System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving personal characteristic information provided by a user; means for receiving customer characteristic information and business requirements provided by the user; means for calculating a matching score between the personal and the customer based on the personal characteristic information and the customer characteristic information and the business requirements; and means for selecting an optimal personal based on the matching score.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional staffing systems have difficulty quickly and accurately matching the most suitable personnel to a client's specific job requirements, personality, and hobbies and preferences. This has led to problems such as lower customer satisfaction and a lack of operational efficiency. In particular, there is a need to consider not only the match of skills and experience, but also the client's personality and past feedback, but no system that can achieve this has existed. Given this background, there is a need to develop a new system that can improve the accuracy and efficiency of staffing. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means.

[0006] First, a means for receiving individual characteristic information (age, gender, personality, hobbies, past work experience, etc.) provided by a user and a means for receiving customer characteristic information and specific job requirements (skill set, work experience, personality, hobbies, preferences, etc.) provided by a customer are provided. Next, a means for calculating a matching score between an individual and a customer based on the individual characteristic information, the customer characteristic information, and the job requirements is provided. This matching score is specifically evaluated using a machine learning algorithm or similarity calculation. Then, a means for selecting the most suitable individual based on the matching score is provided. Furthermore, by providing a means for preprocessing and quantifying the individual characteristic information and a means for filtering individual candidates based on the customer characteristic information, more accurate matching can be achieved. This makes it possible to quickly and accurately select and provide the personnel best suited to the customer's needs.

[0007] "Individual characteristic information" refers to detailed profiles of individual personnel, such as age, gender, personality, hobbies, and past work experience.

[0008] "Customer characteristic information" refers to detailed customer profiles, such as the customer's personality, hobbies and preferences, and past feedback.

[0009] "Job requirements" refers to information that indicates the conditions desired by a customer, such as the skill set, work experience, personality, hobbies, and preferences required to perform a specific job.

[0010] "Matching score" refers to a numerical value calculated based on the degree of compatibility between an individual and a customer, based on the individual's characteristic information, the customer's characteristic information, and business requirements.

[0011] "Preprocessing" refers to the initial stage of data processing to convert raw data into a form suitable for analysis and calculation.

[0012] "Quantification" refers to the process of converting character data or categorical data into numerical values ​​in order to quantitatively evaluate and compare the data.

[0013] "Filtering" refers to the process of selecting potential individuals based on customer characteristic information and eliminating unsuitable candidates.

[0014] "Machine learning algorithms" refer to computer algorithms that analyze large amounts of data, extract patterns, and make future predictions and classifications.

[0015] "Similarity calculation" refers to a calculation method for quantitatively evaluating the similarity between two data sets. [Brief explanation of the drawings]

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

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

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

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

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

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

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

[0037] This invention is a human resources matching system for quickly and accurately selecting the most suitable human resources according to the customer's request. This system is implemented mainly by the following components.

[0038] Data Entry

[0039] The server receives "personal characteristic information" provided by the user. This information includes age, gender, personality, hobbies, past work experience, etc. It also receives "customer characteristic information" and "job requirements" provided by the customer. The customer characteristic information includes the customer's personality, hobbies and preferences, past feedback, etc., while the job requirements include the skill set, work experience, personality, hobbies and preferences, etc. required to perform a specific job.

[0040] Data Preprocessing

[0041] The server preprocesses the received "personal characteristic information." This preprocessing includes quantifying categorical values ​​(e.g., personality, hobbies) and text data. It also calculates the number of past work experiences. The same preprocessing is performed on "customer characteristic information."

[0042] Matching Score Calculation

[0043] The server calculates a matching score based on the preprocessed "personal characteristic information," "customer characteristic information," and "business requirements." This score calculation uses a machine learning algorithm and a similarity calculation method (e.g., cosine similarity).

[0044] Selection of the best individuals

[0045] The server selects the most suitable individual based on the calculated matching score, and then filters the candidates based on the specific customer's personality and hobbies and preferences to narrow down the most suitable candidates.

[0046] Specific examples

[0047] 1. Data Entry Example

[0048] The user provides the following data as personal characteristic information:

[0049] Name: Alice

[0050] Age: 28

[0051] Gender: Female

[0052] Personality: extroverted

[0053] Hobbies: Reading

[0054] Previous work experience: Engineer, Manager

[0055] The user provides the following data as customer characteristic information and business requirements.

[0056] Customer Name: Company A

[0057] Past feedback: Good communication

[0058] Job requirements: Age 30 or older, 5+ years of experience, extroverted personality, reading hobby

[0059] 2. Pretreatment

[0060] The server calculates the number of past work experiences of an individual, and in Alice's case it is "2".

[0061] The server converts category information such as "personality" and "hobbies" into numerical values.

[0062] 3. Calculating the Matching Score

[0063] The server calculates the similarity between Alice's information and the business requirements. At this time, Alice's information is quantified and compared with the business requirements.

[0064] 4. Selecting the best individuals

[0065] The server determines that Alice is the best candidate based on the calculated matching score, and after filtering, it confirms that Alice best meets the customer requirements.

[0066] This system allows users to efficiently and effectively select and dispatch personnel who are best suited to customer needs. This process is automated, with the server processing the data and presenting the results, significantly reducing the user's workload.

[0067] The processing flow will be explained below.

[0068] Step 1:

[0069] The server receives personal characteristic information from the user, including the individual's age, gender, personality, hobbies, and past work experience, and stores this information in a database.

[0070] Step 2:

[0071] The server receives customer characteristic information and job requirements from the user. The customer characteristic information includes the customer's personality, hobbies and preferences, and past feedback, while the job requirements include the required skill set, work experience, personality, hobbies and preferences, etc. This information is also stored in the database.

[0072] Step 3:

[0073] The server preprocesses the stored individual characteristic information. This preprocessing includes converting categorical values ​​(e.g., personality, hobbies) into numerical values ​​and calculating the number of past work experiences. For example, if the person has work experience such as "engineer" and "manager," the number is calculated to be "2."

[0074] Step 4:

[0075] The server also preprocesses the customer's characteristic information and business requirements, which quantifies the customer's personality and preferences, and expresses each item of the business requirements as a specific numerical value.

[0076] Step 5:

[0077] The server calculates a matching score based on the preprocessed individual feature information, the customer feature information, and the business requirements. This score is calculated using a similarity calculation method (e.g., cosine similarity), which quantifies how well each individual matches the customer's requirements.

[0078] Step 6:

[0079] The server sorts the list of individuals based on the calculated matching scores, creating a list sorted by highest score first.

[0080] Step 7:

[0081] The server filters individual candidates based on the specific customer's personality and preferences, narrowing down the candidates to the most suitable candidates.

[0082] Step 8:

[0083] The server presents the filtered list of optimal personnel to the user, who then makes a final selection based on the provided list and dispatches the appropriate personnel.

[0084] Step 9:

[0085] The user checks the list of optimal personnel provided by the server and selects the personnel who best meets the request. After further detailed checks and adjustments as necessary, the user is ready to dispatch the personnel to the customer.

[0086] Through these steps, users can quickly and accurately select and dispatch the personnel best suited to their client's requirements. This process is automated, significantly reducing the user's time and effort.

[0087] Example 1

[0088] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0089] With conventional talent matching systems, it was difficult to quickly and accurately select the talent that best met the customer's requirements. In particular, without preprocessing of input data or appropriate filtering, matching accuracy decreased, and inappropriate talent was often selected. In addition, the method of notifying the selection results was complicated, which significantly increased the user's workload.

[0090] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0091] In this invention, the server includes means for receiving personal characteristic information provided by the user, means for receiving customer characteristic information and business requirements, means for calculating a matching score based on the characteristic information quantified through preprocessing, means for selecting and filtering the most suitable individuals based on the calculated matching score, and means for notifying the user of the selection results. This makes it possible to efficiently and accurately select personnel who are most suited to the customer's requirements and significantly reduce the user's workload.

[0092] "Personal characteristic information" refers to specific attributes and data about a person, such as age, gender, personality, hobbies, and past work experience.

[0093] "Customer characteristic information" refers to attributes and data related to customers, such as their personality, hobbies and preferences, and past feedback.

[0094] "Job requirements" refer to the conditions that customers desire, such as the skill set, work experience, personality, hobbies, and preferences needed to perform a specific job.

[0095] "Matching score" refers to the numerical value of similarity calculated using machine learning algorithms and similarity calculation methods based on individual characteristic information, customer characteristic information, and business requirements.

[0096] "Preprocessing" refers to a series of processes that properly format, digitize, and vectorize received data before analyzing or calculating it.

[0097] "Filtering" refers to the process of narrowing down the individuals who best fit a particular criteria based on a calculated matching score.

[0098] "Notification" refers to the act of informing users of the selected results and other information via email, the system dashboard, etc.

[0099] This invention is a human resources matching system for quickly and accurately selecting the most suitable human resources according to the customer's needs. This system consists of a server, a terminal, and a user.

[0100] Hardware and Software Configuration

[0101] The server includes a database system (e.g., MySQL (registered trademark) or MongoDB), a backend that executes the program logic (e.g., Python, Django, or Flask), and a machine learning algorithm (e.g., Scikit-learn, TENSORFLOW (registered trademark)). The terminal consists of a web browser or application that provides a user interface and communicates with the server via HTTP requests.

