system

Abstract

We provide the system. [Solution] Methods for obtaining application information from external sources, A means for analyzing the aforementioned application information and generating quantified patterns and trends, A means for detecting failure to meet the target number of applications based on the analysis results, A means of issuing a warning if the target is not met, A means of proposing notification activities and promotion measures in response to failure to meet targets, A means of aggregating and visually displaying applicant attribute information, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Problems include that it takes a great deal of effort to analyze the application situation and create reports, the target achievement rate of the number of applications cannot be quickly grasped and the response is delayed, and it is difficult to quickly formulate effective promotion measures when the number of applications is sluggish. As a result, effective measures cannot be implemented at an appropriate time, and the problem that the increase in the number of applications cannot be achieved as expected occurs.

Means for Solving the Problems

[0005] This invention provides means for acquiring application data from an external database and means for analyzing the application data to generate quantified patterns and trends. Furthermore, it includes means for detecting failure to meet application targets based on the analysis results and issuing alerts, enabling immediate response. Through means for proposing reminder campaigns and promotional measures in response to failure to meet targets, it is possible to automate the planning of effective measures tailored to the situation and improve the number of applications.

[0006] "Application data" refers to information obtained from an external database, including information about the applicant and information regarding the date, time, and content of the application.

[0007] An "external database" is a data storage system where application data is stored, and the data can be accessed and retrieved via APIs, etc.

[0008] "Analysis" is the process of quantifying patterns and trends in acquired application data and converting them into an understandable format.

[0009] "Failure to meet target" refers to a situation where the actual number of applications does not reach the pre-set target.

[0010] An "alert" is a warning or alert signal that is sent to users when the number of applications falls below the target.

[0011] A "remind campaign" is a marketing activity designed to encourage applicants or potential applicants to apply again.

[0012] "Promotional measures" refer to a series of strategies and action plans implemented to increase the number of applications. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention aims to build a system that automates the monitoring and analysis of application status and efficiently proposes countermeasures. Specifically, it begins with periodically retrieving application data from an external database using a server. The server has the capability to process more than 5,000 application data entries in a short time and is accessed via an API. The retrieved data is then sent by the server to an AI agent.

[0035] The AI ​​agent analyzes the received application data and extracts quantifiable patterns and trends. The analysis process analyzes data points such as application trends over the past 30 days, enabling application predictions and identification of peak times. These analysis results are returned to the server and visualized as graphs and reports. For example, a line graph can show the change in application numbers over time, and a pie chart can display the attribute distribution of applicants.

[0036] The server also has the functionality to generate these reports daily and weekly and automatically send them to the responsible person's terminal. Furthermore, a system is in place to send an alert if the number of applications does not meet the pre-set target. This alert is sent to the user's terminal via SMS or email, prompting a quick response.

[0037] After an alert is issued, the AI ​​agent proposes reminder campaigns and promotional measures. Specific measures include social media posts and email newsletters tailored to the target applicant demographic, as well as reward incentive plans including exclusive benefits. For example, for a campaign targeting younger demographics, it might propose an influencer collaboration campaign on Instagram. This allows users to quickly develop concrete action plans to increase the number of applications.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The server connects to an external database via an API to retrieve the latest application data. The server periodically performs this process to collect new application information and temporarily stores it.

[0041] Step 2:

[0042] The server transfers the collected application data to the AI ​​agent. The data includes details such as the applicant's name, inquiry date and time, and application channel, which are necessary items for analysis by the AI ​​agent.

[0043] Step 3:

[0044] The AI ​​agent analyzes the received application data to extract patterns and trends in the number of applications and their attributes. For example, it can evaluate whether the number of applications increases during a specific period and understand weekly application trends.

[0045] Step 4:

[0046] The server receives the analysis results from the AI ​​agent and generates data for visualization. It visualizes fluctuations in the number of applications and the breakdown of applicant attributes in graph and chart format.

[0047] Step 5:

[0048] The server sends the generated graphs and reports to the user's terminal. Users receive detailed analysis reports daily or weekly to understand the application status.

[0049] Step 6:

[0050] If the number of applications falls short of the target, the server will create an alert and notify the user. The notification will be sent via email or SMS, allowing for immediate action.

[0051] Step 7:

[0052] The AI ​​agent proposes reminder campaigns and promotional measures as recovery measures for failing to meet targets. These measures are then implemented as suggested social media posts, reward incentives, or specific email newsletters.

[0053] Step 8:

[0054] The user reviews the proposed measures and decides whether or not to implement them. Based on the user's decision, the measures deemed most effective are selected.

[0055] Step 9:

[0056] Based on the selected measures, the server performs the necessary configurations and prepares for scheduled social media posts and email newsletter distribution. These are then executed automatically according to the pre-set schedule.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] In today's information-driven society, it is crucial to process large volumes of application information quickly and efficiently, and to provide the necessary information for developing appropriate strategies. However, manual data processing and analysis are time-consuming and labor-intensive, making them insufficient in a business environment where rapid response is essential. To address this challenge, an automated data acquisition, analysis, and notification system is necessary.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes means for acquiring application information from an external information source, means for analyzing the application information and generating quantified trends, means for detecting failure to meet application targets based on the analysis results, means for issuing warnings in the event of failure to meet targets, means for providing reminder information and proposing measures in accordance with the failure to meet targets, means for converting and displaying the analysis results as time-series data, and means for automatically generating and electronically transmitting reports. This enables immediate analysis and proposal of countermeasures for large amounts of application information, realizing rapid strategic planning and execution.

[0062] "Application information" refers to a collection of data and information provided by the applicant, including application details and related attribute information.

[0063] An "external information source" refers to a database or data server located outside the system where application information is stored.

[0064] "Analysis" is the process of processing acquired application information numerically or pattern-wise to derive specific trends or meanings.

[0065] "Quantified trends" refer to quantitative indicators and patterns related to the number of applications and applicant attributes obtained as a result of data analysis.

[0066] "Failure to meet targets" refers to a situation where the set number of applications or other criteria have not been met.

[0067] A "warning" is a notification issued when specific conditions occur, such as failing to meet targets, and is intended to encourage prompt action.

[0068] "Reminder information provision" refers to information or suggestions sent when goals are not met, intended to draw attention to applicants and related parties and encourage action.

[0069] A "policy" refers to a specific action plan or strategy implemented to achieve a set goal.

[0070] "Time-series data" refers to data recorded over time and is used to visually represent changes and trends in the number of applications.

[0071] A "report" is a document that includes a visual representation of analysis results and application information, and is intended to provide information for decision-making and strategy formulation.

[0072] "Electronically transmitted" refers to the method of sending generated reports and notices via the internet or email.

[0073] This invention is a system that automatically processes large amounts of application information and supports strategic decision-making. Specific embodiments are described below.

[0074] First, the server establishes communication with external information sources and periodically retrieves application information using APIs. The server has high-performance computing capabilities to efficiently process large amounts of data.

[0075] The acquired data undergoes data cleansing on the server. Programming languages ​​such as Python are used to organize duplicate data and format inconsistencies, and to convert the data into a format that can be easily processed by the analysis engine.

[0076] The formatted data is sent from the server to the AI ​​agent. The AI ​​agent uses a generative AI model to analyze the quantified trends in the application information. In this process, time-series data of the number of applications is handled in particular to analyze and predict application trends.

[0077] The analysis results are returned to the server, where the data is visualized. The analysis results are displayed graphically using a JavaScript® library (for example, Chart.js), and are converted into a visible form such as a line graph or pie chart.

[0078] Based on this, the server automatically generates a report and saves it in PDF or Excel format. This report is electronically delivered to the user's terminal, providing information to relevant parties. Furthermore, the system detects failure to meet targets and issues warnings to users as needed. Warnings are promptly notified using SMS gateways, etc.

[0079] Regarding the proposal of countermeasures, the server generates prompt messages based on the analysis results to devise specific marketing strategies. An example of such a prompt message is, "The number of applications has not reached the target. Please propose effective countermeasures."

[0080] Finally, as part of the proposed strategies, promotional plans targeting specific applicant groups will be provided. For example, it may be possible to increase the number of applications by proposing information dissemination using social media or reward incentive plans.

[0081] Through this series of processes, the system provides the ability to support efficient data analysis and strategic decision-making.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The server connects to an external information source to retrieve application information. The input is the application information stored in the external information source, and the output is the retrieved raw data. Specifically, it periodically accesses the information source via an API and downloads the application information.

[0085] Step 2:

[0086] The server formats the acquired application information. The input is raw application data, and the output is cleaned application data. In this step, preprocessing such as data duplication removal and formatting is performed using a Python script.

[0087] Step 3:

[0088] The server sends the formatted data to the AI ​​agent. The input is cleansed application data, and the output is ready data for analysis. In this process, the data format is adjusted according to the AI ​​agent's requirements.

[0089] Step 4:

[0090] The AI ​​agent analyzes the received data and extracts quantifiable trends. The input is pre-prepared data for analysis, and the output obtained from the analysis is trend information and prediction results. Specifically, it uses a generative AI model to perform time series analysis and analyze application trends and predict peak times.

[0091] Step 5:

[0092] The server receives the analysis results and visualizes the data. The input is the analysis results from the AI ​​agent, and the output is the visualized data (graphs, charts, etc.). The server uses a JavaScript library (e.g., Chart.js) to convert it into a format that can be visually displayed in a browser.

[0093] Step 6:

[0094] The server generates reports based on visualized data and saves them electronically. Input is visualized data, and output is a report in PDF or Excel format. The automated process ensures regular reporting.

[0095] Step 7:

[0096] The server generates the report and then delivers it to the user's terminal. The input is the generated report, and the output is the delivered electronic report. SMTP is used to provide the report to the user as an attachment.

[0097] Step 8:

[0098] The server issues a warning if it detects that the set target has not been met. The inputs are the analysis results and the target value, and the output is a warning notification. Specifically, it uses an SMS gateway to send a warning message to the user.

[0099] Step 9:

[0100] The AI ​​agent generates a prompt message and proposes countermeasures after issuing a warning. The input consists of unmet targets and candidate countermeasure data, while the output is a specific countermeasure proposal. For example, it can make effective suggestions in situations requiring a quick response, such as proposing an SNS campaign to a specific target audience.

[0101] (Application Example 1)

[0102] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0103] It is difficult to efficiently analyze multiple application data and understand their trends. Furthermore, a system is needed to quickly implement countermeasures when the number of applications does not reach the target. In addition, there are insufficient means of presenting applicant attribute information in a visually easy-to-understand format. Solving these challenges is crucial.

[0104] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0105] In this invention, the server includes means for acquiring application information from an external information source, means for analyzing the application information and generating quantified patterns and trends, and means for aggregating and visually displaying applicant attribute information. This enables efficient analysis of application information and visualization of trends.

[0106] "Application information" is a general term for data about applicants collected from external sources.

[0107] "External information sources" refer to external data sources such as the internet and external databases, which are accessed by the system to obtain the information it needs.

[0108] A "quantified pattern" is an indicator that shows application trends and tendencies as numerical data obtained by analyzing collected application information.

[0109] "Failure to meet the target number of applications" means that the actual number of applications is insufficient compared to the set target number.

[0110] A "warning" is a notification sent to users to prompt action when the number of applications has not reached the target.

[0111] "Notification activities" refer to information dissemination and campaign activities directed at a target group when goals are not met.

[0112] "Promotional measures" refer to specific action plans proposed to increase the number of applications, including posting on online communication platforms and electronic newsletters.

[0113] "Applicant attribute information" refers to information that indicates characteristics of the applicant, such as age, gender, and region.

[0114] "Visually displaying" refers to the process of transforming aggregated data into a form that is easy to understand visually, such as graphs and diagrams.

[0115] As a form for carrying out the invention, the system that realizes this application example consists of a server, an AI agent, a user terminal, and a network connecting them.

[0116] The server uses an API to collect application information from external sources and sends it to an AI agent. The AI ​​agent uses a generative AI model to analyze the application information and extract quantifiable patterns. This analysis process clarifies past application trends and applicant attribute information.

[0117] Based on the acquired analysis results, the server automatically sends a warning to the user's terminal if the number of applications has not reached the target. This is done using email or SMS notification functions. Furthermore, graphs and charts are generated to visually display the analysis results and clearly show the application status to the user.

[0118] This allows users to quickly and efficiently grasp application information and take necessary measures. For example, if application trends are skewed towards younger generations, the system will suggest strategies to appeal to younger generations based on those results. An example of a prompt message would be, "If the number of applications has not reached 80% of the target, please suggest new promotional measures."

