System

Abstract

A system is provided.SOLUTION: A system comprising: means for scraping business and culture information for each area from the Internet; means for collecting salesperson characteristics from a database; means for analyzing the collected business, culture, and salesperson characteristics and generating optimal mappings; means for notifying salespersons and administrators of the generated mappings; and means for receiving feedback and optimizing analysis algorithms.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] In today's business environment, deploying the right salespeople to the right locations is essential to business success. However, there are limitations to efficient, optimal person-to-location mapping performed manually. Furthermore, collecting and analyzing business and cultural information for each area and optimally deploying salespeople while taking into account the characteristics of each salesperson requires massive data processing, making traditional methods inefficient and inaccurate. Furthermore, it is difficult to continuously evaluate the effectiveness of deployment and incorporate feedback. The present invention aims to solve these issues and maximize sales efficiency. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes: means for scraping business and cultural information for each area from the Internet; means for collecting sales representative characteristics from a database; means for analyzing the collected business information, cultural information, and sales representative characteristics to generate an optimal mapping; means for notifying sales representatives and managers of the generated mapping; and means for receiving feedback and optimizing the analysis algorithm. The present invention enables automatic optimal sales representative allocation based on business needs and cultural information, and further enables dynamic optimization of the allocation based on feedback.

[0006] "Business information" refers to information about business realities and trends, such as the economic situation in each area, major industries, competitive information, and economic indexes.

[0007] "Cultural information" refers to information about the cultural background specific to each area, such as the local culture, lifestyle, language, events, and regional characteristics.

[0008] A "sales representative" is a company staff member whose role is to conduct business activities in a specific area and provide products and services to customers.

[0009] "Characteristics" refers to the specific qualities and skills that a salesperson possesses, such as their work experience, expertise, personality, and past performance.

[0010] A "database" is a data management system that can efficiently store, manage, search, and retrieve large amounts of data.

[0011] "Scraping" is a technique and process for automatically collecting data present on a website.

[0012] An "analysis algorithm" is a set of mathematical formulas or calculation procedures used to analyze collected data and extract meaningful information.

[0013] "Mapping" is the process of determining optimal sales representative placement based on business information, cultural information, and sales representative characteristics.

[0014] "Feedback" refers to the process and data by which sales representatives report the results of their field activities and their evaluations to the system.

[0015] "Notification" is a communication method for conveying the generated mapping results to sales representatives and managers.

[0016] "Optimization" is the process of continuously improving mapping algorithms and placement plans based on feedback data. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention provides a system for collecting business information and cultural information for each area and generating an optimal mapping based on the characteristics of sales representatives. Specific embodiments will be described below.

[0039] This system consists of a server, terminals, and users. The server plays a central role and is mainly responsible for data collection, analysis, mapping generation, notifications, and optimization. Terminals are devices mainly used by the HR system and sales representatives, and users are sales representatives or managers who use the system to carry out activities.

[0040] Data collection

[0041] The server scrapes business and cultural information for each area from the Internet. For example, the server periodically retrieves economic indexes and information on major industries from the official Tokyo Metropolitan Government website and local information sites, and stores this information in a database. It also collects text data from websites about local culture and lifestyles, and stores this data in a database for analysis.

[0042] The terminal collects characteristic data of sales representatives from the personnel system and sends it to the server. For example, the terminal extracts information such as the sales representative's work experience, expertise, personality, and past performance from the database and transfers it to the server via API.

[0043] Data analysis

[0044] The server applies advanced algorithms to analyze the collected business and cultural information, using statistical methods and natural language processing (NLP) techniques to identify economic indexes and key industry trends, assess the business needs of each area, and evaluate and score the unique characteristics of each region using cultural information.

[0045] The server then analyzes the characteristics of each salesperson and applies a rating model to assess their strengths and weaknesses. This rating model is built based on the salesperson's past performance data, expertise, work experience, etc.

[0046] Mapping Generation

[0047] Based on the analysis results, the server optimally maps the business needs and cultural information of each area, as well as the characteristics of sales representatives. For example, the server may determine that there is high demand for IT-related services in Tokyo, and generate a proposal to assign sales representatives with expertise in the IT field to Tokyo.

[0048] The server notifies salespeople and administrators of the generated mapping results via email and a dedicated dashboard, allowing salespeople to view their new deployment areas.

[0049] Feedback and Optimization

[0050] The user (sales representative) reports the results of their activities at the assigned location to the server as feedback. For example, they input data such as the number of new customers acquired, sales, and customer satisfaction through a dedicated application and send it to the server.

[0051] The server analyzes this feedback data and evaluates the effectiveness of each sales representative's placement. The analysis results are used to optimize the algorithm the next time mapping is generated. For example, if activities in Tokyo are highly successful, the algorithm is adjusted to apply the same sales strategy to other areas with similar characteristics.

[0052] Specific examples

[0053] As a specific example, consider the case where the IT industry in Tokyo is growing rapidly. The server scrapes this information and stores it in a database. Next, the information of salesperson A, who has extensive experience in the IT industry, is also stored in the database. The server's algorithm analyzes the business needs and cultural information of Tokyo, as well as the characteristics of salesperson A, and determines that it is optimal to assign him to Tokyo. The server notifies salesperson A of this mapping result, and he begins his sales activities in Tokyo. After that, the user (salesperson A) reports the results of his activities, and the server analyzes the data and optimizes the next mapping algorithm.

[0054] In this way, the present invention provides efficient and effective people and place mapping.

[0055] The processing flow will be explained below.

[0056] Step 1: Data collection

[0057] The server scrapes business information for each area (e.g., economic indexes, major industries, competitive information, etc.) from the Internet.

[0058] Specific operation: The server uses a crawler to obtain the latest data from official government websites and business-related news sites and stores it in a database.

[0059] The server also scrapes cultural information (e.g., local culture, lifestyle, language, events, etc.).

[0060] Specific operation: The server collects text data from local information sites and tourist association websites and stores it in an analysis database.

[0061] The terminal transmits the characteristics of the sales representative (e.g., work experience, expertise, personality, past performance, etc.) from the personnel system to the server.

[0062] Specific operation: The terminal extracts sales representative information from the personnel database and sends it to the server's API endpoint.

[0063] Step 2: Data analysis

[0064] The server runs algorithms to analyze the collected business information.

[0065] How it works: The server uses text analysis and statistical techniques to extract and index economic indices and trends in key industries.

[0066] The server analyzes the culture information and evaluates the characteristics of each region.

[0067] How it works: The server uses natural language processing (NLP) techniques to analyze text data and score cultural characteristics for each region.

[0068] The server analyzes the characteristic data of the sales representatives.

[0069] Specific operation: The server uses an evaluation model based on data on each sales representative's past performance, expertise, and work experience to score their strengths and weaknesses.

[0070] Step 3: Generate mappings

[0071] The server assesses the demand for each area based on business and cultural information.

[0072] What it does: The server combines business and cultural indexes to create a demand map for each area.

[0073] The server runs an algorithm that matches the characteristics of salespeople with area demand.

[0074] Specific operation: The server performs optimal matching based on the demand map and the sales representative's evaluation score, and generates a placement plan.

[0075] The server notifies the sales representative and the manager of the generated mapping results.

[0076] Specific operation: The server notifies each sales representative and manager of the mapping results via email or dashboard.

[0077] Step 4: Feedback and optimization

[0078] Users (salespeople) send field activity results and feedback to the server.

[0079] Specific operation: The user enters the activity results through a dedicated app or web form and sends them to the server.

[0080] The server analyzes the feedback sent and evaluates the effectiveness of the placement.

[0081] Specific operation: The server analyzes the feedback data, calculates performance indicators (e.g., sales, customer satisfaction, etc.), and evaluates the performance of the algorithm.

[0082] The server optimizes the analysis algorithm based on the feedback.

[0083] Specific operation: The server adjusts the algorithm parameters based on the insights gained from the feedback and reflects these in the next data analysis and mapping creation.

[0084] Example 1

[0085] 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."

[0086] Conventional sales support systems lacked the functionality to efficiently collect business and cultural information for each area and then optimally allocate sales representatives based on that information. As a result, optimal mapping based on the characteristics of sales representatives and area demand was not performed, resulting in a decline in sales efficiency. Furthermore, the functionality to dynamically adjust analysis algorithms based on feedback was insufficient, preventing sufficient optimization of allocation.

[0087] 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.

[0088] In this invention, the server includes: means for scraping business and cultural information for each area from the Internet; means for collecting salesperson characteristics from a database; means for analyzing the collected business information, cultural information, and salesperson characteristics and using statistical methods and natural language processing technology to generate an optimal mapping; means for notifying the salesperson and manager of the generated mapping; and means for receiving activity results as feedback and optimizing the analysis algorithm using regression analysis and Bayesian estimation. This makes it possible to achieve optimal allocation that takes into account the demand in each area and the characteristics of the salesperson, significantly improving sales efficiency.

[0089] "Scraping" is a technique for automatically extracting necessary data from a website's HTML source code.

[0090] "Business information" is information related to economic activity, such as economic indexes and data on major industries in a particular region.

[0091] "Cultural information" is information about the culture, lifestyles, and social characteristics of a particular region.

[0092] "Characteristics of a salesperson" refers to attributes related to sales activities, such as the salesperson's work experience, expertise, personality, and past performance.

[0093] A "database" is a system for efficiently storing and managing large amounts of data.

[0094] "Statistical methods" are mathematical methods for analyzing and evaluating data.

[0095] "Natural language processing technology (NLP)" is a technology that allows computers to analyze and understand human language.

[0096] "Mapping" is a deployment plan that optimally matches the business needs and cultural information of each area with the characteristics of sales representatives.

[0097] "Notification" is a means for informing interested parties of the generated mapping results.

[0098] "Feedback" is the process of inputting data on the results of sales representatives' activities into the system to help improve the analysis algorithm.

[0099] An "analysis algorithm" is a computational procedure for analyzing data and generating an optimal mapping.

[0100] "Regression analysis" is a statistical method for modeling relationships between data.

[0101] "Bayesian estimation" is a statistical method for calculating posterior probabilities based on observed data and estimating unknown parameters.

[0102] The present invention is a system that collects business information and cultural information for each area and generates an optimal mapping based on the characteristics of sales representatives. Specific embodiments will be described below.

[0103] This system consists of a server, terminals, and users. The server plays a central role and is mainly responsible for data collection, analysis, mapping generation, notifications, and optimization. Terminals are devices mainly used by the HR system and sales representatives, and users are sales representatives or managers who use the system to carry out activities.

[0104] Data collection

[0105] The server scrapes business and cultural information for each area from the Internet. For example, the server periodically retrieves economic indexes and information on major industries from official government and regional information sites, analyzes the HTML source code using the BeautifulSoup library, extracts the necessary data, and stores it in a database. It also collects text data from websites about regional culture and lifestyles and stores it in a database for analysis.

[0106] The device collects characteristic data about salespeople from the company's personnel system and sends it to the server. Specifically, it obtains information about the salespeople's work experience, expertise, personality, past performance, etc. via API and transfers it to the server.

[0107] Data analysis

[0108] The server applies advanced algorithms to analyze the collected business and cultural information. Specifically, it applies ARIMA models to identify economic indexes and key industry trends, and evaluates the business needs of each area. Similarly, it uses natural language processing (NLP) techniques to analyze cultural information, tokenize text data, perform TF-IDF vectorization, and score region-specific characteristics.

[0109] The server then inputs the sales representative's characteristic data into an evaluation model to analyze each sales representative's strengths and weaknesses. This evaluation model is built using machine learning algorithms such as random forests and support vector machines (SVMs) based on past performance data, expertise, and work experience.

[0110] Mapping Generation

[0111] Based on the analysis results, the server optimally maps the business needs and cultural information of each area, as well as the characteristics of sales representatives. Specifically, it matches the appropriate sales representative with the area using multidimensional scaling (MDS) and clustering techniques (e.g., k-means clustering). For example, it assesses that there is high demand for IT-related products in Tokyo and generates a proposal to assign sales representatives with the respective strengths to Tokyo.

[0112] The server notifies sales representatives and administrators of the generated mapping results by email using the SMTP protocol and provides an interface where they can check the results in real time on a dedicated dashboard.

[0113] Feedback and Optimization

[0114] Users (salespeople) report the results of their activities at their assigned locations to the server as feedback. Specific feedback data, such as the number of new customers acquired, sales, and customer satisfaction, is entered through a dedicated application and sent to the server via an API.

[0115] The server analyzes this feedback data and evaluates the effectiveness of each sales representative's placement. Statistical methods such as regression analysis and Bayesian estimation are used for the analysis, and the algorithm is optimized the next time a mapping is generated. Methods that produce high results under similar conditions are learned and reflected in the algorithm.

[0116] Specific examples

[0117] Consider the case of Tokyo, where the IT industry is growing rapidly. The server scrapes information from the official government website, analyzes the HTML code using BeautifulSoup, and saves the necessary information in a database. Next, it obtains information about Salesperson A, who has extensive experience in the IT industry, from the human resources system via an API and saves it in the database. The server's algorithm analyzes business needs and cultural information using the ARIMA model and TF-IDF vectorization, and matches this with Salesperson A's characteristics. It then determines that Tokyo is the best place for the assignment and notifies Salesperson A via email and a dashboard. After the assignment, the user (Salesperson A) reports activity results such as the number of new customers acquired and sales data to the server via a dedicated application. The server then analyzes this feedback data using regression analysis and optimizes the next mapping algorithm.

[0118] Prompt Sentence Examples

[0119] "Please assess the IT business needs in Tokyo and generate a mapping proposal for assigning the most suitable sales representatives."

[0120] In this way, the present invention provides efficient and effective people and place mapping.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Detailed explanation of the processing steps

[0123] Step 1: Data collection

[0124] The server scrapes business and cultural information for each area from the Internet. Specifically, the server uses the BeautifulSoup library to parse HTML source code from official government websites and local information sites, extracting information on economic indexes and major industries and storing it in a database. For example, information on Tokyo's economic index and major industries is obtained daily and updated regularly. The input is the website's HTML code, and the output is economic and cultural information formatted in JSON format.

[0125] Step 2: Collect data on salesperson characteristics

[0126] The terminal collects sales representative characteristic data from the company's internal human resources system and sends it to the server using an API. Specifically, it obtains sales representative work experience, expertise, personality, and past performance data from the human resources system, converts it into JSON format, and sends it to the server. The input is XML or CSV data from the human resources system, and the output is sales representative data in JSON format, which is sent to the server via the API.

[0127] Step 3: Parse business and cultural information

[0128] The server analyzes the collected business and cultural information. Specifically, it uses an ARIMA model to identify trends in economic indexes and scores the data. It also uses NLP technology to tokenize the cultural information and perform TF-IDF vectorization to evaluate region-specific characteristics. The input is business and cultural information in JSON format, and the output is the score for each area as an analysis result.

[0129] Step 4: Salesperson Profile Analysis

[0130] The server applies machine learning algorithms to analyze sales representative characteristic data. Specifically, it uses random forests and support vector machines (SVMs) to evaluate sales representatives' strengths and weaknesses. This evaluation model is built based on past performance data, specialized knowledge, and work experience. The input is sales representative data in JSON format, and the output is an evaluation score for each sales representative.

[0131] Step 5: Generate the optimal mapping

[0132] Based on the analysis results, the server optimally maps the business needs, cultural information, and characteristics of each salesperson for each area. For example, it uses multidimensional scaling (MDS) or k-means clustering to allocate salespeople to the most suitable areas. The inputs are scores for business and cultural information, and the evaluation scores of salespeople, and the output is an optimal allocation plan for each area.

[0133] Step 6: Notification of mapping results

[0134] The server notifies sales representatives and administrators of the generated mapping results. Notifications are sent by email using the SMTP protocol, and an interface is provided where results can be checked in real time on a dedicated dashboard. The input is the optimal placement plan, and the output is a notification email and updated information on the dashboard.

[0135] Step 7: Feedback and optimization of activity results

[0136] Users (salespeople) report the results of their activities to the server as feedback. They input the number of new customers acquired, sales, customer satisfaction, etc. through a dedicated application and send it to the server via API. The server receives this feedback data, analyzes it using regression analysis and Bayesian estimation, and optimizes the analysis algorithm. The input is the feedback data, and the output is the next optimized mapping algorithm.

[0137] (Application example 1)

[0138] 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."

[0139] Conventional business mapping and security patrol systems struggle to properly consider the specific business needs and crime data of each area and generate optimal personnel and patrol routes. This reduces the efficiency of sales and security activities, resulting in lower satisfaction for businesses and local communities. Furthermore, they lack the ability to dynamically adjust analysis algorithms based on feedback, making long-term optimization difficult.

[0140] 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.

[0141] In this invention, the server includes: means for scraping business and cultural information for each area from the Internet; means for collecting characteristics of sales representatives from a database; means for analyzing the collected business information, cultural information, and characteristics of sales representatives to generate an optimal mapping; means for notifying the sales representatives and managers of the generated mapping; means for receiving feedback and optimizing the analysis algorithm; means for scraping crime data and security-related information for the area from the Internet; means for collecting characteristics of security guards from a database; means for analyzing the collected crime data and security information to generate an optimal patrol route; and means for notifying the security guards and managers of the generated patrol route. This allows the specific needs of each area to be reflected, improving the efficiency of sales and security activities, and further achieving long-term results through dynamic optimization.

[0142] "Business information" refers to data on economic activity and industry in each area, as well as information including corporate trends and market trends.

[0143] "Cultural information" is data about the culture, customs, and lifestyle of a particular region or community.

[0144] "Scraping" is a technique for automatically collecting information that is publicly available on the Internet.

[0145] A "sales representative" is an employee whose role is to sell a company's products or services to customers.

[0146] "Characteristics" refers to data about the attributes and abilities of individual sales representatives and security guards, such as their work experience, expertise, personality, and past performance.

[0147] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[0148] "Analysis" is the process of analyzing collected data using statistical methods and algorithms to extract meaningful information.

[0149] "Mapping" refers to determining optimal placement and correspondence based on collected and analyzed data.

[0150] "Notification" is a means of informing the subject of the generated results.

[0151] "Feedback" is the process of collecting user evaluations and results and using them to help with future improvements.

[0152] An "algorithm" refers to a procedure or computational method for solving a specific problem.

[0153] "Crime data" refers to data that includes crime occurrences in a specific area and detailed information about those crimes.

[0154] "Security-related information" refers to data related to crime prevention measures and risk assessments.

[0155] A "patrol route" refers to the optimized route taken by security guards for patrol.

[0156] The system that realizes this application example consists of a server, terminals, and users. The server plays a central role in collecting data, analyzing it, generating mapping, notifying users, and optimizing it. Terminals are devices mainly used by personnel systems, sales representatives, and security guards, while users refer to the sales representatives or security guards who use the system to carry out their activities, as well as their managers.

[0157] Data collection

[0158] The server scrapes business, cultural, and crime data for each area from the internet. The software used for this is the Python requests library. For example, the required data is obtained from specific APIs (https: / / api.example.com / crime-data, https: / / api.example.com / guards) and stored in a database. Text data on regional culture and lifestyles is also collected from websites and stored in a database for analysis.

[0159] The terminal collects data on the characteristics of sales representatives and security guards from the personnel system and sends it to the server. For example, information such as the sales representative's work experience, expertise, personality, past performance, and the security guard's qualifications and experience is extracted from the database and transferred to the server via API.

[0160] Data analysis

[0161] The server applies advanced algorithms to analyze the collected business, cultural, and crime data. Specifically, it uses statistical methods and natural language processing (NLP) techniques to identify economic indexes and key industry trends, assess the business needs of each area, and evaluate and score the unique characteristics of each area using cultural and crime data.

[0162] The server also analyzes the characteristics of sales representatives and security guards and applies a rating model to assess their strengths and weaknesses. This rating model is generated by clustering based on crime rates and population density in a specific area, standardizing the data using Python's scikit-learn library, and clustering using KMeans.

[0163] Mapping Generation

[0164] Based on the analysis results, the server optimally maps each area's business needs, cultural information, crime data, and the characteristics of sales representatives and security guards. The generated mapping results are notified to sales representatives, security guards, and managers via email and a dedicated dashboard.

[0165] As a specific example, if information is collected that crime rates are rising in the Shinjuku area, the server analyzes that information, evaluates whether the characteristics of the security guards currently in charge of the Shinjuku area are suitable for this area, and assigns patrols to the most suitable security guards.

[0166] Feedback and Optimization

[0167] Users (sales representatives and security guards) report the results of their activities at their assigned locations to the server as feedback. Data such as the number of new customers acquired, sales, customer satisfaction, or reductions in crimes is entered through a dedicated application and sent to the server.

[0168] The server analyzes this feedback data and evaluates the effectiveness of each sales representative and security guard placement. The analysis results are used to optimize the algorithm the next time mapping is generated. For example, if activity in the Shinjuku area is highly successful, the algorithm adjusts to apply the same strategy to other areas with similar characteristics.

[0169] Prompt Sentence Examples

[0170] As a concrete example, the following prompt sentence can be input to a generative AI model:

[0171] Generate Python code for an application that generates optimal security patrol routes based on area crime data and population density. The URLs for the collected data are obtained from https: / / api.example.com / crime-data and https: / / api.example.com / guards. The area data includes crime rate (crime_rate) and population density (population_density).

[0172] In this way, the present invention can provide efficient and effective people and place mapping, greatly improving the efficiency of business and security operations.

[0173] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0174] Step 1:

[0175] Data collection:

[0176] The server scrapes business, cultural, and crime data for each area from the internet. Specifically, it uses the Python requests library to retrieve data from an API (e.g., https: / / api.example.com / crime-data or https: / / api.example.com / guards) and saves it in a database. The URL to be collected using the API is given as input, and the data is obtained in JSON format as output. This is then stored in the database.

[0177] Step 2:

[0178] Feature data collection:

[0179] The terminal collects characteristic data of sales representatives and security guards from the personnel system and sends it to the server. Specifically, it extracts information such as the sales representative's work experience and past performance, and the security guard's qualifications and experience from the database, and transfers it to the server via API. A database query is given as input, and the characteristic data of the sales representatives and security guards is obtained as output in JSON format. This is then transferred to the server.

[0180] Step 3:

[0181] Data Analysis:

[0182] The server analyzes the collected business, cultural, and crime data. It standardizes the data using Python's scikit-learn and performs clustering using KMeans. The standardized data is given as input, and the clustering results are obtained as output. Specifically, the business needs and crime levels of each region are scored and classified into each cluster.