[0102] Program processing explanation

[0103] 1. Data Entry

[0104] A user inputs personal characteristics information, such as name, age, sex, personality, hobbies, and past work experience, through a web form.

[0105] The customer inputs their characteristic information and business requirements, such as "more than 3 years of engineering experience, good communication skills," and sends this data to the server.

[0106] The server receives this information and stores it in a database.

[0107] 2. Data Preprocessing

[0108] The server retrieves the necessary data from the database and converts the categorical data into numerical values. For example, "Personality: Extroverted" is converted to the numerical value "1" and "Hobby: Reading" is converted to the numerical value "2."

[0109] The server vectorizes the text data using techniques such as TF-IDF. For example, it vectorizes "Past feedback: communication is good."

[0110] The server calculates the number of past work experiences and treats it as numerical data.

[0111] 3. Calculating the Matching Score

[0112] The server calculates a matching score based on the preprocessed data using a machine learning algorithm or a similarity calculation method. For example, it calculates the angle between the vectors of the individual and customer feature information using cosine similarity to calculate the similarity score.

[0113] The server stores the calculated matching scores in a database.

[0114] 4. Selecting the best individuals

[0115] The server selects the best individuals based on the calculated matching scores, sorts them by highest score, and filters them.

[0116] The server then further filters based on the specific customer's personality and preferences to narrow down the most suitable candidates.

[0117] Specific examples

[0118] Example of data entry:

[0119] The user enters "Name: XX, Age: 28, Gender: Female, Personality: Outgoing, Hobbies: Reading, Past Work Experience: Engineer, Manager."

[0120] The customer enters the following information: "Customer characteristics: personality, hobbies, preferences, past feedback; job requirements: age 30 or older, 5 or more years of engineering experience, personality: extrovert, hobby: reading."

[0121] Prompt Sentence Examples

[0122] "Select the best person to meet the client's business requirements. Consider the following information: client characteristics, business requirements, and personal characteristics."

[0123] This system allows users to efficiently and accurately select and dispatch personnel who are best suited to customer needs, significantly reducing the user's workload.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1:

[0126] Data Entry

[0127] The user enters personal characteristic information into a web form and submits it.

[0128] Specifically, you enter information such as your name, age, gender, personality, hobbies, and past work experience.

[0129] The server receives the transmitted data and stores it in a database.

[0130] Input: Data entered by a user into a web form

[0131] Output: Personal characteristics stored in a database

[0132] The user also inputs and submits customer characteristic information and business requirements.

[0133] Specifically, you enter information such as the customer's personality, hobbies and preferences, past feedback, and required skill set.

[0134] The server also receives this data and stores it in a database.

[0135] Input: Customer characteristics and business requirements entered by the user

[0136] Output: Customer characteristics and business requirements stored in a database

[0137] Step 2:

[0138] Data Preprocessing

[0139] The server retrieves personal and customer characteristic information from a database.

[0140] Input: Personal and customer characteristics stored in the database

[0141] Output: Retrieved data

[0142] The server preprocesses the acquired data. First, it quantifies the category values.

[0143] For example, "Personality: Extroverted" is converted into a numerical value of "1" and "Hobby: Reading" is converted into a numerical value of "2".

[0144] Input: Acquired data (category information)

[0145] Output: digitized data

[0146] The server vectorizes the text data using TF-IDF.

[0147] For example, vectorize "Past feedback: Good communication."

[0148] Input: Text data

[0149] Output: Vectorized text data

[0150] The server calculates the number of past work experiences and treats it as numerical data.

[0151] Input: Previous work experience (text information)

[0152] Output: Quantified past work experience

[0153] Step 3:

[0154] Matching Score Calculation

[0155] The server calculates a matching score based on the pre-processed data.

[0156] The server uses machine learning algorithms (e.g., Random Forest or Support Vector Machine) and similarity calculation methods (e.g., cosine similarity).

[0157] Specifically, the angle between the feature information vectors of the individual and the customer is calculated using cosine similarity, and a similarity score is calculated.

[0158] Input: Preprocessed personal and customer characteristics

[0159] Output: The calculated matching score

[0160] The server stores the calculated matching scores in a database.

[0161] Input: The calculated matching score

[0162] Output: Matching scores stored in a database

[0163] Step 4:

[0164] Selection of the best individuals

[0165] The server selects the best individual based on the calculated matching score.

[0166] Sorting is done by highest score and selecting the most suitable individual.

[0167] Input: Matching scores stored in the database

[0168] Output: Selection of the best individual

[0169] The server performs further filtering based on the characteristics and preferences of the particular customer.

[0170] Input: Selected personal data and customer characteristics

[0171] Output: Best candidates after filtering

[0172] The server notifies the user of the selection results by email or by displaying the results on the system dashboard.

[0173] Input: Best candidates after filtering

[0174] Output: Selection result notified to the user

[0175] This system efficiently and accurately selects the personnel best suited to the customer's requirements, significantly reducing the user's workload.

[0176] (Application example 1)

[0177] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0178] In the security services industry, a challenge is quickly and accurately selecting security personnel who meet customer requirements. With conventional personnel matching systems, it takes time to select highly suitable security personnel and there are also limitations to the accuracy of the matching. This makes it difficult to provide security services efficiently and effectively.

[0179] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0180] In this invention, the server includes means for receiving personal characteristic information provided by a user, means for receiving customer characteristic information and business requirements provided by a user, means for calculating a matching score between the individual and the customer based on the individual characteristic information, the customer characteristic information and business requirements, means for selecting an optimal individual based on the matching score, means for selecting an optimal security officer based on security service requirements, and means for outputting information on the selected security officer, thereby enabling security officers suitable for security services to be selected quickly and accurately.

[0181] 1. "Personal characteristic information" refers to characteristic information related to an individual, such as age, gender, personality, hobbies, and past work experience.

[0182] 2. "Customer characteristic information" refers to characteristic information related to a customer, such as the customer's personality, hobbies and preferences, and past feedback.

[0183] 3. "Job requirements" refer to the skill sets, work experience, personality traits, hobbies, and other conditions necessary to perform a specific job.

[0184] 4. "Matching score" refers to a similarity score calculated based on personal characteristic information, customer characteristic information, and business requirements.

[0185] 5. "Security services" means services that provide security, guarding, and surveillance.

[0186] 6. "Security Officer" means an individual selected to perform security service duties.

[0187] 7. "Outputting information" means displaying, notifying, or transmitting calculated results or selected data to another system.

[0188] The system for carrying out the present invention is for quickly and accurately selecting security personnel in the field of security services in response to customer requests. The system is mainly composed of the following components:

[0189] Data Entry

[0190] The server receives "personal characteristic information" provided by the user. This information includes age, gender, personality, hobbies, past work experience, etc. It also receives "customer characteristic information" and "job requirements" provided by the user. Customer characteristic information includes the customer's personality, hobbies and preferences, past feedback, etc., while job requirements include the skill set, work experience, personality, hobbies and preferences, etc. required to perform a specific job.

[0191] Data Preprocessing

[0192] The server preprocesses the received "personal characteristic information." This preprocessing includes quantifying categorical values ​​(e.g., personality, hobbies) and text data. It also calculates the number of past work experiences. The same preprocessing is performed on "customer characteristic information."

[0193] Matching Score Calculation

[0194] The server calculates a matching score based on the preprocessed "personal characteristic information," "customer characteristic information," and "business requirements." This score calculation uses a machine learning algorithm or a similarity calculation method (e.g., cosine similarity).

[0195] Selection of the best individuals

[0196] The server selects the most suitable individual based on the calculated matching score. Furthermore, filtering is performed based on the specific customer's personality and hobbies and preferences to narrow down the most suitable security personnel. During this selection process, filtering specific to the security service requirements is also performed.

[0197] Output of information

[0198] The server outputs information about the selected security officer to the terminal, including the reason for the selection and detailed characteristic information about the security officer.

[0199] For example, if the following data is entered:

[0200] Personal characteristic information

[0201] Name: Security Officer A

[0202] Age: 35

[0203] Gender: Male

[0204] Personality: extroverted

[0205] Hobbies: Reading

[0206] Previous work experience: 10 years

[0207] Customer characteristics and business requirements

[0208] Customer Name: Customer Company B

[0209] Past feedback: Good communication

[0210] Job requirements: 8+ years of experience, outgoing personality, reading hobby

[0211] Based on this data, the server determines that security officer A is the best candidate and outputs that information.

[0212] An example of a prompt sentence to be input to a specific generative AI model is as follows:

[0213] Write a program to select the best security officer for a customer based on user-input data. Receive personal and customer characteristics as input data, calculate the cosine similarity based on the data, and use a method to select the best candidate.

[0214] In this way, it becomes possible to quickly and accurately select security personnel suitable for security services.

[0215] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0216] Step 1:

[0217] The server receives personal characteristic information provided by the user as input. This information includes age, gender, personality, hobbies, past work experience, etc., and is important data for identifying an individual. Each piece of data is in text or numerical format. The server stores this data in temporary storage.

[0218] Step 2:

[0219] The server receives as input the customer characteristics and job requirements provided by the user, including the customer's personality, hobbies and preferences, past feedback, and the skill set required for a particular job. This data is also stored in temporary storage.

