used in subsequent processing.

[1726] Next, the server identifies companies. It uses specific keywords (e.g., "cashier operation" or "data entry") to filter out companies with tasks that can be automated for the job data retrieved from the database. For example, the server identifies a company based on the keywords "cashier operation" or "data entry."

[1727] The server then screens the identified companies. This involves using external databases such as the Google Finance API to obtain financial data and evaluating the companies' intentions to adopt technology. Companies with high scores are then ranked. For example, the server evaluates the financial data and intentions to adopt technology of "Company B" and gives it a high score.

[1728] Next, the server generates an automation plan for each highly rated company. It creates a plan in the form of a report that includes implementation costs, effects, and implementation procedures, such as an automated cash register system implementation plan. This generated plan is saved in a database. For example, it generates an automated cash register system implementation plan for Company B's cash register operations and compiles it into a PDF report.

[1729] The server notifies the person in charge (user) of the target company of the generated plan. The notification method is an email service such as SendGrid. For example, the server sends an email with the implementation plan for the automated cash register system to the person in charge at "Company B," who then receives the email and checks the contents.

[1730] Additionally, users can provide feedback on the plan. Emotional data is collected through the analysis of user-entered text, facial expressions, and voice using an emotion engine (powered by IBM Watson and Google Cloud Natural Language API). For example, users can enter their concerns about the implementation cost into a feedback form, while their facial expressions are captured with a webcam.

[1731] The server then modifies the automation plan based on the emotion data obtained from the emotion engine. Specifically, it regenerates the plan by adding cost-saving options and detailed breakdowns, and notifies the user again. For example, the server may send the modified automated cash register system implementation plan to the person in charge at "Company B" again by email.

[1732] By following these steps, the system can manage a series of processes, from collecting and analyzing job information, notifying companies, and analyzing user feedback, effectively supporting companies in promoting digital transformation (DX).

[1733] Specific examples of prompts include:

[1734] "Please review Company B's plan to implement an automated cash register system for cash register operations and provide your opinion on the implementation costs."

[1735] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1736] Step 1:

[1737] The server collects job information.

[1738] Input: URL of website or API.

[1739] How it works: It uses Python's Beautiful Soup and Scrapy to scrape job information, retrieves it using a RESTful API, and sets up a scheduler to run it periodically.

[1740] Output: Job listings in raw data format.

[1741] Specific operation: The server retrieves job information for "cashier staff" from "job site A" and saves it in raw data format.

[1742] Step 2:

[1743] The server analyzes the collected job information.

[1744] Input: Job information collected in step 1 (raw data format).

[1745] How it works: Uses regular expressions and natural language processing (NLP) to extract company names, job titles, required skills, salary information, and more.

[1746] Output: Parsed job listings.

[1747] Specific operation: The server analyzes the job information obtained from "job site A" and extracts information such as "Company B," "cashier staff," and "monthly salary of 200,000 yen."

[1748] Step 3:

[1749] The server stores the analysis results in a database.

[1750] Input: The job information parsed in step 2.

[1751] What it does: Generates and executes an insert statement to save to a database such as MySQL or PostgreSQL.

[1752] Output: Job information stored in a database.

[1753] Specific operation: The server creates the analysis results as an insert statement and stores information such as "Company B," "cashier staff," and "monthly salary of 200,000 yen" in the MySQL database.

[1754] Step 4:

[1755] The server queries the database.

[1756] Input: Keywords for filtering (e.g., "cashier" or "data entry").

[1757] What it does: Retrieves relevant job listings from the database using an SQL query.

[1758] Output: Filtered job listings.

[1759] Specific operation: The server queries job information from the database based on keywords such as "cashier operation" and "data entry" and identifies "Company B."

[1760] Step 5:

[1761] The server performs company identification.

[1762] Input: Job listings filtered in step 4.

[1763] How it works: It uses machine learning algorithms to identify companies with jobs that can be automated from job postings.