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The server retrieves application information from external sources using an API. The input is the application data obtained via the API, and the output is the raw data stored within the server. This data is then deployed for subsequent analysis processes.

[0122] Step 2:

[0123] The server transmits the acquired application information to the AI ​​agent. The input is the application information stored on the server, and the output is the data transfer to the AI ​​agent. The server uses a transmission protocol to ensure that the data is reliably delivered to the agent.

[0124] Step 3:

[0125] The AI ​​agent analyzes application information and extracts quantified patterns using a generative AI model. The input is application information received from the server, and the output is the analysis results of application trends and applicant attributes. This analysis process is performed using numerical algorithms and data learning models.

[0126] Step 4:

[0127] Based on the analysis results, the server sends a warning to the user's terminal if the number of applications has not reached the target. The input is the analysis results received from the AI ​​agent, and the output is the warning notification sent to the user. The server sends this notification via email or SMS to support a quick response.

[0128] Step 5:

[0129] The server generates graphs and charts to visually display the analysis results. The input is the analyzed data, and the output is graphs and charts that can be viewed on the user's terminal. The server uses visualization software to graphically transform the data.

[0130] Step 6:

[0131] Based on these results, the user takes the necessary countermeasures. The input is visual information presented by the server, and the output is a concrete action plan. For example, this could involve planning and executing a social media campaign targeting young people.

[0132] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0133] In this invention, the application status monitoring system is built around a server. First, the server retrieves application data from an external database via an API. This ensures that the server always maintains the latest application information and sends it to the AI ​​agent each time data is retrieved.

[0134] The AI ​​agent quickly analyzes submitted application data, generating quantifiable patterns and trends. The analysis results are sent back to the server and visualized in graphs and charts. Users receive these reports in real time on their devices, allowing them to monitor application trends and goal achievement rates.

[0135] In particular, by utilizing an emotion engine, a mechanism has been added to analyze emotions from user feedback and the content entered in application forms. The emotion engine estimates emotions based on the applicant's text data and provides the results to the AI ​​agent. For example, it can detect whether an applicant is satisfied or dissatisfied and customize the response accordingly.

[0136] The server generates an alert if the number of applications does not reach the set target. It also uses data from sentiment analysis to suggest more effective communication styles. For example, if an applicant is experiencing stress, it can design a reminder campaign that sends messages to alleviate that stress.

[0137] Users receive suggested strategies and alerts from the server, and based on this, they can determine specific action plans to improve the application status. The content of the strategies can be adapted to the target audience by adjusting them according to the results of sentiment analysis.

[0138] Thus, a key feature of this embodiment of the present invention is that by using an emotion engine, it is possible to not only perform data analysis but also to provide more effective measures that are tailored to the emotions of applicants.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The server connects to an external database via an API and periodically retrieves application data. Specifically, application information is collected every 10 minutes and stored in the database.

[0142] Step 2:

[0143] The server sends the collected application data to the AI ​​agent. The data includes the applicant's personal information, application details, and comments made during the application process.

[0144] Step 3:

[0145] The AI ​​agent analyzes the received data and quantifies the trends and patterns of applicants. Furthermore, the AI ​​agent uses an emotion engine to extract emotional data from application texts and comments.

[0146] Step 4:

[0147] The emotion engine classifies the candidate's emotions as positive, negative, or neutral, and feeds the result back to the AI ​​agent.

[0148] Step 5:

[0149] The server receives analysis results and sentiment data from the AI ​​agent and generates a visualized report. Graphs and charts visualize trends in the number of applications and the proportion of sentiment data.

[0150] Step 6:

[0151] The server automatically generates reports and sends them to the employee's terminal. The employee reviews the daily reports to understand the current status of applications and the applicants' emotional tendencies.

[0152] Step 7:

[0153] If the number of applications falls short of the target, the server will issue an alert. This alert will be delivered to the person in charge via email notification or as a warning on the dashboard.

[0154] Step 8:

[0155] Based on the emotional tendencies detected by the emotion engine, the AI ​​agent proposes reminder campaigns and promotional measures. For example, if negative emotions are high, it will plan an email campaign with content that addresses the applicant's dissatisfaction.

[0156] Step 9:

[0157] Users review the proposed measures from the server and select the measures they wish to implement. The selected measures are then used to provide the most appropriate response to each applicant.

[0158] Step 10:

[0159] The server executes the selected measures. It automates scheduled social media posts and sentiment-based email distribution to maximize effectiveness.

[0160] (Example 2)

[0161] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0162] When companies and organizations conduct diverse campaigns, they need to quickly grasp trends in the number of applications and implement flexible measures that reflect the emotional state of applicants. However, conventional systems have faced challenges in that the process of acquiring and analyzing application data is inefficient, making it difficult to respond based on applicants' emotions.

[0163] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0164] In this invention, the server includes means for acquiring application data from a recording device, means for evaluating the application data using an analysis device and generating quantified patterns and trends, and means for estimating emotions from text data and using the results to make suggestions that correspond to the emotional state of the applicant. This makes it possible to accurately grasp application trends and quickly propose measures that take into account the emotions of the applicants.

[0165] "Application data" refers to all information related to applications that is acquired from recording devices and used for analysis.

[0166] An "analysis device" is a device that evaluates application data and generates quantified patterns and trends.

[0167] "Patterns and trends" refer to numerical representations of application trends and characteristics obtained as a result of data analysis.

[0168] A "warning" refers to a notice or alert issued when the number of applications has not reached the set target.

[0169] "Campaigns and promotional activities" refer to special proposals or actions designed to attract users' attention and encourage participation.

[0170] "Methods for estimating emotions from text data" refers to technologies and methods for inferring the emotional state of applicants through text analysis and utilizing the results.

[0171] "Users" refers to individuals or organizations that use the system to receive analysis results of application data and proposed measures.

[0172] To implement this invention, the following configuration is necessary: ​​The server periodically retrieves application data from an external database and transmits it to the analysis device. This retrieval is performed via an API, and a specific data exchange format (such as JSON) is typically used in this process.

[0173] The analysis system uses a generative AI model to evaluate the data in detail and extract quantifiable patterns and trends. This analysis system could be built using a machine learning framework (e.g., TENSORFLOW® or PyTorch).

[0174] Furthermore, based on the analysis results, the server uses sentiment analysis tools to estimate the emotions of applicants from the text data they provide. At this time, natural language processing techniques are used to analyze the applicants' emotions from the text. Sentiment analysis is expected to be performed using NLP libraries (e.g., spaCy or NLTK).

[0175] The visualized analysis results are sent to the device in real time, allowing users to understand trends in the number of applications. This visualization utilizes libraries such as D3.js and Chart.js to build the user interface.

[0176] As a concrete example, in an online sales campaign, the server retrieves application data, analyzes it through a generated AI model, and then proposes a new promotional strategy to the user based on the results. An example of a prompt message would be, "Analyze the latest application data and report on applicant satisfaction and application trends. Also, suggest a suitable messaging campaign if applicants are experiencing stress." By inputting this, the system can provide useful insights.

[0177] A system configured in this way processes application data quickly and efficiently, providing users with accurate information. This enhances the management of application status and maximizes the effectiveness of campaigns.

[0178] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0179] Step 1:

[0180] The server periodically sends API requests to an external database to retrieve application data. This input allows the server to receive application data in JSON format, including the user's name, application date, and feedback comments. The received data is then prepared for analysis in the next step.

[0181] Step 2:

[0182] The server sends the received application data to the analysis device. The analysis device uses a generative AI model to analyze the input data and extract applicant behavior patterns and quantifiable trends. Specific data processing includes correlation analysis with historical data and applicant classification through clustering. The analysis results are temporarily returned to the server for use in the next step.

[0183] Step 3:

[0184] The server uses an emotion engine based on the analysis results to estimate emotions from applicants' text data. The input data consists of applicant comments, and natural language processing techniques are used to extract positive or negative emotions. The output is an emotion scoring result and emotion trend. This information will be used to propose subsequent measures.

[0185] Step 4:

[0186] The server visualizes the number of applications in real time based on the analysis results and sentiment scores. The visualized data is sent to the terminal and displayed to the user. Depending on the library used (e.g., D3.js), graphs of the trend in the number of applications and sentiment status are generated and provided to the user in an intuitively understandable format.

[0187] Step 5:

[0188] If the number of applications does not reach the target, the server will issue an alert and present suggested measures based on the results of sentiment analysis. In this step, for example, a message campaign could be designed to encourage stressed applicants to relax. Based on the information received by users on their devices, an effective action plan can be formulated.

[0189] (Application Example 2)

[0190] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0191] In modern recruitment processes, it is difficult to fully understand applicants' emotions and application trends, and there are challenges in responding quickly to changes in application trends. Furthermore, it is difficult to implement communication and measures that take applicants' emotions into consideration, which can result in failing to meet application targets.

[0192] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0193] In this invention, the server includes means for acquiring application information from an external information storage device, means for analyzing the application information and generating quantified patterns and trends, and means for analyzing the emotions of applicants from text information and customizing responses based on the results. This makes it possible to provide appropriate responses that take into account the emotions of applicants and to more effectively support the achievement of application number targets.

[0194] "Application information" refers to data related to recruitment activities obtained from external data storage devices.

[0195] "Analysis" is a series of processes that generate quantified patterns and trends from application information.

[0196] "Patterns and trends" refer to quantified patterns and trends based on application information obtained as a result of the analysis.

[0197] A "warning" refers to a notification or alert issued when the target number of applications is not met.

[0198] "Emotional state" refers to the feelings and psychological condition that can be inferred from the applicant's text information.

[0199] A "remind campaign" refers to emotionally sensitive information and messages sent to applicants to encourage them to participate in the application process.

[0200] "Promotional measures" refer to all measures and approaches implemented to increase the number of applications.

[0201] A "proposal for posting on an information sharing service" refers to a proposal for a campaign or initiative to be posted on an information sharing platform.

[0202] "Electronic message documents" refer to texts and content sent to applicants via email or other means.

[0203] A "reward incentive plan" is a strategic plan designed to encourage applicants to participate in the application process through rewards and incentives.

[0204] This invention provides a server-centric system for effectively managing application information in recruitment activities. The server retrieves application information from an external data storage device, analyzes it, and generates quantified patterns and trends. The analysis tools used are Python and the Flask framework, and the JavaScript library D3.js is used for data visualization.

[0205] The analyzed data is further analyzed in detail by an AI agent to estimate the applicant's emotions from their text information. This emotion analysis utilizes a TensorFlow model. The results of the emotion analysis are presented to the user as reminder campaigns and promotional strategies. This allows the user to respond in a way that is sensitive to the applicant's emotions. For example, if an applicant's emotions are positive, more proactive contact is recommended.

[0206] Users can receive these analysis results in real time via their devices and adjust their application strategies as needed. An example of a prompt might be, "Please tell me the current sentiment of applicants. What steps should we take?" This system allows for more effective implementation of measures to achieve application targets.

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The server retrieves application information from an external data storage device via an API. The input is query parameters, and the output is a dataset of the retrieved application information. This information includes the applicant's name, work experience, application date and time, etc.

[0210] Step 2:

[0211] The server sends application information to an AI agent for data analysis. The input is a dataset of application information, and the output is a quantified pattern or trend that indicates the applicant's application tendencies and emotions. In this process, Python and TensorFlow models are used to estimate emotions from the applicant's text information.

[0212] Step 3:

[0213] A server receives analysis results from an AI agent, visualizes the data using D3.js, and displays it on the user's device. Input is quantified patterns and trends, while output is visualized data in graph and chart format. Users can view this in real time.

[0214] Step 4:

[0215] The server generates emotionally conscious reminder campaigns and promotional strategies based on the analysis results. The input is the result of the emotional analysis, and the output is a proposal for a specific campaign or strategy tailored to that emotion. This proposal is automatically generated using a generative AI model.

[0216] Step 5:

[0217] Users receive notifications from the server in real time via their devices and adjust their application strategies accordingly. Inputs are suggestions and warnings from the server, while outputs are specific actions the user should take. Based on this, the user decides how to respond.

[0218] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0219] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0220] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0221] [Second Embodiment]

[0222] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0223] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0224] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0225] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0226] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0227] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0228] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0229] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0230] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0231] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0232] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0233] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0234] This invention aims to build a system that automates the monitoring and analysis of application status and efficiently proposes countermeasures. Specifically, it begins with periodically retrieving application data from an external database using a server. The server has the capability to process more than 5,000 application data entries in a short time and is accessed via an API. The retrieved data is then sent by the server to an AI agent.