[0183] Step 4:

[0184] Mapping Generation:

[0185] Based on the analysis results, the server optimally maps each area to the characteristics of sales representatives or security guards. The analyzed clustering data and characteristic data of sales representatives and security guards are given as input, and the mapping results are obtained as output. Specifically, it generates the optimal sales representative placement and patrol routes for a specific area.

[0186] Step 5:

[0187] notification:

[0188] The server notifies the generated mapping results to sales representatives, security guards, and managers in real time via email and a dedicated dashboard. The mapping result data is given as input, and a notification message is generated as output. Specifically, each person in charge can check the new deployment and route.

[0189] Step 6:

[0190] Feedback collection:

[0191] Users (sales representatives and security guards) report the results of their activities at their assigned locations to the server as feedback. They input data such as the number of new customers acquired, sales, customer satisfaction, and reductions in crimes through a dedicated application. Data manually entered by the user is given as input, and feedback data is obtained as output. This is then sent to the server.

[0192] Step 7:

[0193] Algorithm optimization:

[0194] The server analyzes the feedback data and optimizes the algorithm for the next mapping generation. The feedback data is given as input and an optimized algorithm is generated as output. Specifically, it adjusts activities in similar areas based on successful cases and derives effective placements and routes.

[0195] The above processing steps make it possible to reflect the specific needs of each area and significantly improve the efficiency of sales and security activities.

[0196] 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.

[0197] The present invention provides a system that collects business information and cultural information for each area and generates an optimal mapping by taking into account the emotional information of sales representatives and users. Specific embodiments will be described below.

[0198] This system consists of a server, terminals, users, and an emotion engine. The server plays a central role in collecting data, analyzing it, generating mappings, notifying users, and optimizing the system. Terminals are devices primarily used by the human resources system and sales representatives. Users are sales representatives or managers who use the system to carry out their activities, and the emotion engine recognizes and analyzes the user's emotions.

[0199] Data collection

[0200] The server periodically scrapes business information (e.g., economic indexes, major industries, competitive information, etc.) for each area from the Internet and stores it in a database. It also scrapes cultural information (e.g., local culture, lifestyles, language, events, etc.) and stores it in a database for analysis.

[0201] The terminal collects characteristic data of sales representatives (e.g., work experience, expertise, personality, past performance, etc.) from the personnel system and transmits it to the server.

[0202] Data analysis

[0203] The server applies data analysis algorithms to analyze the collected business and cultural information. Specifically, it analyzes economic indexes and trends in major industries to assess the business needs of each area. Similarly, it evaluates the characteristics of each region based on cultural information.

[0204] The server also applies an evaluation model to analyze the salesperson's characteristic data, which analyzes the salesperson's past performance, expertise, and work experience to evaluate their strengths and weaknesses.

[0205] The emotion engine recognizes and analyzes user emotions. For example, it analyzes the mood and motivation of salespeople using text and voice analysis to generate emotion data.

[0206] Mapping Generation

[0207] The server evaluates demand in each area based on business and cultural information, and generates optimal mapping based on the characteristics and emotional data of sales representatives. For example, the server determines that IT-related demand is high in Tokyo, and proposes the placement of sales representative A, who has strengths in the IT field, in Tokyo so that he can work most effectively.

[0208] The server then notifies sales representatives and managers of the generated mapping results via email and a dedicated dashboard.

[0209] Feedback and Optimization

[0210] Users (salespeople) report the results of their field activities and feedback to the server, including data such as sales performance and customer reactions.

[0211] The server analyzes the feedback data to evaluate the effectiveness of the placement. It also incorporates emotion data provided by the emotion engine. Based on this data, it optimizes the next mapping algorithm.

[0212] Specific examples

[0213] For example, if there is a surge in demand for the IT industry in Tokyo, the server scrapes that information and stores it in a database. Next, the information of salesperson A, who has extensive experience in the IT industry, is also registered in the database. The emotion engine also analyzes salesperson A's emotions and identifies that he is highly motivated.

[0214] The server's algorithm analyzes the business needs and cultural information of Tokyo, as well as the characteristics and emotional data of sales representative A, and determines that it is best to assign him to Tokyo. The server notifies sales representative A of the generated mapping results, and he begins his sales activities in Tokyo.

[0215] After that, the user (Salesperson A) reports the results of their activities and their emotional state as feedback. The server analyzes this data and reflects it in the next mapping, further improving the accuracy of the placement.

[0216] In this way, the present invention is a system that realizes more effective and personalized sales representative mapping by adding user emotional information.

[0217] The processing flow will be explained below.

[0218] Step 1: Data collection

[0219] The server scrapes business information for each area (e.g., economic indexes, major industries, competitive information, etc.) from the Internet.

[0220] Specific operation: The server uses a crawler to periodically collect the latest data from official government websites and business-related news sites and store it in a database.

[0221] The server also scrapes cultural information (e.g., local culture, lifestyle, language, events, etc.).

[0222] Specific operation: The server collects text data from local information sites and tourist association websites and stores it in an analysis database.

[0223] The terminal transmits characteristic data of the sales representative (e.g., work experience, expertise, personality, past performance, etc.) from the personnel system to the server.

[0224] Specific operation: The terminal extracts sales representative information from the personnel database via API and stores it in the server database.

[0225] Step 2: Collecting Emotional Data

[0226] The user (salesperson) inputs his / her own feelings in daily activities.

[0227] Specific operation: The user selects and enters their emotional state from a list using a dedicated app or a web form.

[0228] The emotion engine automatically analyzes emotions from the user's voice and text.

[0229] How it works: The emotion engine uses emotion analysis algorithms to analyze voice and text data in real time and generate an emotion score.

[0230] Step 3: Data analysis

[0231] The server runs algorithms to analyze the collected business information.

[0232] Specific operation: The server extracts business indexes and trends of major industries using statistical methods and text analysis, and evaluates the business needs of each area.

[0233] The server analyzes the culture information and evaluates the characteristics of each region.

[0234] Specific operation: The server uses natural language processing (NLP) technology to extract region-specific characteristics from text data and assigns an evaluation score.

[0235] The server analyzes the characteristic data of the sales representative based on the evaluation model.

[0236] Specific operation: The server applies a model to score past performance data, expertise, and work experience, and evaluates each employee.

[0237] The server analyzes the emotion data from the emotion engine and makes a comprehensive evaluation.

[0238] Specific operation: The emotion scores provided by the emotion engine are integrated and analyzed taking into account the salesperson's current psychological state.

[0239] Step 4: Mapping Generation

[0240] The server evaluates the demand in each area based on business information, cultural information, characteristics of sales representatives, and emotional data, and generates an optimal mapping.

[0241] Specific operation: The server runs a matching algorithm based on the evaluation scores to determine the optimal combination of sales representative and area.

[0242] The server notifies the sales representative and the manager of the generated mapping results.

[0243] Specific operation: The server sends the results to sales representatives and managers via email notifications or dedicated dashboards.

[0244] Step 5: Feedback and optimization

[0245] Users (salespeople) send field activity results and feedback to the server.

[0246] Specific operation: The user enters performance data (e.g., sales, customer satisfaction, etc.) and emotional feedback through a dedicated app or web form and sends them to the server.

[0247] The server analyzes the transmitted feedback data and evaluates the effectiveness of the deployment.

[0248] Specific Operation: The server uses an analytical algorithm to analyze the feedback data and evaluate changes in the salesperson's performance and emotional state.

[0249] The server optimizes the analysis algorithm based on the feedback and sentiment data.

[0250] Specific operation: Based on the insights gained from the feedback and emotion data, the server adjusts the parameters of the matching algorithm and reflects the results in the next mapping.

[0251] Example 2

[0252] 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."

[0253] In modern sales activities, it is difficult to effectively collect local business and cultural information and optimally assign sales representatives based on that information. Furthermore, conventional systems cannot take into account the emotional information of sales representatives, resulting in inefficient mapping. As a result, sales activities are not fully effective and sales performance declines.

[0254] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for scraping business information and cultural information for each area from the Internet, means for collecting salesperson characteristics from an information management system, means for analyzing the collected business information, cultural information, and salesperson characteristic data to generate an optimal mapping, means for analyzing user emotion data and reflecting it in the mapping, means for notifying the salesperson and manager of the generated mapping, and means for receiving feedback and optimizing the analysis algorithm. This enables more effective and optimal salesperson allocation that takes into account local business needs and salesperson emotion information.

[0255] "Business Information" refers to economic data, such as economic indexes, key industries, and competitive information, relating to a particular region or industry.

[0256] "Cultural information" refers to social and cultural data such as local culture, lifestyles, language, and events.

[0257] "Internet scraping" refers to techniques and tools used to automatically extract information from websites on the Internet.

[0258] "Characteristics of a salesperson" refers to individual data such as the salesperson's work experience, expertise, personality, and past performance.

[0259] An "information management system" refers to software or a platform for managing and operating data held by a company or organization.

[0260] "Analysis methods" refer to the technologies and algorithms used to find and evaluate relationships and patterns based on collected data.

[0261] "Means for generating optimal mapping" refers to technologies and algorithms that use analyzed data to place sales representatives in the optimal areas and to the optimal customers.

[0262] "User emotion data" refers to data that represents the mood and motivation of salespeople and other users.

[0263] "Notification means" refers to the technology and tools used to communicate the generated mapping results to sales representatives and managers.

[0264] "Means of receiving feedback" refers to the techniques and tools used to collect the results of sales activities and opinions and feedback from sales representatives.

[0265] "Means for optimizing the analysis algorithm" refers to techniques and methods for improving the accuracy and effectiveness of the analysis algorithm based on collected feedback data.

[0266] The present invention relates to a system that collects business information and cultural information for each area and generates an optimal mapping by taking into account the characteristics of sales representatives and emotional information of users. Specific embodiments will be described below.

[0267] System Configuration

[0268] This system consists of a server, terminals, users, and an emotion engine. The server plays a central role in collecting data, analyzing it, generating mappings, notifying users, and optimizing the results. Terminals are devices primarily used by salespeople. Users are salespeople or managers who use the system to carry out their activities, and the emotion engine recognizes and analyzes users' emotions.

[0269] Data collection

[0270] The server periodically scrapes business and cultural information for each area from the Internet. The software used is the Python Scrapy framework. This method collects data such as economic indexes, major industries, competitive information, and local culture and events, and stores it in a MongoDB database. The terminal also collects sales representative characteristic data (work experience, expertise, personality, past performance, etc.) from an information management system (e.g., an HR management tool) and sends it to the server via HTTP.

[0271] Data analysis

[0272] The server analyzes the collected business and cultural information using Pandas and Scikit-learn. Specifically, it analyzes trends in economic indexes for each area, evaluates the competitive situation in major industries, and extracts regional characteristics. To analyze salesperson characteristic data, it also builds an evaluation model (e.g., a logistic regression model) using Scikit-learn to evaluate the salesperson's strengths and weaknesses. Furthermore, the emotion engine recognizes and analyzes user emotions using the Google Cloud Speech-to-Text API for voice analysis and the NLTK library for text analysis. This analysis generates emotion data that indicates the salesperson's mood and motivation.

[0273] Mapping Generation

[0274] The server evaluates demand in each area based on the analyzed business information, cultural information, and sales representative characteristic and emotional data, and generates an optimal mapping. This process uses the SciPy linear algebra package. For example, the server determines that IT-related demand is high in Tokyo, and decides that it would be optimal to assign sales representative A, who has strengths in the IT field, to Tokyo. The generated mapping results are notified to sales representatives and managers via email or a dedicated dashboard (e.g., Tableau).

[0275] Feedback and Optimization

[0276] Users (salespeople) report their field activity results and feedback to the server. This includes data such as sales performance, customer reactions, and self-emotional evaluations. Feedback is entered via a mobile app or web portal and sent to the server. The server analyzes the reported feedback data using Apache Hadoop and Spark to optimize the next mapping algorithm. This results in more accurate placement that reflects the user's emotional data and feedback.

[0277] Specific examples

[0278] If there is a surge in demand for the IT industry in Tokyo, the server uses Scrapy to collect that information and stores it in a MongoDB database. Data about Salesperson A's extensive experience in the IT field, collected from SAP SuccessFactors, is also received via HTTP and added to the database. The emotion engine also uses the Google Cloud Speech-to-Text API and NLTK to identify that Salesperson A has high motivation. The server analyzes this data using Pandas and Scikit-learn, combining IT demand with Salesperson A's characteristic information, and determines that it is optimal to assign A to Tokyo. The results are notified on a Tableau dashboard, and Salesperson A begins sales activities in Tokyo. By reporting the results of the activities and the salesperson's own emotional state as feedback via a mobile app, the server improves the accuracy of the mapping for the next time.

[0279] Specific examples of prompts to be input to generative AI models

[0280] Based on the following text, select the sales representative who best suits the business needs in the IT industry in Tokyo, and generate the optimal placement proposal taking into account emotional information.

[0281] (Tokyo business information)

[0282] IT-related demand surges

[0283] (Cultural information)

[0284] Many highly skilled professionals

[0285] (Characteristic data of Salesperson A)

[0286] Extensive experience in the IT field

[0287] Past performance is excellent

[0288] (Salesperson A's emotional data)

[0289] Maintain high motivation

[0290] Please output the results in a table format and provide a bulleted list of reasons for your recommendation.

[0291] The system adds user emotional information to enable more effective and personalized sales representative mapping.

[0292] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0293] Step 1:

[0294] The server scrapes business and cultural information for each area from the Internet. The software used is the Python Scrapy framework. Specifically, the server periodically crawls web pages to collect data such as economic indexes, major industries, competitive information, and local culture and events. The collected data is stored in a MongoDB database.

[0295] Input: List of web page URLs

[0296] Data Processing: Web Scraping with Scrapy

[0297] Output: Business and cultural information stored in a MongoDB database

[0298] Step 2:

[0299] The terminal collects sales representative characteristic data from the HR system. The device used is a Windows PC or mobile terminal, and the software is an HR management tool (e.g., SAP SuccessFactors). The collected data is sent to the server using the HTTP protocol.

[0300] Input: characteristic data about salespeople (work experience, expertise, personality, past performance)

[0301] Data processing: None (data transfer)

[0302] Output: Salesperson characteristics data sent to the server

[0303] Step 3:

[0304] The server uses Pandas and Scikit-learn to analyze the collected business and cultural information, specifically analyzing trends in economic indexes, assessing the competitive situation in major industries, and extracting regional characteristics.

[0305] Input: Business and cultural information stored in a MongoDB database

[0306] Data processing: Data preprocessing using Pandas, trend analysis and evaluation using Scikit-learn

[0307] Output: Evaluation data of business needs and regional characteristics for each area

[0308] Step 4:

[0309] The server applies a rating model to analyze the sales representative characteristic data. The model, built using Scikit-learn, assesses each representative's strengths and weaknesses based on their past performance and areas of expertise.

[0310] Input: Salesperson characteristics data sent to the server

[0311] Data processing: Model evaluation and analysis with Scikit-learn

[0312] Output: Salesperson strengths and weaknesses evaluation data

[0313] Step 5:

[0314] The emotion engine recognizes and analyzes user emotions, using the Google Cloud Speech-to-Text API for speech analysis and the NLTK library for text analysis to generate emotional data that assesses the mood and motivation of salespeople.

[0315] Input: User voice and text data

[0316] Data processing: Speech analysis with Google Cloud Speech-to-Text API, text analysis with NLTK

[0317] Output: Emotion data

[0318] Step 6:

[0319] The server evaluates the demand for each area based on the analyzed business information, cultural information, salesperson characteristics data, and sentiment data, and generates an optimal mapping. It uses the linear algebra package in SciPy to run the algorithm and calculate the optimal placement.

[0320] Input: Business information, cultural information, salesperson characteristics data, emotion data

[0321] Data processing: Demand assessment and mapping generation using algorithms in SciPy

[0322] Output: Optimal mapping data

[0323] Step 7:

[0324] The server notifies sales representatives and managers of the generated mapping results via email or a dedicated dashboard (e.g., Tableau).

[0325] Input: Optimal mapping data

[0326] Data processing: Converting data into notification format

[0327] Output: Email and dashboard notifications

[0328] Step 8:

[0329] Users (salespeople) report field activity results and feedback to the server, which is entered via a mobile app or web portal.

[0330] Input: Sales performance, customer response, self-emotion evaluation

[0331] Data processing: None (data transfer)

[0332] Output: Feedback data sent to the server

[0333] Step 9:

[0334] The server analyzes the reported feedback data using Apache Hadoop and Spark to evaluate the effectiveness of the placement and optimize the next mapping algorithm.

[0335] Input: Feedback data

[0336] Data Processing: Data Analysis using Hadoop and Spark

[0337] Output: Optimized mapping algorithm

[0338] In this way, data analysis incorporating user emotional information and optimal mapping are performed, maximizing the effectiveness of sales activities.

[0339] (Application example 2)

[0340] 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."

[0341] The present invention relates to a system for automatically generating optimal worker allocations based on the business needs and cultural characteristics of each area, thereby achieving efficient business operations. In particular, there is a demand for optimal allocation of work robots and workers within factories to improve production efficiency and worker satisfaction. Conventional systems have difficulty fully considering the characteristics and emotional information of workers, resulting in an inability to achieve optimal allocation.

[0342] The specific processing by the specific 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 scraping business information and cultural information for each area from a data communication network, means for collecting worker characteristics from an information base, means for analyzing the collected business information, cultural information, and worker characteristics to generate an optimal mapping, means for collecting production information, area characteristics, machine performance information, and emotion information for each area and storing them in a database, means for notifying workers and managers of the generated mapping, and means for receiving feedback and optimizing the analysis algorithm. This enables optimal allocation taking into account the production needs, machine performance, and emotion information of each area.

[0343] "Business information" refers to data related to business and work in each area, including economic indicators, major industries, competitive information, production status, etc.

[0344] "Cultural information" refers to data on the unique culture, lifestyle, language, events, etc. of each area.

[0345] "Characteristics of the worker" refers to data such as the worker's work experience, expertise, personality, past performance, skill level, etc.

[0346] "Data communications network" means an infrastructure for the transmission of data, including the Internet and other networks.

[0347] "Scraping" refers to the technology and methods of automatically collecting necessary information from a website.

[0348] An "information base" refers to a storage device or system such as a database in which data and information are stored.

[0349] "Production information for each area" refers to data related to production at factories and manufacturing sites, specifically including production volume, operating rate, maintenance status, etc.

[0350] "Area characteristics" refers to the characteristics and conditions unique to a particular region or area, including geographical conditions, climate, infrastructure conditions, etc.

[0351] "Machine performance information" refers to data on the performance of machines and equipment used within a factory, including, specifically, processing speed, operating hours, and failure history.

[0352] "Emotional information" refers to data related to the emotions and mental state of workers and managers, and specifically includes motivation, stress levels, mood, etc.

[0353] "Optimal mapping" refers to a deployment plan for allocating workers and machines to optimal locations based on collected and analyzed data.

[0354] "Feedback" refers to workers and managers reporting actual work results, opinions, and feelings to the server.

[0355] "Analysis algorithm" refers to the calculation methods and rules used to analyze collected data and derive optimal placement and areas for improvement.

[0356] The present invention is a system that automatically achieves optimal placement of work robots within a factory. Specific embodiments are described below. This system collects business and cultural information for each area, generates an optimal mapping based on that information, and notifies workers and managers. It also collects feedback and optimizes the analysis algorithm.

[0357] Hardware and Software Configuration

[0358] Hardware used

[0359] Server: The central location for data collection, analysis, mapping generation, and notification.

[0360] Devices: Robots used in factories, and smartphones and tablets used by managers.

[0361] Sensors: Includes emotion engines such as voice analysis and heart rate sensors to collect the worker's emotional state.

[0362] Software used

[0363] Data scraping engine: Software for scraping business and cultural information from the internet.

[0364] Database Management System: A system for storing and managing collected data.

[0365] Analysis algorithms: Algorithms for analyzing the data and generating optimal mappings.

[0366] Emotion engine: Software for analyzing the emotional information of workers and managers.

[0367] Notification system: A system for notifying workers and managers of the generated mapping results.

[0368] Processing Details

[0369] The server periodically scrapes business and cultural information from each area using a data communication network and stores it in a database. It also collects characteristic data and emotional data from workers and sends it to the server. Specifically, this data includes the worker's work experience, expertise, past performance, skill level, etc.

[0370] The collected data is analyzed using an analytical algorithm. The server evaluates the business needs of each area based on business and cultural information, and generates an optimal mapping based on the characteristics and emotional data of the workers. For example, if production demand is high in a particular area, a work robot with high processing speed will be deployed in that area.

[0371] The emotion engine analyzes the emotional information of workers and managers, specifically their motivation, stress levels, and mood, using data from voice analysis and heart rate sensors.

[0372] The generated mapping results are sent to the workers and managers via a notification system. Notifications are sent via email and a dedicated dashboard. The managers and workers can then check the results and take action.

[0373] Feedback data from workers and managers is also collected and sent back to the analysis algorithm. This feedback includes actual work results and emotional states. The server analyzes the feedback data and optimizes the algorithm for the next mapping generation.

[0374] Specific examples

[0375] For example, suppose a factory experiences a sudden increase in production demand in a particular area. The server collects this information from the data communication network and stores it in a database. Next, it registers the characteristic data of robots with high processing speeds in the database. The emotion engine also recognizes that the worker operating the robot is highly motivated.

[0376] Based on this information, the analysis algorithm determines that it is optimal to deploy robots with high processing speeds in areas where demand is increasing. The server then notifies the generated mapping results to workers and managers, who then plan their next work.

[0377] The worker then reports the actual work results and their emotional state as feedback. The server analyzes the feedback data and reflects it in the next deployment plan, further improving the accuracy of the deployment.

[0378] Prompt Sentence Examples

[0379] Area: Tokyo

[0380] Demand: IT-related

[0381] Robot Features: High speed processing

[0382] Emotional data: High motivation

[0383] Generate the optimal placement.

[0384] In this way, the present invention aims to realize efficient allocation of work robots and improve production efficiency and the work environment by combining business information, cultural information, and emotional information for each area.

[0385] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0386] Step 1:

[0387] The server uses a data communication network to scrape business and cultural information from each area. The input data is business and cultural information that is publicly available on the Internet, which is periodically accessed and collected. Specifically, a data scraping engine is used to extract the necessary information and store it in a database. This process accumulates the latest business and cultural information in the database.

[0388] Step 2:

[0389] The terminal collects characteristic data of the worker and sends it to the server. The input data includes the worker's work experience, specialized knowledge, past performance, skill level, etc. Specifically, this data is automatically extracted from the factory management system and sent to the server. In this way, the latest characteristic data of the worker is collected on the server.