[0220] Step 3:

[0221] The server preprocesses the individual's characteristic information. Preprocessing includes quantifying category values, quantifying text data, and quantifying past work experience. For example, "Personality: Extroverted" is quantified, and "Past work experience: 10 years" is treated as a number. This ensures that all data is in a unified format. The output is preprocessed numerical data.

[0222] Step 4:

[0223] The server also preprocesses customer characteristic information and business requirements, converting categorical values ​​into numbers and quantifying text data, and standardizing the data format. The output is preprocessed numerical data.

[0224] Step 5:

[0225] The server calculates a matching score based on the preprocessed individual feature information, customer feature information, and business requirements. This score is calculated using similarity calculation methods such as machine learning algorithms and cosine similarity. Specifically, the degree of compatibility between an individual and a customer is quantified by calculating the cosine similarity between feature vectors. The output is a matching score.

[0226] Step 6:

[0227] The server selects the best individuals based on the matching scores. First, it lists the calculated matching scores and sorts them by highest score. Then it performs filtering specific to the security service requirements to narrow down the best security officers. The output is a list of selected individuals.

[0228] Step 7:

[0229] The server outputs information about the selected security officer to the terminal. This information includes the name, age, gender, past work experience, and reasons for the selection of the best candidate. The terminal displays this information on the screen or in a notification message. The user checks this information and makes the final decision on whether to actually dispatch the security officer.

[0230] For example, you can issue prompts to the server using the following:

[0231] Write a program to select the best security officer for a customer based on user-input data. Receive personal and customer characteristics as input data, calculate the cosine similarity based on the data, and use a method to select the best candidate.

[0232] Through the above process, it becomes possible to quickly and accurately select an appropriate security officer for security services.

[0233] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0234] This invention is a talent matching system for quickly and accurately selecting the most suitable talent in response to customer requests. This system achieves highly accurate matching by incorporating an emotion engine that recognizes the user's emotions. Detailed embodiments of the system are described below.

[0235] Data Entry

[0236] The server receives personal characteristic information from the user. The received information includes the individual's age, gender, personality, hobbies, and past work experience. This information is stored in a database. The server also receives customer characteristic information and job requirements from the user. The customer characteristic information includes the customer's personality, hobbies and preferences, and past feedback, and the job requirements include the required skill set, work experience, personality, hobbies and preferences, etc. This information is also stored in a database.

[0237] Preprocessing with emotion engine

[0238] The server uses an emotion engine to recognize the user's emotions, thereby improving the reliability and consistency of input information. The emotion engine analyzes the user's emotional reactions to the characteristic information and business requirements entered by the user and incorporates this data into preprocessing.

[0239] Data Preprocessing

[0240] The server preprocesses the individual's characteristic information, including the data obtained by the emotion engine. This preprocessing includes quantifying categorical values ​​(e.g., personality, hobbies) and text data. The number of past work experiences is also calculated. The same preprocessing is performed on the "customer's characteristic information," and the analysis results of the emotion engine are reflected.

[0241] Matching Score Calculation

[0242] The server calculates a matching score based on the preprocessed individual feature information, the customer feature information, and the business requirements. This score is calculated using a similarity calculation method (e.g., cosine similarity), which quantifies how well each individual matches the customer's requirements.

[0243] Selection of the best individuals

[0244] The server sorts the list of individuals based on the calculated matching score. A list sorted by highest score is created, and individual candidates are filtered based on the personality and hobbies of the specific customer. An emotion engine can be used to further refine the filtering.

[0245] Specific examples

[0246] 1. Data Entry Example

[0247] The user provides the following data as personal characteristic information:

[0248] Name: Alice

[0249] Age: 28

[0250] Gender: Female

[0251] Personality: extroverted

[0252] Hobbies: Reading

[0253] Previous work experience: Engineer, Manager

[0254] The user provides the following data as customer characteristic information and business requirements.

[0255] Customer Name: Company A

[0256] Past feedback: Good communication

[0257] Job requirements: Age 30 or older, 5+ years of experience, extroverted personality, reading hobby

[0258] 2. Preprocessing by the emotion engine

[0259] The server analyzes the input data from the user using an emotion engine. For example, if the user's emotion at the time of input is positive, it is evaluated as a factor that increases the reliability of the data.

[0260] 3. Data Preprocessing

[0261] The server calculates the number of past work experiences of each individual, and in Alice's case, it sets it to "2." It also quantifies category information such as "personality" and "hobbies."

[0262] 4. Calculating the Matching Score

[0263] The server calculates the similarity between Alice's information and the business requirements. At this time, Alice's information is quantified and compared with the business requirements.

[0264] 5. Selecting the best individuals

[0265] The server determines that Alice is the best candidate based on the calculated matching score, and also takes into account data from the sentiment engine to confirm that Alice best meets the customer requirements.

[0266] This system allows users to quickly and accurately select and dispatch the personnel best suited to their client's requirements. Furthermore, the use of an emotion engine improves the reliability of input data, resulting in more accurate matching. This process is automated, significantly reducing the user's workload.

[0267] The processing flow will be explained below.

[0268] Step 1:

[0269] The server receives personal characteristic information from the user. The received information includes the individual's age, gender, personality, hobbies, and past work experience. This information is stored in a database. For example, when information about an individual named Alice is provided, that information is sent to the server in digital format.

[0270] Step 2:

[0271] The server receives customer characteristic information and business requirements from the user. Customer characteristic information includes the customer's personality, hobbies and preferences, and past feedback, while business requirements include the required skill set, work experience, personality, hobbies and preferences, etc. This information is also stored in the database. For example, the business requirements and characteristic information of Company A are entered into the server.

[0272] Step 3:

[0273] The server uses an emotion engine to analyze the personal characteristic information entered by the user. For example, it recognizes the user's emotional state (positive, negative, etc.) at the time of input and adds that information to the input data. The results of this analysis are used to evaluate the reliability of the data and correct it.

[0274] Step 4:

[0275] The server preprocesses the individual's characteristic information, including the data analyzed by the emotion engine. This preprocessing includes converting categorical values ​​(e.g., personality, hobbies) into numerical values ​​and calculating the number of past work experiences. For example, Alice's personality trait "extroverted" is converted to the numerical value "1," and her hobby "reading" is converted to the numerical value "2."

[0276] Step 5:

[0277] The server also preprocesses customer characteristic information and business requirements, including data analyzed by the emotion engine. This quantifies the customer's personality and hobbies and preferences, and each item in the business requirements is expressed as a specific numerical value. For example, Company A's requirement "extroverted personality" is converted to the numerical value "1," and "hobby reading" is converted to the numerical value "2."

[0278] Step 6:

[0279] The server calculates a matching score based on the preprocessed individual characteristic information, customer characteristic information, and business requirements. A similarity calculation method (e.g., cosine similarity) is used to calculate this score. This quantifies the degree to which each individual matches the customer requirements. For example, Alice's information is compared with Company A's business requirements to generate a matching score.

[0280] Step 7:

[0281] The server sorts the list of individuals based on the calculated matching scores, creating a list sorted by highest score first. For example, Alice, Bob, Charlie might be listed in descending order of scores.

[0282] Step 8:

[0283] The server filters individual candidates based on the specific customer's personality and hobbies and preferences. This narrows down the candidates to the most suitable. The filtering process also takes into account the analysis results of the emotion engine. For example, Alice is narrowed down as the most suitable candidate.

[0284] Step 9:

[0285] The server presents the filtered list of optimal candidates to the user. The user makes a final selection based on the provided list and prepares to dispatch the appropriate candidate. For example, Alice's detailed information is displayed to the user, and the user can decide whether to dispatch her to the customer.

[0286] These steps enable users to quickly and accurately select and dispatch the best personnel for their customer requirements. This process, combined with the emotion engine, improves the reliability of input data and achieves more accurate matching.

[0287] Example 2

[0288] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0289] Conventional talent matching systems lacked the reliability and consistency of input data, making it difficult to quickly and accurately select the talent most suited to customer requirements. Furthermore, data processing was performed without taking the user's emotional state into consideration, making it difficult to achieve highly accurate matching. This resulted in increased user effort and hindered efficient talent selection.

[0290] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0291] In this invention, the server includes means for receiving personal characteristic information provided by the user, means for receiving customer characteristic information and business requirements provided by the user, means for calculating a matching score based on the personal characteristic information, customer characteristic information and business requirements, means for selecting the most suitable individual based on the matching score, means for analyzing the user's emotions using an emotion engine and improving the reliability and consistency of input data, means for reflecting the analysis results of the emotion engine in preprocessing, and means for reflecting the user's emotional state in calculations based on the preprocessed data. This enables highly accurate matching and significantly reduces the user's workload.

[0292] "Individual characteristic information" is attribute information about a specific individual, such as age, gender, personality, hobbies, and past work experience.

[0293] "Customer characteristic information" is attribute information about a specific customer, such as the customer's personality, hobbies and preferences, and past feedback.

[0294] "Job requirements" are the conditions necessary to perform a specific job, such as the necessary skill set, work experience, personality, hobbies, and preferences.

[0295] The "matching score" is a numerical representation of the compatibility between an individual and a customer, calculated based on the individual's characteristic information, the customer's characteristic information, and business requirements.

[0296] An "emotion engine" is a technology used to analyze a user's emotional response to input data, improving reliability and consistency.