[0235] The AI ​​agent analyzes the received application data and extracts quantifiable patterns and trends. The analysis process analyzes data points such as application trends over the past 30 days, enabling application predictions and identification of peak times. These analysis results are returned to the server and visualized as graphs and reports. For example, a line graph can show the change in application numbers over time, and a pie chart can display the attribute distribution of applicants.

[0236] The server also has the functionality to generate these reports daily and weekly and automatically send them to the responsible person's terminal. Furthermore, a system is in place to send an alert if the number of applications does not meet the pre-set target. This alert is sent to the user's terminal via SMS or email, prompting a quick response.

[0237] After an alert is issued, the AI ​​agent proposes reminder campaigns and promotional measures. Specific measures include social media posts and email newsletters tailored to the target applicant demographic, as well as reward incentive plans including exclusive benefits. For example, for a campaign targeting younger demographics, it might propose an influencer collaboration campaign on Instagram. This allows users to quickly develop concrete action plans to increase the number of applications.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The server connects to an external database via an API to retrieve the latest application data. The server periodically performs this process to collect new application information and temporarily stores it.

[0241] Step 2:

[0242] The server transfers the collected application data to the AI ​​agent. The data includes details such as the applicant's name, inquiry date and time, and application channel, which are necessary items for analysis by the AI ​​agent.

[0243] Step 3:

[0244] The AI ​​agent analyzes the received application data to extract patterns and trends in the number of applications and their attributes. For example, it can evaluate whether the number of applications increases during a specific period and understand weekly application trends.

[0245] Step 4:

[0246] The server receives the analysis results from the AI ​​agent and generates data for visualization. It visualizes fluctuations in the number of applications and the breakdown of applicant attributes in graph and chart format.

[0247] Step 5:

[0248] The server sends the generated graphs and reports to the user's terminal. Users receive detailed analysis reports daily or weekly to understand the application status.

[0249] Step 6:

[0250] If the number of applications falls short of the target, the server will create an alert and notify the user. The notification will be sent via email or SMS, allowing for immediate action.

[0251] Step 7:

[0252] The AI ​​agent proposes reminder campaigns and promotional measures as recovery measures for failing to meet targets. These measures are then implemented as suggested social media posts, reward incentives, or specific email newsletters.

[0253] Step 8:

[0254] The user reviews the proposed measures and decides whether or not to implement them. Based on the user's decision, the measures deemed most effective are selected.

[0255] Step 9:

[0256] Based on the selected measures, the server performs the necessary configurations and prepares for scheduled social media posts and email newsletter distribution. These are then executed automatically according to the pre-set schedule.

[0257] (Example 1)

[0258] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0259] In today's information-driven society, it is crucial to process large volumes of application information quickly and efficiently, and to provide the necessary information for developing appropriate strategies. However, manual data processing and analysis are time-consuming and labor-intensive, making them insufficient in a business environment where rapid response is essential. To address this challenge, an automated data acquisition, analysis, and notification system is necessary.

[0260] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0261] In this invention, the server includes means for acquiring application information from an external information source, means for analyzing the application information and generating quantified trends, means for detecting failure to meet application targets based on the analysis results, means for issuing warnings in the event of failure to meet targets, means for providing reminder information and proposing measures in accordance with the failure to meet targets, means for converting and displaying the analysis results as time-series data, and means for automatically generating and electronically transmitting reports. This enables immediate analysis and proposal of countermeasures for large amounts of application information, realizing rapid strategic planning and execution.

[0262] "Application information" refers to a collection of data and information provided by the applicant, including application details and related attribute information.

[0263] An "external information source" refers to a database or data server located outside the system where application information is stored.

[0264] "Analysis" is the process of processing acquired application information numerically or pattern-wise to derive specific trends or meanings.

[0265] "Quantified trends" refer to quantitative indicators and patterns related to the number of applications and applicant attributes obtained as a result of data analysis.

[0266] "Failure to meet targets" refers to a situation where the set number of applications or other criteria have not been met.

[0267] A "warning" is a notification issued when specific conditions occur, such as failing to meet targets, and is intended to encourage prompt action.

[0268] "Reminder information provision" refers to information or suggestions sent when goals are not met, intended to draw attention to applicants and related parties and encourage action.

[0269] A "policy" refers to a specific action plan or strategy implemented to achieve a set goal.

[0270] "Time-series data" refers to data recorded over time and is used to visually represent changes and trends in the number of applications.

[0271] A "report" is a document that includes a visual representation of analysis results and application information, and is intended to provide information for decision-making and strategy formulation.

[0272] "Electronically transmitted" refers to the method of sending generated reports and notices via the internet or email.

[0273] This invention is a system that automatically processes large amounts of application information and supports strategic decision-making. Specific embodiments are described below.

[0274] First, the server establishes communication with external information sources and periodically retrieves application information using APIs. The server has high-performance computing capabilities to efficiently process large amounts of data.

[0275] The acquired data undergoes data cleansing on the server. Programming languages ​​such as Python are used to organize duplicate data and format inconsistencies, and to convert the data into a format that can be easily processed by the analysis engine.

[0276] The formatted data is sent from the server to the AI ​​agent. The AI ​​agent uses a generative AI model to analyze the quantified trends in the application information. In this process, time-series data of the number of applications is handled in particular to analyze and predict application trends.

[0277] The analysis results are returned to the server, where the data is visualized. The analysis results are displayed graphically using a JavaScript library (for example, Chart.js), and are converted into a visible form such as a line graph or pie chart.

[0278] Based on this, the server automatically generates a report and saves it in PDF or Excel format. This report is electronically delivered to the user's terminal, providing information to relevant parties. Furthermore, the system detects failure to meet targets and issues warnings to users as needed. Warnings are promptly notified using SMS gateways, etc.

[0279] Regarding the proposal of countermeasures, the server generates prompt messages based on the analysis results to devise specific marketing strategies. An example of such a prompt message is, "The number of applications has not reached the target. Please propose effective countermeasures."

[0280] Finally, as a policy proposal, a promotion plan targeted at specific applicant groups is provided. For example, it is possible to increase the number of applications by disseminating information using SNS or proposing a reward incentive plan.

[0281] Through such a series of processes, the system provides the ability to support efficient data analysis and strategic decision-making.

[0282] The flow of the specific process in Example 1 will be described using FIG. 11.

[0283] Step 1:

[0284] The server connects to an external information source to obtain application information. The input is the application information stored in the external information source, and the output is the raw data obtained. As a specific operation, it periodically accesses the information source through an API and downloads the application information.

[0285] Step 2:

[0286] The server formats the obtained application information. The input is the raw application data, and the output is the cleansed application data. In this step, preprocessing such as data duplication removal and format unification is performed using Python scripts.

[0287] Step 3:

[0288] The server sends the formatted data to the AI agent. The input is the cleansed application data, and the output is the data prepared for analysis. In this process, the data format is adjusted according to the requirements of the AI agent.

[0289] Step 4:

[0290] The AI ​​agent analyzes the received data and extracts quantifiable trends. The input is pre-prepared data for analysis, and the output obtained from the analysis is trend information and prediction results. Specifically, it uses a generative AI model to perform time series analysis and analyze application trends and predict peak times.

[0291] Step 5:

[0292] The server receives the analysis results and visualizes the data. The input is the analysis results from the AI ​​agent, and the output is the visualized data (graphs, charts, etc.). The server uses a JavaScript library (e.g., Chart.js) to convert it into a format that can be visually displayed in a browser.

[0293] Step 6:

[0294] The server generates reports based on visualized data and saves them electronically. Input is visualized data, and output is a report in PDF or Excel format. The automated process ensures regular reporting.

[0295] Step 7:

[0296] The server generates the report and then delivers it to the user's terminal. The input is the generated report, and the output is the delivered electronic report. SMTP is used to provide the report to the user as an attachment.

[0297] Step 8:

[0298] The server issues a warning if it detects that the set target has not been met. The inputs are the analysis results and the target value, and the output is a warning notification. Specifically, it uses an SMS gateway to send a warning message to the user.

[0299] Step 9:

[0300] After receiving a warning, the AI agent generates a prompt text and proposes measures. The input is the unmet target and candidate measure data, and the output is a specific measure proposal. For example, an effective proposal is made in a situation where a quick response is required, such as proposing an SNS campaign for a specific target.

[0301] (Application Example 1)

[0302] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0303] It is difficult to efficiently analyze a plurality of application information and grasp its trends. In addition, a system for quickly taking countermeasures when the number of applicants does not reach the target is required. In addition, means for presenting the attribute information of applicants in a visually understandable form are also insufficient. It is important to solve these problems. [[ID=一十三]]

[0304] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0305] In this invention, the server includes means for acquiring application information from an external information source, means for analyzing the application information and generating quantified patterns and trends, and means for aggregating and visually displaying the attribute information of applicants. As a result, efficient analysis of application information and visualization of trends become possible. [[ID=二十二]]

[0306] "Application information" is a general term for data related to applicants collected from an external information source.

[0307] "External information source" refers to an external data provider such as the Internet or an external database, which is the target to be accessed by the system to obtain necessary information.

[0308] "Quantified pattern" is an index indicating the application trends and tendencies as numerical data obtained by analyzing the collected application information.

[0309] "Failure to meet the target number of applications" means that the actual number of applications is insufficient compared to the set target number.

[0310] A "warning" is a notification sent to users to prompt action when the number of applications has not reached the target.

[0311] "Notification activities" refer to information dissemination and campaign activities directed at a target group when goals are not met.

[0312] "Promotional measures" refer to specific action plans proposed to increase the number of applications, including posting on online communication platforms and electronic newsletters.

[0313] "Applicant attribute information" refers to information that indicates characteristics of the applicant, such as age, gender, and region.

[0314] "Visually displaying" refers to the process of transforming aggregated data into a form that is easy to understand visually, such as graphs and diagrams.

[0315] As a form for carrying out the invention, the system that realizes this application example consists of a server, an AI agent, a user terminal, and a network connecting them.

[0316] The server uses an API to collect application information from external sources and sends it to an AI agent. The AI ​​agent uses a generative AI model to analyze the application information and extract quantifiable patterns. This analysis process clarifies past application trends and applicant attribute information.

[0317] Based on the acquired analysis results, the server automatically sends a warning to the user's terminal if the number of applications has not reached the target. This is done using email or SMS notification functions. Furthermore, graphs and charts are generated to visually display the analysis results and clearly show the application status to the user.

[0318] This allows users to quickly and efficiently grasp application information and take necessary measures. For example, if application trends are skewed towards younger generations, the system will suggest strategies to appeal to younger generations based on those results. An example of a prompt message would be, "If the number of applications has not reached 80% of the target, please suggest new promotional measures."

[0319] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0320] Step 1:

[0321] The server retrieves application information from external sources using an API. The input is the application data obtained via the API, and the output is the raw data stored within the server. This data is then deployed for subsequent analysis processes.

[0322] Step 2:

[0323] The server transmits the acquired application information to the AI ​​agent. The input is the application information stored on the server, and the output is the data transfer to the AI ​​agent. The server uses a transmission protocol to ensure that the data is reliably delivered to the agent.

[0324] Step 3:

[0325] The AI ​​agent analyzes application information and extracts quantified patterns using a generative AI model. The input is application information received from the server, and the output is the analysis results of application trends and applicant attributes. This analysis process is performed using numerical algorithms and data learning models.

[0326] Step 4:

[0327] Based on the analysis results, the server sends a warning to the user's terminal if the number of applications has not reached the target. The input is the analysis results received from the AI ​​agent, and the output is the warning notification sent to the user. The server sends this notification via email or SMS to support a quick response.

[0328] Step 5:

[0329] The server generates graphs and charts to visually display the analysis results. The input is the analyzed data, and the output is graphs and charts that can be viewed on the user's terminal. The server uses visualization software to graphically transform the data.

[0330] Step 6:

[0331] Based on these results, the user takes the necessary countermeasures. The input is visual information presented by the server, and the output is a concrete action plan. For example, this could involve planning and executing a social media campaign targeting young people.

[0332] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0333] In this invention, the application status monitoring system is built around a server. First, the server retrieves application data from an external database via an API. This ensures that the server always maintains the latest application information and sends it to the AI ​​agent each time data is retrieved.