[0390] Step 3:

[0391] The server uses an emotion engine to collect and analyze the worker's emotional information. The input data is the worker's voice data and biometric data such as heart rate. Specifically, the system performs voice analysis and heart rate analysis and converts the data into text data and numerical data. The output is the worker's emotional state (motivation, stress level, etc.).

[0392] Step 4:

[0393] The server analyzes the collected business information, cultural information, worker characteristics data, and emotion data to generate an optimal mapping. The input data is all the data collected in the previous stage. Specifically, it analyzes the data using an analytical algorithm and calculates the optimal placement of work robots based on the business and production needs of each area. The output is the optimized mapping result.

[0394] Step 5:

[0395] The server notifies the worker and administrator of the generated mapping results. The input data is the generated mapping results. Specifically, the notification system is used to display the mapping results via email or on a dedicated dashboard. This allows the worker and administrator to check the next work plan.

[0396] Step 6:

[0397] Users collect actual work status and feedback and send it to the server. The input data is feedback on work results and emotional state. Specifically, workers and managers enter data through a dedicated feedback form and send it to the server. This collects data for the next improvement.

[0398] Step 7:

[0399] The server analyzes the feedback data and optimizes the analysis algorithm. The input data is the collected feedback data. Specifically, it analyzes the past mapping results and the corresponding feedback and adjusts the parameters of the analysis algorithm. The output is a newly optimized analysis algorithm, which is reflected in the next mapping.

[0400] Through this series of processes, the system dynamically provides optimal placement, improving work efficiency and worker satisfaction.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] [Second embodiment]

[0405] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0406] 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.

[0407] 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).

[0408] 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.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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."

[0417] The present invention provides a system for collecting business information and cultural information for each area and generating an optimal mapping based on the characteristics of sales representatives. Specific embodiments will be described below.

[0418] This system consists of a server, terminals, and users. The server plays a central role and is mainly responsible for data collection, analysis, mapping generation, notifications, and optimization. Terminals are devices mainly used by the HR system and sales representatives, and users are sales representatives or managers who use the system to carry out activities.

[0419] Data collection

[0420] The server scrapes business and cultural information for each area from the Internet. For example, the server periodically retrieves economic indexes and information on major industries from the official Tokyo Metropolitan Government website and local information sites, and stores this information in a database. It also collects text data from websites about local culture and lifestyles, and stores this data in a database for analysis.

[0421] The terminal collects characteristic data of sales representatives from the personnel system and sends it to the server. For example, the terminal extracts information such as the sales representative's work experience, expertise, personality, and past performance from the database and transfers it to the server via API.

[0422] Data analysis

[0423] The server applies advanced algorithms to analyze the collected business and cultural information, using statistical methods and natural language processing (NLP) techniques to identify economic indexes and key industry trends, assess the business needs of each area, and evaluate and score the unique characteristics of each region using cultural information.

[0424] The server then analyzes the characteristics of each salesperson and applies a rating model to assess their strengths and weaknesses. This rating model is built based on the salesperson's past performance data, expertise, work experience, etc.

[0425] Mapping Generation

[0426] Based on the analysis results, the server optimally maps the business needs and cultural information of each area, as well as the characteristics of sales representatives. For example, the server may determine that there is high demand for IT-related services in Tokyo, and generate a proposal to assign sales representatives with expertise in the IT field to Tokyo.

[0427] The server notifies salespeople and administrators of the generated mapping results via email and a dedicated dashboard, allowing salespeople to view their new deployment areas.

[0428] Feedback and Optimization

[0429] The user (sales representative) reports the results of their activities at the assigned location to the server as feedback. For example, they input data such as the number of new customers acquired, sales, and customer satisfaction through a dedicated application and send it to the server.

[0430] The server analyzes this feedback data and evaluates the effectiveness of each sales representative's placement. The analysis results are used to optimize the algorithm the next time mapping is generated. For example, if activities in Tokyo are highly successful, the algorithm is adjusted to apply the same sales strategy to other areas with similar characteristics.

[0431] Specific examples

[0432] As a specific example, consider the case where the IT industry in Tokyo is growing rapidly. The server scrapes this information and stores it in a database. Next, the information of salesperson A, who has extensive experience in the IT industry, is also stored in the database. The server's algorithm analyzes the business needs and cultural information of Tokyo, as well as the characteristics of salesperson A, and determines that it is optimal to assign him to Tokyo. The server notifies salesperson A of this mapping result, and he begins his sales activities in Tokyo. After that, the user (salesperson A) reports the results of his activities, and the server analyzes the data and optimizes the next mapping algorithm.

[0433] In this way, the present invention provides efficient and effective people and place mapping.

[0434] The processing flow will be explained below.

[0435] Step 1: Data collection

[0436] The server scrapes business information for each area (e.g., economic indexes, major industries, competitive information, etc.) from the Internet.

[0437] Specific operation: The server uses a crawler to obtain the latest data from official government websites and business-related news sites and stores it in a database.

[0438] The server also scrapes cultural information (e.g., local culture, lifestyle, language, events, etc.).

[0439] Specific operation: The server collects text data from local information sites and tourist association websites and stores it in an analysis database.

[0440] The terminal transmits the characteristics of the sales representative (e.g., work experience, expertise, personality, past performance, etc.) from the personnel system to the server.

[0441] Specific operation: The terminal extracts sales representative information from the personnel database and sends it to the server's API endpoint.

[0442] Step 2: Data analysis

[0443] The server runs algorithms to analyze the collected business information.

[0444] How it works: The server uses text analysis and statistical techniques to extract and index economic indices and trends in key industries.

[0445] The server analyzes the culture information and evaluates the characteristics of each region.

[0446] How it works: The server uses natural language processing (NLP) techniques to analyze text data and score cultural characteristics for each region.

[0447] The server analyzes the characteristic data of the sales representatives.

[0448] Specific operation: The server uses an evaluation model based on data on each sales representative's past performance, expertise, and work experience to score their strengths and weaknesses.

[0449] Step 3: Generate mappings

[0450] The server assesses the demand for each area based on business and cultural information.

[0451] What it does: The server combines business and cultural indexes to create a demand map for each area.

[0452] The server runs an algorithm that matches the characteristics of salespeople with area demand.

[0453] Specific operation: The server performs optimal matching based on the demand map and the sales representative's evaluation score, and generates a placement plan.

[0454] The server notifies the sales representative and the manager of the generated mapping results.

[0455] Specific operation: The server notifies each sales representative and manager of the mapping results via email or dashboard.

[0456] Step 4: Feedback and optimization

[0457] Users (salespeople) send field activity results and feedback to the server.

[0458] Specific operation: The user enters the activity results through a dedicated app or web form and sends them to the server.

[0459] The server analyzes the feedback sent and evaluates the effectiveness of the placement.

[0460] Specific operation: The server analyzes the feedback data, calculates performance indicators (e.g., sales, customer satisfaction, etc.), and evaluates the performance of the algorithm.

[0461] The server optimizes the analysis algorithm based on the feedback.

[0462] Specific operation: The server adjusts the algorithm parameters based on the insights gained from the feedback and reflects these in the next data analysis and mapping creation.

[0463] Example 1

[0464] 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."

[0465] Conventional sales support systems lacked the functionality to efficiently collect business and cultural information for each area and then optimally allocate sales representatives based on that information. As a result, optimal mapping based on the characteristics of sales representatives and area demand was not performed, resulting in a decline in sales efficiency. Furthermore, the functionality to dynamically adjust analysis algorithms based on feedback was insufficient, preventing sufficient optimization of allocation.

[0466] 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.

[0467] In this invention, the server includes: means for scraping business and cultural information for each area from the Internet; means for collecting salesperson characteristics from a database; means for analyzing the collected business information, cultural information, and salesperson characteristics and using statistical methods and natural language processing technology to generate an optimal mapping; means for notifying the salesperson and manager of the generated mapping; and means for receiving activity results as feedback and optimizing the analysis algorithm using regression analysis and Bayesian estimation. This makes it possible to achieve optimal allocation that takes into account the demand in each area and the characteristics of the salesperson, significantly improving sales efficiency.

[0468] "Scraping" is a technique for automatically extracting necessary data from a website's HTML source code.

[0469] "Business information" is information related to economic activity, such as economic indexes and data on major industries in a particular region.

[0470] "Cultural information" is information about the culture, lifestyles, and social characteristics of a particular region.

[0471] "Characteristics of a salesperson" refers to attributes related to sales activities, such as the salesperson's work experience, expertise, personality, and past performance.

[0472] A "database" is a system for efficiently storing and managing large amounts of data.

[0473] "Statistical methods" are mathematical methods for analyzing and evaluating data.

[0474] "Natural language processing technology (NLP)" is a technology that allows computers to analyze and understand human language.

[0475] "Mapping" is a deployment plan that optimally matches the business needs and cultural information of each area with the characteristics of sales representatives.

[0476] "Notification" is a means for informing interested parties of the generated mapping results.

[0477] "Feedback" is the process of inputting data on the results of sales representatives' activities into the system to help improve the analysis algorithm.

[0478] An "analysis algorithm" is a computational procedure for analyzing data and generating an optimal mapping.

[0479] "Regression analysis" is a statistical method for modeling relationships between data.

[0480] "Bayesian estimation" is a statistical method for calculating posterior probabilities based on observed data and estimating unknown parameters.

[0481] The present invention is a system that collects business information and cultural information for each area and generates an optimal mapping based on the characteristics of sales representatives. Specific embodiments will be described below.

[0482] This system consists of a server, terminals, and users. The server plays a central role and is mainly responsible for data collection, analysis, mapping generation, notifications, and optimization. Terminals are devices mainly used by the HR system and sales representatives, and users are sales representatives or managers who use the system to carry out activities.

[0483] Data collection

[0484] The server scrapes business and cultural information for each area from the Internet. For example, the server periodically retrieves economic indexes and information on major industries from official government and regional information sites, analyzes the HTML source code using the BeautifulSoup library, extracts the necessary data, and stores it in a database. It also collects text data from websites about regional culture and lifestyles and stores it in a database for analysis.

[0485] The device collects characteristic data about salespeople from the company's personnel system and sends it to the server. Specifically, it obtains information about the salespeople's work experience, expertise, personality, past performance, etc. via API and transfers it to the server.

[0486] Data analysis

[0487] The server applies advanced algorithms to analyze the collected business and cultural information. Specifically, it applies ARIMA models to identify economic indexes and key industry trends, and evaluates the business needs of each area. Similarly, it uses natural language processing (NLP) techniques to analyze cultural information, tokenize text data, perform TF-IDF vectorization, and score region-specific characteristics.

[0488] The server then inputs the sales representative's characteristic data into an evaluation model to analyze each sales representative's strengths and weaknesses. This evaluation model is built using machine learning algorithms such as random forests and support vector machines (SVMs) based on past performance data, expertise, and work experience.

[0489] Mapping Generation

[0490] Based on the analysis results, the server optimally maps the business needs and cultural information of each area, as well as the characteristics of sales representatives. Specifically, it matches the appropriate sales representative with the area using multidimensional scaling (MDS) and clustering techniques (e.g., k-means clustering). For example, it assesses that there is high demand for IT-related products in Tokyo and generates a proposal to assign sales representatives with the respective strengths to Tokyo.

[0491] The server notifies sales representatives and administrators of the generated mapping results by email using the SMTP protocol and provides an interface where they can check the results in real time on a dedicated dashboard.

[0492] Feedback and Optimization

[0493] Users (salespeople) report the results of their activities at their assigned locations to the server as feedback. Specific feedback data, such as the number of new customers acquired, sales, and customer satisfaction, is entered through a dedicated application and sent to the server via an API.

[0494] The server analyzes this feedback data and evaluates the effectiveness of each sales representative's placement. Statistical methods such as regression analysis and Bayesian estimation are used for the analysis, and the algorithm is optimized the next time a mapping is generated. Methods that produce high results under similar conditions are learned and reflected in the algorithm.

[0495] Specific examples

[0496] Consider the case of Tokyo, where the IT industry is growing rapidly. The server scrapes information from the official government website, analyzes the HTML code using BeautifulSoup, and saves the necessary information in a database. Next, it obtains information about Salesperson A, who has extensive experience in the IT industry, from the human resources system via an API and saves it in the database. The server's algorithm analyzes business needs and cultural information using the ARIMA model and TF-IDF vectorization, and matches this with Salesperson A's characteristics. It then determines that Tokyo is the best place for the assignment and notifies Salesperson A via email and a dashboard. After the assignment, the user (Salesperson A) reports activity results such as the number of new customers acquired and sales data to the server via a dedicated application. The server then analyzes this feedback data using regression analysis and optimizes the next mapping algorithm.

[0497] Prompt Sentence Examples

[0498] "Please assess the IT business needs in Tokyo and generate a mapping proposal for assigning the most suitable sales representatives."

[0499] In this way, the present invention provides efficient and effective people and place mapping.

[0500] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0501] Detailed explanation of the processing steps

[0502] Step 1: Data collection

[0503] The server scrapes business and cultural information for each area from the Internet. Specifically, the server uses the BeautifulSoup library to parse HTML source code from official government websites and local information sites, extracting information on economic indexes and major industries and storing it in a database. For example, information on Tokyo's economic index and major industries is obtained daily and updated regularly. The input is the website's HTML code, and the output is economic and cultural information formatted in JSON format.

[0504] Step 2: Collect data on salesperson characteristics

[0505] The terminal collects sales representative characteristic data from the company's internal human resources system and sends it to the server using an API. Specifically, it obtains sales representative work experience, expertise, personality, and past performance data from the human resources system, converts it into JSON format, and sends it to the server. The input is XML or CSV data from the human resources system, and the output is sales representative data in JSON format, which is sent to the server via the API.

[0506] Step 3: Parse business and cultural information

[0507] The server analyzes the collected business and cultural information. Specifically, it uses an ARIMA model to identify trends in economic indexes and scores the data. It also uses NLP technology to tokenize the cultural information and perform TF-IDF vectorization to evaluate region-specific characteristics. The input is business and cultural information in JSON format, and the output is the score for each area as an analysis result.

[0508] Step 4: Salesperson Profile Analysis

[0509] The server applies machine learning algorithms to analyze sales representative characteristic data. Specifically, it uses random forests and support vector machines (SVMs) to evaluate sales representatives' strengths and weaknesses. This evaluation model is built based on past performance data, specialized knowledge, and work experience. The input is sales representative data in JSON format, and the output is an evaluation score for each sales representative.

[0510] Step 5: Generate the optimal mapping

[0511] Based on the analysis results, the server optimally maps the business needs, cultural information, and characteristics of each salesperson for each area. For example, it uses multidimensional scaling (MDS) or k-means clustering to allocate salespeople to the most suitable areas. The inputs are scores for business and cultural information, and the evaluation scores of salespeople, and the output is an optimal allocation plan for each area.

[0512] Step 6: Notification of mapping results

[0513] The server notifies sales representatives and administrators of the generated mapping results. Notifications are sent by email using the SMTP protocol, and an interface is provided where results can be checked in real time on a dedicated dashboard. The input is the optimal placement plan, and the output is a notification email and updated information on the dashboard.

[0514] Step 7: Feedback and optimization of activity results

[0515] Users (salespeople) report the results of their activities to the server as feedback. They input the number of new customers acquired, sales, customer satisfaction, etc. through a dedicated application and send it to the server via API. The server receives this feedback data, analyzes it using regression analysis and Bayesian estimation, and optimizes the analysis algorithm. The input is the feedback data, and the output is the next optimized mapping algorithm.

[0516] (Application example 1)

[0517] 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."

[0518] Conventional business mapping and security patrol systems struggle to properly consider the specific business needs and crime data of each area and generate optimal personnel and patrol routes. This reduces the efficiency of sales and security activities, resulting in lower satisfaction for businesses and local communities. Furthermore, they lack the ability to dynamically adjust analysis algorithms based on feedback, making long-term optimization difficult.

[0519] 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.

[0520] In this invention, the server includes: means for scraping business and cultural information for each area from the Internet; means for collecting characteristics of sales representatives from a database; means for analyzing the collected business information, cultural information, and characteristics of sales representatives to generate an optimal mapping; means for notifying the sales representatives and managers of the generated mapping; means for receiving feedback and optimizing the analysis algorithm; means for scraping crime data and security-related information for the area from the Internet; means for collecting characteristics of security guards from a database; means for analyzing the collected crime data and security information to generate an optimal patrol route; and means for notifying the security guards and managers of the generated patrol route. This allows the specific needs of each area to be reflected, improving the efficiency of sales and security activities, and further achieving long-term results through dynamic optimization.

[0521] "Business information" refers to data on economic activity and industry in each area, as well as information including corporate trends and market trends.

[0522] "Cultural information" is data about the culture, customs, and lifestyle of a particular region or community.

[0523] "Scraping" is a technique for automatically collecting information that is publicly available on the Internet.

[0524] A "sales representative" is an employee whose role is to sell a company's products or services to customers.

[0525] "Characteristics" refers to data about the attributes and abilities of individual sales representatives and security guards, such as their work experience, expertise, personality, and past performance.

[0526] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[0527] "Analysis" is the process of analyzing collected data using statistical methods and algorithms to extract meaningful information.

[0528] "Mapping" refers to determining optimal placement and correspondence based on collected and analyzed data.

[0529] "Notification" is a means of informing the subject of the generated results.

[0530] "Feedback" is the process of collecting user evaluations and results and using them to help with future improvements.

[0531] An "algorithm" refers to a procedure or computational method for solving a specific problem.

[0532] "Crime data" refers to data that includes crime occurrences in a specific area and detailed information about those crimes.

[0533] "Security-related information" refers to data related to crime prevention measures and risk assessments.

[0534] A "patrol route" refers to the optimized route taken by security guards for patrol.

[0535] The system that realizes this application example consists of a server, terminals, and users. The server plays a central role in collecting data, analyzing it, generating mapping, notifying users, and optimizing it. Terminals are devices mainly used by personnel systems, sales representatives, and security guards, while users refer to the sales representatives or security guards who use the system to carry out their activities, as well as their managers.

[0536] Data collection

[0537] The server scrapes business, cultural, and crime data for each area from the internet. The software used for this is the Python requests library. For example, the required data is obtained from specific APIs (https: / / api.example.com / crime-data, https: / / api.example.com / guards) and stored in a database. Text data on regional culture and lifestyles is also collected from websites and stored in a database for analysis.

[0538] The terminal collects data on the characteristics of sales representatives and security guards from the personnel system and sends it to the server. For example, information such as the sales representative's work experience, expertise, personality, past performance, and the security guard's qualifications and experience is extracted from the database and transferred to the server via API.

[0539] Data analysis

[0540] The server applies advanced algorithms to analyze the collected business, cultural, and crime data. Specifically, it uses statistical methods and natural language processing (NLP) techniques to identify economic indexes and key industry trends, assess the business needs of each area, and evaluate and score the unique characteristics of each area using cultural and crime data.

[0541] The server also analyzes the characteristics of sales representatives and security guards and applies a rating model to assess their strengths and weaknesses. This rating model is generated by clustering based on crime rates and population density in a specific area, standardizing the data using Python's scikit-learn library, and clustering using KMeans.

[0542] Mapping Generation

[0543] Based on the analysis results, the server optimally maps each area's business needs, cultural information, crime data, and the characteristics of sales representatives and security guards. The generated mapping results are notified to sales representatives, security guards, and managers via email and a dedicated dashboard.

[0544] As a specific example, if information is collected that crime rates are rising in the Shinjuku area, the server analyzes that information, evaluates whether the characteristics of the security guards currently in charge of the Shinjuku area are suitable for this area, and assigns patrols to the most suitable security guards.

[0545] Feedback and Optimization

[0546] Users (sales representatives and security guards) report the results of their activities at their assigned locations to the server as feedback. Data such as the number of new customers acquired, sales, customer satisfaction, or reductions in crimes is entered through a dedicated application and sent to the server.

[0547] The server analyzes this feedback data and evaluates the effectiveness of each sales representative and security guard placement. The analysis results are used to optimize the algorithm the next time mapping is generated. For example, if activity in the Shinjuku area is highly successful, the algorithm adjusts to apply the same strategy to other areas with similar characteristics.

[0548] Prompt Sentence Examples

[0549] As a concrete example, the following prompt sentence can be input to a generative AI model:

[0550] Generate Python code for an application that generates optimal security patrol routes based on area crime data and population density. The URLs for the collected data are obtained from https: / / api.example.com / crime-data and https: / / api.example.com / guards. The area data includes crime rate (crime_rate) and population density (population_density).

[0551] In this way, the present invention can provide efficient and effective people and place mapping, greatly improving the efficiency of business and security operations.

[0552] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0553] Step 1:

[0554] Data collection:

[0555] The server scrapes business, cultural, and crime data for each area from the internet. Specifically, it uses the Python requests library to retrieve data from an API (e.g., https: / / api.example.com / crime-data or https: / / api.example.com / guards) and saves it in a database. The URL to be collected using the API is given as input, and the data is obtained in JSON format as output. This is then stored in the database.

[0556] Step 2:

[0557] Feature data collection:

[0558] The terminal collects characteristic data of sales representatives and security guards from the personnel system and sends it to the server. Specifically, it extracts information such as the sales representative's work experience and past performance, and the security guard's qualifications and experience from the database, and transfers it to the server via API. A database query is given as input, and the characteristic data of the sales representatives and security guards is obtained as output in JSON format. This is then transferred to the server.

[0559] Step 3:

[0560] Data Analysis:

[0561] The server analyzes the collected business, cultural, and crime data. It standardizes the data using Python's scikit-learn and performs clustering using KMeans. The standardized data is given as input, and the clustering results are obtained as output. Specifically, the business needs and crime levels of each region are scored and classified into each cluster.

[0562] Step 4:

[0563] Mapping Generation:

[0564] Based on the analysis results, the server optimally maps each area to the characteristics of sales representatives or security guards. The analyzed clustering data and characteristic data of sales representatives and security guards are given as input, and the mapping results are obtained as output. Specifically, it generates the optimal sales representative placement and patrol routes for a specific area.

[0565] Step 5:

[0566] notification:

[0567] The server notifies the generated mapping results to sales representatives, security guards, and managers in real time via email and a dedicated dashboard. The mapping result data is given as input, and a notification message is generated as output. Specifically, each person in charge can check the new deployment and route.

[0568] Step 6:

[0569] Feedback collection:

[0570] Users (sales representatives and security guards) report the results of their activities at their assigned locations to the server as feedback. They input data such as the number of new customers acquired, sales, customer satisfaction, and reductions in crimes through a dedicated application. Data manually entered by the user is given as input, and feedback data is obtained as output. This is then sent to the server.