[1764] Output: A list of identified companies.

[1765] Specific operation: The server identifies "Company B" based on keywords such as "cashier operation" and "data entry."

[1766] Step 6:

[1767] The server performs screening for the identified companies.

[1768] Input: List of identified companies.

[1769] How it works: Evaluates companies by retrieving financial data and technology adoption intentions from external databases, using Google Finance APIs and other similar tools.

[1770] Output: Ranking of assessed companies.

[1771] Specific operation: The server retrieves the financial data of "Company B" from the Google Finance API, evaluates its intention to adopt technology, and assigns it a high score.

[1772] Step 7:

[1773] The server generates a mechanized plan.

[1774] Enter: a list of highly rated companies.

[1775] How it works: Generates an optimal mechanization plan including the required technology, costs, and post-implementation effects, and summarizes it in a report format.

[1776] Output: Mechanization plan report.

[1777] Specific operation: The server generates an implementation plan for an automated cash register system for Company B and compiles it into a PDF report.

[1778] Step 8:

[1779] The server notifies the generated mechanization plan.

[1780] Input: Mechanization plan report.

[1781] How it works: Sent via email or in-platform notification. Use an email service like SendGrid.

[1782] Output: Notification to company personnel.

[1783] Specific operation: The server sends the generated implementation plan for the automated cash register system to the person in charge at Company B via email.

[1784] Step 9:

[1785] Users provide feedback on the plan.

[1786] Input: Notified mechanization plan.

[1787] How it works: Enter your thoughts and opinions through a feedback form and capture your facial expressions with a webcam.

[1788] Output: Feedback information and emotion data.

[1789] Specific operation: The user enters "The implementation cost is high" in the feedback form and captures their facial expression with a webcam.

[1790] Step 10:

[1791] The emotion engine analyzes the feedback.

[1792] Input: User feedback and emotional data.

[1793] How it works: Analyzes user emotions and opinions using natural language processing and facial expression analysis technology. Uses IBM Watson and Google Cloud Natural Language APIs.

[1794] Output: Parsed emotion data and feedback information.

[1795] Specific operation: The emotion engine analyzes the text "The implementation cost is high" and the anxious facial expression, and provides this information to the server.

[1796] Step 11:

[1797] The server modifies the plan based on the emotional data.

[1798] Input: Parsed emotion data and feedback information.

[1799] Action: Identify corrections and regenerate revised mechanization plans.

[1800] Output: Revised mechanization plan.

[1801] What it does: The server takes the user's concerns and generates a remediation plan with a detailed breakdown of implementation costs and cost-saving options.

[1802] Step 12:

[1803] The server notifies the modified plan.

[1804] Input: Revised mechanization plan.

[1805] Action: Re-inform the user about the remediation plan.

[1806] Output: Re-notification to company representative.

[1807] Specific operation: The server sends the revised automated cash register system implementation plan again to the person in charge at "Company B" by email.

[1808] This allows the system to manage a series of processes, from collecting job information and analyzing it, to notifying companies and analyzing user feedback, effectively supporting companies in promoting digital transformation (DX).

[1809] (Application example 2)

[1810] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1811] When mechanizing factory operations, it is difficult to allocate personnel efficiently and optimally allocate machines. There is also the problem of not being able to properly reflect the feelings and feedback of factory managers regarding mechanization plans. This can lead to delays in implementing mechanization plans and the failure to create an optimized working environment.

[1812] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting job information and in-factory personnel allocation data, means for analyzing the collected data to identify tasks that can be mechanized, means for screening identified companies, means for generating a mechanization plan for each screened company, means for notifying company and factory managers of the generated mechanization plan, means for collecting feedback and emotion data from company personnel, and means for analyzing the collected feedback and emotion data to revise the mechanization plan. This enables efficient mechanization of tasks within a factory and the provision of an optimal plan that reflects managerial feedback.