[0297] "Preprocessing" refers to the process of making the collected raw data easier to analyze, and includes converting categorical values ​​into numerical values ​​and quantifying text data.

[0298] "Filtering" is the process of sorting data based on specific conditions and extracting only useful information.

[0299] "Reliability" refers to the degree of accuracy and consistency of data.

[0300] "Consistency" indicates that the data follows certain rules or patterns.

[0301] This invention is a talent matching system for quickly and accurately selecting the best talent according to customer needs. This system achieves highly accurate matching by combining an emotion engine that recognizes the user's emotions.

[0302] First, the server receives personal characteristic information (age, gender, personality, hobbies, past work experience) provided by the user and stores it in the database. The server also receives customer characteristic information (personality, hobbies and preferences, past feedback) and job requirements (required skill set, work experience, personality, hobbies and preferences) and stores them in the database.

[0303] The server then analyzes the user's emotions using an emotion engine, which analyzes the emotional response to the input data to improve reliability and consistency. For example, if the user's emotion at the time of input is positive, it is evaluated as a factor that increases the reliability of the data.

[0304] In the data preprocessing stage, the server performs preprocessing on the collected data to make it easier to analyze. This includes quantifying categorical information such as personality and hobbies, and work experience. The analysis results from the emotion engine are also reflected here, and a reliability score for the data is calculated.

[0305] The server then calculates a matching score based on the preprocessed data. This calculation uses a similarity calculation method such as cosine similarity. As a result, the degree of match between the individual's characteristic information, the customer's characteristic information, and the business requirements is quantified.

[0306] Finally, the server generates a list of candidates based on the calculated matching scores. This list is sorted by highest score and filtered based on the personality and preferences of the specific customer. An emotion engine can be used to further refine the filtering.

[0307] Specific examples

[0308] 1. Data Entry Example

[0309] The user provides the following data as personal characteristic information:

[0310] Name: Individual A

[0311] Age: 28

[0312] Gender: Female

[0313] Personality: extroverted

[0314] Hobbies: Reading

[0315] Previous work experience: Engineer, Manager

[0316] The user provides the following data as customer characteristic information and business requirements.

[0317] Customer Name: Customer A

[0318] Past feedback: Good communication

[0319] Job requirements: Age 30 or older, 5+ years of experience, extroverted personality, reading hobby

[0320] 2. Preprocessing by the emotion engine

[0321] The server analyzes the input data from the user using an emotion engine. For example, if the user's emotion at the time of input is positive, it is evaluated as a factor that increases the reliability of the data.

[0322] 3. Data Preprocessing

[0323] The server calculates the number of past work experiences, and sets the number to "2" in the case of Individual A. It also quantifies category information such as "personality" and "hobbies."

[0324] 4. Calculating the Matching Score

[0325] Based on the business requirements, the server calculates the degree of similarity with the information of person A. At this time, person A's information is quantified and compared with the business requirements.

[0326] 5. Selecting the best individuals

[0327] Based on the calculated matching score, the server determines that Person A is the best candidate. Data from the emotion engine is also taken into account to confirm that Person A best meets the customer requirements.

[0328] Prompt Sentence Examples

[0329] "Please register Individual A, a 28-year-old extroverted female engineer whose hobby is reading."

[0330] "Looking for someone over 30, with at least 5 years of experience, who is extroverted and enjoys reading."

[0331] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0332] Step 1:

[0333] Data Entry

[0334] The server receives personal characteristic information (name, age, gender, personality, hobbies, past work experience) provided by the user. The input data is sent to the server via an HTTP request. The server stores the received data in a database. It also receives customer characteristic information (personality, hobbies and preferences, past feedback) and job requirements (required skill set, work experience, personality, hobbies and preferences) and stores them in the database.

[0335] Specific operation example: When a user enters personal and customer characteristic information into a web form and presses the submit button, the information is sent to the server, which processes this data using Python and stores it in a database (e.g., MySQL).

[0336] Input: User-entered personal and customer characteristics information

[0337] Output: Feature information stored in a database

[0338] Step 2:

[0339] Preprocessing with emotion engine

[0340] The server sends the acquired feature information to the emotion engine to analyze the user's emotional state. The emotion engine determines the emotional response (positive, negative, neutral, etc.) based on the input data. This result is used as additional information to improve the reliability and consistency of the data.

[0341] Specific operation example: The server calls the API for the emotion engine and sends the user's characteristic information. The emotion engine returns the analysis results, and the server stores the results in a database.

[0342] Input: Feature information

[0343] Output: Analysis results by the emotion engine

[0344] Step 3:

[0345] Data Preprocessing

[0346] The server preprocesses the collected data, including the analysis results of the emotion engine. This preprocessing includes quantifying categorical information such as personality and hobbies, quantifying past work experience, and calculating a reliability score for the data. This facilitates the subsequent calculation of matching scores.

[0347] Specific example: Using Python's pandas library, the collected data is processed as a data frame. Categorical information and text data are converted into numerical data, and the number of work experiences is calculated.

[0348] Input: Feature information including the analysis results of the emotion engine

[0349] Output: Preprocessed data

[0350] Step 4:

[0351] Matching Score Calculation

[0352] The server calculates a matching score based on the preprocessed individual and customer characteristic information and business requirements. The similarity calculation uses, for example, cosine similarity. The calculated matching score quantifies the degree of agreement between the individual and customer requirements.

[0353] Specific example: Using the scikit-learn library, calculate the cosine similarity between vectors of preprocessed data. The calculation results are stored in a database.

[0354] Input: Preprocessed individual and customer characteristics information

[0355] Output: Matching score

[0356] Step 5:

[0357] Selection of the best individuals

[0358] The server generates a candidate list based on the calculated matching scores. It sorts the candidates by highest score and filters them based on the characteristics and hobbies of specific customers. It also takes into account the results of the emotion engine to create an even more accurate candidate list.

[0359] Specific example of operation: Using an SQL query, data is retrieved from the database in descending order of matching score, a list reflecting the results of sentiment analysis is generated, and then provided to the user.

[0360] Input: Matching score

[0361] Output: A list of the best candidates

[0362] (Application example 2)

[0363] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0364] Conventional talent matching systems have issues with the reliability and consistency of input information because they do not take into account user emotional data. Also, in factory management using robots, there is a problem with the inability to quickly and accurately allocate appropriate robots.

[0365] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving individual characteristic information provided by a user; means for receiving customer characteristic information and business requirements provided by a user; means for calculating a matching score between the individual and the customer based on the individual characteristic information, the customer characteristic information, and the business requirements; means for selecting the most suitable individual based on the matching score; means for analyzing the user's emotional response using an emotion engine and evaluating the reliability of the data based on the analysis; and means for a factory manager to input robot characteristic information and work station requirements using a smart device and match robots with work stations based on the input. This enables highly accurate personnel matching that takes user emotional data into account and efficient deployment of robots in the factory.

[0366] "User emotional response" refers to the psychological state or feelings a user exhibits when entering information.

[0367] The "matching score" is a numerical representation of the degree of match between the individual's characteristic information, the customer's characteristic information, and the business requirements.

[0368] An "emotion engine" is a system that analyzes user emotions in response to input data and evaluates the reliability and consistency of that data.

[0369] "Smart devices" refers to electronic devices with internet connectivity, such as smartphones, tablets, smart glasses, and head-mounted displays.

[0370] "Robot characteristic information" includes information such as the robot's identification number, performance, tasks that it can handle, operating time, and reliability.

[0371] "Work station" refers to a location within a factory where a specific task is performed.

[0372] A "factory manager" is a person in charge of managing work and robots within the factory.

[0373] The present invention is a system for matching human resources and robots with consideration of the user's emotions. Specific embodiments will be described below.

[0374] Data Entry

[0375] First, the server receives personal characteristic information provided by the user. This information includes age, gender, personality, hobbies, past work experience, etc. The user also inputs customer characteristic information and work requirements. This includes the customer's personality, hobbies and preferences, past feedback, required skill set, work experience, etc. The factory manager inputs robot characteristic information (identification number, performance, work that can be performed, operating time, reliability) and work station requirements (required skills, operating time, work content). All of this data is stored in a database.

[0376] Preprocessing with emotion engine

[0377] The server uses an emotion engine to analyze the user's emotional response to the input data, which improves the reliability and consistency of the input information. For example, if the user shows positive emotions, the data will be rated as more reliable.

[0378] Data Preprocessing

[0379] The server preprocesses the individual and robot characteristic information, including the data obtained by the emotion engine. This preprocessing involves converting category values ​​into numerical values ​​and quantifying text data. The number of past work experiences is then calculated. Similar preprocessing is performed on the "customer characteristic information" and "workstation requirements," and the analysis results of the emotion engine are reflected.

[0380] Matching Score Calculation

[0381] The server calculates a matching score based on the preprocessed individual feature information, the robot feature information, the customer feature information, the business requirements, and the requirements of the work station. This score is calculated using a similarity calculation method such as cosine similarity, which quantifies how well each individual or robot matches the requirements of the customer or work station.

[0382] Selection of the best individuals and robots

[0383] The server selects the best individuals and robots based on the calculated matching scores. A list is created sorted by highest score, and candidates are filtered based on the specific customer's personality, hobbies, and work station requirements. An emotion engine can be used to further refine the filtering.