[0571] Step 7:

[0572] Algorithm optimization:

[0573] The server analyzes the feedback data and optimizes the algorithm for the next mapping generation. The feedback data is given as input and an optimized algorithm is generated as output. Specifically, it adjusts activities in similar areas based on successful cases and derives effective placements and routes.

[0574] The above processing steps make it possible to reflect the specific needs of each area and significantly improve the efficiency of sales and security activities.

[0575] 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.

[0576] The present invention provides a system that collects business information and cultural information for each area and generates an optimal mapping by taking into account the emotional information of sales representatives and users. Specific embodiments will be described below.

[0577] This system consists of a server, terminals, users, and an emotion engine. The server plays a central role in collecting data, analyzing it, generating mappings, notifying users, and optimizing the system. Terminals are devices primarily used by the human resources system and sales representatives. Users are sales representatives or managers who use the system to carry out their activities, and the emotion engine recognizes and analyzes the user's emotions.

[0578] Data collection

[0579] The server periodically scrapes business information (e.g., economic indexes, major industries, competitive information, etc.) for each area from the Internet and stores it in a database. It also scrapes cultural information (e.g., local culture, lifestyles, language, events, etc.) and stores it in a database for analysis.

[0580] The terminal collects characteristic data of sales representatives (e.g., work experience, expertise, personality, past performance, etc.) from the personnel system and transmits it to the server.

[0581] Data analysis

[0582] The server applies data analysis algorithms to analyze the collected business and cultural information. Specifically, it analyzes economic indexes and trends in major industries to assess the business needs of each area. Similarly, it evaluates the characteristics of each region based on cultural information.

[0583] The server also applies an evaluation model to analyze the salesperson's characteristic data, which analyzes the salesperson's past performance, expertise, and work experience to evaluate their strengths and weaknesses.

[0584] The emotion engine recognizes and analyzes user emotions. For example, it analyzes the mood and motivation of salespeople using text and voice analysis to generate emotion data.

[0585] Mapping Generation

[0586] The server evaluates demand in each area based on business and cultural information, and generates optimal mapping based on the characteristics and emotional data of sales representatives. For example, the server determines that IT-related demand is high in Tokyo, and proposes the placement of sales representative A, who has strengths in the IT field, in Tokyo so that he can work most effectively.

[0587] The server then notifies sales representatives and managers of the generated mapping results via email and a dedicated dashboard.

[0588] Feedback and Optimization

[0589] Users (salespeople) report the results of their field activities and feedback to the server, including data such as sales performance and customer reactions.

[0590] The server analyzes the feedback data to evaluate the effectiveness of the placement. It also incorporates emotion data provided by the emotion engine. Based on this data, it optimizes the next mapping algorithm.

[0591] Specific examples

[0592] For example, if there is a surge in demand for the IT industry in Tokyo, the server scrapes that information and stores it in a database. Next, the information of salesperson A, who has extensive experience in the IT industry, is also registered in the database. The emotion engine also analyzes salesperson A's emotions and identifies that he is highly motivated.

[0593] The server's algorithm analyzes the business needs and cultural information of Tokyo, as well as the characteristics and emotional data of sales representative A, and determines that it is best to assign him to Tokyo. The server notifies sales representative A of the generated mapping results, and he begins his sales activities in Tokyo.

[0594] After that, the user (Salesperson A) reports the results of their activities and their emotional state as feedback. The server analyzes this data and reflects it in the next mapping, further improving the accuracy of the placement.

[0595] In this way, the present invention is a system that realizes more effective and personalized sales representative mapping by adding user emotional information.

[0596] The processing flow will be explained below.

[0597] Step 1: Data collection

[0598] The server scrapes business information for each area (e.g., economic indexes, major industries, competitive information, etc.) from the Internet.

[0599] Specific operation: The server uses a crawler to periodically collect the latest data from official government websites and business-related news sites and store it in a database.

[0600] The server also scrapes cultural information (e.g., local culture, lifestyle, language, events, etc.).

[0601] Specific operation: The server collects text data from local information sites and tourist association websites and stores it in an analysis database.

[0602] The terminal transmits characteristic data of the sales representative (e.g., work experience, expertise, personality, past performance, etc.) from the personnel system to the server.

[0603] Specific operation: The terminal extracts sales representative information from the personnel database via API and stores it in the server database.

[0604] Step 2: Collecting Emotional Data

[0605] The user (salesperson) inputs his / her own feelings in daily activities.

[0606] Specific operation: The user selects and enters their emotional state from a list using a dedicated app or a web form.

[0607] The emotion engine automatically analyzes emotions from the user's voice and text.

[0608] How it works: The emotion engine uses emotion analysis algorithms to analyze voice and text data in real time and generate an emotion score.

[0609] Step 3: Data analysis

[0610] The server runs algorithms to analyze the collected business information.

[0611] Specific operation: The server extracts business indexes and trends of major industries using statistical methods and text analysis, and evaluates the business needs of each area.

[0612] The server analyzes the culture information and evaluates the characteristics of each region.

[0613] Specific operation: The server uses natural language processing (NLP) technology to extract region-specific characteristics from text data and assigns an evaluation score.

[0614] The server analyzes the characteristic data of the sales representative based on the evaluation model.

[0615] Specific operation: The server applies a model to score past performance data, expertise, and work experience, and evaluates each employee.

[0616] The server analyzes the emotion data from the emotion engine and makes a comprehensive evaluation.

[0617] Specific operation: The emotion scores provided by the emotion engine are integrated and analyzed taking into account the salesperson's current psychological state.

[0618] Step 4: Mapping Generation

[0619] The server evaluates the demand in each area based on business information, cultural information, characteristics of sales representatives, and emotional data, and generates an optimal mapping.

[0620] Specific operation: The server runs a matching algorithm based on the evaluation scores to determine the optimal combination of sales representative and area.

[0621] The server notifies the sales representative and the manager of the generated mapping results.

[0622] Specific operation: The server sends the results to sales representatives and managers via email notifications or dedicated dashboards.

[0623] Step 5: Feedback and optimization

[0624] Users (salespeople) send field activity results and feedback to the server.

[0625] Specific operation: The user enters performance data (e.g., sales, customer satisfaction, etc.) and emotional feedback through a dedicated app or web form and sends them to the server.

[0626] The server analyzes the transmitted feedback data and evaluates the effectiveness of the deployment.

[0627] Specific Operation: The server uses an analytical algorithm to analyze the feedback data and evaluate changes in the salesperson's performance and emotional state.

[0628] The server optimizes the analysis algorithm based on the feedback and sentiment data.

[0629] Specific operation: Based on the insights gained from the feedback and emotion data, the server adjusts the parameters of the matching algorithm and reflects the results in the next mapping.

[0630] Example 2

[0631] 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."

[0632] In modern sales activities, it is difficult to effectively collect local business and cultural information and optimally assign sales representatives based on that information. Furthermore, conventional systems cannot take into account the emotional information of sales representatives, resulting in inefficient mapping. As a result, sales activities are not fully effective and sales performance declines.

[0633] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for scraping business information and cultural information for each area from the Internet, means for collecting salesperson characteristics from an information management system, means for analyzing the collected business information, cultural information, and salesperson characteristic data to generate an optimal mapping, means for analyzing user emotion data and reflecting it in the mapping, means for notifying the salesperson and manager of the generated mapping, and means for receiving feedback and optimizing the analysis algorithm. This enables more effective and optimal salesperson allocation that takes into account local business needs and salesperson emotion information.

[0634] "Business Information" refers to economic data, such as economic indexes, key industries, and competitive information, relating to a particular region or industry.

[0635] "Cultural information" refers to social and cultural data such as local culture, lifestyles, language, and events.

[0636] "Internet scraping" refers to techniques and tools used to automatically extract information from websites on the Internet.

[0637] "Characteristics of a salesperson" refers to individual data such as the salesperson's work experience, expertise, personality, and past performance.

[0638] An "information management system" refers to software or a platform for managing and operating data held by a company or organization.

[0639] "Analysis methods" refer to the technologies and algorithms used to find and evaluate relationships and patterns based on collected data.

[0640] "Means for generating optimal mapping" refers to technologies and algorithms that use analyzed data to place sales representatives in the optimal areas and to the optimal customers.

[0641] "User emotion data" refers to data that represents the mood and motivation of salespeople and other users.

[0642] "Notification means" refers to the technology and tools used to communicate the generated mapping results to sales representatives and managers.

[0643] "Means of receiving feedback" refers to the techniques and tools used to collect the results of sales activities and opinions and feedback from sales representatives.

[0644] "Means for optimizing the analysis algorithm" refers to techniques and methods for improving the accuracy and effectiveness of the analysis algorithm based on collected feedback data.

[0645] The present invention relates to a system that collects business information and cultural information for each area and generates an optimal mapping by taking into account the characteristics of sales representatives and emotional information of users. Specific embodiments will be described below.

[0646] System Configuration

[0647] This system consists of a server, terminals, users, and an emotion engine. The server plays a central role in collecting data, analyzing it, generating mappings, notifying users, and optimizing the results. Terminals are devices primarily used by salespeople. Users are salespeople or managers who use the system to carry out their activities, and the emotion engine recognizes and analyzes users' emotions.

[0648] Data collection

[0649] The server periodically scrapes business and cultural information for each area from the Internet. The software used is the Python Scrapy framework. This method collects data such as economic indexes, major industries, competitive information, and local culture and events, and stores it in a MongoDB database. The terminal also collects sales representative characteristic data (work experience, expertise, personality, past performance, etc.) from an information management system (e.g., an HR management tool) and sends it to the server via HTTP.

[0650] Data analysis

[0651] The server analyzes the collected business and cultural information using Pandas and Scikit-learn. Specifically, it analyzes trends in economic indexes for each area, evaluates the competitive situation in major industries, and extracts regional characteristics. To analyze salesperson characteristic data, it also builds an evaluation model (e.g., a logistic regression model) using Scikit-learn to evaluate the salesperson's strengths and weaknesses. Furthermore, the emotion engine recognizes and analyzes user emotions using the Google Cloud Speech-to-Text API for voice analysis and the NLTK library for text analysis. This analysis generates emotion data that indicates the salesperson's mood and motivation.

[0652] Mapping Generation

[0653] The server evaluates demand in each area based on the analyzed business information, cultural information, and sales representative characteristic and emotional data, and generates an optimal mapping. This process uses the SciPy linear algebra package. For example, the server determines that IT-related demand is high in Tokyo, and decides that it would be optimal to assign sales representative A, who has strengths in the IT field, to Tokyo. The generated mapping results are notified to sales representatives and managers via email or a dedicated dashboard (e.g., Tableau).

[0654] Feedback and Optimization

[0655] Users (salespeople) report their field activity results and feedback to the server. This includes data such as sales performance, customer reactions, and self-emotional evaluations. Feedback is entered via a mobile app or web portal and sent to the server. The server analyzes the reported feedback data using Apache Hadoop and Spark to optimize the next mapping algorithm. This results in more accurate placement that reflects the user's emotional data and feedback.

[0656] Specific examples

[0657] If there is a surge in demand for the IT industry in Tokyo, the server uses Scrapy to collect that information and stores it in a MongoDB database. Data about Salesperson A's extensive experience in the IT field, collected from SAP SuccessFactors, is also received via HTTP and added to the database. The emotion engine also uses the Google Cloud Speech-to-Text API and NLTK to identify that Salesperson A has high motivation. The server analyzes this data using Pandas and Scikit-learn, combining IT demand with Salesperson A's characteristic information, and determines that it is optimal to assign A to Tokyo. The results are notified on a Tableau dashboard, and Salesperson A begins sales activities in Tokyo. By reporting the results of the activities and the salesperson's own emotional state as feedback via a mobile app, the server improves the accuracy of the mapping for the next time.

[0658] Specific examples of prompts to be input to generative AI models

[0659] Based on the following text, select the sales representative who best suits the business needs in the IT industry in Tokyo, and generate the optimal placement proposal taking into account emotional information.

[0660] (Tokyo business information)

[0661] IT-related demand surges

[0662] (Cultural information)

[0663] Many highly skilled professionals

[0664] (Characteristic data of Salesperson A)

[0665] Extensive experience in the IT field

[0666] Past performance is excellent

[0667] (Salesperson A's emotional data)

[0668] Maintain high motivation

[0669] Please output the results in a table format and provide a bulleted list of reasons for your recommendation.

[0670] The system adds user emotional information to enable more effective and personalized sales representative mapping.

[0671] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0672] Step 1:

[0673] The server scrapes business and cultural information for each area from the Internet. The software used is the Python Scrapy framework. Specifically, the server periodically crawls web pages to collect data such as economic indexes, major industries, competitive information, and local culture and events. The collected data is stored in a MongoDB database.

[0674] Input: List of web page URLs

[0675] Data Processing: Web Scraping with Scrapy

[0676] Output: Business and cultural information stored in a MongoDB database

[0677] Step 2:

[0678] The terminal collects sales representative characteristic data from the HR system. The device used is a Windows PC or mobile terminal, and the software is an HR management tool (e.g., SAP SuccessFactors). The collected data is sent to the server using the HTTP protocol.

[0679] Input: characteristic data about salespeople (work experience, expertise, personality, past performance)

[0680] Data processing: None (data transfer)

[0681] Output: Salesperson characteristics data sent to the server

[0682] Step 3:

[0683] The server uses Pandas and Scikit-learn to analyze the collected business and cultural information, specifically analyzing trends in economic indexes, assessing the competitive situation in major industries, and extracting regional characteristics.

[0684] Input: Business and cultural information stored in a MongoDB database

[0685] Data processing: Data preprocessing using Pandas, trend analysis and evaluation using Scikit-learn

[0686] Output: Evaluation data of business needs and regional characteristics for each area

[0687] Step 4:

[0688] The server applies a rating model to analyze the sales representative characteristic data. The model, built using Scikit-learn, assesses each representative's strengths and weaknesses based on their past performance and areas of expertise.

[0689] Input: Salesperson characteristics data sent to the server

[0690] Data processing: Model evaluation and analysis with Scikit-learn

[0691] Output: Salesperson strengths and weaknesses evaluation data

[0692] Step 5:

[0693] The emotion engine recognizes and analyzes user emotions, using the Google Cloud Speech-to-Text API for speech analysis and the NLTK library for text analysis to generate emotional data that assesses the mood and motivation of salespeople.

[0694] Input: User voice and text data

[0695] Data processing: Speech analysis with Google Cloud Speech-to-Text API, text analysis with NLTK

[0696] Output: Emotion data

[0697] Step 6:

[0698] The server evaluates the demand for each area based on the analyzed business information, cultural information, salesperson characteristics data, and sentiment data, and generates an optimal mapping. It uses the linear algebra package in SciPy to run the algorithm and calculate the optimal placement.

[0699] Input: Business information, cultural information, salesperson characteristics data, emotion data

[0700] Data processing: Demand assessment and mapping generation using algorithms in SciPy

[0701] Output: Optimal mapping data

[0702] Step 7:

[0703] The server notifies sales representatives and managers of the generated mapping results via email or a dedicated dashboard (e.g., Tableau).

[0704] Input: Optimal mapping data

[0705] Data processing: Converting data into notification format

[0706] Output: Email and dashboard notifications

[0707] Step 8:

[0708] Users (salespeople) report field activity results and feedback to the server, which is entered via a mobile app or web portal.

[0709] Input: Sales performance, customer response, self-emotion evaluation

[0710] Data processing: None (data transfer)

[0711] Output: Feedback data sent to the server

[0712] Step 9:

[0713] The server analyzes the reported feedback data using Apache Hadoop and Spark to evaluate the effectiveness of the placement and optimize the next mapping algorithm.

[0714] Input: Feedback data

[0715] Data Processing: Data Analysis using Hadoop and Spark

[0716] Output: Optimized mapping algorithm

[0717] In this way, data analysis incorporating user emotional information and optimal mapping are performed, maximizing the effectiveness of sales activities.

[0718] (Application example 2)

[0719] 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."

[0720] The present invention relates to a system for automatically generating optimal worker allocations based on the business needs and cultural characteristics of each area, thereby achieving efficient business operations. In particular, there is a demand for optimal allocation of work robots and workers within factories to improve production efficiency and worker satisfaction. Conventional systems have difficulty fully considering the characteristics and emotional information of workers, resulting in an inability to achieve optimal allocation.

[0721] The specific processing by the specific 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 scraping business information and cultural information for each area from a data communication network, means for collecting worker characteristics from an information base, means for analyzing the collected business information, cultural information, and worker characteristics to generate an optimal mapping, means for collecting production information, area characteristics, machine performance information, and emotion information for each area and storing them in a database, means for notifying workers and managers of the generated mapping, and means for receiving feedback and optimizing the analysis algorithm. This enables optimal allocation taking into account the production needs, machine performance, and emotion information of each area.

[0722] "Business information" refers to data related to business and work in each area, including economic indicators, major industries, competitive information, production status, etc.

[0723] "Cultural information" refers to data on the unique culture, lifestyle, language, events, etc. of each area.

[0724] "Characteristics of the worker" refers to data such as the worker's work experience, expertise, personality, past performance, skill level, etc.

[0725] "Data communications network" means an infrastructure for the transmission of data, including the Internet and other networks.

[0726] "Scraping" refers to the technology and methods of automatically collecting necessary information from a website.

[0727] An "information base" refers to a storage device or system such as a database in which data and information are stored.

[0728] "Production information for each area" refers to data related to production at factories and manufacturing sites, specifically including production volume, operating rate, maintenance status, etc.

[0729] "Area characteristics" refers to the characteristics and conditions unique to a particular region or area, including geographical conditions, climate, infrastructure conditions, etc.

[0730] "Machine performance information" refers to data on the performance of machines and equipment used within a factory, including, specifically, processing speed, operating hours, and failure history.

[0731] "Emotional information" refers to data related to the emotions and mental state of workers and managers, and specifically includes motivation, stress levels, mood, etc.

[0732] "Optimal mapping" refers to a deployment plan for allocating workers and machines to optimal locations based on collected and analyzed data.

[0733] "Feedback" refers to workers and managers reporting actual work results, opinions, and feelings to the server.

[0734] "Analysis algorithm" refers to the calculation methods and rules used to analyze collected data and derive optimal placement and areas for improvement.

[0735] The present invention is a system that automatically achieves optimal placement of work robots within a factory. Specific embodiments are described below. This system collects business and cultural information for each area, generates an optimal mapping based on that information, and notifies workers and managers. It also collects feedback and optimizes the analysis algorithm.

[0736] Hardware and Software Configuration

[0737] Hardware used

[0738] Server: The central location for data collection, analysis, mapping generation, and notification.

[0739] Devices: Robots used in factories, and smartphones and tablets used by managers.

[0740] Sensors: Includes emotion engines such as voice analysis and heart rate sensors to collect the worker's emotional state.

[0741] Software used

[0742] Data scraping engine: Software for scraping business and cultural information from the internet.

[0743] Database Management System: A system for storing and managing collected data.

[0744] Analysis algorithms: Algorithms for analyzing the data and generating optimal mappings.

[0745] Emotion engine: Software for analyzing the emotional information of workers and managers.

[0746] Notification system: A system for notifying workers and managers of the generated mapping results.

[0747] Processing Details

[0748] The server periodically scrapes business and cultural information from each area using a data communication network and stores it in a database. It also collects characteristic data and emotional data from workers and sends it to the server. Specifically, this data includes the worker's work experience, expertise, past performance, skill level, etc.

[0749] The collected data is analyzed using an analytical algorithm. The server evaluates the business needs of each area based on business and cultural information, and generates an optimal mapping based on the characteristics and emotional data of the workers. For example, if production demand is high in a particular area, a work robot with high processing speed will be deployed in that area.

[0750] The emotion engine analyzes the emotional information of workers and managers, specifically their motivation, stress levels, and mood, using data from voice analysis and heart rate sensors.

[0751] The generated mapping results are sent to the workers and managers via a notification system. Notifications are sent via email and a dedicated dashboard. The managers and workers can then check the results and take action.

[0752] Feedback data from workers and managers is also collected and sent back to the analysis algorithm. This feedback includes actual work results and emotional states. The server analyzes the feedback data and optimizes the algorithm for the next mapping generation.

[0753] Specific examples

[0754] For example, suppose a factory experiences a sudden increase in production demand in a particular area. The server collects this information from the data communication network and stores it in a database. Next, it registers the characteristic data of robots with high processing speeds in the database. The emotion engine also recognizes that the worker operating the robot is highly motivated.

[0755] Based on this information, the analysis algorithm determines that it is optimal to deploy robots with high processing speeds in areas where demand is increasing. The server then notifies the generated mapping results to workers and managers, who then plan their next work.

[0756] The worker then reports the actual work results and their emotional state as feedback. The server analyzes the feedback data and reflects it in the next deployment plan, further improving the accuracy of the deployment.

[0757] Prompt Sentence Examples

[0758] Area: Tokyo

[0759] Demand: IT-related

[0760] Robot Features: High speed processing

[0761] Emotional data: High motivation

[0762] Generate the optimal placement.

[0763] In this way, the present invention aims to realize efficient allocation of work robots and improve production efficiency and the work environment by combining business information, cultural information, and emotional information for each area.

[0764] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0765] Step 1:

[0766] The server uses a data communication network to scrape business and cultural information from each area. The input data is business and cultural information that is publicly available on the Internet, which is periodically accessed and collected. Specifically, a data scraping engine is used to extract the necessary information and store it in a database. This process accumulates the latest business and cultural information in the database.

[0767] Step 2:

[0768] The terminal collects characteristic data of the worker and sends it to the server. The input data includes the worker's work experience, specialized knowledge, past performance, skill level, etc. Specifically, this data is automatically extracted from the factory management system and sent to the server. In this way, the latest characteristic data of the worker is collected on the server.

[0769] Step 3:

[0770] The server uses an emotion engine to collect and analyze the worker's emotional information. The input data is the worker's voice data and biometric data such as heart rate. Specifically, the system performs voice analysis and heart rate analysis and converts the data into text data and numerical data. The output is the worker's emotional state (motivation, stress level, etc.).

[0771] Step 4:

[0772] The server analyzes the collected business information, cultural information, worker characteristics data, and emotion data to generate an optimal mapping. The input data is all the data collected in the previous stage. Specifically, it analyzes the data using an analytical algorithm and calculates the optimal placement of work robots based on the business and production needs of each area. The output is the optimized mapping result.

[0773] Step 5:

[0774] The server notifies the worker and administrator of the generated mapping results. The input data is the generated mapping results. Specifically, the notification system is used to display the mapping results via email or on a dedicated dashboard. This allows the worker and administrator to check the next work plan.