[0334] The AI ​​agent quickly analyzes submitted application data, generating quantifiable patterns and trends. The analysis results are sent back to the server and visualized in graphs and charts. Users receive these reports in real time on their devices, allowing them to monitor application trends and goal achievement rates.

[0335] In particular, by utilizing an emotion engine, a mechanism has been added to analyze emotions from user feedback and the content entered in application forms. The emotion engine estimates emotions based on the applicant's text data and provides the results to the AI ​​agent. For example, it can detect whether an applicant is satisfied or dissatisfied and customize the response accordingly.

[0336] The server generates an alert if the number of applications does not reach the set target. It also uses data from sentiment analysis to suggest more effective communication styles. For example, if an applicant is experiencing stress, it can design a reminder campaign that sends messages to alleviate that stress.

[0337] Users receive suggested strategies and alerts from the server, and based on this, they can determine specific action plans to improve the application status. The content of the strategies can be adapted to the target audience by adjusting them according to the results of sentiment analysis.

[0338] Thus, a key feature of this embodiment of the present invention is that by using an emotion engine, it is possible to not only perform data analysis but also to provide more effective measures that are tailored to the emotions of applicants.

[0339] The following describes the processing flow.

[0340] Step 1:

[0341] The server connects to an external database via an API and periodically retrieves application data. Specifically, application information is collected every 10 minutes and stored in the database.

[0342] Step 2:

[0343] The server sends the collected application data to the AI ​​agent. The data includes the applicant's personal information, application details, and comments made during the application process.

[0344] Step 3:

[0345] The AI ​​agent analyzes the received data and quantifies the trends and patterns of applicants. Furthermore, the AI ​​agent uses an emotion engine to extract emotional data from application texts and comments.

[0346] Step 4:

[0347] The emotion engine classifies the candidate's emotions as positive, negative, or neutral, and feeds the result back to the AI ​​agent.

[0348] Step 5:

[0349] The server receives analysis results and sentiment data from the AI ​​agent and generates a visualized report. Graphs and charts visualize trends in the number of applications and the proportion of sentiment data.

[0350] Step 6:

[0351] The server automatically generates reports and sends them to the employee's terminal. The employee reviews the daily reports to understand the current status of applications and the applicants' emotional tendencies.

[0352] Step 7:

[0353] If the number of applications falls short of the target, the server will issue an alert. This alert will be delivered to the person in charge via email notification or as a warning on the dashboard.

[0354] Step 8:

[0355] Based on the emotional tendencies detected by the emotion engine, the AI ​​agent proposes reminder campaigns and promotional measures. For example, if negative emotions are high, it will plan an email campaign with content that addresses the applicant's dissatisfaction.

[0356] Step 9:

[0357] Users review the proposed measures from the server and select the measures they wish to implement. The selected measures are then used to provide the most appropriate response to each applicant.

[0358] Step 10:

[0359] The server executes the selected measures. It automates scheduled social media posts and sentiment-based email distribution to maximize effectiveness.

[0360] (Example 2)

[0361] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0362] When companies and organizations conduct diverse campaigns, they need to quickly grasp trends in the number of applications and implement flexible measures that reflect the emotional state of applicants. However, conventional systems have faced challenges in that the process of acquiring and analyzing application data is inefficient, making it difficult to respond based on applicants' emotions.

[0363] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0364] In this invention, the server includes means for acquiring application data from a recording device, means for evaluating the application data using an analysis device and generating quantified patterns and trends, and means for estimating emotions from text data and using the results to make suggestions that correspond to the emotional state of the applicant. This makes it possible to accurately grasp application trends and quickly propose measures that take into account the emotions of the applicants.

[0365] "Application data" refers to all information related to applications that is acquired from recording devices and used for analysis.

[0366] An "analysis device" is a device that evaluates application data and generates quantified patterns and trends.

[0367] "Patterns and trends" refer to numerical representations of application trends and characteristics obtained as a result of data analysis.

[0368] A "warning" refers to a notice or alert issued when the number of applications has not reached the set target.

[0369] "Campaigns and promotional activities" refer to special proposals or actions designed to attract users' attention and encourage participation.

[0370] "Methods for estimating emotions from text data" refers to technologies and methods for inferring the emotional state of applicants through text analysis and utilizing the results.

[0371] "Users" refers to individuals or organizations that use the system to receive analysis results of application data and proposed measures.

[0372] To implement this invention, the following configuration is necessary: ​​The server periodically retrieves application data from an external database and transmits it to the analysis device. This retrieval is performed via an API, and a specific data exchange format (such as JSON) is typically used in this process.

[0373] The analysis system uses a generative AI model to evaluate the data in detail and extract quantifiable patterns and trends. This analysis system is likely to be built using a machine learning framework (e.g., TensorFlow or PyTorch).

[0374] Furthermore, based on the analysis results, the server uses sentiment analysis tools to estimate the emotions of applicants from the text data they provide. At this time, natural language processing techniques are used to analyze the applicants' emotions from the text. Sentiment analysis is expected to be performed using NLP libraries (e.g., spaCy or NLTK).

[0375] The visualized analysis results are sent to the device in real time, allowing users to understand trends in the number of applications. This visualization utilizes libraries such as D3.js and Chart.js to build the user interface.

[0376] As a concrete example, in an online sales campaign, the server retrieves application data, analyzes it through a generated AI model, and then proposes a new promotional strategy to the user based on the results. An example of a prompt message would be, "Analyze the latest application data and report on applicant satisfaction and application trends. Also, suggest a suitable messaging campaign if applicants are experiencing stress." By inputting this, the system can provide useful insights.

[0377] A system configured in this way processes application data quickly and efficiently, providing users with accurate information. This enhances the management of application status and maximizes the effectiveness of campaigns.

[0378] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0379] Step 1:

[0380] The server periodically sends API requests to an external database to retrieve application data. This input allows the server to receive application data in JSON format, including the user's name, application date, and feedback comments. The received data is then prepared for analysis in the next step.

[0381] Step 2:

[0382] The server sends the received application data to the analysis device. The analysis device uses a generative AI model to analyze the input data and extract applicant behavior patterns and quantifiable trends. Specific data processing includes correlation analysis with historical data and applicant classification through clustering. The analysis results are temporarily returned to the server for use in the next step.

[0383] Step 3:

[0384] The server uses an emotion engine based on the analysis results to estimate emotions from applicants' text data. The input data consists of applicant comments, and natural language processing techniques are used to extract positive or negative emotions. The output is an emotion scoring result and emotion trend. This information will be used to propose subsequent measures.

[0385] Step 4:

[0386] The server visualizes the number of applications in real time based on the analysis results and sentiment scores. The visualized data is sent to the terminal and displayed to the user. Depending on the library used (e.g., D3.js), graphs of the trend in the number of applications and sentiment status are generated and provided to the user in an intuitively understandable format.

[0387] Step 5:

[0388] If the number of applications does not reach the target, the server will issue an alert and present suggested measures based on the results of sentiment analysis. In this step, for example, a message campaign could be designed to encourage stressed applicants to relax. Based on the information received by users on their devices, an effective action plan can be formulated.

[0389] (Application Example 2)

[0390] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0391] In modern recruitment processes, it is difficult to fully understand applicants' emotions and application trends, and there are challenges in responding quickly to changes in application trends. Furthermore, it is difficult to implement communication and measures that take applicants' emotions into consideration, which can result in failing to meet application targets.

[0392] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0393] In this invention, the server includes means for acquiring application information from an external information storage device, means for analyzing the application information and generating quantified patterns and trends, and means for analyzing the emotions of applicants from text information and customizing responses based on the results. This makes it possible to provide appropriate responses that take into account the emotions of applicants and to more effectively support the achievement of application number targets.

[0394] "Application information" refers to data related to recruitment activities obtained from external data storage devices.

[0395] "Analysis" is a series of processes that generate quantified patterns and trends from application information.

[0396] "Patterns and trends" refer to quantified patterns and trends based on application information obtained as a result of the analysis.

[0397] A "warning" refers to a notification or alert issued when the target number of applications is not met.

[0398] "Emotional state" refers to the feelings and psychological condition that can be inferred from the applicant's text information.

[0399] A "remind campaign" refers to emotionally sensitive information and messages sent to applicants to encourage them to participate in the application process.

[0400] "Promotional measures" refer to all measures and approaches implemented to increase the number of applications.

[0401] A "proposal for posting on an information sharing service" refers to a proposal for a campaign or initiative to be posted on an information sharing platform.

[0402] "Electronic message documents" refer to texts and content sent to applicants via email or other means.

[0403] A "reward incentive plan" is a strategic plan designed to encourage applicants to participate in the application process through rewards and incentives.

[0404] This invention provides a server-centric system for effectively managing application information in recruitment activities. The server retrieves application information from an external data storage device, analyzes it, and generates quantified patterns and trends. The analysis tools used are Python and the Flask framework, and the JavaScript library D3.js is used for data visualization.

[0405] The analyzed data is further analyzed in detail by an AI agent to estimate the applicant's emotions from their text information. This emotion analysis utilizes a TensorFlow model. The results of the emotion analysis are presented to the user as reminder campaigns and promotional strategies. This allows the user to respond in a way that is sensitive to the applicant's emotions. For example, if an applicant's emotions are positive, more proactive contact is recommended.

[0406] Users can receive these analysis results in real time via their devices and adjust their application strategies as needed. An example of a prompt might be, "Please tell me the current sentiment of applicants. What steps should we take?" This system allows for more effective implementation of measures to achieve application targets.

[0407] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0408] Step 1:

[0409] The server retrieves application information from an external data storage device via an API. The input is query parameters, and the output is a dataset of the retrieved application information. This information includes the applicant's name, work experience, application date and time, etc.

[0410] Step 2:

[0411] The server sends application information to an AI agent for data analysis. The input is a dataset of application information, and the output is a quantified pattern or trend that indicates the applicant's application tendencies and emotions. In this process, Python and TensorFlow models are used to estimate emotions from the applicant's text information.

[0412] Step 3:

[0413] A server receives analysis results from an AI agent, visualizes the data using D3.js, and displays it on the user's device. Input is quantified patterns and trends, while output is visualized data in graph and chart format. Users can view this in real time.

[0414] Step 4:

[0415] The server generates emotionally conscious reminder campaigns and promotional strategies based on the analysis results. The input is the result of the emotional analysis, and the output is a proposal for a specific campaign or strategy tailored to that emotion. This proposal is automatically generated using a generative AI model.

[0416] Step 5:

[0417] Users receive notifications from the server in real time via their devices and adjust their application strategies accordingly. Inputs are suggestions and warnings from the server, while outputs are specific actions the user should take. Based on this, the user decides how to respond.

[0418] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0419] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0420] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0421] [Third Embodiment]

[0422] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0423] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0424] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0425] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0426] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0427] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0428] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0429] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0430] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0431] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0432] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0433] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0434] This invention aims to build a system that automates the monitoring and analysis of application status and efficiently proposes countermeasures. Specifically, it begins with periodically retrieving application data from an external database using a server. The server has the capability to process more than 5,000 application data entries in a short time and is accessed via an API. The retrieved data is then sent by the server to an AI agent.

[0435] The AI ​​agent analyzes the received application data and extracts quantifiable patterns and trends. The analysis process analyzes data points such as application trends over the past 30 days, enabling application predictions and identification of peak times. These analysis results are returned to the server and visualized as graphs and reports. For example, a line graph can show the change in application numbers over time, and a pie chart can display the attribute distribution of applicants.

[0436] The server also has the functionality to generate these reports daily and weekly and automatically send them to the responsible person's terminal. Furthermore, a system is in place to send an alert if the number of applications does not meet the pre-set target. This alert is sent to the user's terminal via SMS or email, prompting a quick response.

[0437] After an alert is issued, the AI ​​agent proposes reminder campaigns and promotional measures. Specific measures include social media posts and email newsletters tailored to the target applicant demographic, as well as reward incentive plans including exclusive benefits. For example, for a campaign targeting younger demographics, it might propose an influencer collaboration campaign on Instagram. This allows users to quickly develop concrete action plans to increase the number of applications.

[0438] The following describes the processing flow.

[0439] Step 1:

[0440] The server connects to an external database via an API to retrieve the latest application data. The server periodically performs this process to collect new application information and temporarily stores it.

[0441] Step 2:

[0442] The server transfers the collected application data to the AI ​​agent. The data includes details such as the applicant's name, inquiry date and time, and application channel, which are necessary items for analysis by the AI ​​agent.