[0384] Specific examples

[0385] The user provides the following data as personal characteristic information:

[0386] Name: Taro

[0387] Age: 35

[0388] Gender: Male

[0389] Personality: introverted

[0390] Hobbies: Programming

[0391] Previous work experience: Systems engineer, project manager

[0392] In addition, the factory manager provides the following data as characteristic information of the robot:

[0393] Identification number: R123

[0394] Performance: High

[0395] Available work: Assembly, packaging

[0396] Operating time: 3000 hours

[0397] Reliability: 90%

[0398] The administrator provides the following data as requirements for the workstation:

[0399] Required skills: Assembly

[0400] Operating time: 2500 hours

[0401] Required work: Parts assembly

[0402] The server receives this information, analyzes it with an emotion engine, performs preprocessing, calculates a matching score, and selects the most suitable individual and robot.

[0403] Prompt Sentence Examples

[0404] Based on the data below, come up with an algorithm to optimally match robots and workstations, and implement it in Python.

[0405] Robot data (identification number, performance, skills, operating time, reliability)

[0406] Workstation data (skills required, uptime required, reliability required)

[0407] Consider also using a sentiment engine to assess the reliability of input data.

[0408] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0409] Step 1:

[0410] The user uses a terminal to input personal characteristic information (age, gender, personality, hobbies, past work experience). The terminal sends this information to the server and stores it in a database. This allows the system to obtain the necessary characteristic information.

[0411] Input: Personal characteristics information

[0412] Output: Personal characteristics stored in a database

[0413] Specific operation: The user enters the required information on the form input screen and clicks the "Submit" button. The device sends the input data in JSON format to the server's API.

[0414] Step 2:

[0415] Factory managers use terminals to input the robot's characteristic information (identification number, performance, tasks it can handle, operating hours, reliability). The terminals then send this information to the server and store it in a database. This allows the system to obtain the necessary robot characteristic information.

[0416] Input: Robot characteristics information

[0417] Output: Robot characteristics stored in a database

[0418] Specific operation: The administrator enters the robot details into the input form and presses the "Submit" button. The data sent from the terminal is processed by the server and stored in the database.

[0419] Step 3:

[0420] The server uses an emotion engine to perform emotion analysis on the data entered by users and administrators, which evaluates the reliability and consistency of the data.

[0421] Input: Input feature information

[0422] Output: Emotion analysis results

[0423] How it works: The emotion engine uses natural language processing (NLP) techniques to analyze the sentiment of the words and style contained in the input data and generate a confidence score, which is stored in a database.

[0424] Step 4:

[0425] The server performs preprocessing and quantifies the individual and robot feature information, including converting categorical values ​​and quantifying text data.

[0426] Input: Personal characteristic information, robot characteristic information

[0427] Output: Quantified feature information

[0428] Specific operation: Using Python libraries (e.g., pandas, scikit-learn), categorical data is converted to numerical values ​​and text data is vectorized. The calculation results are stored in a database as numerical data.

[0429] Step 5:

[0430] The server calculates a matching score based on the quantified individual characteristic information, customer characteristic information, business requirements, robot characteristic information, and work station requirements. This score calculation uses the cosine similarity calculation method.

[0431] Input: Quantified characteristic information, customer characteristic information, business requirements, work station requirements

[0432] Output: Matching score

[0433] Specific operation: Using existing data processing libraries (e.g., numpy, scipy), the cosine similarity is calculated and a matching score for each individual and robot is calculated. This score is then stored in a database.

[0434] Step 6:

[0435] The server selects the best individuals and robots based on the matching scores, creates a list sorted by the highest score, and presents it to the user and administrator.

[0436] Input: Matching score

[0437] Output: List of best individuals and robots

[0438] Specific operation: The server sorts the matching scores in descending order and lists the most suitable individuals and robots. This list is displayed on the user's and administrator's terminals.

[0439] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0440] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0441] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0442] [Second embodiment]

[0443] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0444] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0445] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0446] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0447] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0448] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0449] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0450] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0451] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0452] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0453] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0454] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0455] This invention is a human resources matching system for quickly and accurately selecting the most suitable human resources according to the customer's request. This system is implemented mainly by the following components.

[0456] Data Entry

[0457] The server receives "personal characteristic information" provided by the user. This information includes age, gender, personality, hobbies, past work experience, etc. It also receives "customer characteristic information" and "job requirements" provided by the customer. The customer characteristic information includes the customer's personality, hobbies and preferences, past feedback, etc., while the job requirements include the skill set, work experience, personality, hobbies and preferences, etc. required to perform a specific job.

[0458] Data Preprocessing

[0459] The server preprocesses the received "personal characteristic information." This preprocessing includes quantifying categorical values ​​(e.g., personality, hobbies) and text data. It also calculates the number of past work experiences. The same preprocessing is performed on "customer characteristic information."

[0460] Matching Score Calculation

[0461] The server calculates a matching score based on the preprocessed "personal characteristic information," "customer characteristic information," and "business requirements." This score calculation uses a machine learning algorithm and a similarity calculation method (e.g., cosine similarity).

[0462] Selection of the best individuals

[0463] The server selects the most suitable individual based on the calculated matching score, and then filters the candidates based on the specific customer's personality and hobbies and preferences to narrow down the most suitable candidates.

[0464] Specific examples

[0465] 1. Data Entry Example

[0466] The user provides the following data as personal characteristic information:

[0467] Name: Alice

[0468] Age: 28

[0469] Gender: Female

[0470] Personality: extroverted

[0471] Hobbies: Reading

[0472] Previous work experience: Engineer, Manager

[0473] The user provides the following data as customer characteristic information and business requirements.

[0474] Customer Name: Company A

[0475] Past feedback: Good communication

[0476] Job requirements: Age 30 or older, 5+ years of experience, extroverted personality, reading hobby

[0477] 2. Pretreatment

[0478] The server calculates the number of past work experiences of an individual, and in Alice's case it is "2".

[0479] The server converts category information such as "personality" and "hobbies" into numerical values.

[0480] 3. Calculating the Matching Score

[0481] The server calculates the similarity between Alice's information and the business requirements. At this time, Alice's information is quantified and compared with the business requirements.

[0482] 4. Selecting the best individuals

[0483] The server determines that Alice is the best candidate based on the calculated matching score, and after filtering, it confirms that Alice best meets the customer requirements.

[0484] This system allows users to efficiently and effectively select and dispatch personnel who are best suited to customer needs. This process is automated, with the server processing the data and presenting the results, significantly reducing the user's workload.

[0485] The processing flow will be explained below.

[0486] Step 1:

[0487] The server receives personal characteristic information from the user, including the individual's age, gender, personality, hobbies, and past work experience, and stores this information in a database.

[0488] Step 2:

[0489] The server receives customer characteristic information and job requirements from the user. The customer characteristic information includes the customer's personality, hobbies and preferences, and past feedback, while the job requirements include the required skill set, work experience, personality, hobbies and preferences, etc. This information is also stored in the database.

[0490] Step 3:

[0491] The server preprocesses the stored individual characteristic information. This preprocessing includes converting categorical values ​​(e.g., personality, hobbies) into numerical values ​​and calculating the number of past work experiences. For example, if the person has work experience such as "engineer" and "manager," the number is calculated to be "2."

[0492] Step 4:

[0493] The server also preprocesses the customer's characteristic information and business requirements, which quantifies the customer's personality and preferences, and expresses each item of the business requirements as a specific numerical value.

[0494] Step 5:

[0495] The server calculates a matching score based on the preprocessed individual feature information, the customer feature information, and the business requirements. This score is calculated using a similarity calculation method (e.g., cosine similarity), which quantifies how well each individual matches the customer's requirements.

[0496] Step 6:

[0497] The server sorts the list of individuals based on the calculated matching scores, creating a list sorted by highest score first.

[0498] Step 7:

[0499] The server filters individual candidates based on the specific customer's personality and preferences, narrowing down the candidates to the most suitable candidates.

[0500] Step 8:

[0501] The server presents the filtered list of optimal personnel to the user, who then makes a final selection based on the provided list and dispatches the appropriate personnel.

[0502] Step 9:

[0503] The user checks the list of optimal personnel provided by the server and selects the personnel who best meets the request. After further detailed checks and adjustments as necessary, the user is ready to dispatch the personnel to the customer.

[0504] Through these steps, users can quickly and accurately select and dispatch the personnel best suited to their client's requirements. This process is automated, significantly reducing the user's time and effort.

[0505] Example 1

[0506] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0507] With conventional talent matching systems, it was difficult to quickly and accurately select the talent that best met the customer's requirements. In particular, without preprocessing of input data or appropriate filtering, matching accuracy decreased, and inappropriate talent was often selected. In addition, the method of notifying the selection results was complicated, which significantly increased the user's workload.

[0508] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0509] In this invention, the server includes means for receiving personal characteristic information provided by the user, means for receiving customer characteristic information and business requirements, means for calculating a matching score based on the characteristic information quantified through preprocessing, means for selecting and filtering the most suitable individuals based on the calculated matching score, and means for notifying the user of the selection results. This makes it possible to efficiently and accurately select personnel who are most suited to the customer's requirements and significantly reduce the user's workload.