[1813] "Job information" refers to detailed information such as job type, required skills, salary, and work location that is published by a company when recruiting personnel.

[1814] "Feedback" is information provided by company representatives and factory managers that indicates responses such as areas for improvement, opinions, and satisfaction.

[1815] "Emotion data" is data that indicates the emotional state of a user extracted from facial expressions, voice, input text, etc.

[1816] A "mechanization plan" is a plan that includes specific procedures, implementation costs, and effects for automating specific tasks using machines or robots.

[1817] "Screening" is the process of evaluating and selecting the suitability of companies and businesses based on collected data.

[1818] "Analysis" is the process of processing collected data to extract and understand information suitable for a specific purpose.

[1819] "Revise" means adjusting and improving the initially generated plan or initiative based on feedback and sentiment data.

[1820] "Notification" is the process of communicating plans and information to relevant personnel and users.

[1821] This invention is a system that mechanizes factory operations and realizes optimal robot placement. This system is composed of a server, terminals, users, and an emotion engine.

[1822] server

[1823] The server operates this system using the following methods:

[1824] 1. Data collection methods:

[1825] The server collects job information and factory staffing data via websites and APIs and stores it in a database using scraping technology and APIs, specifically Python, BeautifulSoup, and an SQL database.

[1826] 2. Analysis method:

[1827] Machine learning algorithms (such as scikit-learn) are used to analyze collected data and identify tasks that can be automated. For example, collected data such as "machine operation" and "logistics management" can be classified and tasks that can be automated can be extracted.

[1828] 3. Screening measures:

[1829] The screening method evaluates companies' financial data and intentions to adopt technology based on the analyzed data, and identifies companies with high scores. In this process, APIs are used to obtain information from external databases.

[1830] 4. Mechanized plan generation means:

[1831] A mechanization plan is generated for each high-scoring company. This plan includes implementation costs, benefits, and implementation procedures. The plan is compiled into a report using Python and saved on the server.

[1832] 5. Means of notification:

[1833] The mechanization plan generated using the notification function is sent to the factory manager via email or push notification. Notifications are sent using email service APIs (e.g., SendGrid) or push notification mechanisms (e.g., Firebase).

[1834] 6. Emotional data collection methods:

[1835] To collect feedback and emotional data from factory managers, cameras and microphones for emotion analysis are used. The emotion engine (Emotion API) analyzes facial expressions and voice data to obtain the content of the feedback.

[1836] 7. Sentiment data analysis methods:

[1837] The collected emotional data is analyzed to help refine the mechanized plan, using an emotional analysis engine to optimize the plan according to the emotions expressed by the user.

[1838] 8. Plan Modification Methods:

[1839] The plan is revised based on the sentiment data and notified to the user again. The revised plan includes new cost-saving ideas and implementation steps, and is sent via email and push notifications.

[1840] Terminal

[1841] The factory manager's device (smartphone or tablet) is used to input feedback and collect sentiment data, allowing the manager to review the proposed mechanization plan and provide feedback.

[1842] User

[1843] The user, the factory manager, can review the notified plan and provide feedback and emotions, which will be used to optimize the plan.

[1844] Specific examples

[1845] For example, the server may identify from collected data that mechanization of "logistics management" tasks is possible and generate a plan proposing the introduction of automated transport robots. This plan is then notified to the factory manager, and if the manager mentions "the introduction cost is high" as emotional feedback, the server will regenerate a revised plan including cost reduction proposals and notify the manager again.

[1846] Example prompt sentence:

[1847] This email is to inform you about your factory's mechanization plan. Please review the plan below and let us know your opinions and feedback.

[1848] Plan details:

[1849] Operations to be mechanized: Logistics management

[1850] Proposed technology: Automatic transport robot deployment

[1851] Estimated cost: 5 million yen

[1852] Introduction effect: Reduction of work time, improvement of labor efficiency

[1853] Please leave your comments and feedback here: [Link]

[1854] Thank you for your cooperation.