[0443] Step 3:

[0444] The AI ​​agent analyzes the received application data to extract patterns and trends in the number of applications and their attributes. For example, it can evaluate whether the number of applications increases during a specific period and understand weekly application trends.

[0445] Step 4:

[0446] The server receives the analysis results from the AI ​​agent and generates data for visualization. It visualizes fluctuations in the number of applications and the breakdown of applicant attributes in graph and chart format.

[0447] Step 5:

[0448] The server sends the generated graphs and reports to the user's terminal. Users receive detailed analysis reports daily or weekly to understand the application status.

[0449] Step 6:

[0450] If the number of applications falls short of the target, the server will create an alert and notify the user. The notification will be sent via email or SMS, allowing for immediate action.

[0451] Step 7:

[0452] The AI ​​agent proposes reminder campaigns and promotional measures as recovery measures for failing to meet targets. These measures are then implemented as suggested social media posts, reward incentives, or specific email newsletters.

[0453] Step 8:

[0454] The user reviews the proposed measures and decides whether or not to implement them. Based on the user's decision, the measures deemed most effective are selected.

[0455] Step 9:

[0456] Based on the selected measures, the server performs the necessary configurations and prepares for scheduled social media posts and email newsletter distribution. These are then executed automatically according to the pre-set schedule.

[0457] (Example 1)

[0458] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0459] In today's information-driven society, it is crucial to process large volumes of application information quickly and efficiently, and to provide the necessary information for developing appropriate strategies. However, manual data processing and analysis are time-consuming and labor-intensive, making them insufficient in a business environment where rapid response is essential. To address this challenge, an automated data acquisition, analysis, and notification system is necessary.

[0460] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0461] In this invention, the server includes means for acquiring application information from an external information source, means for analyzing the application information and generating quantified trends, means for detecting failure to meet application targets based on the analysis results, means for issuing warnings in the event of failure to meet targets, means for providing reminder information and proposing measures in accordance with the failure to meet targets, means for converting and displaying the analysis results as time-series data, and means for automatically generating and electronically transmitting reports. This enables immediate analysis and proposal of countermeasures for large amounts of application information, realizing rapid strategic planning and execution.

[0462] "Application information" refers to a collection of data and information provided by the applicant, including application details and related attribute information.

[0463] An "external information source" refers to a database or data server located outside the system where application information is stored.

[0464] "Analysis" is the process of processing acquired application information numerically or pattern-wise to derive specific trends or meanings.

[0465] "Quantified trends" refer to quantitative indicators and patterns related to the number of applications and applicant attributes obtained as a result of data analysis.

[0466] "Failure to meet targets" refers to a situation where the set number of applications or other criteria have not been met.

[0467] A "warning" is a notification issued when specific conditions occur, such as failing to meet targets, and is intended to encourage prompt action.

[0468] "Reminder information provision" refers to information or suggestions sent when goals are not met, intended to draw attention to applicants and related parties and encourage action.

[0469] A "policy" refers to a specific action plan or strategy implemented to achieve a set goal.

[0470] "Time-series data" refers to data recorded over time and is used to visually represent changes and trends in the number of applications.

[0471] A "report" is a document that includes a visual representation of analysis results and application information, and is intended to provide information for decision-making and strategy formulation.

[0472] "Electronically transmitted" refers to the method of sending generated reports and notices via the internet or email.

[0473] This invention is a system that automatically processes large amounts of application information and supports strategic decision-making. Specific embodiments are described below.

[0474] First, the server establishes communication with external information sources and periodically retrieves application information using APIs. The server has high-performance computing capabilities to efficiently process large amounts of data.

[0475] The acquired data undergoes data cleansing on the server. Programming languages ​​such as Python are used to organize duplicate data and format inconsistencies, and to convert the data into a format that can be easily processed by the analysis engine.

[0476] The formatted data is sent from the server to the AI ​​agent. The AI ​​agent uses a generative AI model to analyze the quantified trends in the application information. In this process, time-series data of the number of applications is handled in particular to analyze and predict application trends.

[0477] The analysis results are returned to the server, where the data is visualized. The analysis results are displayed graphically using a JavaScript library (for example, Chart.js), and are converted into a visible form such as a line graph or pie chart.

[0478] Based on this, the server automatically generates a report and saves it in PDF or Excel format. This report is electronically delivered to the user's terminal, providing information to relevant parties. Furthermore, the system detects failure to meet targets and issues warnings to users as needed. Warnings are promptly notified using SMS gateways, etc.

[0479] Regarding the proposal of countermeasures, the server generates prompt messages based on the analysis results to devise specific marketing strategies. An example of such a prompt message is, "The number of applications has not reached the target. Please propose effective countermeasures."

[0480] Finally, as part of the proposed strategies, promotional plans targeting specific applicant groups will be provided. For example, it may be possible to increase the number of applications by proposing information dissemination using social media or reward incentive plans.

[0481] Through this series of processes, the system provides the ability to support efficient data analysis and strategic decision-making.

[0482] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0483] Step 1:

[0484] The server connects to an external information source to retrieve application information. The input is the application information stored in the external information source, and the output is the retrieved raw data. Specifically, it periodically accesses the information source via an API and downloads the application information.

[0485] Step 2:

[0486] The server formats the acquired application information. The input is raw application data, and the output is cleaned application data. In this step, preprocessing such as data duplication removal and formatting is performed using a Python script.

[0487] Step 3:

[0488] The server sends the formatted data to the AI ​​agent. The input is cleansed application data, and the output is ready data for analysis. In this process, the data format is adjusted according to the AI ​​agent's requirements.

[0489] Step 4:

[0490] The AI ​​agent analyzes the received data and extracts quantifiable trends. The input is pre-prepared data for analysis, and the output obtained from the analysis is trend information and prediction results. Specifically, it uses a generative AI model to perform time series analysis and analyze application trends and predict peak times.

[0491] Step 5:

[0492] The server receives the analysis results and visualizes the data. The input is the analysis results from the AI ​​agent, and the output is the visualized data (graphs, charts, etc.). The server uses a JavaScript library (e.g., Chart.js) to convert it into a format that can be visually displayed in a browser.

[0493] Step 6:

[0494] The server generates reports based on visualized data and saves them electronically. Input is visualized data, and output is a report in PDF or Excel format. The automated process ensures regular reporting.

[0495] Step 7:

[0496] The server generates the report and then delivers it to the user's terminal. The input is the generated report, and the output is the delivered electronic report. SMTP is used to provide the report to the user as an attachment.

[0497] Step 8:

[0498] The server issues a warning if it detects that the set target has not been met. The inputs are the analysis results and the target value, and the output is a warning notification. Specifically, it uses an SMS gateway to send a warning message to the user.

[0499] Step 9:

[0500] The AI ​​agent generates a prompt message and proposes countermeasures after issuing a warning. The input consists of unmet targets and candidate countermeasure data, while the output is a specific countermeasure proposal. For example, it can make effective suggestions in situations requiring a quick response, such as proposing an SNS campaign to a specific target audience.

[0501] (Application Example 1)

[0502] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0503] It is difficult to efficiently analyze multiple application data and understand their trends. Furthermore, a system is needed to quickly implement countermeasures when the number of applications does not reach the target. In addition, there are insufficient means of presenting applicant attribute information in a visually easy-to-understand format. Solving these challenges is crucial.

[0504] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0505] In this invention, the server includes means for acquiring application information from an external information source, means for analyzing the application information and generating quantified patterns and trends, and means for aggregating and visually displaying applicant attribute information. This enables efficient analysis of application information and visualization of trends.

[0506] "Application information" is a general term for data about applicants collected from external sources.

[0507] "External information sources" refer to external data sources such as the internet and external databases, which are accessed by the system to obtain the information it needs.

[0508] A "quantified pattern" is an indicator that shows application trends and tendencies as numerical data obtained by analyzing collected application information.

[0509] "Failure to meet the target number of applications" means that the actual number of applications is insufficient compared to the set target number.

[0510] A "warning" is a notification sent to users to prompt action when the number of applications has not reached the target.

[0511] "Notification activities" refer to information dissemination and campaign activities directed at a target group when goals are not met.

[0512] "Promotional measures" refer to specific action plans proposed to increase the number of applications, including posting on online communication platforms and electronic newsletters.

[0513] "Applicant attribute information" refers to information that indicates characteristics of the applicant, such as age, gender, and region.

[0514] "Visually displaying" refers to the process of transforming aggregated data into a form that is easy to understand visually, such as graphs and diagrams.

[0515] As a form for carrying out the invention, the system that realizes this application example consists of a server, an AI agent, a user terminal, and a network connecting them.

[0516] The server uses an API to collect application information from external sources and sends it to an AI agent. The AI ​​agent uses a generative AI model to analyze the application information and extract quantifiable patterns. This analysis process clarifies past application trends and applicant attribute information.

[0517] Based on the acquired analysis results, the server automatically sends a warning to the user's terminal if the number of applications has not reached the target. This is done using email or SMS notification functions. Furthermore, graphs and charts are generated to visually display the analysis results and clearly show the application status to the user.

[0518] This allows users to quickly and efficiently grasp application information and take necessary measures. For example, if application trends are skewed towards younger generations, the system will suggest strategies to appeal to younger generations based on those results. An example of a prompt message would be, "If the number of applications has not reached 80% of the target, please suggest new promotional measures."

[0519] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0520] Step 1:

[0521] The server retrieves application information from external sources using an API. The input is the application data obtained via the API, and the output is the raw data stored within the server. This data is then deployed for subsequent analysis processes.

[0522] Step 2:

[0523] The server transmits the acquired application information to the AI ​​agent. The input is the application information stored on the server, and the output is the data transfer to the AI ​​agent. The server uses a transmission protocol to ensure that the data is reliably delivered to the agent.

[0524] Step 3:

[0525] The AI ​​agent analyzes application information and extracts quantified patterns using a generative AI model. The input is application information received from the server, and the output is the analysis results of application trends and applicant attributes. This analysis process is performed using numerical algorithms and data learning models.

[0526] Step 4:

[0527] Based on the analysis results, the server sends a warning to the user's terminal if the number of applications has not reached the target. The input is the analysis results received from the AI ​​agent, and the output is the warning notification sent to the user. The server sends this notification via email or SMS to support a quick response.

[0528] Step 5:

[0529] The server generates graphs and charts to visually display the analysis results. The input is the analyzed data, and the output is graphs and charts that can be viewed on the user's terminal. The server uses visualization software to graphically transform the data.

[0530] Step 6:

[0531] Based on these results, the user takes the necessary countermeasures. The input is visual information presented by the server, and the output is a concrete action plan. For example, this could involve planning and executing a social media campaign targeting young people.

[0532] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0533] In this invention, the application status monitoring system is built around a server. First, the server retrieves application data from an external database via an API. This ensures that the server always maintains the latest application information and sends it to the AI ​​agent each time data is retrieved.

[0534] The AI ​​agent quickly analyzes submitted application data, generating quantifiable patterns and trends. The analysis results are sent back to the server and visualized in graphs and charts. Users receive these reports in real time on their devices, allowing them to monitor application trends and goal achievement rates.

[0535] In particular, by utilizing an emotion engine, a mechanism has been added to analyze emotions from user feedback and the content entered in application forms. The emotion engine estimates emotions based on the applicant's text data and provides the results to the AI ​​agent. For example, it can detect whether an applicant is satisfied or dissatisfied and customize the response accordingly.

[0536] The server generates an alert if the number of applications does not reach the set target. It also uses data from sentiment analysis to suggest more effective communication styles. For example, if an applicant is experiencing stress, it can design a reminder campaign that sends messages to alleviate that stress.

[0537] Users receive suggested strategies and alerts from the server, and based on this, they can determine specific action plans to improve the application status. The content of the strategies can be adapted to the target audience by adjusting them according to the results of sentiment analysis.

[0538] Thus, a key feature of this embodiment of the present invention is that by using an emotion engine, it is possible to not only perform data analysis but also to provide more effective measures that are tailored to the emotions of applicants.

[0539] The following describes the processing flow.

[0540] Step 1:

[0541] The server connects to an external database via an API and periodically retrieves application data. Specifically, application information is collected every 10 minutes and stored in the database.

[0542] Step 2:

[0543] The server sends the collected application data to the AI ​​agent. The data includes the applicant's personal information, application details, and comments made during the application process.