[0510] "Personal characteristic information" refers to specific attributes and data about a person, such as age, gender, personality, hobbies, and past work experience.

[0511] "Customer characteristic information" refers to attributes and data related to customers, such as their personality, hobbies and preferences, and past feedback.

[0512] "Job requirements" refer to the conditions that customers desire, such as the skill set, work experience, personality, hobbies, and preferences needed to perform a specific job.

[0513] "Matching score" refers to the numerical value of similarity calculated using machine learning algorithms and similarity calculation methods based on individual characteristic information, customer characteristic information, and business requirements.

[0514] "Preprocessing" refers to a series of processes that properly format, digitize, and vectorize received data before analyzing or calculating it.

[0515] "Filtering" refers to the process of narrowing down the individuals who best fit a particular criteria based on a calculated matching score.

[0516] "Notification" refers to the act of informing users of the selected results and other information via email, the system dashboard, etc.

[0517] This invention is a human resources matching system for quickly and accurately selecting the most suitable human resources according to the customer's needs. This system consists of a server, a terminal, and a user.

[0518] Hardware and Software Configuration

[0519] The server contains the database system (e.g., MySQL or MongoDB), the backend that executes the program logic (e.g., Python, Django, or Flask), and the machine learning algorithms (e.g., Scikit-learn, TensorFlow). The terminal consists of a web browser or application that provides the user interface and communicates with the server via HTTP requests.

[0520] Program processing explanation

[0521] 1. Data Entry

[0522] A user inputs personal characteristics information, such as name, age, sex, personality, hobbies, and past work experience, through a web form.

[0523] The customer inputs their characteristic information and business requirements, such as "more than 3 years of engineering experience, good communication skills," and sends this data to the server.

[0524] The server receives this information and stores it in a database.

[0525] 2. Data Preprocessing

[0526] The server retrieves the necessary data from the database and converts the categorical data into numerical values. For example, "Personality: Extroverted" is converted to the numerical value "1" and "Hobby: Reading" is converted to the numerical value "2."

[0527] The server vectorizes the text data using techniques such as TF-IDF. For example, it vectorizes "Past feedback: communication is good."

[0528] The server calculates the number of past work experiences and treats it as numerical data.

[0529] 3. Calculating the Matching Score

[0530] The server calculates a matching score based on the preprocessed data using a machine learning algorithm or a similarity calculation method. For example, it calculates the angle between the vectors of the individual and customer feature information using cosine similarity to calculate the similarity score.

[0531] The server stores the calculated matching scores in a database.

[0532] 4. Selecting the best individuals

[0533] The server selects the best individuals based on the calculated matching scores, sorts them by highest score, and filters them.

[0534] The server then further filters based on the specific customer's personality and preferences to narrow down the most suitable candidates.

[0535] Specific examples

[0536] Example of data entry:

[0537] The user enters "Name: XX, Age: 28, Gender: Female, Personality: Outgoing, Hobbies: Reading, Past Work Experience: Engineer, Manager."

[0538] The customer enters the following information: "Customer characteristics: personality, hobbies, preferences, past feedback; job requirements: age 30 or older, 5 or more years of engineering experience, personality: extrovert, hobby: reading."

[0539] Prompt Sentence Examples

[0540] "Select the best person to meet the client's business requirements. Consider the following information: client characteristics, business requirements, and personal characteristics."

[0541] This system allows users to efficiently and accurately select and dispatch personnel who are best suited to customer needs, significantly reducing the user's workload.

[0542] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0543] Step 1:

[0544] Data Entry

[0545] The user enters personal characteristic information into a web form and submits it.

[0546] Specifically, you enter information such as your name, age, gender, personality, hobbies, and past work experience.

[0547] The server receives the transmitted data and stores it in a database.

[0548] Input: Data entered by a user into a web form

[0549] Output: Personal characteristics stored in a database

[0550] The user also inputs and submits customer characteristic information and business requirements.

[0551] Specifically, you enter information such as the customer's personality, hobbies and preferences, past feedback, and required skill set.

[0552] The server also receives this data and stores it in a database.

[0553] Input: Customer characteristics and business requirements entered by the user

[0554] Output: Customer characteristics and business requirements stored in a database

[0555] Step 2:

[0556] Data Preprocessing

[0557] The server retrieves personal and customer characteristic information from a database.

[0558] Input: Personal and customer characteristics stored in the database

[0559] Output: Retrieved data

[0560] The server preprocesses the acquired data. First, it quantifies the category values.

[0561] For example, "Personality: Extroverted" is converted into a numerical value of "1" and "Hobby: Reading" is converted into a numerical value of "2".

[0562] Input: Acquired data (category information)

[0563] Output: digitized data

[0564] The server vectorizes the text data using TF-IDF.

[0565] For example, vectorize "Past feedback: Good communication."

[0566] Input: Text data

[0567] Output: Vectorized text data

[0568] The server calculates the number of past work experiences and treats it as numerical data.

[0569] Input: Previous work experience (text information)

[0570] Output: Quantified past work experience

[0571] Step 3:

[0572] Matching Score Calculation

[0573] The server calculates a matching score based on the pre-processed data.

[0574] The server uses machine learning algorithms (e.g., Random Forest or Support Vector Machine) and similarity calculation methods (e.g., cosine similarity).

[0575] Specifically, the angle between the feature information vectors of the individual and the customer is calculated using cosine similarity, and a similarity score is calculated.

[0576] Input: Preprocessed personal and customer characteristics

[0577] Output: The calculated matching score

[0578] The server stores the calculated matching scores in a database.

[0579] Input: The calculated matching score

[0580] Output: Matching scores stored in a database

[0581] Step 4:

[0582] Selection of the best individuals

[0583] The server selects the best individual based on the calculated matching score.

[0584] Sorting is done by highest score and selecting the most suitable individual.

[0585] Input: Matching scores stored in the database

[0586] Output: Selection of the best individual

[0587] The server performs further filtering based on the characteristics and preferences of the particular customer.

[0588] Input: Selected personal data and customer characteristics

[0589] Output: Best candidates after filtering

[0590] The server notifies the user of the selection results by email or by displaying the results on the system dashboard.

[0591] Input: Best candidates after filtering

[0592] Output: Selection result notified to the user

[0593] This system efficiently and accurately selects the personnel best suited to the customer's requirements, significantly reducing the user's workload.

[0594] (Application example 1)

[0595] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0596] In the security services industry, a challenge is quickly and accurately selecting security personnel who meet customer requirements. With conventional personnel matching systems, it takes time to select highly suitable security personnel and there are also limitations to the accuracy of the matching. This makes it difficult to provide security services efficiently and effectively.

[0597] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0598] In this invention, the server includes means for receiving personal characteristic information provided by a user, means for receiving customer characteristic information and business requirements provided by a user, means for calculating a matching score between the individual and the customer based on the individual characteristic information, the customer characteristic information and business requirements, means for selecting an optimal individual based on the matching score, means for selecting an optimal security officer based on security service requirements, and means for outputting information on the selected security officer, thereby enabling security officers suitable for security services to be selected quickly and accurately.

[0599] 1. "Personal characteristic information" refers to characteristic information related to an individual, such as age, gender, personality, hobbies, and past work experience.

[0600] 2. "Customer characteristic information" refers to characteristic information related to a customer, such as the customer's personality, hobbies and preferences, and past feedback.

[0601] 3. "Job requirements" refer to the skill sets, work experience, personality traits, hobbies, and other conditions necessary to perform a specific job.

[0602] 4. "Matching score" refers to a similarity score calculated based on personal characteristic information, customer characteristic information, and business requirements.

[0603] 5. "Security services" means services that provide security, guarding, and surveillance.

[0604] 6. "Security Officer" means an individual selected to perform security service duties.

[0605] 7. "Outputting information" means displaying, notifying, or transmitting calculated results or selected data to another system.

[0606] The system for carrying out the present invention is for quickly and accurately selecting security personnel in the field of security services in response to customer requests. The system is mainly composed of the following components:

[0607] Data Entry

[0608] The server receives "personal characteristic information" provided by the user. This information includes age, gender, personality, hobbies, past work experience, etc. It also receives "customer characteristic information" and "job requirements" provided by the user. Customer characteristic information includes the customer's personality, hobbies and preferences, past feedback, etc., while job requirements include the skill set, work experience, personality, hobbies and preferences, etc. required to perform a specific job.

[0609] Data Preprocessing

[0610] The server preprocesses the received "personal characteristic information." This preprocessing includes quantifying categorical values ​​(e.g., personality, hobbies) and text data. It also calculates the number of past work experiences. The same preprocessing is performed on "customer characteristic information."

[0611] Matching Score Calculation

[0612] The server calculates a matching score based on the preprocessed "personal characteristic information," "customer characteristic information," and "business requirements." This score calculation uses a machine learning algorithm or a similarity calculation method (e.g., cosine similarity).

[0613] Selection of the best individuals

[0614] The server selects the most suitable individual based on the calculated matching score. Furthermore, filtering is performed based on the specific customer's personality and hobbies and preferences to narrow down the most suitable security personnel. During this selection process, filtering specific to the security service requirements is also performed.

[0615] Output of information

[0616] The server outputs information about the selected security officer to the terminal, including the reason for the selection and detailed characteristic information about the security officer.