[0775] Step 6:

[0776] Users collect actual work status and feedback and send it to the server. The input data is feedback on work results and emotional state. Specifically, workers and managers enter data through a dedicated feedback form and send it to the server. This collects data for the next improvement.

[0777] Step 7:

[0778] The server analyzes the feedback data and optimizes the analysis algorithm. The input data is the collected feedback data. Specifically, it analyzes the past mapping results and the corresponding feedback and adjusts the parameters of the analysis algorithm. The output is a newly optimized analysis algorithm, which is reflected in the next mapping.

[0779] Through this series of processes, the system dynamically provides optimal placement, improving work efficiency and worker satisfaction.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] [Third embodiment]

[0784] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0785] 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.

[0786] 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).

[0787] 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.

[0788] 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.

[0789] 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).

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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."

[0796] The present invention provides a system for collecting business information and cultural information for each area and generating an optimal mapping based on the characteristics of sales representatives. Specific embodiments will be described below.

[0797] This system consists of a server, terminals, and users. The server plays a central role and is mainly responsible for data collection, analysis, mapping generation, notifications, and optimization. Terminals are devices mainly used by the HR system and sales representatives, and users are sales representatives or managers who use the system to carry out activities.

[0798] Data collection

[0799] The server scrapes business and cultural information for each area from the Internet. For example, the server periodically retrieves economic indexes and information on major industries from the official Tokyo Metropolitan Government website and local information sites, and stores this information in a database. It also collects text data from websites about local culture and lifestyles, and stores this data in a database for analysis.

[0800] The terminal collects characteristic data of sales representatives from the personnel system and sends it to the server. For example, the terminal extracts information such as the sales representative's work experience, expertise, personality, and past performance from the database and transfers it to the server via API.

[0801] Data analysis

[0802] The server applies advanced algorithms to analyze the collected business and cultural information, using statistical methods and natural language processing (NLP) techniques to identify economic indexes and key industry trends, assess the business needs of each area, and evaluate and score the unique characteristics of each region using cultural information.

[0803] The server then analyzes the characteristics of each salesperson and applies a rating model to assess their strengths and weaknesses. This rating model is built based on the salesperson's past performance data, expertise, work experience, etc.

[0804] Mapping Generation

[0805] Based on the analysis results, the server optimally maps the business needs and cultural information of each area, as well as the characteristics of sales representatives. For example, the server may determine that there is high demand for IT-related services in Tokyo, and generate a proposal to assign sales representatives with expertise in the IT field to Tokyo.

[0806] The server notifies salespeople and administrators of the generated mapping results via email and a dedicated dashboard, allowing salespeople to view their new deployment areas.

[0807] Feedback and Optimization

[0808] The user (sales representative) reports the results of their activities at the assigned location to the server as feedback. For example, they input data such as the number of new customers acquired, sales, and customer satisfaction through a dedicated application and send it to the server.

[0809] The server analyzes this feedback data and evaluates the effectiveness of each sales representative's placement. The analysis results are used to optimize the algorithm the next time mapping is generated. For example, if activities in Tokyo are highly successful, the algorithm is adjusted to apply the same sales strategy to other areas with similar characteristics.

[0810] Specific examples

[0811] As a specific example, consider the case where the IT industry in Tokyo is growing rapidly. The server scrapes this information and stores it in a database. Next, the information of salesperson A, who has extensive experience in the IT industry, is also stored in the database. The server's algorithm analyzes the business needs and cultural information of Tokyo, as well as the characteristics of salesperson A, and determines that it is optimal to assign him to Tokyo. The server notifies salesperson A of this mapping result, and he begins his sales activities in Tokyo. After that, the user (salesperson A) reports the results of his activities, and the server analyzes the data and optimizes the next mapping algorithm.

[0812] In this way, the present invention provides efficient and effective people and place mapping.

[0813] The processing flow will be explained below.

[0814] Step 1: Data collection

[0815] The server scrapes business information for each area (e.g., economic indexes, major industries, competitive information, etc.) from the Internet.

[0816] Specific operation: The server uses a crawler to obtain the latest data from official government websites and business-related news sites and stores it in a database.

[0817] The server also scrapes cultural information (e.g., local culture, lifestyle, language, events, etc.).

[0818] Specific operation: The server collects text data from local information sites and tourist association websites and stores it in an analysis database.

[0819] The terminal transmits the characteristics of the sales representative (e.g., work experience, expertise, personality, past performance, etc.) from the personnel system to the server.

[0820] Specific operation: The terminal extracts sales representative information from the personnel database and sends it to the server's API endpoint.

[0821] Step 2: Data analysis

[0822] The server runs algorithms to analyze the collected business information.

[0823] How it works: The server uses text analysis and statistical techniques to extract and index economic indices and trends in key industries.

[0824] The server analyzes the culture information and evaluates the characteristics of each region.

[0825] How it works: The server uses natural language processing (NLP) techniques to analyze text data and score cultural characteristics for each region.

[0826] The server analyzes the characteristic data of the sales representatives.

[0827] Specific operation: The server uses an evaluation model based on data on each sales representative's past performance, expertise, and work experience to score their strengths and weaknesses.

[0828] Step 3: Generate mappings

[0829] The server assesses the demand for each area based on business and cultural information.

[0830] What it does: The server combines business and cultural indexes to create a demand map for each area.

[0831] The server runs an algorithm that matches the characteristics of salespeople with area demand.

[0832] Specific operation: The server performs optimal matching based on the demand map and the sales representative's evaluation score, and generates a placement plan.

[0833] The server notifies the sales representative and the manager of the generated mapping results.

[0834] Specific operation: The server notifies each sales representative and manager of the mapping results via email or dashboard.

[0835] Step 4: Feedback and optimization

[0836] Users (salespeople) send field activity results and feedback to the server.

[0837] Specific operation: The user enters the activity results through a dedicated app or web form and sends them to the server.

[0838] The server analyzes the feedback sent and evaluates the effectiveness of the placement.

[0839] Specific operation: The server analyzes the feedback data, calculates performance indicators (e.g., sales, customer satisfaction, etc.), and evaluates the performance of the algorithm.

[0840] The server optimizes the analysis algorithm based on the feedback.

[0841] Specific operation: The server adjusts the algorithm parameters based on the insights gained from the feedback and reflects these in the next data analysis and mapping creation.

[0842] Example 1

[0843] 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."

[0844] Conventional sales support systems lacked the functionality to efficiently collect business and cultural information for each area and then optimally allocate sales representatives based on that information. As a result, optimal mapping based on the characteristics of sales representatives and area demand was not performed, resulting in a decline in sales efficiency. Furthermore, the functionality to dynamically adjust analysis algorithms based on feedback was insufficient, preventing sufficient optimization of allocation.

[0845] 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.

[0846] In this invention, the server includes: means for scraping business and cultural information for each area from the Internet; means for collecting salesperson characteristics from a database; means for analyzing the collected business information, cultural information, and salesperson characteristics and using statistical methods and natural language processing technology to generate an optimal mapping; means for notifying the salesperson and manager of the generated mapping; and means for receiving activity results as feedback and optimizing the analysis algorithm using regression analysis and Bayesian estimation. This makes it possible to achieve optimal allocation that takes into account the demand in each area and the characteristics of the salesperson, significantly improving sales efficiency.

[0847] "Scraping" is a technique for automatically extracting necessary data from a website's HTML source code.

[0848] "Business information" is information related to economic activity, such as economic indexes and data on major industries in a particular region.

[0849] "Cultural information" is information about the culture, lifestyles, and social characteristics of a particular region.

[0850] "Characteristics of a salesperson" refers to attributes related to sales activities, such as the salesperson's work experience, expertise, personality, and past performance.

[0851] A "database" is a system for efficiently storing and managing large amounts of data.

[0852] "Statistical methods" are mathematical methods for analyzing and evaluating data.

[0853] "Natural language processing technology (NLP)" is a technology that allows computers to analyze and understand human language.

[0854] "Mapping" is a deployment plan that optimally matches the business needs and cultural information of each area with the characteristics of sales representatives.

[0855] "Notification" is a means for informing interested parties of the generated mapping results.

[0856] "Feedback" is the process of inputting data on the results of sales representatives' activities into the system to help improve the analysis algorithm.

[0857] An "analysis algorithm" is a computational procedure for analyzing data and generating an optimal mapping.

[0858] "Regression analysis" is a statistical method for modeling relationships between data.

[0859] "Bayesian estimation" is a statistical method for calculating posterior probabilities based on observed data and estimating unknown parameters.

[0860] The present invention is a system that collects business information and cultural information for each area and generates an optimal mapping based on the characteristics of sales representatives. Specific embodiments will be described below.

[0861] This system consists of a server, terminals, and users. The server plays a central role and is mainly responsible for data collection, analysis, mapping generation, notifications, and optimization. Terminals are devices mainly used by the HR system and sales representatives, and users are sales representatives or managers who use the system to carry out activities.

[0862] Data collection

[0863] The server scrapes business and cultural information for each area from the Internet. For example, the server periodically retrieves economic indexes and information on major industries from official government and regional information sites, analyzes the HTML source code using the BeautifulSoup library, extracts the necessary data, and stores it in a database. It also collects text data from websites about regional culture and lifestyles and stores it in a database for analysis.

[0864] The device collects characteristic data about salespeople from the company's personnel system and sends it to the server. Specifically, it obtains information about the salespeople's work experience, expertise, personality, past performance, etc. via API and transfers it to the server.

[0865] Data analysis

[0866] The server applies advanced algorithms to analyze the collected business and cultural information. Specifically, it applies ARIMA models to identify economic indexes and key industry trends, and evaluates the business needs of each area. Similarly, it uses natural language processing (NLP) techniques to analyze cultural information, tokenize text data, perform TF-IDF vectorization, and score region-specific characteristics.

[0867] The server then inputs the sales representative's characteristic data into an evaluation model to analyze each sales representative's strengths and weaknesses. This evaluation model is built using machine learning algorithms such as random forests and support vector machines (SVMs) based on past performance data, expertise, and work experience.

[0868] Mapping Generation

[0869] Based on the analysis results, the server optimally maps the business needs and cultural information of each area, as well as the characteristics of sales representatives. Specifically, it matches the appropriate sales representative with the area using multidimensional scaling (MDS) and clustering techniques (e.g., k-means clustering). For example, it assesses that there is high demand for IT-related products in Tokyo and generates a proposal to assign sales representatives with the respective strengths to Tokyo.

[0870] The server notifies sales representatives and administrators of the generated mapping results by email using the SMTP protocol and provides an interface where they can check the results in real time on a dedicated dashboard.

[0871] Feedback and Optimization

[0872] Users (salespeople) report the results of their activities at their assigned locations to the server as feedback. Specific feedback data, such as the number of new customers acquired, sales, and customer satisfaction, is entered through a dedicated application and sent to the server via an API.

[0873] The server analyzes this feedback data and evaluates the effectiveness of each sales representative's placement. Statistical methods such as regression analysis and Bayesian estimation are used for the analysis, and the algorithm is optimized the next time a mapping is generated. Methods that produce high results under similar conditions are learned and reflected in the algorithm.

[0874] Specific examples

[0875] Consider the case of Tokyo, where the IT industry is growing rapidly. The server scrapes information from the official government website, analyzes the HTML code using BeautifulSoup, and saves the necessary information in a database. Next, it obtains information about Salesperson A, who has extensive experience in the IT industry, from the human resources system via an API and saves it in the database. The server's algorithm analyzes business needs and cultural information using the ARIMA model and TF-IDF vectorization, and matches this with Salesperson A's characteristics. It then determines that Tokyo is the best place for the assignment and notifies Salesperson A via email and a dashboard. After the assignment, the user (Salesperson A) reports activity results such as the number of new customers acquired and sales data to the server via a dedicated application. The server then analyzes this feedback data using regression analysis and optimizes the next mapping algorithm.

[0876] Prompt Sentence Examples

[0877] "Please assess the IT business needs in Tokyo and generate a mapping proposal for assigning the most suitable sales representatives."

[0878] In this way, the present invention provides efficient and effective people and place mapping.

[0879] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0880] Detailed explanation of the processing steps

[0881] Step 1: Data collection

[0882] The server scrapes business and cultural information for each area from the Internet. Specifically, the server uses the BeautifulSoup library to parse HTML source code from official government websites and local information sites, extracting information on economic indexes and major industries and storing it in a database. For example, information on Tokyo's economic index and major industries is obtained daily and updated regularly. The input is the website's HTML code, and the output is economic and cultural information formatted in JSON format.

[0883] Step 2: Collect data on salesperson characteristics

[0884] The terminal collects sales representative characteristic data from the company's internal human resources system and sends it to the server using an API. Specifically, it obtains sales representative work experience, expertise, personality, and past performance data from the human resources system, converts it into JSON format, and sends it to the server. The input is XML or CSV data from the human resources system, and the output is sales representative data in JSON format, which is sent to the server via the API.

[0885] Step 3: Parse business and cultural information

[0886] The server analyzes the collected business and cultural information. Specifically, it uses an ARIMA model to identify trends in economic indexes and scores the data. It also uses NLP technology to tokenize the cultural information and perform TF-IDF vectorization to evaluate region-specific characteristics. The input is business and cultural information in JSON format, and the output is the score for each area as an analysis result.

[0887] Step 4: Salesperson Profile Analysis

[0888] The server applies machine learning algorithms to analyze sales representative characteristic data. Specifically, it uses random forests and support vector machines (SVMs) to evaluate sales representatives' strengths and weaknesses. This evaluation model is built based on past performance data, specialized knowledge, and work experience. The input is sales representative data in JSON format, and the output is an evaluation score for each sales representative.

[0889] Step 5: Generate the optimal mapping

[0890] Based on the analysis results, the server optimally maps the business needs, cultural information, and characteristics of each salesperson for each area. For example, it uses multidimensional scaling (MDS) or k-means clustering to allocate salespeople to the most suitable areas. The inputs are scores for business and cultural information, and the evaluation scores of salespeople, and the output is an optimal allocation plan for each area.

[0891] Step 6: Notification of mapping results

[0892] The server notifies sales representatives and administrators of the generated mapping results. Notifications are sent by email using the SMTP protocol, and an interface is provided where results can be checked in real time on a dedicated dashboard. The input is the optimal placement plan, and the output is a notification email and updated information on the dashboard.

[0893] Step 7: Feedback and optimization of activity results

[0894] Users (salespeople) report the results of their activities to the server as feedback. They input the number of new customers acquired, sales, customer satisfaction, etc. through a dedicated application and send it to the server via API. The server receives this feedback data, analyzes it using regression analysis and Bayesian estimation, and optimizes the analysis algorithm. The input is the feedback data, and the output is the next optimized mapping algorithm.

[0895] (Application example 1)

[0896] 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."

[0897] Conventional business mapping and security patrol systems struggle to properly consider the specific business needs and crime data of each area and generate optimal personnel and patrol routes. This reduces the efficiency of sales and security activities, resulting in lower satisfaction for businesses and local communities. Furthermore, they lack the ability to dynamically adjust analysis algorithms based on feedback, making long-term optimization difficult.

[0898] 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.

[0899] In this invention, the server includes: means for scraping business and cultural information for each area from the Internet; means for collecting characteristics of sales representatives from a database; means for analyzing the collected business information, cultural information, and characteristics of sales representatives to generate an optimal mapping; means for notifying the sales representatives and managers of the generated mapping; means for receiving feedback and optimizing the analysis algorithm; means for scraping crime data and security-related information for the area from the Internet; means for collecting characteristics of security guards from a database; means for analyzing the collected crime data and security information to generate an optimal patrol route; and means for notifying the security guards and managers of the generated patrol route. This allows the specific needs of each area to be reflected, improving the efficiency of sales and security activities, and further achieving long-term results through dynamic optimization.

[0900] "Business information" refers to data on economic activity and industry in each area, as well as information including corporate trends and market trends.

[0901] "Cultural information" is data about the culture, customs, and lifestyle of a particular region or community.

[0902] "Scraping" is a technique for automatically collecting information that is publicly available on the Internet.

[0903] A "sales representative" is an employee whose role is to sell a company's products or services to customers.

[0904] "Characteristics" refers to data about the attributes and abilities of individual sales representatives and security guards, such as their work experience, expertise, personality, and past performance.

[0905] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[0906] "Analysis" is the process of analyzing collected data using statistical methods and algorithms to extract meaningful information.

[0907] "Mapping" refers to determining optimal placement and correspondence based on collected and analyzed data.

[0908] "Notification" is a means of informing the subject of the generated results.

[0909] "Feedback" is the process of collecting user evaluations and results and using them to help with future improvements.

[0910] An "algorithm" refers to a procedure or computational method for solving a specific problem.

[0911] "Crime data" refers to data that includes crime occurrences in a specific area and detailed information about those crimes.

[0912] "Security-related information" refers to data related to crime prevention measures and risk assessments.

[0913] A "patrol route" refers to the optimized route taken by security guards for patrol.

[0914] The system that realizes this application example consists of a server, terminals, and users. The server plays a central role in collecting data, analyzing it, generating mapping, notifying users, and optimizing it. Terminals are devices mainly used by personnel systems, sales representatives, and security guards, while users refer to the sales representatives or security guards who use the system to carry out their activities, as well as their managers.

[0915] Data collection

[0916] The server scrapes business, cultural, and crime data for each area from the internet. The software used for this is the Python requests library. For example, the required data is obtained from specific APIs (https: / / api.example.com / crime-data, https: / / api.example.com / guards) and stored in a database. Text data on regional culture and lifestyles is also collected from websites and stored in a database for analysis.

[0917] The terminal collects data on the characteristics of sales representatives and security guards from the personnel system and sends it to the server. For example, information such as the sales representative's work experience, expertise, personality, past performance, and the security guard's qualifications and experience is extracted from the database and transferred to the server via API.

[0918] Data analysis

[0919] The server applies advanced algorithms to analyze the collected business, cultural, and crime data. Specifically, it uses statistical methods and natural language processing (NLP) techniques to identify economic indexes and key industry trends, assess the business needs of each area, and evaluate and score the unique characteristics of each area using cultural and crime data.

[0920] The server also analyzes the characteristics of sales representatives and security guards and applies a rating model to assess their strengths and weaknesses. This rating model is generated by clustering based on crime rates and population density in a specific area, standardizing the data using Python's scikit-learn library, and clustering using KMeans.

[0921] Mapping Generation

[0922] Based on the analysis results, the server optimally maps each area's business needs, cultural information, crime data, and the characteristics of sales representatives and security guards. The generated mapping results are notified to sales representatives, security guards, and managers via email and a dedicated dashboard.

[0923] As a specific example, if information is collected that crime rates are rising in the Shinjuku area, the server analyzes that information, evaluates whether the characteristics of the security guards currently in charge of the Shinjuku area are suitable for this area, and assigns patrols to the most suitable security guards.

[0924] Feedback and Optimization

[0925] Users (sales representatives and security guards) report the results of their activities at their assigned locations to the server as feedback. Data such as the number of new customers acquired, sales, customer satisfaction, or reductions in crimes is entered through a dedicated application and sent to the server.

[0926] The server analyzes this feedback data and evaluates the effectiveness of each sales representative and security guard placement. The analysis results are used to optimize the algorithm the next time mapping is generated. For example, if activity in the Shinjuku area is highly successful, the algorithm adjusts to apply the same strategy to other areas with similar characteristics.

[0927] Prompt Sentence Examples

[0928] As a concrete example, the following prompt sentence can be input to a generative AI model:

[0929] Generate Python code for an application that generates optimal security patrol routes based on area crime data and population density. The URLs for the collected data are obtained from https: / / api.example.com / crime-data and https: / / api.example.com / guards. The area data includes crime rate (crime_rate) and population density (population_density).

[0930] In this way, the present invention can provide efficient and effective people and place mapping, greatly improving the efficiency of business and security operations.

[0931] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0932] Step 1:

[0933] Data collection:

[0934] The server scrapes business, cultural, and crime data for each area from the internet. Specifically, it uses the Python requests library to retrieve data from an API (e.g., https: / / api.example.com / crime-data or https: / / api.example.com / guards) and saves it in a database. The URL to be collected using the API is given as input, and the data is obtained in JSON format as output. This is then stored in the database.

[0935] Step 2:

[0936] Feature data collection:

[0937] The terminal collects characteristic data of sales representatives and security guards from the personnel system and sends it to the server. Specifically, it extracts information such as the sales representative's work experience and past performance, and the security guard's qualifications and experience from the database, and transfers it to the server via API. A database query is given as input, and the characteristic data of the sales representatives and security guards is obtained as output in JSON format. This is then transferred to the server.

[0938] Step 3:

[0939] Data Analysis:

[0940] The server analyzes the collected business, cultural, and crime data. It standardizes the data using Python's scikit-learn and performs clustering using KMeans. The standardized data is given as input, and the clustering results are obtained as output. Specifically, the business needs and crime levels of each region are scored and classified into each cluster.

[0941] Step 4:

[0942] Mapping Generation:

[0943] Based on the analysis results, the server optimally maps each area to the characteristics of sales representatives or security guards. The analyzed clustering data and characteristic data of sales representatives and security guards are given as input, and the mapping results are obtained as output. Specifically, it generates the optimal sales representative placement and patrol routes for a specific area.

[0944] Step 5:

[0945] notification:

[0946] The server notifies the generated mapping results to sales representatives, security guards, and managers in real time via email and a dedicated dashboard. The mapping result data is given as input, and a notification message is generated as output. Specifically, each person in charge can check the new deployment and route.

[0947] Step 6:

[0948] Feedback collection:

[0949] Users (sales representatives and security guards) report the results of their activities at their assigned locations to the server as feedback. They input data such as the number of new customers acquired, sales, customer satisfaction, and reductions in crimes through a dedicated application. Data manually entered by the user is given as input, and feedback data is obtained as output. This is then sent to the server.

[0950] Step 7:

[0951] Algorithm optimization:

[0952] The server analyzes the feedback data and optimizes the algorithm for the next mapping generation. The feedback data is given as input and an optimized algorithm is generated as output. Specifically, it adjusts activities in similar areas based on successful cases and derives effective placements and routes.

[0953] The above processing steps make it possible to reflect the specific needs of each area and significantly improve the efficiency of sales and security activities.

[0954] 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.

[0955] The present invention provides a system that collects business information and cultural information for each area and generates an optimal mapping by taking into account the emotional information of sales representatives and users. Specific embodiments will be described below.