[0544] Step 3:

[0545] The AI ​​agent analyzes the received data and quantifies the trends and patterns of applicants. Furthermore, the AI ​​agent uses an emotion engine to extract emotional data from application texts and comments.

[0546] Step 4:

[0547] The emotion engine classifies the candidate's emotions as positive, negative, or neutral, and feeds the result back to the AI ​​agent.

[0548] Step 5:

[0549] The server receives analysis results and sentiment data from the AI ​​agent and generates a visualized report. Graphs and charts visualize trends in the number of applications and the proportion of sentiment data.

[0550] Step 6:

[0551] The server automatically generates reports and sends them to the employee's terminal. The employee reviews the daily reports to understand the current status of applications and the applicants' emotional tendencies.

[0552] Step 7:

[0553] If the number of applications falls short of the target, the server will issue an alert. This alert will be delivered to the person in charge via email notification or as a warning on the dashboard.

[0554] Step 8:

[0555] Based on the emotional tendencies detected by the emotion engine, the AI ​​agent proposes reminder campaigns and promotional measures. For example, if negative emotions are high, it will plan an email campaign with content that addresses the applicant's dissatisfaction.

[0556] Step 9:

[0557] Users review the proposed measures from the server and select the measures they wish to implement. The selected measures are then used to provide the most appropriate response to each applicant.

[0558] Step 10:

[0559] The server executes the selected measures. It automates scheduled social media posts and sentiment-based email distribution to maximize effectiveness.

[0560] (Example 2)

[0561] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0562] When companies and organizations conduct diverse campaigns, they need to quickly grasp trends in the number of applications and implement flexible measures that reflect the emotional state of applicants. However, conventional systems have faced challenges in that the process of acquiring and analyzing application data is inefficient, making it difficult to respond based on applicants' emotions.

[0563] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0564] In this invention, the server includes means for acquiring application data from a recording device, means for evaluating the application data using an analysis device and generating quantified patterns and trends, and means for estimating emotions from text data and using the results to make suggestions that correspond to the emotional state of the applicant. This makes it possible to accurately grasp application trends and quickly propose measures that take into account the emotions of the applicants.

[0565] "Application data" refers to all information related to applications that is acquired from recording devices and used for analysis.

[0566] An "analysis device" is a device that evaluates application data and generates quantified patterns and trends.

[0567] "Patterns and trends" refer to numerical representations of application trends and characteristics obtained as a result of data analysis.

[0568] A "warning" refers to a notice or alert issued when the number of applications has not reached the set target.

[0569] "Campaigns and promotional activities" refer to special proposals or actions designed to attract users' attention and encourage participation.

[0570] "Methods for estimating emotions from text data" refers to technologies and methods for inferring the emotional state of applicants through text analysis and utilizing the results.

[0571] "Users" refers to individuals or organizations that use the system to receive analysis results of application data and proposed measures.

[0572] To implement this invention, the following configuration is necessary: ​​The server periodically retrieves application data from an external database and transmits it to the analysis device. This retrieval is performed via an API, and a specific data exchange format (such as JSON) is typically used in this process.

[0573] The analysis system uses a generative AI model to evaluate the data in detail and extract quantifiable patterns and trends. This analysis system is likely to be built using a machine learning framework (e.g., TensorFlow or PyTorch).

[0574] Furthermore, based on the analysis results, the server uses sentiment analysis tools to estimate the emotions of applicants from the text data they provide. At this time, natural language processing techniques are used to analyze the applicants' emotions from the text. Sentiment analysis is expected to be performed using NLP libraries (e.g., spaCy or NLTK).

[0575] The visualized analysis results are sent to the device in real time, allowing users to understand trends in the number of applications. This visualization utilizes libraries such as D3.js and Chart.js to build the user interface.

[0576] As a concrete example, in an online sales campaign, the server retrieves application data, analyzes it through a generated AI model, and then proposes a new promotional strategy to the user based on the results. An example of a prompt message would be, "Analyze the latest application data and report on applicant satisfaction and application trends. Also, suggest a suitable messaging campaign if applicants are experiencing stress." By inputting this, the system can provide useful insights.

[0577] A system configured in this way processes application data quickly and efficiently, providing users with accurate information. This enhances the management of application status and maximizes the effectiveness of campaigns.

[0578] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0579] Step 1:

[0580] The server periodically sends API requests to an external database to retrieve application data. This input allows the server to receive application data in JSON format, including the user's name, application date, and feedback comments. The received data is then prepared for analysis in the next step.

[0581] Step 2:

[0582] The server sends the received application data to the analysis device. The analysis device uses a generative AI model to analyze the input data and extract applicant behavior patterns and quantifiable trends. Specific data processing includes correlation analysis with historical data and applicant classification through clustering. The analysis results are temporarily returned to the server for use in the next step.

[0583] Step 3:

[0584] The server uses an emotion engine based on the analysis results to estimate emotions from applicants' text data. The input data consists of applicant comments, and natural language processing techniques are used to extract positive or negative emotions. The output is an emotion scoring result and emotion trend. This information will be used to propose subsequent measures.

[0585] Step 4:

[0586] The server visualizes the number of applications in real time based on the analysis results and sentiment scores. The visualized data is sent to the terminal and displayed to the user. Depending on the library used (e.g., D3.js), graphs of the trend in the number of applications and sentiment status are generated and provided to the user in an intuitively understandable format.

[0587] Step 5:

[0588] If the number of applications does not reach the target, the server will issue an alert and present suggested measures based on the results of sentiment analysis. In this step, for example, a message campaign could be designed to encourage stressed applicants to relax. Based on the information received by users on their devices, an effective action plan can be formulated.

[0589] (Application Example 2)

[0590] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0591] In modern recruitment processes, it is difficult to fully understand applicants' emotions and application trends, and there are challenges in responding quickly to changes in application trends. Furthermore, it is difficult to implement communication and measures that take applicants' emotions into consideration, which can result in failing to meet application targets.

[0592] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0593] In this invention, the server includes means for acquiring application information from an external information storage device, means for analyzing the application information and generating quantified patterns and trends, and means for analyzing the emotions of applicants from text information and customizing responses based on the results. This makes it possible to provide appropriate responses that take into account the emotions of applicants and to more effectively support the achievement of application number targets.

[0594] "Application information" refers to data related to recruitment activities obtained from external data storage devices.

[0595] "Analysis" is a series of processes that generate quantified patterns and trends from application information.

[0596] "Patterns and trends" refer to quantified patterns and trends based on application information obtained as a result of the analysis.

[0597] A "warning" refers to a notification or alert issued when the target number of applications is not met.

[0598] "Emotional state" refers to the feelings and psychological condition that can be inferred from the applicant's text information.

[0599] A "remind campaign" refers to emotionally sensitive information and messages sent to applicants to encourage them to participate in the application process.

[0600] "Promotional measures" refer to all measures and approaches implemented to increase the number of applications.

[0601] A "proposal for posting on an information sharing service" refers to a proposal for a campaign or initiative to be posted on an information sharing platform.

[0602] "Electronic message documents" refer to texts and content sent to applicants via email or other means.

[0603] A "reward incentive plan" is a strategic plan designed to encourage applicants to participate in the application process through rewards and incentives.

[0604] This invention provides a server-centric system for effectively managing application information in recruitment activities. The server retrieves application information from an external data storage device, analyzes it, and generates quantified patterns and trends. The analysis tools used are Python and the Flask framework, and the JavaScript library D3.js is used for data visualization.

[0605] The analyzed data is further analyzed in detail by an AI agent to estimate the applicant's emotions from their text information. This emotion analysis utilizes a TensorFlow model. The results of the emotion analysis are presented to the user as reminder campaigns and promotional strategies. This allows the user to respond in a way that is sensitive to the applicant's emotions. For example, if an applicant's emotions are positive, more proactive contact is recommended.

[0606] Users can receive these analysis results in real time via their devices and adjust their application strategies as needed. An example of a prompt might be, "Please tell me the current sentiment of applicants. What steps should we take?" This system allows for more effective implementation of measures to achieve application targets.

[0607] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0608] Step 1:

[0609] The server retrieves application information from an external data storage device via an API. The input is query parameters, and the output is a dataset of the retrieved application information. This information includes the applicant's name, work experience, application date and time, etc.

[0610] Step 2:

[0611] The server sends application information to an AI agent for data analysis. The input is a dataset of application information, and the output is a quantified pattern or trend that indicates the applicant's application tendencies and emotions. In this process, Python and TensorFlow models are used to estimate emotions from the applicant's text information.

[0612] Step 3:

[0613] A server receives analysis results from an AI agent, visualizes the data using D3.js, and displays it on the user's device. Input is quantified patterns and trends, while output is visualized data in graph and chart format. Users can view this in real time.

[0614] Step 4:

[0615] The server generates emotionally conscious reminder campaigns and promotional strategies based on the analysis results. The input is the result of the emotional analysis, and the output is a proposal for a specific campaign or strategy tailored to that emotion. This proposal is automatically generated using a generative AI model.

[0616] Step 5:

[0617] Users receive notifications from the server in real time via their devices and adjust their application strategies accordingly. Inputs are suggestions and warnings from the server, while outputs are specific actions the user should take. Based on this, the user decides how to respond.

[0618] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0619] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0620] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0621] [Fourth Embodiment]

[0622] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0623] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0624] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0625] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0626] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0627] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0628] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0629] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0630] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0631] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0632] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0633] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0634] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0635] This invention aims to build a system that automates the monitoring and analysis of application status and efficiently proposes countermeasures. Specifically, it begins with periodically retrieving application data from an external database using a server. The server has the capability to process more than 5,000 application data entries in a short time and is accessed via an API. The retrieved data is then sent by the server to an AI agent.

[0636] The AI ​​agent analyzes the received application data and extracts quantifiable patterns and trends. The analysis process analyzes data points such as application trends over the past 30 days, enabling application predictions and identification of peak times. These analysis results are returned to the server and visualized as graphs and reports. For example, a line graph can show the change in application numbers over time, and a pie chart can display the attribute distribution of applicants.

[0637] The server also has the functionality to generate these reports daily and weekly and automatically send them to the responsible person's terminal. Furthermore, a system is in place to send an alert if the number of applications does not meet the pre-set target. This alert is sent to the user's terminal via SMS or email, prompting a quick response.

[0638] After an alert is issued, the AI ​​agent proposes reminder campaigns and promotional measures. Specific measures include social media posts and email newsletters tailored to the target applicant demographic, as well as reward incentive plans including exclusive benefits. For example, for a campaign targeting younger demographics, it might propose an influencer collaboration campaign on Instagram. This allows users to quickly develop concrete action plans to increase the number of applications.

[0639] The following describes the processing flow.

[0640] Step 1:

[0641] The server connects to an external database via an API to retrieve the latest application data. The server periodically performs this process to collect new application information and temporarily stores it.

[0642] Step 2:

[0643] The server transfers the collected application data to the AI ​​agent. The data includes details such as the applicant's name, inquiry date and time, and application channel, which are necessary items for analysis by the AI ​​agent.

[0644] Step 3:

[0645] The AI ​​agent analyzes the received application data to extract patterns and trends in the number of applications and their attributes. For example, it can evaluate whether the number of applications increases during a specific period and understand weekly application trends.

[0646] Step 4:

[0647] The server receives the analysis results from the AI ​​agent and generates data for visualization. It visualizes fluctuations in the number of applications and the breakdown of applicant attributes in graph and chart format.

[0648] Step 5:

[0649] The server sends the generated graphs and reports to the user's terminal. Users receive detailed analysis reports daily or weekly to understand the application status.

[0650] Step 6:

[0651] If the number of applications falls short of the target, the server will create an alert and notify the user. The notification will be sent via email or SMS, allowing for immediate action.

[0652] Step 7:

[0653] The AI ​​agent proposes reminder campaigns and promotional measures as recovery measures for failing to meet targets. These measures are then implemented as suggested social media posts, reward incentives, or specific email newsletters.

[0654] Step 8:

[0655] The user reviews the proposed measures and decides whether or not to implement them. Based on the user's decision, the measures deemed most effective are selected.

[0656] Step 9:

[0657] Based on the selected measures, the server performs the necessary configurations and prepares for scheduled social media posts and email newsletter distribution. These are then executed automatically according to the pre-set schedule.

[0658] (Example 1)

[0659] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0660] In today's information-driven society, it is crucial to process large volumes of application information quickly and efficiently, and to provide the necessary information for developing appropriate strategies. However, manual data processing and analysis are time-consuming and labor-intensive, making them insufficient in a business environment where rapid response is essential. To address this challenge, an automated data acquisition, analysis, and notification system is necessary.