[0617] For example, if the following data is entered:

[0618] Personal characteristic information

[0619] Name: Security Officer A

[0620] Age: 35

[0621] Gender: Male

[0622] Personality: extroverted

[0623] Hobbies: Reading

[0624] Previous work experience: 10 years

[0625] Customer characteristics and business requirements

[0626] Customer Name: Customer Company B

[0627] Past feedback: Good communication

[0628] Job requirements: 8+ years of experience, outgoing personality, reading hobby

[0629] Based on this data, the server determines that security officer A is the best candidate and outputs that information.

[0630] An example of a prompt sentence to be input to a specific generative AI model is as follows:

[0631] Write a program to select the best security officer for a customer based on user-input data. Receive personal and customer characteristics as input data, calculate the cosine similarity based on the data, and use a method to select the best candidate.

[0632] In this way, it becomes possible to quickly and accurately select security personnel suitable for security services.

[0633] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0634] Step 1:

[0635] The server receives personal characteristic information provided by the user as input. This information includes age, gender, personality, hobbies, past work experience, etc., and is important data for identifying an individual. Each piece of data is in text or numerical format. The server stores this data in temporary storage.

[0636] Step 2:

[0637] The server receives as input the customer characteristics and job requirements provided by the user, including the customer's personality, hobbies and preferences, past feedback, and the skill set required for a particular job. This data is also stored in temporary storage.

[0638] Step 3:

[0639] The server preprocesses the individual's characteristic information. Preprocessing includes quantifying category values, quantifying text data, and quantifying past work experience. For example, "Personality: Extroverted" is quantified, and "Past work experience: 10 years" is treated as a number. This ensures that all data is in a unified format. The output is preprocessed numerical data.

[0640] Step 4:

[0641] The server also preprocesses customer characteristic information and business requirements, converting categorical values ​​into numbers and quantifying text data, and standardizing the data format. The output is preprocessed numerical data.

[0642] Step 5:

[0643] The server calculates a matching score based on the preprocessed individual feature information, customer feature information, and business requirements. This score is calculated using similarity calculation methods such as machine learning algorithms and cosine similarity. Specifically, the degree of compatibility between an individual and a customer is quantified by calculating the cosine similarity between feature vectors. The output is a matching score.

[0644] Step 6:

[0645] The server selects the best individuals based on the matching scores. First, it lists the calculated matching scores and sorts them by highest score. Then it performs filtering specific to the security service requirements to narrow down the best security officers. The output is a list of selected individuals.

[0646] Step 7:

[0647] The server outputs information about the selected security officer to the terminal. This information includes the name, age, gender, past work experience, and reasons for the selection of the best candidate. The terminal displays this information on the screen or in a notification message. The user checks this information and makes the final decision on whether to actually dispatch the security officer.

[0648] For example, you can issue prompts to the server using the following:

[0649] Write a program to select the best security officer for a customer based on user-input data. Receive personal and customer characteristics as input data, calculate the cosine similarity based on the data, and use a method to select the best candidate.

[0650] Through the above process, it becomes possible to quickly and accurately select an appropriate security officer for security services.

[0651] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0652] This invention is a talent matching system for quickly and accurately selecting the most suitable talent in response to customer requests. This system achieves highly accurate matching by incorporating an emotion engine that recognizes the user's emotions. Detailed embodiments of the system are described below.

[0653] Data Entry

[0654] The server receives personal characteristic information from the user. The received information includes the individual's age, gender, personality, hobbies, and past work experience. This information is stored in a database. The server also receives customer characteristic information and job requirements from the user. The customer characteristic information includes the customer's personality, hobbies and preferences, and past feedback, and the job requirements include the required skill set, work experience, personality, hobbies and preferences, etc. This information is also stored in a database.

[0655] Preprocessing with emotion engine

[0656] The server uses an emotion engine to recognize the user's emotions, thereby improving the reliability and consistency of input information. The emotion engine analyzes the user's emotional reactions to the characteristic information and business requirements entered by the user and incorporates this data into preprocessing.

[0657] Data Preprocessing

[0658] The server preprocesses the individual's characteristic information, including the data obtained by the emotion engine. This preprocessing includes quantifying categorical values ​​(e.g., personality, hobbies) and text data. The number of past work experiences is also calculated. The same preprocessing is performed on the "customer's characteristic information," and the analysis results of the emotion engine are reflected.

[0659] Matching Score Calculation

[0660] The server calculates a matching score based on the preprocessed individual feature information, the customer feature information, and the business requirements. This score is calculated using a similarity calculation method (e.g., cosine similarity), which quantifies how well each individual matches the customer's requirements.

[0661] Selection of the best individuals

[0662] The server sorts the list of individuals based on the calculated matching score. A list sorted by highest score is created, and individual candidates are filtered based on the personality and hobbies of the specific customer. An emotion engine can be used to further refine the filtering.

[0663] Specific examples

[0664] 1. Data Entry Example

[0665] The user provides the following data as personal characteristic information:

[0666] Name: Alice

[0667] Age: 28

[0668] Gender: Female

[0669] Personality: extroverted

[0670] Hobbies: Reading

[0671] Previous work experience: Engineer, Manager

[0672] The user provides the following data as customer characteristic information and business requirements.

[0673] Customer Name: Company A

[0674] Past feedback: Good communication

[0675] Job requirements: Age 30 or older, 5+ years of experience, extroverted personality, reading hobby

[0676] 2. Preprocessing by the emotion engine

[0677] The server analyzes the input data from the user using an emotion engine. For example, if the user's emotion at the time of input is positive, it is evaluated as a factor that increases the reliability of the data.

[0678] 3. Data Preprocessing

[0679] The server calculates the number of past work experiences of each individual, and in Alice's case, it sets it to "2." It also quantifies category information such as "personality" and "hobbies."

[0680] 4. Calculating the Matching Score

[0681] The server calculates the similarity between Alice's information and the business requirements. At this time, Alice's information is quantified and compared with the business requirements.

[0682] 5. Selecting the best individuals

[0683] The server determines that Alice is the best candidate based on the calculated matching score, and also takes into account data from the sentiment engine to confirm that Alice best meets the customer requirements.

[0684] This system allows users to quickly and accurately select and dispatch the personnel best suited to their client's requirements. Furthermore, the use of an emotion engine improves the reliability of input data, resulting in more accurate matching. This process is automated, significantly reducing the user's workload.

[0685] The processing flow will be explained below.

[0686] Step 1:

[0687] The server receives personal characteristic information from the user. The received information includes the individual's age, gender, personality, hobbies, and past work experience. This information is stored in a database. For example, when information about an individual named Alice is provided, that information is sent to the server in digital format.

[0688] Step 2:

[0689] The server receives customer characteristic information and business requirements from the user. Customer characteristic information includes the customer's personality, hobbies and preferences, and past feedback, while business requirements include the required skill set, work experience, personality, hobbies and preferences, etc. This information is also stored in the database. For example, the business requirements and characteristic information of Company A are entered into the server.

[0690] Step 3:

[0691] The server uses an emotion engine to analyze the personal characteristic information entered by the user. For example, it recognizes the user's emotional state (positive, negative, etc.) at the time of input and adds that information to the input data. The results of this analysis are used to evaluate the reliability of the data and correct it.

[0692] Step 4:

[0693] The server preprocesses the individual's characteristic information, including the data analyzed by the emotion engine. This preprocessing includes converting categorical values ​​(e.g., personality, hobbies) into numerical values ​​and calculating the number of past work experiences. For example, Alice's personality trait "extroverted" is converted to the numerical value "1," and her hobby "reading" is converted to the numerical value "2."

[0694] Step 5:

[0695] The server also preprocesses customer characteristic information and business requirements, including data analyzed by the emotion engine. This quantifies the customer's personality and hobbies and preferences, and each item in the business requirements is expressed as a specific numerical value. For example, Company A's requirement "extroverted personality" is converted to the numerical value "1," and "hobby reading" is converted to the numerical value "2."

[0696] Step 6:

[0697] The server calculates a matching score based on the preprocessed individual characteristic information, customer characteristic information, and business requirements. A similarity calculation method (e.g., cosine similarity) is used to calculate this score. This quantifies the degree to which each individual matches the customer requirements. For example, Alice's information is compared with Company A's business requirements to generate a matching score.

[0698] Step 7:

[0699] The server sorts the list of individuals based on the calculated matching scores, creating a list sorted by highest score first. For example, Alice, Bob, Charlie might be listed in descending order of scores.

[0700] Step 8:

[0701] The server filters individual candidates based on the specific customer's personality and hobbies and preferences. This narrows down the candidates to the most suitable. The filtering process also takes into account the analysis results of the emotion engine. For example, Alice is narrowed down as the most suitable candidate.

[0702] Step 9:

[0703] The server presents the filtered list of optimal candidates to the user. The user makes a final selection based on the provided list and prepares to dispatch the appropriate candidate. For example, Alice's detailed information is displayed to the user, and the user can decide whether to dispatch her to the customer.

[0704] These steps enable users to quickly and accurately select and dispatch the best personnel for their customer requirements. This process, combined with the emotion engine, improves the reliability of input data and achieves more accurate matching.