[0956] This system consists of a server, terminals, users, and an emotion engine. The server plays a central role in collecting data, analyzing it, generating mappings, notifying users, and optimizing the system. Terminals are devices primarily used by the human resources system and sales representatives. Users are sales representatives or managers who use the system to carry out their activities, and the emotion engine recognizes and analyzes the user's emotions.

[0957] Data collection

[0958] The server periodically scrapes business information (e.g., economic indexes, major industries, competitive information, etc.) for each area from the Internet and stores it in a database. It also scrapes cultural information (e.g., local culture, lifestyles, language, events, etc.) and stores it in a database for analysis.

[0959] The terminal collects characteristic data of sales representatives (e.g., work experience, expertise, personality, past performance, etc.) from the personnel system and transmits it to the server.

[0960] Data analysis

[0961] The server applies data analysis algorithms to analyze the collected business and cultural information. Specifically, it analyzes economic indexes and trends in major industries to assess the business needs of each area. Similarly, it evaluates the characteristics of each region based on cultural information.

[0962] The server also applies an evaluation model to analyze the salesperson's characteristic data, which analyzes the salesperson's past performance, expertise, and work experience to evaluate their strengths and weaknesses.

[0963] The emotion engine recognizes and analyzes user emotions. For example, it analyzes the mood and motivation of salespeople using text and voice analysis to generate emotion data.

[0964] Mapping Generation

[0965] The server evaluates demand in each area based on business and cultural information, and generates optimal mapping based on the characteristics and emotional data of sales representatives. For example, the server determines that IT-related demand is high in Tokyo, and proposes the placement of sales representative A, who has strengths in the IT field, in Tokyo so that he can work most effectively.

[0966] The server then notifies sales representatives and managers of the generated mapping results via email and a dedicated dashboard.

[0967] Feedback and Optimization

[0968] Users (salespeople) report the results of their field activities and feedback to the server, including data such as sales performance and customer reactions.

[0969] The server analyzes the feedback data to evaluate the effectiveness of the placement. It also incorporates emotion data provided by the emotion engine. Based on this data, it optimizes the next mapping algorithm.

[0970] Specific examples

[0971] For example, if there is a surge in demand for the IT industry in Tokyo, the server scrapes that information and stores it in a database. Next, the information of salesperson A, who has extensive experience in the IT industry, is also registered in the database. The emotion engine also analyzes salesperson A's emotions and identifies that he is highly motivated.

[0972] The server's algorithm analyzes the business needs and cultural information of Tokyo, as well as the characteristics and emotional data of sales representative A, and determines that it is best to assign him to Tokyo. The server notifies sales representative A of the generated mapping results, and he begins his sales activities in Tokyo.

[0973] After that, the user (Salesperson A) reports the results of their activities and their emotional state as feedback. The server analyzes this data and reflects it in the next mapping, further improving the accuracy of the placement.

[0974] In this way, the present invention is a system that realizes more effective and personalized sales representative mapping by adding user emotional information.

[0975] The processing flow will be explained below.

[0976] Step 1: Data collection

[0977] The server scrapes business information for each area (e.g., economic indexes, major industries, competitive information, etc.) from the Internet.

[0978] Specific operation: The server uses a crawler to periodically collect the latest data from official government websites and business-related news sites and store it in a database.

[0979] The server also scrapes cultural information (e.g., local culture, lifestyle, language, events, etc.).

[0980] Specific operation: The server collects text data from local information sites and tourist association websites and stores it in an analysis database.

[0981] The terminal transmits characteristic data of the sales representative (e.g., work experience, expertise, personality, past performance, etc.) from the personnel system to the server.

[0982] Specific operation: The terminal extracts sales representative information from the personnel database via API and stores it in the server database.

[0983] Step 2: Collecting Emotional Data

[0984] The user (salesperson) inputs his / her own feelings in daily activities.

[0985] Specific operation: The user selects and enters their emotional state from a list using a dedicated app or a web form.

[0986] The emotion engine automatically analyzes emotions from the user's voice and text.

[0987] How it works: The emotion engine uses emotion analysis algorithms to analyze voice and text data in real time and generate an emotion score.

[0988] Step 3: Data analysis

[0989] The server runs algorithms to analyze the collected business information.

[0990] Specific operation: The server extracts business indexes and trends of major industries using statistical methods and text analysis, and evaluates the business needs of each area.

[0991] The server analyzes the culture information and evaluates the characteristics of each region.

[0992] Specific operation: The server uses natural language processing (NLP) technology to extract region-specific characteristics from text data and assigns an evaluation score.

[0993] The server analyzes the characteristic data of the sales representative based on the evaluation model.

[0994] Specific operation: The server applies a model to score past performance data, expertise, and work experience, and evaluates each employee.

[0995] The server analyzes the emotion data from the emotion engine and makes a comprehensive evaluation.

[0996] Specific operation: The emotion scores provided by the emotion engine are integrated and analyzed taking into account the salesperson's current psychological state.

[0997] Step 4: Mapping Generation

[0998] The server evaluates the demand in each area based on business information, cultural information, characteristics of sales representatives, and emotional data, and generates an optimal mapping.

[0999] Specific operation: The server runs a matching algorithm based on the evaluation scores to determine the optimal combination of sales representative and area.

[1000] The server notifies the sales representative and the manager of the generated mapping results.

[1001] Specific operation: The server sends the results to sales representatives and managers via email notifications or dedicated dashboards.

[1002] Step 5: Feedback and optimization

[1003] Users (salespeople) send field activity results and feedback to the server.

[1004] Specific operation: The user enters performance data (e.g., sales, customer satisfaction, etc.) and emotional feedback through a dedicated app or web form and sends them to the server.

[1005] The server analyzes the transmitted feedback data and evaluates the effectiveness of the deployment.

[1006] Specific Operation: The server uses an analytical algorithm to analyze the feedback data and evaluate changes in the salesperson's performance and emotional state.

[1007] The server optimizes the analysis algorithm based on the feedback and sentiment data.

[1008] Specific operation: Based on the insights gained from the feedback and emotion data, the server adjusts the parameters of the matching algorithm and reflects the results in the next mapping.

[1009] Example 2

[1010] 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."

[1011] In modern sales activities, it is difficult to effectively collect local business and cultural information and optimally assign sales representatives based on that information. Furthermore, conventional systems cannot take into account the emotional information of sales representatives, resulting in inefficient mapping. As a result, sales activities are not fully effective and sales performance declines.

[1012] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for scraping business information and cultural information for each area from the Internet, means for collecting salesperson characteristics from an information management system, means for analyzing the collected business information, cultural information, and salesperson characteristic data to generate an optimal mapping, means for analyzing user emotion data and reflecting it in the mapping, means for notifying the salesperson and manager of the generated mapping, and means for receiving feedback and optimizing the analysis algorithm. This enables more effective and optimal salesperson allocation that takes into account local business needs and salesperson emotion information.

[1013] "Business Information" refers to economic data, such as economic indexes, key industries, and competitive information, relating to a particular region or industry.

[1014] "Cultural information" refers to social and cultural data such as local culture, lifestyles, language, and events.

[1015] "Internet scraping" refers to techniques and tools used to automatically extract information from websites on the Internet.

[1016] "Characteristics of a salesperson" refers to individual data such as the salesperson's work experience, expertise, personality, and past performance.

[1017] An "information management system" refers to software or a platform for managing and operating data held by a company or organization.

[1018] "Analysis methods" refer to the technologies and algorithms used to find and evaluate relationships and patterns based on collected data.

[1019] "Means for generating optimal mapping" refers to technologies and algorithms that use analyzed data to place sales representatives in the optimal areas and to the optimal customers.

[1020] "User emotion data" refers to data that represents the mood and motivation of salespeople and other users.

[1021] "Notification means" refers to the technology and tools used to communicate the generated mapping results to sales representatives and managers.

[1022] "Means of receiving feedback" refers to the techniques and tools used to collect the results of sales activities and opinions and feedback from sales representatives.

[1023] "Means for optimizing the analysis algorithm" refers to techniques and methods for improving the accuracy and effectiveness of the analysis algorithm based on collected feedback data.

[1024] The present invention relates to a system that collects business information and cultural information for each area and generates an optimal mapping by taking into account the characteristics of sales representatives and emotional information of users. Specific embodiments will be described below.

[1025] System Configuration

[1026] This system consists of a server, terminals, users, and an emotion engine. The server plays a central role in collecting data, analyzing it, generating mappings, notifying users, and optimizing the results. Terminals are devices primarily used by salespeople. Users are salespeople or managers who use the system to carry out their activities, and the emotion engine recognizes and analyzes users' emotions.

[1027] Data collection

[1028] The server periodically scrapes business and cultural information for each area from the Internet. The software used is the Python Scrapy framework. This method collects data such as economic indexes, major industries, competitive information, and local culture and events, and stores it in a MongoDB database. The terminal also collects sales representative characteristic data (work experience, expertise, personality, past performance, etc.) from an information management system (e.g., an HR management tool) and sends it to the server via HTTP.

[1029] Data analysis

[1030] The server analyzes the collected business and cultural information using Pandas and Scikit-learn. Specifically, it analyzes trends in economic indexes for each area, evaluates the competitive situation in major industries, and extracts regional characteristics. To analyze salesperson characteristic data, it also builds an evaluation model (e.g., a logistic regression model) using Scikit-learn to evaluate the salesperson's strengths and weaknesses. Furthermore, the emotion engine recognizes and analyzes user emotions using the Google Cloud Speech-to-Text API for voice analysis and the NLTK library for text analysis. This analysis generates emotion data that indicates the salesperson's mood and motivation.

[1031] Mapping Generation

[1032] The server evaluates demand in each area based on the analyzed business information, cultural information, and sales representative characteristic and emotional data, and generates an optimal mapping. This process uses the SciPy linear algebra package. For example, the server determines that IT-related demand is high in Tokyo, and decides that it would be optimal to assign sales representative A, who has strengths in the IT field, to Tokyo. The generated mapping results are notified to sales representatives and managers via email or a dedicated dashboard (e.g., Tableau).

[1033] Feedback and Optimization

[1034] Users (salespeople) report their field activity results and feedback to the server. This includes data such as sales performance, customer reactions, and self-emotional evaluations. Feedback is entered via a mobile app or web portal and sent to the server. The server analyzes the reported feedback data using Apache Hadoop and Spark to optimize the next mapping algorithm. This results in more accurate placement that reflects the user's emotional data and feedback.

[1035] Specific examples

[1036] If there is a surge in demand for the IT industry in Tokyo, the server uses Scrapy to collect that information and stores it in a MongoDB database. Data about Salesperson A's extensive experience in the IT field, collected from SAP SuccessFactors, is also received via HTTP and added to the database. The emotion engine also uses the Google Cloud Speech-to-Text API and NLTK to identify that Salesperson A has high motivation. The server analyzes this data using Pandas and Scikit-learn, combining IT demand with Salesperson A's characteristic information, and determines that it is optimal to assign A to Tokyo. The results are notified on a Tableau dashboard, and Salesperson A begins sales activities in Tokyo. By reporting the results of the activities and the salesperson's own emotional state as feedback via a mobile app, the server improves the accuracy of the mapping for the next time.

[1037] Specific examples of prompts to be input to generative AI models

[1038] Based on the following text, select the sales representative who best suits the business needs in the IT industry in Tokyo, and generate the optimal placement proposal taking into account emotional information.

[1039] (Tokyo business information)

[1040] IT-related demand surges

[1041] (Cultural information)

[1042] Many highly skilled professionals

[1043] (Characteristic data of Salesperson A)

[1044] Extensive experience in the IT field

[1045] Past performance is excellent

[1046] (Salesperson A's emotional data)

[1047] Maintain high motivation

[1048] Please output the results in a table format and provide a bulleted list of reasons for your recommendation.

[1049] The system adds user emotional information to enable more effective and personalized sales representative mapping.

[1050] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1051] Step 1:

[1052] The server scrapes business and cultural information for each area from the Internet. The software used is the Python Scrapy framework. Specifically, the server periodically crawls web pages to collect data such as economic indexes, major industries, competitive information, and local culture and events. The collected data is stored in a MongoDB database.

[1053] Input: List of web page URLs

[1054] Data Processing: Web Scraping with Scrapy

[1055] Output: Business and cultural information stored in a MongoDB database

[1056] Step 2:

[1057] The terminal collects sales representative characteristic data from the HR system. The device used is a Windows PC or mobile terminal, and the software is an HR management tool (e.g., SAP SuccessFactors). The collected data is sent to the server using the HTTP protocol.

[1058] Input: characteristic data about salespeople (work experience, expertise, personality, past performance)

[1059] Data processing: None (data transfer)

[1060] Output: Salesperson characteristics data sent to the server

[1061] Step 3:

[1062] The server uses Pandas and Scikit-learn to analyze the collected business and cultural information, specifically analyzing trends in economic indexes, assessing the competitive situation in major industries, and extracting regional characteristics.

[1063] Input: Business and cultural information stored in a MongoDB database

[1064] Data processing: Data preprocessing using Pandas, trend analysis and evaluation using Scikit-learn

[1065] Output: Evaluation data of business needs and regional characteristics for each area

[1066] Step 4:

[1067] The server applies a rating model to analyze the sales representative characteristic data. The model, built using Scikit-learn, assesses each representative's strengths and weaknesses based on their past performance and areas of expertise.

[1068] Input: Salesperson characteristics data sent to the server

[1069] Data processing: Model evaluation and analysis with Scikit-learn

[1070] Output: Salesperson strengths and weaknesses evaluation data

[1071] Step 5:

[1072] The emotion engine recognizes and analyzes user emotions, using the Google Cloud Speech-to-Text API for speech analysis and the NLTK library for text analysis to generate emotional data that assesses the mood and motivation of salespeople.

[1073] Input: User voice and text data

[1074] Data processing: Speech analysis with Google Cloud Speech-to-Text API, text analysis with NLTK

[1075] Output: Emotion data

[1076] Step 6:

[1077] The server evaluates the demand for each area based on the analyzed business information, cultural information, salesperson characteristics data, and sentiment data, and generates an optimal mapping. It uses the linear algebra package in SciPy to run the algorithm and calculate the optimal placement.

[1078] Input: Business information, cultural information, salesperson characteristics data, emotion data

[1079] Data processing: Demand assessment and mapping generation using algorithms in SciPy

[1080] Output: Optimal mapping data

[1081] Step 7:

[1082] The server notifies sales representatives and managers of the generated mapping results via email or a dedicated dashboard (e.g., Tableau).

[1083] Input: Optimal mapping data

[1084] Data processing: Converting data into notification format

[1085] Output: Email and dashboard notifications

[1086] Step 8:

[1087] Users (salespeople) report field activity results and feedback to the server, which is entered via a mobile app or web portal.

[1088] Input: Sales performance, customer response, self-emotion evaluation

[1089] Data processing: None (data transfer)

[1090] Output: Feedback data sent to the server

[1091] Step 9:

[1092] The server analyzes the reported feedback data using Apache Hadoop and Spark to evaluate the effectiveness of the placement and optimize the next mapping algorithm.

[1093] Input: Feedback data

[1094] Data Processing: Data Analysis using Hadoop and Spark

[1095] Output: Optimized mapping algorithm

[1096] In this way, data analysis incorporating user emotional information and optimal mapping are performed, maximizing the effectiveness of sales activities.

[1097] (Application example 2)

[1098] 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."

[1099] The present invention relates to a system for automatically generating optimal worker allocations based on the business needs and cultural characteristics of each area, thereby achieving efficient business operations. In particular, there is a demand for optimal allocation of work robots and workers within factories to improve production efficiency and worker satisfaction. Conventional systems have difficulty fully considering the characteristics and emotional information of workers, resulting in an inability to achieve optimal allocation.

[1100] The specific processing by the specific 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 scraping business information and cultural information for each area from a data communication network, means for collecting worker characteristics from an information base, means for analyzing the collected business information, cultural information, and worker characteristics to generate an optimal mapping, means for collecting production information, area characteristics, machine performance information, and emotion information for each area and storing them in a database, means for notifying workers and managers of the generated mapping, and means for receiving feedback and optimizing the analysis algorithm. This enables optimal allocation taking into account the production needs, machine performance, and emotion information of each area.

[1101] "Business information" refers to data related to business and work in each area, including economic indicators, major industries, competitive information, production status, etc.

[1102] "Cultural information" refers to data on the unique culture, lifestyle, language, events, etc. of each area.

[1103] "Characteristics of the worker" refers to data such as the worker's work experience, expertise, personality, past performance, skill level, etc.

[1104] "Data communications network" means an infrastructure for the transmission of data, including the Internet and other networks.

[1105] "Scraping" refers to the technology and methods of automatically collecting necessary information from a website.

[1106] An "information base" refers to a storage device or system such as a database in which data and information are stored.

[1107] "Production information for each area" refers to data related to production at factories and manufacturing sites, specifically including production volume, operating rate, maintenance status, etc.

[1108] "Area characteristics" refers to the characteristics and conditions unique to a particular region or area, including geographical conditions, climate, infrastructure conditions, etc.

[1109] "Machine performance information" refers to data on the performance of machines and equipment used within a factory, including, specifically, processing speed, operating hours, and failure history.

[1110] "Emotional information" refers to data related to the emotions and mental state of workers and managers, and specifically includes motivation, stress levels, mood, etc.

[1111] "Optimal mapping" refers to a deployment plan for allocating workers and machines to optimal locations based on collected and analyzed data.

[1112] "Feedback" refers to workers and managers reporting actual work results, opinions, and feelings to the server.

[1113] "Analysis algorithm" refers to the calculation methods and rules used to analyze collected data and derive optimal placement and areas for improvement.

[1114] The present invention is a system that automatically achieves optimal placement of work robots within a factory. Specific embodiments are described below. This system collects business and cultural information for each area, generates an optimal mapping based on that information, and notifies workers and managers. It also collects feedback and optimizes the analysis algorithm.

[1115] Hardware and Software Configuration

[1116] Hardware used

[1117] Server: The central location for data collection, analysis, mapping generation, and notification.

[1118] Devices: Robots used in factories, and smartphones and tablets used by managers.

[1119] Sensors: Includes emotion engines such as voice analysis and heart rate sensors to collect the worker's emotional state.

[1120] Software used

[1121] Data scraping engine: Software for scraping business and cultural information from the internet.

[1122] Database Management System: A system for storing and managing collected data.

[1123] Analysis algorithms: Algorithms for analyzing the data and generating optimal mappings.

[1124] Emotion engine: Software for analyzing the emotional information of workers and managers.

[1125] Notification system: A system for notifying workers and managers of the generated mapping results.

[1126] Processing Details

[1127] The server periodically scrapes business and cultural information from each area using a data communication network and stores it in a database. It also collects characteristic data and emotional data from workers and sends it to the server. Specifically, this data includes the worker's work experience, expertise, past performance, skill level, etc.

[1128] The collected data is analyzed using an analytical algorithm. The server evaluates the business needs of each area based on business and cultural information, and generates an optimal mapping based on the characteristics and emotional data of the workers. For example, if production demand is high in a particular area, a work robot with high processing speed will be deployed in that area.

[1129] The emotion engine analyzes the emotional information of workers and managers, specifically their motivation, stress levels, and mood, using data from voice analysis and heart rate sensors.

[1130] The generated mapping results are sent to the workers and managers via a notification system. Notifications are sent via email and a dedicated dashboard. The managers and workers can then check the results and take action.

[1131] Feedback data from workers and managers is also collected and sent back to the analysis algorithm. This feedback includes actual work results and emotional states. The server analyzes the feedback data and optimizes the algorithm for the next mapping generation.

[1132] Specific examples

[1133] For example, suppose a factory experiences a sudden increase in production demand in a particular area. The server collects this information from the data communication network and stores it in a database. Next, it registers the characteristic data of robots with high processing speeds in the database. The emotion engine also recognizes that the worker operating the robot is highly motivated.

[1134] Based on this information, the analysis algorithm determines that it is optimal to deploy robots with high processing speeds in areas where demand is increasing. The server then notifies the generated mapping results to workers and managers, who then plan their next work.

[1135] The worker then reports the actual work results and their emotional state as feedback. The server analyzes the feedback data and reflects it in the next deployment plan, further improving the accuracy of the deployment.

[1136] Prompt Sentence Examples

[1137] Area: Tokyo

[1138] Demand: IT-related

[1139] Robot Features: High speed processing

[1140] Emotional data: High motivation

[1141] Generate the optimal placement.

[1142] In this way, the present invention aims to realize efficient allocation of work robots and improve production efficiency and the work environment by combining business information, cultural information, and emotional information for each area.

[1143] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1144] Step 1:

[1145] The server uses a data communication network to scrape business and cultural information from each area. The input data is business and cultural information that is publicly available on the Internet, which is periodically accessed and collected. Specifically, a data scraping engine is used to extract the necessary information and store it in a database. This process accumulates the latest business and cultural information in the database.

[1146] Step 2:

[1147] The terminal collects characteristic data of the worker and sends it to the server. The input data includes the worker's work experience, specialized knowledge, past performance, skill level, etc. Specifically, this data is automatically extracted from the factory management system and sent to the server. In this way, the latest characteristic data of the worker is collected on the server.

[1148] Step 3:

[1149] The server uses an emotion engine to collect and analyze the worker's emotional information. The input data is the worker's voice data and biometric data such as heart rate. Specifically, the system performs voice analysis and heart rate analysis and converts the data into text data and numerical data. The output is the worker's emotional state (motivation, stress level, etc.).

[1150] Step 4:

[1151] The server analyzes the collected business information, cultural information, worker characteristics data, and emotion data to generate an optimal mapping. The input data is all the data collected in the previous stage. Specifically, it analyzes the data using an analytical algorithm and calculates the optimal placement of work robots based on the business and production needs of each area. The output is the optimized mapping result.

[1152] Step 5:

[1153] The server notifies the worker and administrator of the generated mapping results. The input data is the generated mapping results. Specifically, the notification system is used to display the mapping results via email or on a dedicated dashboard. This allows the worker and administrator to check the next work plan.

[1154] Step 6:

[1155] Users collect actual work status and feedback and send it to the server. The input data is feedback on work results and emotional state. Specifically, workers and managers enter data through a dedicated feedback form and send it to the server. This collects data for the next improvement.

[1156] Step 7:

[1157] The server analyzes the feedback data and optimizes the analysis algorithm. The input data is the collected feedback data. Specifically, it analyzes the past mapping results and the corresponding feedback and adjusts the parameters of the analysis algorithm. The output is a newly optimized analysis algorithm, which is reflected in the next mapping.

[1158] Through this series of processes, the system dynamically provides optimal placement, improving work efficiency and worker satisfaction.

[1159] 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.

[1160] 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.

[1161] 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.