[0661] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0662] In this invention, the server includes means for acquiring application information from an external information source, means for analyzing the application information and generating quantified trends, means for detecting failure to meet application targets based on the analysis results, means for issuing warnings in the event of failure to meet targets, means for providing reminder information and proposing measures in accordance with the failure to meet targets, means for converting and displaying the analysis results as time-series data, and means for automatically generating and electronically transmitting reports. This enables immediate analysis and proposal of countermeasures for large amounts of application information, realizing rapid strategic planning and execution.

[0663] "Application information" refers to a collection of data and information provided by the applicant, including application details and related attribute information.

[0664] An "external information source" refers to a database or data server located outside the system where application information is stored.

[0665] "Analysis" is the process of processing acquired application information numerically or pattern-wise to derive specific trends or meanings.

[0666] "Quantified trends" refer to quantitative indicators and patterns related to the number of applications and applicant attributes obtained as a result of data analysis.

[0667] "Failure to meet targets" refers to a situation where the set number of applications or other criteria have not been met.

[0668] A "warning" is a notification issued when specific conditions occur, such as failing to meet targets, and is intended to encourage prompt action.

[0669] "Reminder information provision" refers to information or suggestions sent when goals are not met, intended to draw attention to applicants and related parties and encourage action.

[0670] A "policy" refers to a specific action plan or strategy implemented to achieve a set goal.

[0671] "Time-series data" refers to data recorded over time and is used to visually represent changes and trends in the number of applications.

[0672] A "report" is a document that includes a visual representation of analysis results and application information, and is intended to provide information for decision-making and strategy formulation.

[0673] "Electronically transmitted" refers to the method of sending generated reports and notices via the internet or email.

[0674] This invention is a system that automatically processes large amounts of application information and supports strategic decision-making. Specific embodiments are described below.

[0675] First, the server establishes communication with external information sources and periodically retrieves application information using APIs. The server has high-performance computing capabilities to efficiently process large amounts of data.

[0676] The acquired data undergoes data cleansing on the server. Programming languages ​​such as Python are used to organize duplicate data and format inconsistencies, and to convert the data into a format that can be easily processed by the analysis engine.

[0677] The formatted data is sent from the server to the AI ​​agent. The AI ​​agent uses a generative AI model to analyze the quantified trends in the application information. In this process, time-series data of the number of applications is handled in particular to analyze and predict application trends.

[0678] The analysis results are returned to the server, where the data is visualized. The analysis results are displayed graphically using a JavaScript library (for example, Chart.js), and are converted into a visible form such as a line graph or pie chart.

[0679] Based on this, the server automatically generates a report and saves it in PDF or Excel format. This report is electronically delivered to the user's terminal, providing information to relevant parties. Furthermore, the system detects failure to meet targets and issues warnings to users as needed. Warnings are promptly notified using SMS gateways, etc.

[0680] Regarding the proposal of countermeasures, the server generates prompt messages based on the analysis results to devise specific marketing strategies. An example of such a prompt message is, "The number of applications has not reached the target. Please propose effective countermeasures."

[0681] Finally, as part of the proposed strategies, promotional plans targeting specific applicant groups will be provided. For example, it may be possible to increase the number of applications by proposing information dissemination using social media or reward incentive plans.

[0682] Through this series of processes, the system provides the ability to support efficient data analysis and strategic decision-making.

[0683] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0684] Step 1:

[0685] The server connects to an external information source to retrieve application information. The input is the application information stored in the external information source, and the output is the retrieved raw data. Specifically, it periodically accesses the information source via an API and downloads the application information.

[0686] Step 2:

[0687] The server formats the acquired application information. The input is raw application data, and the output is cleaned application data. In this step, preprocessing such as data duplication removal and formatting is performed using a Python script.

[0688] Step 3:

[0689] The server sends the formatted data to the AI ​​agent. The input is cleansed application data, and the output is ready data for analysis. In this process, the data format is adjusted according to the AI ​​agent's requirements.

[0690] Step 4:

[0691] The AI ​​agent analyzes the received data and extracts quantifiable trends. The input is pre-prepared data for analysis, and the output obtained from the analysis is trend information and prediction results. Specifically, it uses a generative AI model to perform time series analysis and analyze application trends and predict peak times.

[0692] Step 5:

[0693] The server receives the analysis results and visualizes the data. The input is the analysis results from the AI ​​agent, and the output is the visualized data (graphs, charts, etc.). The server uses a JavaScript library (e.g., Chart.js) to convert it into a format that can be visually displayed in a browser.

[0694] Step 6:

[0695] The server generates reports based on visualized data and saves them electronically. Input is visualized data, and output is a report in PDF or Excel format. The automated process ensures regular reporting.

[0696] Step 7:

[0697] The server generates the report and then delivers it to the user's terminal. The input is the generated report, and the output is the delivered electronic report. SMTP is used to provide the report to the user as an attachment.

[0698] Step 8:

[0699] The server issues a warning if it detects that the set target has not been met. The inputs are the analysis results and the target value, and the output is a warning notification. Specifically, it uses an SMS gateway to send a warning message to the user.

[0700] Step 9:

[0701] The AI ​​agent generates a prompt message and proposes countermeasures after issuing a warning. The input consists of unmet targets and candidate countermeasure data, while the output is a specific countermeasure proposal. For example, it can make effective suggestions in situations requiring a quick response, such as proposing an SNS campaign to a specific target audience.

[0702] (Application Example 1)

[0703] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0704] It is difficult to efficiently analyze multiple application data and understand their trends. Furthermore, a system is needed to quickly implement countermeasures when the number of applications does not reach the target. In addition, there are insufficient means of presenting applicant attribute information in a visually easy-to-understand format. Solving these challenges is crucial.

[0705] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0706] In this invention, the server includes means for acquiring application information from an external information source, means for analyzing the application information and generating quantified patterns and trends, and means for aggregating and visually displaying applicant attribute information. This enables efficient analysis of application information and visualization of trends.

[0707] "Application information" is a general term for data about applicants collected from external sources.

[0708] "External information sources" refer to external data sources such as the internet and external databases, which are accessed by the system to obtain the information it needs.

[0709] A "quantified pattern" is an indicator that shows application trends and tendencies as numerical data obtained by analyzing collected application information.

[0710] "Failure to meet the target number of applications" means that the actual number of applications is insufficient compared to the set target number.

[0711] A "warning" is a notification sent to users to prompt action when the number of applications has not reached the target.

[0712] "Notification activities" refer to information dissemination and campaign activities directed at a target group when goals are not met.

[0713] "Promotional measures" refer to specific action plans proposed to increase the number of applications, including posting on online communication platforms and electronic newsletters.

[0714] "Applicant attribute information" refers to information that indicates characteristics of the applicant, such as age, gender, and region.

[0715] "Visually displaying" refers to the process of transforming aggregated data into a form that is easy to understand visually, such as graphs and diagrams.

[0716] As a form for carrying out the invention, the system that realizes this application example consists of a server, an AI agent, a user terminal, and a network connecting them.

[0717] The server uses an API to collect application information from external sources and sends it to an AI agent. The AI ​​agent uses a generative AI model to analyze the application information and extract quantifiable patterns. This analysis process clarifies past application trends and applicant attribute information.

[0718] Based on the acquired analysis results, the server automatically sends a warning to the user's terminal if the number of applications has not reached the target. This is done using email or SMS notification functions. Furthermore, graphs and charts are generated to visually display the analysis results and clearly show the application status to the user.

[0719] This allows users to quickly and efficiently grasp application information and take necessary measures. For example, if application trends are skewed towards younger generations, the system will suggest strategies to appeal to younger generations based on those results. An example of a prompt message would be, "If the number of applications has not reached 80% of the target, please suggest new promotional measures."

[0720] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0721] Step 1:

[0722] The server retrieves application information from external sources using an API. The input is the application data obtained via the API, and the output is the raw data stored within the server. This data is then deployed for subsequent analysis processes.

[0723] Step 2:

[0724] The server transmits the acquired application information to the AI ​​agent. The input is the application information stored on the server, and the output is the data transfer to the AI ​​agent. The server uses a transmission protocol to ensure that the data is reliably delivered to the agent.

[0725] Step 3:

[0726] The AI ​​agent analyzes application information and extracts quantified patterns using a generative AI model. The input is application information received from the server, and the output is the analysis results of application trends and applicant attributes. This analysis process is performed using numerical algorithms and data learning models.

[0727] Step 4:

[0728] Based on the analysis results, the server sends a warning to the user's terminal if the number of applications has not reached the target. The input is the analysis results received from the AI ​​agent, and the output is the warning notification sent to the user. The server sends this notification via email or SMS to support a quick response.

[0729] Step 5:

[0730] The server generates graphs and charts to visually display the analysis results. The input is the analyzed data, and the output is graphs and charts that can be viewed on the user's terminal. The server uses visualization software to graphically transform the data.

[0731] Step 6:

[0732] Based on these results, the user takes the necessary countermeasures. The input is visual information presented by the server, and the output is a concrete action plan. For example, this could involve planning and executing a social media campaign targeting young people.

[0733] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0734] In this invention, the application status monitoring system is built around a server. First, the server retrieves application data from an external database via an API. This ensures that the server always maintains the latest application information and sends it to the AI ​​agent each time data is retrieved.

[0735] The AI ​​agent quickly analyzes submitted application data, generating quantifiable patterns and trends. The analysis results are sent back to the server and visualized in graphs and charts. Users receive these reports in real time on their devices, allowing them to monitor application trends and goal achievement rates.

[0736] In particular, by utilizing an emotion engine, a mechanism has been added to analyze emotions from user feedback and the content entered in application forms. The emotion engine estimates emotions based on the applicant's text data and provides the results to the AI ​​agent. For example, it can detect whether an applicant is satisfied or dissatisfied and customize the response accordingly.

[0737] The server generates an alert if the number of applications does not reach the set target. It also uses data from sentiment analysis to suggest more effective communication styles. For example, if an applicant is experiencing stress, it can design a reminder campaign that sends messages to alleviate that stress.

[0738] Users receive suggested strategies and alerts from the server, and based on this, they can determine specific action plans to improve the application status. The content of the strategies can be adapted to the target audience by adjusting them according to the results of sentiment analysis.

[0739] Thus, a key feature of this embodiment of the present invention is that by using an emotion engine, it is possible to not only perform data analysis but also to provide more effective measures that are tailored to the emotions of applicants.

[0740] The following describes the processing flow.

[0741] Step 1:

[0742] The server connects to an external database via an API and periodically retrieves application data. Specifically, application information is collected every 10 minutes and stored in the database.

[0743] Step 2:

[0744] The server sends the collected application data to the AI ​​agent. The data includes the applicant's personal information, application details, and comments made during the application process.

[0745] Step 3:

[0746] The AI ​​agent analyzes the received data and quantifies the trends and patterns of applicants. Furthermore, the AI ​​agent uses an emotion engine to extract emotional data from application texts and comments.

[0747] Step 4:

[0748] The emotion engine classifies the candidate's emotions as positive, negative, or neutral, and feeds the result back to the AI ​​agent.

[0749] Step 5:

[0750] The server receives analysis results and sentiment data from the AI ​​agent and generates a visualized report. Graphs and charts visualize trends in the number of applications and the proportion of sentiment data.

[0751] Step 6:

[0752] The server automatically generates reports and sends them to the employee's terminal. The employee reviews the daily reports to understand the current status of applications and the applicants' emotional tendencies.

[0753] Step 7:

[0754] If the number of applications falls short of the target, the server will issue an alert. This alert will be delivered to the person in charge via email notification or as a warning on the dashboard.

[0755] Step 8:

[0756] Based on the emotional tendencies detected by the emotion engine, the AI ​​agent proposes reminder campaigns and promotional measures. For example, if negative emotions are high, it will plan an email campaign with content that addresses the applicant's dissatisfaction.

[0757] Step 9:

[0758] Users review the proposed measures from the server and select the measures they wish to implement. The selected measures are then used to provide the most appropriate response to each applicant.

[0759] Step 10:

[0760] The server executes the selected measures. It automates scheduled social media posts and sentiment-based email distribution to maximize effectiveness.