[1855] This invention allows for efficient mechanization and optimal allocation of work within a factory, and makes it possible to provide optimal plans that take into account the opinions and feelings of managers.

[1856] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1857] Step 1: Data collection

[1858] The server collects job information and factory staffing data from websites and APIs. Specifically, it uses scraping technology (e.g., Python's BeautifulSoup) and APIs (e.g., the API of a job information service) to collect data such as "machine operation" and "logistics management." The collected data is then stored in a database (e.g., an SQL database).

[1859] Input: Job postings and staffing data.

[1860] Data processing: Convert data into structured data using scraping technology or APIs.

[1861] Output: Information stored in a database.

[1862] Step 2: Data analysis

[1863] The server analyzes the collected data and identifies tasks that can be automated. It uses machine learning algorithms (e.g., scikit-learn) to classify the data based on specific keywords. For example, based on data on "logistics management," it identifies tasks for which automated transport robots can be introduced.

[1864] Input: Job postings and placement data from the database.

[1865] Data computation: analysis using machine learning algorithms.

[1866] Output: A list of tasks that can be automated.

[1867] Step 3: Screening

[1868] The server screens companies for the identified business, scores them by referencing external databases and survey results (e.g., company financial data and technology adoption intentions), and ranks and prioritizes companies with high scores.

[1869] Input: Parsed business data and information from external databases.

[1870] Data calculations: scoring algorithms.

[1871] Output: A ranked list of the highest scoring companies.

[1872] Step 4: Generate a mechanization plan

[1873] The server generates a mechanization plan for each top-ranked company, including implementation costs, benefits, and implementation procedures, and compiles the plan into a report using Python.

[1874] Input: Ranking list and information on mechanizable tasks.

[1875] Data Processing: Generating plans and converting them into report formats.

[1876] Output: Mechanized plan in report format.

[1877] Step 5: Notification

[1878] The server sends the generated mechanization plan to the factory manager via email or push notification, using an email service API (e.g., SendGrid) or a push notification function (e.g., Firebase).

[1879] Input: Mechanized plan in report format.

[1880] Data processing: Convert into email or push notification.

[1881] Output: Notification to factory manager.

[1882] Step 6: Collect feedback and sentiment data

[1883] Through the terminal, the factory manager provides feedback on the received plan and emotional data (e.g., facial expressions, voice). The data is analyzed by an emotion engine (e.g., Emotion API) using an emotion analysis camera and microphone.

[1884] Input: Feedback and sentiment data from factory managers.

[1885] Data Computing: Text and Sentiment Analysis.

[1886] Output: Parsed emotion data.

[1887] Step 7: Modify the plan

[1888] The server then uses the feedback and sentiment data to revise the original mechanisation plan, including new cost-saving ideas and detailed implementation steps, and compiles the results in a report.

[1889] Input: Emotion data and feedback.

[1890] Data processing: Modifying the plan and converting it back into a report format.

[1891] Output: Revised mechanization plan.

[1892] Step 8: Snooze

[1893] The server again notifies the factory manager of the revised mechanization plan.

[1894] Input: Revised mechanization plan.

[1895] Data processing: Reconvert to email or push notification.

[1896] Output: Re-notify factory manager.

[1897] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1898] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1899] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1900] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1901] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1902] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1903] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1904] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1905] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1906] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1907] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1908] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1909] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1910] 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.

[1911] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1912] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1913] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1914] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1915] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1916] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1917] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1918] The following is further disclosed regarding the above embodi...

Claims

1. A means of collecting job information; A means of analyzing collected job information to identify tasks that can be automated; a means of screening the identified companies; a means for generating a mechanization plan for each screened company; a means for notifying the enterprise of the generated mechanization plan; A system including:

2. The system of claim 1, wherein job information is collected from publicly available websites via scraping or API.

3. The system according to claim 1, wherein the mechanization plan is generated in the form of a report including implementation costs, effects, and implementation procedures.

Images