[1162] [Fourth embodiment]

[1163] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1164] 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.

[1165] 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).

[1166] 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.

[1167] 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.

[1168] 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).

[1169] 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.

[1170] 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.

[1171] 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.

[1172] 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.

[1173] 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.

[1174] 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.

[1175] 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."

[1176] The present invention provides a system for collecting business information and cultural information for each area and generating an optimal mapping based on the characteristics of sales representatives. Specific embodiments will be described below.

[1177] This system consists of a server, terminals, and users. The server plays a central role and is mainly responsible for data collection, analysis, mapping generation, notifications, and optimization. Terminals are devices mainly used by the HR system and sales representatives, and users are sales representatives or managers who use the system to carry out activities.

[1178] Data collection

[1179] The server scrapes business and cultural information for each area from the Internet. For example, the server periodically retrieves economic indexes and information on major industries from the official Tokyo Metropolitan Government website and local information sites, and stores this information in a database. It also collects text data from websites about local culture and lifestyles, and stores this data in a database for analysis.

[1180] The terminal collects characteristic data of sales representatives from the personnel system and sends it to the server. For example, the terminal extracts information such as the sales representative's work experience, expertise, personality, and past performance from the database and transfers it to the server via API.

[1181] Data analysis

[1182] The server applies advanced algorithms to analyze the collected business and cultural information, using statistical methods and natural language processing (NLP) techniques to identify economic indexes and key industry trends, assess the business needs of each area, and evaluate and score the unique characteristics of each region using cultural information.

[1183] The server then analyzes the characteristics of each salesperson and applies a rating model to assess their strengths and weaknesses. This rating model is built based on the salesperson's past performance data, expertise, work experience, etc.

[1184] Mapping Generation

[1185] Based on the analysis results, the server optimally maps the business needs and cultural information of each area, as well as the characteristics of sales representatives. For example, the server may determine that there is high demand for IT-related services in Tokyo, and generate a proposal to assign sales representatives with expertise in the IT field to Tokyo.

[1186] The server notifies salespeople and administrators of the generated mapping results via email and a dedicated dashboard, allowing salespeople to view their new deployment areas.

[1187] Feedback and Optimization

[1188] The user (sales representative) reports the results of their activities at the assigned location to the server as feedback. For example, they input data such as the number of new customers acquired, sales, and customer satisfaction through a dedicated application and send it to the server.

[1189] The server analyzes this feedback data and evaluates the effectiveness of each sales representative's placement. The analysis results are used to optimize the algorithm the next time mapping is generated. For example, if activities in Tokyo are highly successful, the algorithm is adjusted to apply the same sales strategy to other areas with similar characteristics.

[1190] Specific examples

[1191] As a specific example, consider the case where the IT industry in Tokyo is growing rapidly. The server scrapes this information and stores it in a database. Next, the information of salesperson A, who has extensive experience in the IT industry, is also stored in the database. The server's algorithm analyzes the business needs and cultural information of Tokyo, as well as the characteristics of salesperson A, and determines that it is optimal to assign him to Tokyo. The server notifies salesperson A of this mapping result, and he begins his sales activities in Tokyo. After that, the user (salesperson A) reports the results of his activities, and the server analyzes the data and optimizes the next mapping algorithm.

[1192] In this way, the present invention provides efficient and effective people and place mapping.

[1193] The processing flow will be explained below.

[1194] Step 1: Data collection

[1195] The server scrapes business information for each area (e.g., economic indexes, major industries, competitive information, etc.) from the Internet.

[1196] Specific operation: The server uses a crawler to obtain the latest data from official government websites and business-related news sites and stores it in a database.

[1197] The server also scrapes cultural information (e.g., local culture, lifestyle, language, events, etc.).

[1198] Specific operation: The server collects text data from local information sites and tourist association websites and stores it in an analysis database.

[1199] The terminal transmits the characteristics of the sales representative (e.g., work experience, expertise, personality, past performance, etc.) from the personnel system to the server.

[1200] Specific operation: The terminal extracts sales representative information from the personnel database and sends it to the server's API endpoint.

[1201] Step 2: Data analysis

[1202] The server runs algorithms to analyze the collected business information.

[1203] How it works: The server uses text analysis and statistical techniques to extract and index economic indices and trends in key industries.

[1204] The server analyzes the culture information and evaluates the characteristics of each region.

[1205] How it works: The server uses natural language processing (NLP) techniques to analyze text data and score cultural characteristics for each region.

[1206] The server analyzes the characteristic data of the sales representatives.

[1207] Specific operation: The server uses an evaluation model based on data on each sales representative's past performance, expertise, and work experience to score their strengths and weaknesses.

[1208] Step 3: Generate mappings

[1209] The server assesses the demand for each area based on business and cultural information.

[1210] What it does: The server combines business and cultural indexes to create a demand map for each area.

[1211] The server runs an algorithm that matches the characteristics of salespeople with area demand.

[1212] Specific operation: The server performs optimal matching based on the demand map and the sales representative's evaluation score, and generates a placement plan.

[1213] The server notifies the sales representative and the manager of the generated mapping results.

[1214] Specific operation: The server notifies each sales representative and manager of the mapping results via email or dashboard.

[1215] Step 4: Feedback and optimization

[1216] Users (salespeople) send field activity results and feedback to the server.

[1217] Specific operation: The user enters the activity results through a dedicated app or web form and sends them to the server.

[1218] The server analyzes the feedback sent and evaluates the effectiveness of the placement.

[1219] Specific operation: The server analyzes the feedback data, calculates performance indicators (e.g., sales, customer satisfaction, etc.), and evaluates the performance of the algorithm.

[1220] The server optimizes the analysis algorithm based on the feedback.

[1221] Specific operation: The server adjusts the algorithm parameters based on the insights gained from the feedback and reflects these in the next data analysis and mapping creation.

[1222] Example 1

[1223] 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."

[1224] Conventional sales support systems lacked the functionality to efficiently collect business and cultural information for each area and then optimally allocate sales representatives based on that information. As a result, optimal mapping based on the characteristics of sales representatives and area demand was not performed, resulting in a decline in sales efficiency. Furthermore, the functionality to dynamically adjust analysis algorithms based on feedback was insufficient, preventing sufficient optimization of allocation.

[1225] 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.

[1226] In this invention, the server includes: means for scraping business and cultural information for each area from the Internet; means for collecting salesperson characteristics from a database; means for analyzing the collected business information, cultural information, and salesperson characteristics and using statistical methods and natural language processing technology to generate an optimal mapping; means for notifying the salesperson and manager of the generated mapping; and means for receiving activity results as feedback and optimizing the analysis algorithm using regression analysis and Bayesian estimation. This makes it possible to achieve optimal allocation that takes into account the demand in each area and the characteristics of the salesperson, significantly improving sales efficiency.

[1227] "Scraping" is a technique for automatically extracting necessary data from a website's HTML source code.

[1228] "Business information" is information related to economic activity, such as economic indexes and data on major industries in a particular region.

[1229] "Cultural information" is information about the culture, lifestyles, and social characteristics of a particular region.

[1230] "Characteristics of a salesperson" refers to attributes related to sales activities, such as the salesperson's work experience, expertise, personality, and past performance.

[1231] A "database" is a system for efficiently storing and managing large amounts of data.

[1232] "Statistical methods" are mathematical methods for analyzing and evaluating data.

[1233] "Natural language processing technology (NLP)" is a technology that allows computers to analyze and understand human language.

[1234] "Mapping" is a deployment plan that optimally matches the business needs and cultural information of each area with the characteristics of sales representatives.

[1235] "Notification" is a means for informing interested parties of the generated mapping results.

[1236] "Feedback" is the process of inputting data on the results of sales representatives' activities into the system to help improve the analysis algorithm.

[1237] An "analysis algorithm" is a computational procedure for analyzing data and generating an optimal mapping.

[1238] "Regression analysis" is a statistical method for modeling relationships between data.

[1239] "Bayesian estimation" is a statistical method for calculating posterior probabilities based on observed data and estimating unknown parameters.

[1240] The present invention is a system that collects business information and cultural information for each area and generates an optimal mapping based on the characteristics of sales representatives. Specific embodiments will be described below.

[1241] This system consists of a server, terminals, and users. The server plays a central role and is mainly responsible for data collection, analysis, mapping generation, notifications, and optimization. Terminals are devices mainly used by the HR system and sales representatives, and users are sales representatives or managers who use the system to carry out activities.

[1242] Data collection

[1243] The server scrapes business and cultural information for each area from the Internet. For example, the server periodically retrieves economic indexes and information on major industries from official government and regional information sites, analyzes the HTML source code using the BeautifulSoup library, extracts the necessary data, and stores it in a database. It also collects text data from websites about regional culture and lifestyles and stores it in a database for analysis.

[1244] The device collects characteristic data about salespeople from the company's personnel system and sends it to the server. Specifically, it obtains information about the salespeople's work experience, expertise, personality, past performance, etc. via API and transfers it to the server.

[1245] Data analysis

[1246] The server applies advanced algorithms to analyze the collected business and cultural information. Specifically, it applies ARIMA models to identify economic indexes and key industry trends, and evaluates the business needs of each area. Similarly, it uses natural language processing (NLP) techniques to analyze cultural information, tokenize text data, perform TF-IDF vectorization, and score region-specific characteristics.

[1247] The server then inputs the sales representative's characteristic data into an evaluation model to analyze each sales representative's strengths and weaknesses. This evaluation model is built using machine learning algorithms such as random forests and support vector machines (SVMs) based on past performance data, expertise, and work experience.

[1248] Mapping Generation

[1249] Based on the analysis results, the server optimally maps the business needs and cultural information of each area, as well as the characteristics of sales representatives. Specifically, it matches the appropriate sales representative with the area using multidimensional scaling (MDS) and clustering techniques (e.g., k-means clustering). For example, it assesses that there is high demand for IT-related products in Tokyo and generates a proposal to assign sales representatives with the respective strengths to Tokyo.

[1250] The server notifies sales representatives and administrators of the generated mapping results by email using the SMTP protocol and provides an interface where they can check the results in real time on a dedicated dashboard.

[1251] Feedback and Optimization

[1252] Users (salespeople) report the results of their activities at their assigned locations to the server as feedback. Specific feedback data, such as the number of new customers acquired, sales, and customer satisfaction, is entered through a dedicated application and sent to the server via an API.

[1253] The server analyzes this feedback data and evaluates the effectiveness of each sales representative's placement. Statistical methods such as regression analysis and Bayesian estimation are used for the analysis, and the algorithm is optimized the next time a mapping is generated. Methods that produce high results under similar conditions are learned and reflected in the algorithm.

[1254] Specific examples

[1255] Consider the case of Tokyo, where the IT industry is growing rapidly. The server scrapes information from the official government website, analyzes the HTML code using BeautifulSoup, and saves the necessary information in a database. Next, it obtains information about Salesperson A, who has extensive experience in the IT industry, from the human resources system via an API and saves it in the database. The server's algorithm analyzes business needs and cultural information using the ARIMA model and TF-IDF vectorization, and matches this with Salesperson A's characteristics. It then determines that Tokyo is the best place for the assignment and notifies Salesperson A via email and a dashboard. After the assignment, the user (Salesperson A) reports activity results such as the number of new customers acquired and sales data to the server via a dedicated application. The server then analyzes this feedback data using regression analysis and optimizes the next mapping algorithm.

[1256] Prompt Sentence Examples

[1257] "Please assess the IT business needs in Tokyo and generate a mapping proposal for assigning the most suitable sales representatives."

[1258] In this way, the present invention provides efficient and effective people and place mapping.

[1259] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1260] Detailed explanation of the processing steps

[1261] Step 1: Data collection

[1262] The server scrapes business and cultural information for each area from the Internet. Specifically, the server uses the BeautifulSoup library to parse HTML source code from official government websites and local information sites, extracting information on economic indexes and major industries and storing it in a database. For example, information on Tokyo's economic index and major industries is obtained daily and updated regularly. The input is the website's HTML code, and the output is economic and cultural information formatted in JSON format.

[1263] Step 2: Collect data on salesperson characteristics

[1264] The terminal collects sales representative characteristic data from the company's internal human resources system and sends it to the server using an API. Specifically, it obtains sales representative work experience, expertise, personality, and past performance data from the human resources system, converts it into JSON format, and sends it to the server. The input is XML or CSV data from the human resources system, and the output is sales representative data in JSON format, which is sent to the server via the API.

[1265] Step 3: Parse business and cultural information

[1266] The server analyzes the collected business and cultural information. Specifically, it uses an ARIMA model to identify trends in economic indexes and scores the data. It also uses NLP technology to tokenize the cultural information and perform TF-IDF vectorization to evaluate region-specific characteristics. The input is business and cultural information in JSON format, and the output is the score for each area as an analysis result.

[1267] Step 4: Salesperson Profile Analysis

[1268] The server applies machine learning algorithms to analyze sales representative characteristic data. Specifically, it uses random forests and support vector machines (SVMs) to evaluate sales representatives' strengths and weaknesses. This evaluation model is built based on past performance data, specialized knowledge, and work experience. The input is sales representative data in JSON format, and the output is an evaluation score for each sales representative.

[1269] Step 5: Generate the optimal mapping

[1270] Based on the analysis results, the server optimally maps the business needs, cultural information, and characteristics of each salesperson for each area. For example, it uses multidimensional scaling (MDS) or k-means clustering to allocate salespeople to the most suitable areas. The inputs are scores for business and cultural information, and the evaluation scores of salespeople, and the output is an optimal allocation plan for each area.

[1271] Step 6: Notification of mapping results

[1272] The server notifies sales representatives and administrators of the generated mapping results. Notifications are sent by email using the SMTP protocol, and an interface is provided where results can be checked in real time on a dedicated dashboard. The input is the optimal placement plan, and the output is a notification email and updated information on the dashboard.

[1273] Step 7: Feedback and optimization of activity results

[1274] Users (salespeople) report the results of their activities to the server as feedback. They input the number of new customers acquired, sales, customer satisfaction, etc. through a dedicated application and send it to the server via API. The server receives this feedback data, analyzes it using regression analysis and Bayesian estimation, and optimizes the analysis algorithm. The input is the feedback data, and the output is the next optimized mapping algorithm.

[1275] (Application example 1)

[1276] 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."

[1277] Conventional business mapping and security patrol systems struggle to properly consider the specific business needs and crime data of each area and generate optimal personnel and patrol routes. This reduces the efficiency of sales and security activities, resulting in lower satisfaction for businesses and local communities. Furthermore, they lack the ability to dynamically adjust analysis algorithms based on feedback, making long-term optimization difficult.

[1278] 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.

[1279] In this invention, the server includes: means for scraping business and cultural information for each area from the Internet; means for collecting characteristics of sales representatives from a database; means for analyzing the collected business information, cultural information, and characteristics of sales representatives to generate an optimal mapping; means for notifying the sales representatives and managers of the generated mapping; means for receiving feedback and optimizing the analysis algorithm; means for scraping crime data and security-related information for the area from the Internet; means for collecting characteristics of security guards from a database; means for analyzing the collected crime data and security information to generate an optimal patrol route; and means for notifying the security guards and managers of the generated patrol route. This allows the specific needs of each area to be reflected, improving the efficiency of sales and security activities, and further achieving long-term results through dynamic optimization.

[1280] "Business information" refers to data on economic activity and industry in each area, as well as information including corporate trends and market trends.

[1281] "Cultural information" is data about the culture, customs, and lifestyle of a particular region or community.

[1282] "Scraping" is a technique for automatically collecting information that is publicly available on the Internet.

[1283] A "sales representative" is an employee whose role is to sell a company's products or services to customers.

[1284] "Characteristics" refers to data about the attributes and abilities of individual sales representatives and security guards, such as their work experience, expertise, personality, and past performance.

[1285] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[1286] "Analysis" is the process of analyzing collected data using statistical methods and algorithms to extract meaningful information.

[1287] "Mapping" refers to determining optimal placement and correspondence based on collected and analyzed data.

[1288] "Notification" is a means of informing the subject of the generated results.

[1289] "Feedback" is the process of collecting user evaluations and results and using them to help with future improvements.

[1290] An "algorithm" refers to a procedure or computational method for solving a specific problem.

[1291] "Crime data" refers to data that includes crime occurrences in a specific area and detailed information about those crimes.

[1292] "Security-related information" refers to data related to crime prevention measures and risk assessments.

[1293] A "patrol route" refers to the optimized route taken by security guards for patrol.

[1294] The system that realizes this application example consists of a server, terminals, and users. The server plays a central role in collecting data, analyzing it, generating mapping, notifying users, and optimizing it. Terminals are devices mainly used by personnel systems, sales representatives, and security guards, while users refer to the sales representatives or security guards who use the system to carry out their activities, as well as their managers.

[1295] Data collection

[1296] The server scrapes business, cultural, and crime data for each area from the internet. The software used for this is the Python requests library. For example, the required data is obtained from specific APIs (https: / / api.example.com / crime-data, https: / / api.example.com / guards) and stored in a database. Text data on regional culture and lifestyles is also collected from websites and stored in a database for analysis.

[1297] The terminal collects data on the characteristics of sales representatives and security guards from the personnel system and sends it to the server. For example, information such as the sales representative's work experience, expertise, personality, past performance, and the security guard's qualifications and experience is extracted from the database and transferred to the server via API.

[1298] Data analysis

[1299] The server applies advanced algorithms to analyze the collected business, cultural, and crime data. Specifically, it uses statistical methods and natural language processing (NLP) techniques to identify economic indexes and key industry trends, assess the business needs of each area, and evaluate and score the unique characteristics of each area using cultural and crime data.

[1300] The server also analyzes the characteristics of sales representatives and security guards and applies a rating model to assess their strengths and weaknesses. This rating model is generated by clustering based on crime rates and population density in a specific area, standardizing the data using Python's scikit-learn library, and clustering using KMeans.

[1301] Mapping Generation

[1302] Based on the analysis results, the server optimally maps each area's business needs, cultural information, crime data, and the characteristics of sales representatives and security guards. The generated mapping results are notified to sales representatives, security guards, and managers via email and a dedicated dashboard.

[1303] As a specific example, if information is collected that crime rates are rising in the Shinjuku area, the server analyzes that information, evaluates whether the characteristics of the security guards currently in charge of the Shinjuku area are suitable for this area, and assigns patrols to the most suitable security guards.

[1304] Feedback and Optimization

[1305] Users (sales representatives and security guards) report the results of their activities at their assigned locations to the server as feedback. Data such as the number of new customers acquired, sales, customer satisfaction, or reductions in crimes is entered through a dedicated application and sent to the server.

[1306] The server analyzes this feedback data and evaluates the effectiveness of each sales representative and security guard placement. The analysis results are used to optimize the algorithm the next time mapping is generated. For example, if activity in the Shinjuku area is highly successful, the algorithm adjusts to apply the same strategy to other areas with similar characteristics.

[1307] Prompt Sentence Examples

[1308] As a concrete example, the following prompt sentence can be input to a generative AI model:

[1309] Generate Python code for an application that generates optimal security patrol routes based on area crime data and population density. The URLs for the collected data are obtained from https: / / api.example.com / crime-data and https: / / api.example.com / guards. The area data includes crime rate (crime_rate) and population density (population_density).

[1310] In this way, the present invention can provide efficient and effective people and place mapping, greatly improving the efficiency of business and security operations.

[1311] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1312] Step 1:

[1313] Data collection:

[1314] The server scrapes business, cultural, and crime data for each area from the internet. Specifically, it uses the Python requests library to retrieve data from an API (e.g., https: / / api.example.com / crime-data or https: / / api.example.com / guards) and saves it in a database. The URL to be collected using the API is given as input, and the data is obtained in JSON format as output. This is then stored in the database.

[1315] Step 2:

[1316] Feature data collection:

[1317] The terminal collects characteristic data of sales representatives and security guards from the personnel system and sends it to the server. Specifically, it extracts information such as the sales representative's work experience and past performance, and the security guard's qualifications and experience from the database, and transfers it to the server via API. A database query is given as input, and the characteristic data of the sales representatives and security guards is obtained as output in JSON format. This is then transferred to the server.

[1318] Step 3:

[1319] Data Analysis:

[1320] The server analyzes the collected business, cultural, and crime data. It standardizes the data using Python's scikit-learn and performs clustering using KMeans. The standardized data is given as input, and the clustering results are obtained as output. Specifically, the business needs and crime levels of each region are scored and classified into each cluster.

[1321] Step 4:

[1322] Mapping Generation:

[1323] Based on the analysis results, the server optimally maps each area to the characteristics of sales representatives or security guards. The analyzed clustering data and characteristic data of sales representatives and security guards are given as input, and the mapping results are obtained as output. Specifically, it generates the optimal sales representative placement and patrol routes for a specific area.

[1324] Step 5:

[1325] notification:

[1326] The server notifies the generated mapping results to sales representatives, security guards, and managers in real time via email and a dedicated dashboard. The mapping result data is given as input, and a notification message is generated as output. Specifically, each person in charge can check the new deployment and route.

[1327] Step 6:

[1328] Feedback collection:

[1329] Users (sales representatives and security guards) report the results of their activities at their assigned locations to the server as feedback. They input data such as the number of new customers acquired, sales, customer satisfaction, and reductions in crimes through a dedicated application. Data manually entered by the user is given as input, and feedback data is obtained as output. This is then sent to the server.

[1330] Step 7:

[1331] Algorithm optimization:

[1332] The server analyzes the feedback data and optimizes the algorithm for the next mapping generation. The feedback data is given as input and an optimized algorithm is generated as output. Specifically, it adjusts activities in similar areas based on successful cases and derives effective placements and routes.

[1333] The above processing steps make it possible to reflect the specific needs of each area and significantly improve the efficiency of sales and security activities.

[1334] 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.

[1335] The present invention provides a system that collects business information and cultural information for each area and generates an optimal mapping by taking into account the emotional information of sales representatives and users. Specific embodiments will be described below.

[1336] This system consists of a server, terminals, users, and an emotion engine. The server plays a central role in collecting data, analyzing it, generating mappings, notifying users, and optimizing the system. Terminals are devices primarily used by the human resources system and sales representatives. Users are sales representatives or managers who use the system to carry out their activities, and the emotion engine recognizes and analyzes the user's emotions.

[1337] Data collection

[1338] The server periodically scrapes business information (e.g., economic indexes, major industries, competitive information, etc.) for each area from the Internet and stores it in a database. It also scrapes cultural information (e.g., local culture, lifestyles, language, events, etc.) and stores it in a database for analysis.

[1339] The terminal collects characteristic data of sales representatives (e.g., work experience, expertise, personality, past performance, etc.) from the personnel system and transmits it to the server.