[0761] (Example 2)

[0762] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0763] When companies and organizations conduct diverse campaigns, they need to quickly grasp trends in the number of applications and implement flexible measures that reflect the emotional state of applicants. However, conventional systems have faced challenges in that the process of acquiring and analyzing application data is inefficient, making it difficult to respond based on applicants' emotions.

[0764] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0765] In this invention, the server includes means for acquiring application data from a recording device, means for evaluating the application data using an analysis device and generating quantified patterns and trends, and means for estimating emotions from text data and using the results to make suggestions that correspond to the emotional state of the applicant. This makes it possible to accurately grasp application trends and quickly propose measures that take into account the emotions of the applicants.

[0766] "Application data" refers to all information related to applications that is acquired from recording devices and used for analysis.

[0767] An "analysis device" is a device that evaluates application data and generates quantified patterns and trends.

[0768] "Patterns and trends" refer to numerical representations of application trends and characteristics obtained as a result of data analysis.

[0769] A "warning" refers to a notice or alert issued when the number of applications has not reached the set target.

[0770] "Campaigns and promotional activities" refer to special proposals or actions designed to attract users' attention and encourage participation.

[0771] "Methods for estimating emotions from text data" refers to technologies and methods for inferring the emotional state of applicants through text analysis and utilizing the results.

[0772] "Users" refers to individuals or organizations that use the system to receive analysis results of application data and proposed measures.

[0773] To implement this invention, the following configuration is necessary: ​​The server periodically retrieves application data from an external database and transmits it to the analysis device. This retrieval is performed via an API, and a specific data exchange format (such as JSON) is typically used in this process.

[0774] The analysis system uses a generative AI model to evaluate the data in detail and extract quantifiable patterns and trends. This analysis system is likely to be built using a machine learning framework (e.g., TensorFlow or PyTorch).

[0775] Furthermore, based on the analysis results, the server uses sentiment analysis tools to estimate the emotions of applicants from the text data they provide. At this time, natural language processing techniques are used to analyze the applicants' emotions from the text. Sentiment analysis is expected to be performed using NLP libraries (e.g., spaCy or NLTK).

[0776] The visualized analysis results are sent to the device in real time, allowing users to understand trends in the number of applications. This visualization utilizes libraries such as D3.js and Chart.js to build the user interface.

[0777] As a concrete example, in an online sales campaign, the server retrieves application data, analyzes it through a generated AI model, and then proposes a new promotional strategy to the user based on the results. An example of a prompt message would be, "Analyze the latest application data and report on applicant satisfaction and application trends. Also, suggest a suitable messaging campaign if applicants are experiencing stress." By inputting this, the system can provide useful insights.

[0778] A system configured in this way processes application data quickly and efficiently, providing users with accurate information. This enhances the management of application status and maximizes the effectiveness of campaigns.

[0779] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0780] Step 1:

[0781] The server periodically sends API requests to an external database to retrieve application data. This input allows the server to receive application data in JSON format, including the user's name, application date, and feedback comments. The received data is then prepared for analysis in the next step.

[0782] Step 2:

[0783] The server sends the received application data to the analysis device. The analysis device uses a generative AI model to analyze the input data and extract applicant behavior patterns and quantifiable trends. Specific data processing includes correlation analysis with historical data and applicant classification through clustering. The analysis results are temporarily returned to the server for use in the next step.

[0784] Step 3:

[0785] The server uses an emotion engine based on the analysis results to estimate emotions from applicants' text data. The input data consists of applicant comments, and natural language processing techniques are used to extract positive or negative emotions. The output is an emotion scoring result and emotion trend. This information will be used to propose subsequent measures.

[0786] Step 4:

[0787] The server visualizes the number of applications in real time based on the analysis results and sentiment scores. The visualized data is sent to the terminal and displayed to the user. Depending on the library used (e.g., D3.js), graphs of the trend in the number of applications and sentiment status are generated and provided to the user in an intuitively understandable format.

[0788] Step 5:

[0789] If the number of applications does not reach the target, the server will issue an alert and present suggested measures based on the results of sentiment analysis. In this step, for example, a message campaign could be designed to encourage stressed applicants to relax. Based on the information received by users on their devices, an effective action plan can be formulated.

[0790] (Application Example 2)

[0791] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0792] In modern recruitment processes, it is difficult to fully understand applicants' emotions and application trends, and there are challenges in responding quickly to changes in application trends. Furthermore, it is difficult to implement communication and measures that take applicants' emotions into consideration, which can result in failing to meet application targets.

[0793] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0794] In this invention, the server includes means for acquiring application information from an external information storage device, means for analyzing the application information and generating quantified patterns and trends, and means for analyzing the emotions of applicants from text information and customizing responses based on the results. This makes it possible to provide appropriate responses that take into account the emotions of applicants and to more effectively support the achievement of application number targets.

[0795] "Application information" refers to data related to recruitment activities obtained from external data storage devices.

[0796] "Analysis" is a series of processes that generate quantified patterns and trends from application information.

[0797] "Patterns and trends" refer to quantified patterns and trends based on application information obtained as a result of the analysis.

[0798] A "warning" refers to a notification or alert issued when the target number of applications is not met.

[0799] "Emotional state" refers to the feelings and psychological condition that can be inferred from the applicant's text information.

[0800] A "remind campaign" refers to emotionally sensitive information and messages sent to applicants to encourage them to participate in the application process.

[0801] "Promotional measures" refer to all measures and approaches implemented to increase the number of applications.

[0802] A "proposal for posting on an information sharing service" refers to a proposal for a campaign or initiative to be posted on an information sharing platform.

[0803] "Electronic message documents" refer to texts and content sent to applicants via email or other means.

[0804] A "reward incentive plan" is a strategic plan designed to encourage applicants to participate in the application process through rewards and incentives.

[0805] This invention provides a server-centric system for effectively managing application information in recruitment activities. The server retrieves application information from an external data storage device, analyzes it, and generates quantified patterns and trends. The analysis tools used are Python and the Flask framework, and the JavaScript library D3.js is used for data visualization.

[0806] The analyzed data is further analyzed in detail by an AI agent to estimate the applicant's emotions from their text information. This emotion analysis utilizes a TensorFlow model. The results of the emotion analysis are presented to the user as reminder campaigns and promotional strategies. This allows the user to respond in a way that is sensitive to the applicant's emotions. For example, if an applicant's emotions are positive, more proactive contact is recommended.

[0807] Users can receive these analysis results in real time via their devices and adjust their application strategies as needed. An example of a prompt might be, "Please tell me the current sentiment of applicants. What steps should we take?" This system allows for more effective implementation of measures to achieve application targets.

[0808] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0809] Step 1:

[0810] The server retrieves application information from an external data storage device via an API. The input is query parameters, and the output is a dataset of the retrieved application information. This information includes the applicant's name, work experience, application date and time, etc.

[0811] Step 2:

[0812] The server sends application information to an AI agent for data analysis. The input is a dataset of application information, and the output is a quantified pattern or trend that indicates the applicant's application tendencies and emotions. In this process, Python and TensorFlow models are used to estimate emotions from the applicant's text information.

[0813] Step 3:

[0814] A server receives analysis results from an AI agent, visualizes the data using D3.js, and displays it on the user's device. Input is quantified patterns and trends, while output is visualized data in graph and chart format. Users can view this in real time.

[0815] Step 4:

[0816] The server generates emotionally conscious reminder campaigns and promotional strategies based on the analysis results. The input is the result of the emotional analysis, and the output is a proposal for a specific campaign or strategy tailored to that emotion. This proposal is automatically generated using a generative AI model.

[0817] Step 5:

[0818] Users receive notifications from the server in real time via their devices and adjust their application strategies accordingly. Inputs are suggestions and warnings from the server, while outputs are specific actions the user should take. Based on this, the user decides how to respond.

[0819] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0820] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0821] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0822] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0823] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0824] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0825] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0826] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0827] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0828] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0829] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0830] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0831] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0832] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0833] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0834] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0835] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0836] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0837] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0838] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0839] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0840] The following is further disclosed regarding the embodiments described above.

[0841] (Claim 1)

[0842] Methods for obtaining application data from an external database,

[0843] A means for analyzing the aforementioned application data and generating quantified patterns and trends,

[0844] A method for detecting failure to meet the target number of applicants based on the analysis results,

[0845] A means of issuing an alert if the target is not met,

[0846] A means of proposing reminder campaigns and promotional measures in response to failure to meet targets,

[0847] A system that includes this.

[0848] (Claim 2)

[0849] The system according to claim 1, further comprising means for automatically generating a report based on the analysis results and notifying the user thereof.

[0850] (Claim 3)

[0851] The system according to claim 1, further comprising means of presenting the reminder campaign or promotional measure as a social media post, email newsletter content, or reward incentive plan.

[0852] "Example 1"

[0853] (Claim 1)

[0854] Methods for obtaining application information from external sources,

[0855] A means for analyzing the aforementioned application information and generating quantified trends,

[0856] A means to detect failure to meet application targets based on analysis results,

[0857] A means of issuing a warning if the target is not met,

[0858] A means of providing reminder information and proposing measures based on whether goals have been met,

[0859] A means of converting the analysis results into time-series data and displaying it,

[0860] A means of automatically generating and electronically transmitting reports,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, further comprising means for creating a visualized report based on the analysis results and electronically notifying the user thereof.

[0864] (Claim 3)

[0865] The system according to claim 1, further comprising means for proposing the aforementioned reminder information provision or measures as social media posts, electronic communication content, or reward programs.

[0866] "Application Example 1"

[0867] (Claim 1)

[0868] Methods for obtaining application information from external sources,

[0869] A means for analyzing the aforementioned application information and generating quantified patterns and trends,

[0870] A means for detecting failure to meet the target number of applications based on the analysis results,

[0871] A means of issuing a warning if the target is not met,

[0872] A means of proposing notification activities and promotion measures in response to failure to meet targets,

[0873] A means of aggregating and visually displaying applicant attribute information,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, further comprising means for automatically generating a report based on the analysis results and communicating it to the user.

[0877] (Claim 3)

[0878] The system according to claim 1, further comprising means for presenting the notification activity or promotional measures as a proposed post on an online communication platform, content for an electronic communication newsletter, or a reward and motivation plan.

[0879] "Example 2 of combining an emotion engine"

[0880] (Claim 1)

[0881] A means of obtaining application data from a recording device,

[0882] A means for evaluating the aforementioned application data using an analysis device and generating quantified patterns and trends,

[0883] A method for detecting failure to meet the target number of applicants based on the analysis results,

[0884] A means of issuing an alert if the target is not met,

[0885] A means of proposing campaigns and promotional activities in response to failure to meet targets,

[0886] A means of estimating emotions from text data and a means of making suggestions tailored to the emotional state of applicants using the results,

[0887] A system that includes this.

[0888] (Claim 2)

[0889] The system according to claim 1, further comprising means for automatically generating information based on analysis results and notifying the user thereof.

[0890] (Claim 3)

[0891] The system according to claim 1, further comprising means for presenting the campaign or promotional activity as a digital submission proposal, an email communication, or a rewards plan.

[0892] "Application example 2 when combining with an emotional engine"

[0893] (Claim 1)

[0894] A means of obtaining application information from an external information storage device,

[0895] A means for analyzing the aforementioned application information and generating quantified patterns and trends,

[0896] A means to detect failure to meet the target number of applications based on the analysis results,

[0897] A means of issuing a warning if the target is not met,

[0898] A means of analyzing the emotions of applicants from their text information and customizing responses based on the results,

[0899] A means of proposing reminder campaigns and promotional measures that take into account the emotions revealed by the analysis results,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, further comprising means for automatically generating a report based on the analysis results and notifying the user thereof.

[0903] (Claim 3)

[0904] The system according to claim 1, further comprising means for presenting the reminder campaign or promotional measures as a proposed post on an information sharing service, an electronic message, or a reward and stimulus plan. [Explanation of symbols]

[0905] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Methods for obtaining application information from external sources, A means for analyzing the aforementioned application information and generating quantified patterns and trends, A means for detecting failure to meet the target number of applications based on the analysis results, A means of issuing a warning if the target is not met, A means of proposing notification activities and promotion measures in response to failure to meet targets, A means of aggregating and visually displaying applicant attribute information, A system that includes this.

2. The system according to claim 1, further comprising means for automatically generating a report based on the analysis results and communicating it to the user.

3. The system according to claim 1, further comprising means for presenting the notification activity or promotion measures as a proposed post on an online communication platform, content for an electronic communication newsletter, or a reward-motivation plan.

Images