[1340] Data analysis

[1341] The server applies data analysis algorithms to analyze the collected business and cultural information. Specifically, it analyzes economic indexes and trends in major industries to assess the business needs of each area. Similarly, it evaluates the characteristics of each region based on cultural information.

[1342] The server also applies an evaluation model to analyze the salesperson's characteristic data, which analyzes the salesperson's past performance, expertise, and work experience to evaluate their strengths and weaknesses.

[1343] The emotion engine recognizes and analyzes user emotions. For example, it analyzes the mood and motivation of salespeople using text and voice analysis to generate emotion data.

[1344] Mapping Generation

[1345] The server evaluates demand in each area based on business and cultural information, and generates optimal mapping based on the characteristics and emotional data of sales representatives. For example, the server determines that IT-related demand is high in Tokyo, and proposes the placement of sales representative A, who has strengths in the IT field, in Tokyo so that he can work most effectively.

[1346] The server then notifies sales representatives and managers of the generated mapping results via email and a dedicated dashboard.

[1347] Feedback and Optimization

[1348] Users (salespeople) report the results of their field activities and feedback to the server, including data such as sales performance and customer reactions.

[1349] The server analyzes the feedback data to evaluate the effectiveness of the placement. It also incorporates emotion data provided by the emotion engine. Based on this data, it optimizes the next mapping algorithm.

[1350] Specific examples

[1351] For example, if there is a surge in demand for the IT industry in Tokyo, the server scrapes that information and stores it in a database. Next, the information of salesperson A, who has extensive experience in the IT industry, is also registered in the database. The emotion engine also analyzes salesperson A's emotions and identifies that he is highly motivated.

[1352] The server's algorithm analyzes the business needs and cultural information of Tokyo, as well as the characteristics and emotional data of sales representative A, and determines that it is best to assign him to Tokyo. The server notifies sales representative A of the generated mapping results, and he begins his sales activities in Tokyo.

[1353] After that, the user (Salesperson A) reports the results of their activities and their emotional state as feedback. The server analyzes this data and reflects it in the next mapping, further improving the accuracy of the placement.

[1354] In this way, the present invention is a system that realizes more effective and personalized sales representative mapping by adding user emotional information.

[1355] The processing flow will be explained below.

[1356] Step 1: Data collection

[1357] The server scrapes business information for each area (e.g., economic indexes, major industries, competitive information, etc.) from the Internet.

[1358] Specific operation: The server uses a crawler to periodically collect the latest data from official government websites and business-related news sites and store it in a database.

[1359] The server also scrapes cultural information (e.g., local culture, lifestyle, language, events, etc.).

[1360] Specific operation: The server collects text data from local information sites and tourist association websites and stores it in an analysis database.

[1361] The terminal transmits characteristic data of the sales representative (e.g., work experience, expertise, personality, past performance, etc.) from the personnel system to the server.

[1362] Specific operation: The terminal extracts sales representative information from the personnel database via API and stores it in the server database.

[1363] Step 2: Collecting Emotional Data

[1364] The user (salesperson) inputs his / her own feelings in daily activities.

[1365] Specific operation: The user selects and enters their emotional state from a list using a dedicated app or a web form.

[1366] The emotion engine automatically analyzes emotions from the user's voice and text.

[1367] How it works: The emotion engine uses emotion analysis algorithms to analyze voice and text data in real time and generate an emotion score.

[1368] Step 3: Data analysis

[1369] The server runs algorithms to analyze the collected business information.

[1370] Specific operation: The server extracts business indexes and trends of major industries using statistical methods and text analysis, and evaluates the business needs of each area.

[1371] The server analyzes the culture information and evaluates the characteristics of each region.

[1372] Specific operation: The server uses natural language processing (NLP) technology to extract region-specific characteristics from text data and assigns an evaluation score.

[1373] The server analyzes the characteristic data of the sales representative based on the evaluation model.

[1374] Specific operation: The server applies a model to score past performance data, expertise, and work experience, and evaluates each employee.

[1375] The server analyzes the emotion data from the emotion engine and makes a comprehensive evaluation.

[1376] Specific operation: The emotion scores provided by the emotion engine are integrated and analyzed taking into account the salesperson's current psychological state.

[1377] Step 4: Mapping Generation

[1378] The server evaluates the demand in each area based on business information, cultural information, characteristics of sales representatives, and emotional data, and generates an optimal mapping.

[1379] Specific operation: The server runs a matching algorithm based on the evaluation scores to determine the optimal combination of sales representative and area.

[1380] The server notifies the sales representative and the manager of the generated mapping results.

[1381] Specific operation: The server sends the results to sales representatives and managers via email notifications or dedicated dashboards.

[1382] Step 5: Feedback and optimization

[1383] Users (salespeople) send field activity results and feedback to the server.

[1384] Specific operation: The user enters performance data (e.g., sales, customer satisfaction, etc.) and emotional feedback through a dedicated app or web form and sends them to the server.

[1385] The server analyzes the transmitted feedback data and evaluates the effectiveness of the deployment.

[1386] Specific Operation: The server uses an analytical algorithm to analyze the feedback data and evaluate changes in the salesperson's performance and emotional state.

[1387] The server optimizes the analysis algorithm based on the feedback and sentiment data.

[1388] Specific operation: Based on the insights gained from the feedback and emotion data, the server adjusts the parameters of the matching algorithm and reflects the results in the next mapping.

[1389] Example 2

[1390] 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."

[1391] In modern sales activities, it is difficult to effectively collect local business and cultural information and optimally assign sales representatives based on that information. Furthermore, conventional systems cannot take into account the emotional information of sales representatives, resulting in inefficient mapping. As a result, sales activities are not fully effective and sales performance declines.

[1392] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for scraping business information and cultural information for each area from the Internet, means for collecting salesperson characteristics from an information management system, means for analyzing the collected business information, cultural information, and salesperson characteristic data to generate an optimal mapping, means for analyzing user emotion data and reflecting it in the mapping, means for notifying the salesperson and manager of the generated mapping, and means for receiving feedback and optimizing the analysis algorithm. This enables more effective and optimal salesperson allocation that takes into account local business needs and salesperson emotion information.

[1393] "Business Information" refers to economic data, such as economic indexes, key industries, and competitive information, relating to a particular region or industry.

[1394] "Cultural information" refers to social and cultural data such as local culture, lifestyles, language, and events.

[1395] "Internet scraping" refers to techniques and tools used to automatically extract information from websites on the Internet.

[1396] "Characteristics of a salesperson" refers to individual data such as the salesperson's work experience, expertise, personality, and past performance.

[1397] An "information management system" refers to software or a platform for managing and operating data held by a company or organization.

[1398] "Analysis methods" refer to the technologies and algorithms used to find and evaluate relationships and patterns based on collected data.

[1399] "Means for generating optimal mapping" refers to technologies and algorithms that use analyzed data to place sales representatives in the optimal areas and to the optimal customers.

[1400] "User emotion data" refers to data that represents the mood and motivation of salespeople and other users.

[1401] "Notification means" refers to the technology and tools used to communicate the generated mapping results to sales representatives and managers.

[1402] "Means of receiving feedback" refers to the techniques and tools used to collect the results of sales activities and opinions and feedback from sales representatives.

[1403] "Means for optimizing the analysis algorithm" refers to techniques and methods for improving the accuracy and effectiveness of the analysis algorithm based on collected feedback data.

[1404] The present invention relates to a system that collects business information and cultural information for each area and generates an optimal mapping by taking into account the characteristics of sales representatives and emotional information of users. Specific embodiments will be described below.

[1405] System Configuration

[1406] This system consists of a server, terminals, users, and an emotion engine. The server plays a central role in collecting data, analyzing it, generating mappings, notifying users, and optimizing the results. Terminals are devices primarily used by salespeople. Users are salespeople or managers who use the system to carry out their activities, and the emotion engine recognizes and analyzes users' emotions.

[1407] Data collection

[1408] The server periodically scrapes business and cultural information for each area from the Internet. The software used is the Python Scrapy framework. This method collects data such as economic indexes, major industries, competitive information, and local culture and events, and stores it in a MongoDB database. The terminal also collects sales representative characteristic data (work experience, expertise, personality, past performance, etc.) from an information management system (e.g., an HR management tool) and sends it to the server via HTTP.

[1409] Data analysis

[1410] The server analyzes the collected business and cultural information using Pandas and Scikit-learn. Specifically, it analyzes trends in economic indexes for each area, evaluates the competitive situation in major industries, and extracts regional characteristics. To analyze salesperson characteristic data, it also builds an evaluation model (e.g., a logistic regression model) using Scikit-learn to evaluate the salesperson's strengths and weaknesses. Furthermore, the emotion engine recognizes and analyzes user emotions using the Google Cloud Speech-to-Text API for voice analysis and the NLTK library for text analysis. This analysis generates emotion data that indicates the salesperson's mood and motivation.

[1411] Mapping Generation

[1412] The server evaluates demand in each area based on the analyzed business information, cultural information, and sales representative characteristic and emotional data, and generates an optimal mapping. This process uses the SciPy linear algebra package. For example, the server determines that IT-related demand is high in Tokyo, and decides that it would be optimal to assign sales representative A, who has strengths in the IT field, to Tokyo. The generated mapping results are notified to sales representatives and managers via email or a dedicated dashboard (e.g., Tableau).

[1413] Feedback and Optimization

[1414] Users (salespeople) report their field activity results and feedback to the server. This includes data such as sales performance, customer reactions, and self-emotional evaluations. Feedback is entered via a mobile app or web portal and sent to the server. The server analyzes the reported feedback data using Apache Hadoop and Spark to optimize the next mapping algorithm. This results in more accurate placement that reflects the user's emotional data and feedback.

[1415] Specific examples

[1416] If there is a surge in demand for the IT industry in Tokyo, the server uses Scrapy to collect that information and stores it in a MongoDB database. Data about Salesperson A's extensive experience in the IT field, collected from SAP SuccessFactors, is also received via HTTP and added to the database. The emotion engine also uses the Google Cloud Speech-to-Text API and NLTK to identify that Salesperson A has high motivation. The server analyzes this data using Pandas and Scikit-learn, combining IT demand with Salesperson A's characteristic information, and determines that it is optimal to assign A to Tokyo. The results are notified on a Tableau dashboard, and Salesperson A begins sales activities in Tokyo. By reporting the results of the activities and the salesperson's own emotional state as feedback via a mobile app, the server improves the accuracy of the mapping for the next time.

[1417] Specific examples of prompts to be input to generative AI models

[1418] Based on the following text, select the sales representative who best suits the business needs in the IT industry in Tokyo, and generate the optimal placement proposal taking into account emotional information.

[1419] (Tokyo business information)

[1420] IT-related demand surges

[1421] (Cultural information)

[1422] Many highly skilled professionals

[1423] (Characteristic data of Salesperson A)

[1424] Extensive experience in the IT field

[1425] Past performance is excellent

[1426] (Salesperson A's emotional data)

[1427] Maintain high motivation

[1428] Please output the results in a table format and provide a bulleted list of reasons for your recommendation.

[1429] The system adds user emotional information to enable more effective and personalized sales representative mapping.

[1430] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1431] Step 1:

[1432] The server scrapes business and cultural information for each area from the Internet. The software used is the Python Scrapy framework. Specifically, the server periodically crawls web pages to collect data such as economic indexes, major industries, competitive information, and local culture and events. The collected data is stored in a MongoDB database.

[1433] Input: List of web page URLs

[1434] Data Processing: Web Scraping with Scrapy

[1435] Output: Business and cultural information stored in a MongoDB database

[1436] Step 2:

[1437] The terminal collects sales representative characteristic data from the HR system. The device used is a Windows PC or mobile terminal, and the software is an HR management tool (e.g., SAP SuccessFactors). The collected data is sent to the server using the HTTP protocol.

[1438] Input: characteristic data about salespeople (work experience, expertise, personality, past performance)

[1439] Data processing: None (data transfer)

[1440] Output: Salesperson characteristics data sent to the server

[1441] Step 3:

[1442] The server uses Pandas and Scikit-learn to analyze the collected business and cultural information, specifically analyzing trends in economic indexes, assessing the competitive situation in major industries, and extracting regional characteristics.

[1443] Input: Business and cultural information stored in a MongoDB database

[1444] Data processing: Data preprocessing using Pandas, trend analysis and evaluation using Scikit-learn

[1445] Output: Evaluation data of business needs and regional characteristics for each area

[1446] Step 4:

[1447] The server applies a rating model to analyze the sales representative characteristic data. The model, built using Scikit-learn, assesses each representative's strengths and weaknesses based on their past performance and areas of expertise.

[1448] Input: Salesperson characteristics data sent to the server

[1449] Data processing: Model evaluation and analysis with Scikit-learn

[1450] Output: Salesperson strengths and weaknesses evaluation data

[1451] Step 5:

[1452] The emotion engine recognizes and analyzes user emotions, using the Google Cloud Speech-to-Text API for speech analysis and the NLTK library for text analysis to generate emotional data that assesses the mood and motivation of salespeople.

[1453] Input: User voice and text data

[1454] Data processing: Speech analysis with Google Cloud Speech-to-Text API, text analysis with NLTK

[1455] Output: Emotion data

[1456] Step 6:

[1457] The server evaluates the demand for each area based on the analyzed business information, cultural information, salesperson characteristics data, and sentiment data, and generates an optimal mapping. It uses the linear algebra package in SciPy to run the algorithm and calculate the optimal placement.

[1458] Input: Business information, cultural information, salesperson characteristics data, emotion data

[1459] Data processing: Demand assessment and mapping generation using algorithms in SciPy

[1460] Output: Optimal mapping data

[1461] Step 7:

[1462] The server notifies sales representatives and managers of the generated mapping results via email or a dedicated dashboard (e.g., Tableau).

[1463] Input: Optimal mapping data

[1464] Data processing: Converting data into notification format

[1465] Output: Email and dashboard notifications

[1466] Step 8:

[1467] Users (salespeople) report field activity results and feedback to the server, which is entered via a mobile app or web portal.

[1468] Input: Sales performance, customer response, self-emotion evaluation

[1469] Data processing: None (data transfer)

[1470] Output: Feedback data sent to the server

[1471] Step 9:

[1472] The server analyzes the reported feedback data using Apache Hadoop and Spark to evaluate the effectiveness of the placement and optimize the next mapping algorithm.

[1473] Input: Feedback data

[1474] Data Processing: Data Analysis using Hadoop and Spark

[1475] Output: Optimized mapping algorithm

[1476] In this way, data analysis incorporating user emotional information and optimal mapping are performed, maximizing the effectiveness of sales activities.

[1477] (Application example 2)

[1478] 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."

[1479] The present invention relates to a system for automatically generating optimal worker allocations based on the business needs and cultural characteristics of each area, thereby achieving efficient business operations. In particular, there is a demand for optimal allocation of work robots and workers within factories to improve production efficiency and worker satisfaction. Conventional systems have difficulty fully considering the characteristics and emotional information of workers, resulting in an inability to achieve optimal allocation.

[1480] The specific processing by the specific 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 scraping business information and cultural information for each area from a data communication network, means for collecting worker characteristics from an information base, means for analyzing the collected business information, cultural information, and worker characteristics to generate an optimal mapping, means for collecting production information, area characteristics, machine performance information, and emotion information for each area and storing them in a database, means for notifying workers and managers of the generated mapping, and means for receiving feedback and optimizing the analysis algorithm. This enables optimal allocation taking into account the production needs, machine performance, and emotion information of each area.

[1481] "Business information" refers to data related to business and work in each area, including economic indicators, major industries, competitive information, production status, etc.

[1482] "Cultural information" refers to data on the unique culture, lifestyle, language, events, etc. of each area.

[1483] "Characteristics of the worker" refers to data such as the worker's work experience, expertise, personality, past performance, skill level, etc.

[1484] "Data communications network" means an infrastructure for the transmission of data, including the Internet and other networks.

[1485] "Scraping" refers to the technology and methods of automatically collecting necessary information from a website.

[1486] An "information base" refers to a storage device or system such as a database in which data and information are stored.

[1487] "Production information for each area" refers to data related to production at factories and manufacturing sites, specifically including production volume, operating rate, maintenance status, etc.

[1488] "Area characteristics" refers to the characteristics and conditions unique to a particular region or area, including geographical conditions, climate, infrastructure conditions, etc.

[1489] "Machine performance information" refers to data on the performance of machines and equipment used within a factory, including, specifically, processing speed, operating hours, and failure history.

[1490] "Emotional information" refers to data related to the emotions and mental state of workers and managers, and specifically includes motivation, stress levels, mood, etc.

[1491] "Optimal mapping" refers to a deployment plan for allocating workers and machines to optimal locations based on collected and analyzed data.

[1492] "Feedback" refers to workers and managers reporting actual work results, opinions, and feelings to the server.

[1493] "Analysis algorithm" refers to the calculation methods and rules used to analyze collected data and derive optimal placement and areas for improvement.

[1494] The present invention is a system that automatically achieves optimal placement of work robots within a factory. Specific embodiments are described below. This system collects business and cultural information for each area, generates an optimal mapping based on that information, and notifies workers and managers. It also collects feedback and optimizes the analysis algorithm.

[1495] Hardware and Software Configuration

[1496] Hardware used

[1497] Server: The central location for data collection, analysis, mapping generation, and notification.

[1498] Devices: Robots used in factories, and smartphones and tablets used by managers.

[1499] Sensors: Includes emotion engines such as voice analysis and heart rate sensors to collect the worker's emotional state.

[1500] Software used

[1501] Data scraping engine: Software for scraping business and cultural information from the internet.

[1502] Database Management System: A system for storing and managing collected data.

[1503] Analysis algorithms: Algorithms for analyzing the data and generating optimal mappings.

[1504] Emotion engine: Software for analyzing the emotional information of workers and managers.

[1505] Notification system: A system for notifying workers and managers of the generated mapping results.

[1506] Processing Details

[1507] The server periodically scrapes business and cultural information from each area using a data communication network and stores it in a database. It also collects characteristic data and emotional data from workers and sends it to the server. Specifically, this data includes the worker's work experience, expertise, past performance, skill level, etc.

[1508] The collected data is analyzed using an analytical algorithm. The server evaluates the business needs of each area based on business and cultural information, and generates an optimal mapping based on the characteristics and emotional data of the workers. For example, if production demand is high in a particular area, a work robot with high processing speed will be deployed in that area.

[1509] The emotion engine analyzes the emotional information of workers and managers, specifically their motivation, stress levels, and mood, using data from voice analysis and heart rate sensors.

[1510] The generated mapping results are sent to the workers and managers via a notification system. Notifications are sent via email and a dedicated dashboard. The managers and workers can then check the results and take action.

[1511] Feedback data from workers and managers is also collected and sent back to the analysis algorithm. This feedback includes actual work results and emotional states. The server analyzes the feedback data and optimizes the algorithm for the next mapping generation.

[1512] Specific examples

[1513] For example, suppose a factory experiences a sudden increase in production demand in a particular area. The server collects this information from the data communication network and stores it in a database. Next, it registers the characteristic data of robots with high processing speeds in the database. The emotion engine also recognizes that the worker operating the robot is highly motivated.

[1514] Based on this information, the analysis algorithm determines that it is optimal to deploy robots with high processing speeds in areas where demand is increasing. The server then notifies the generated mapping results to workers and managers, who then plan their next work.

[1515] The worker then reports the actual work results and their emotional state as feedback. The server analyzes the feedback data and reflects it in the next deployment plan, further improving the accuracy of the deployment.

[1516] Prompt Sentence Examples

[1517] Area: Tokyo

[1518] Demand: IT-related

[1519] Robot Features: High speed processing

[1520] Emotional data: High motivation

[1521] Generate the optimal placement.

[1522] In this way, the present invention aims to realize efficient allocation of work robots and improve production efficiency and the work environment by combining business information, cultural information, and emotional information for each area.

[1523] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1524] Step 1:

[1525] The server uses a data communication network to scrape business and cultural information from each area. The input data is business and cultural information that is publicly available on the Internet, which is periodically accessed and collected. Specifically, a data scraping engine is used to extract the necessary information and store it in a database. This process accumulates the latest business and cultural information in the database.

[1526] Step 2:

[1527] The terminal collects characteristic data of the worker and sends it to the server. The input data includes the worker's work experience, specialized knowledge, past performance, skill level, etc. Specifically, this data is automatically extracted from the factory management system and sent to the server. In this way, the latest characteristic data of the worker is collected on the server.

[1528] Step 3:

[1529] The server uses an emotion engine to collect and analyze the worker's emotional information. The input data is the worker's voice data and biometric data such as heart rate. Specifically, the system performs voice analysis and heart rate analysis and converts the data into text data and numerical data. The output is the worker's emotional state (motivation, stress level, etc.).

[1530] Step 4:

[1531] The server analyzes the collected business information, cultural information, worker characteristics data, and emotion data to generate an optimal mapping. The input data is all the data collected in the previous stage. Specifically, it analyzes the data using an analytical algorithm and calculates the optimal placement of work robots based on the business and production needs of each area. The output is the optimized mapping result.

[1532] Step 5:

[1533] The server notifies the worker and administrator of the generated mapping results. The input data is the generated mapping results. Specifically, the notification system is used to display the mapping results via email or on a dedicated dashboard. This allows the worker and administrator to check the next work plan.

[1534] Step 6:

[1535] Users collect actual work status and feedback and send it to the server. The input data is feedback on work results and emotional state. Specifically, workers and managers enter data through a dedicated feedback form and send it to the server. This collects data for the next improvement.

[1536] Step 7:

[1537] The server analyzes the feedback data and optimizes the analysis algorithm. The input data is the collected feedback data. Specifically, it analyzes the past mapping results and the corresponding feedback and adjusts the parameters of the analysis algorithm. The output is a newly optimized analysis algorithm, which is reflected in the next mapping.

[1538] Through this series of processes, the system dynamically provides optimal placement, improving work efficiency and worker satisfaction.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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.

[1543] 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.

[1544] 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.

[1545] 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).

[1546] 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. 【1547...

Claims

1. A means of scraping business and cultural information from the internet for each area; a means of collecting characteristics of salespeople from a database; A means for analyzing the collected business information, cultural information, and characteristics of salespeople to generate an optimal mapping; a means for notifying sales representatives and management of the generated mapping; a means for receiving feedback and optimizing the analysis algorithm; A system including:

2. 10. The system of claim 1, further comprising means for assessing business needs in each area based on the collected business and cultural information.

3. The system of claim 1 , further comprising means for dynamically adjusting the analysis algorithm based on the results of the sales representative's activities.

Images