[0705] Example 2

[0706] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0707] Conventional talent matching systems lacked the reliability and consistency of input data, making it difficult to quickly and accurately select the talent most suited to customer requirements. Furthermore, data processing was performed without taking the user's emotional state into consideration, making it difficult to achieve highly accurate matching. This resulted in increased user effort and hindered efficient talent selection.

[0708] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0709] In this invention, the server includes means for receiving personal characteristic information provided by the user, means for receiving customer characteristic information and business requirements provided by the user, means for calculating a matching score based on the personal characteristic information, customer characteristic information and business requirements, means for selecting the most suitable individual based on the matching score, means for analyzing the user's emotions using an emotion engine and improving the reliability and consistency of input data, means for reflecting the analysis results of the emotion engine in preprocessing, and means for reflecting the user's emotional state in calculations based on the preprocessed data. This enables highly accurate matching and significantly reduces the user's workload.

[0710] "Individual characteristic information" is attribute information about a specific individual, such as age, gender, personality, hobbies, and past work experience.

[0711] "Customer characteristic information" is attribute information about a specific customer, such as the customer's personality, hobbies and preferences, and past feedback.

[0712] "Job requirements" are the conditions necessary to perform a specific job, such as the necessary skill set, work experience, personality, hobbies, and preferences.

[0713] The "matching score" is a numerical representation of the compatibility between an individual and a customer, calculated based on the individual's characteristic information, the customer's characteristic information, and business requirements.

[0714] An "emotion engine" is a technology used to analyze a user's emotional response to input data, improving reliability and consistency.

[0715] "Preprocessing" refers to the process of making the collected raw data easier to analyze, and includes converting categorical values ​​into numerical values ​​and quantifying text data.

[0716] "Filtering" is the process of sorting data based on specific conditions and extracting only useful information.

[0717] "Reliability" refers to the degree of accuracy and consistency of data.

[0718] "Consistency" indicates that the data follows certain rules or patterns.

[0719] This invention is a talent matching system for quickly and accurately selecting the best talent according to customer needs. This system achieves highly accurate matching by combining an emotion engine that recognizes the user's emotions.

[0720] First, the server receives personal characteristic information (age, gender, personality, hobbies, past work experience) provided by the user and stores it in the database. The server also receives customer characteristic information (personality, hobbies and preferences, past feedback) and job requirements (required skill set, work experience, personality, hobbies and preferences) and stores them in the database.

[0721] The server then analyzes the user's emotions using an emotion engine, which analyzes the emotional response to the input data to improve reliability and consistency. For example, if the user's emotion at the time of input is positive, it is evaluated as a factor that increases the reliability of the data.

[0722] In the data preprocessing stage, the server performs preprocessing on the collected data to make it easier to analyze. This includes quantifying categorical information such as personality and hobbies, and work experience. The analysis results from the emotion engine are also reflected here, and a reliability score for the data is calculated.

[0723] The server then calculates a matching score based on the preprocessed data. This calculation uses a similarity calculation method such as cosine similarity. As a result, the degree of match between the individual's characteristic information, the customer's characteristic information, and the business requirements is quantified.

[0724] Finally, the server generates a list of candidates based on the calculated matching scores. This list is sorted by highest score and filtered based on the personality and preferences of the specific customer. An emotion engine can be used to further refine the filtering.

[0725] Specific examples

[0726] 1. Data Entry Example

[0727] The user provides the following data as personal characteristic information:

[0728] Name: Individual A

[0729] Age: 28

[0730] Gender: Female

[0731] Personality: extroverted

[0732] Hobbies: Reading

[0733] Previous work experience: Engineer, Manager

[0734] The user provides the following data as customer characteristic information and business requirements.

[0735] Customer Name: Customer A

[0736] Past feedback: Good communication

[0737] Job requirements: Age 30 or older, 5+ years of experience, extroverted personality, reading hobby

[0738] 2. Preprocessing by the emotion engine

[0739] The server analyzes the input data from the user using an emotion engine. For example, if the user's emotion at the time of input is positive, it is evaluated as a factor that increases the reliability of the data.

[0740] 3. Data Preprocessing

[0741] The server calculates the number of past work experiences, and sets the number to "2" in the case of Individual A. It also quantifies category information such as "personality" and "hobbies."

[0742] 4. Calculating the Matching Score

[0743] Based on the business requirements, the server calculates the degree of similarity with the information of person A. At this time, person A's information is quantified and compared with the business requirements.

[0744] 5. Selecting the best individuals

[0745] Based on the calculated matching score, the server determines that Person A is the best candidate. Data from the emotion engine is also taken into account to confirm that Person A best meets the customer requirements.

[0746] Prompt Sentence Examples

[0747] "Please register Individual A, a 28-year-old extroverted female engineer whose hobby is reading."

[0748] "Looking for someone over 30, with at least 5 years of experience, who is extroverted and enjoys reading."

[0749] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0750] Step 1:

[0751] Data Entry

[0752] The server receives personal characteristic information (name, age, gender, personality, hobbies, past work experience) provided by the user. The input data is sent to the server via an HTTP request. The server stores the received data in a database. It also receives customer characteristic information (personality, hobbies and preferences, past feedback) and job requirements (required skill set, work experience, personality, hobbies and preferences) and stores them in the database.

[0753] Specific operation example: When a user enters personal and customer characteristic information into a web form and presses the submit button, the information is sent to the server, which processes this data using Python and stores it in a database (e.g., MySQL).

[0754] Input: User-entered personal and customer characteristics information

[0755] Output: Feature information stored in a database

[0756] Step 2:

[0757] Preprocessing with emotion engine

[0758] The server sends the acquired feature information to the emotion engine to analyze the user's emotional state. The emotion engine determines the emotional response (positive, negative, neutral, etc.) based on the input data. This result is used as additional information to improve the reliability and consistency of the data.

[0759] Specific operation example: The server calls the API for the emotion engine and sends the user's characteristic information. The emotion engine returns the analysis results, and the server stores the results in a database.

[0760] Input: Feature information

[0761] Output: Analysis results by the emotion engine

[0762] Step 3:

[0763] Data Preprocessing

[0764] The server preprocesses the collected data, including the analysis results of the emotion engine. This preprocessing includes quantifying categorical information such as personality and hobbies, quantifying past work experience, and calculating a reliability score for the data. This facilitates the subsequent calculation of matching scores.

[0765] Specific example: Using Python's pandas library, the collected data is processed as a data frame. Categorical information and text data are converted into numerical data, and the number of work experiences is calculated.

[0766] Input: Feature information including the analysis results of the emotion engine

[0767] Output: Preprocessed data

[0768] Step 4:

[0769] Matching Score Calculation

[0770] The server calculates a matching score based on the preprocessed individual and customer characteristic information and business requirements. The similarity calculation uses, for example, cosine similarity. The calculated matching score quantifies the degree of agreement between the individual and customer requirements.

[0771] Specific example: Using the scikit-learn library, calculate the cosine similarity between vectors of preprocessed data. The calculation results are stored in a database.

[0772] Input: Preprocessed individual and customer characteristics information

[0773] Output: Matching score

[0774] Step 5:

[0775] Selection of the best individuals

[0776] The server generates a candidate list based on the calculated matching scores. It sorts the candidates by highest score and filters them based on the characteristics and hobbies of specific customers. It also takes into account the results of the emotion engine to create an even more accurate candidate list.

[0777] Specific example of operation: Using an SQL query, data is retrieved from the database in descending order of matching score, a list reflecting the results of sentiment analysis is generated, and then provided to the user.

[0778] Input: Matching score

[0779] Output: A list of the best candidates

[0780] (Application example 2)

[0781] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0782] Conventional talent matching systems have issues with the reliability and consistency of input information because they do not take into account user emotional data. Also, in factory management using robots, there is a problem with the inability to quickly and accurately allocate appropriate robots.

[0783] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving individual characteristic information provided by a user; means for receiving customer characteristic information and business requirements provided by a user; means for calculating a matching score between the individual and the customer based on the individual characteristic information, the customer characteristic information, and the business requirements; means for selecting the most suitable individual based on the matching score; means for analyzing the user's emotional response using an emotion engine and evaluating the reliability of the data based on the analysis; and means for a factory manager to input robot characteristic information and work station requirements using a smart device and match robots with work stations based on the input. This enables highly accurate personnel matching that takes user emotional data into account and efficient deployment of robots in the factory.

[0784] "User emotional response" refers to the psychological state or feelings a user exhibits when entering information.

[0785] The "matching score" is a numerical representation of the degree of match between the individual's characteristic information, the customer's characteristic information, and the business requirements.

[0786] An "emotion engine" is a system that analyzes user emotions in response to input data and evaluates the reliability and consistency of that data.

[0787] "Smart devices" refers to electronic devices with internet connectivity, such as smartphones, tablets, smart glasses, and head-mounted displays.

[0788] "Robot characteristic information" includes information such as the robot's identification number, performance, tasks that it can handle, operating time, and reliability.

[0789] "Work station" refers to a location within a factory where a specific task is performed.

[0790] A "factory manager" is a person in charge of managing work and robots within the factory.

[0791] The present invention is a system for matching human resources and robots with consideration of the user's emotions. Specific embodiments will be described below.

[0792] Data Entry

[0793] First, the server receives personal characteristic information provided by the user. This information includes age, gender, personality, hobbies, past work experience, etc. The user also inputs customer characteristic information and work requirements. This includes the customer's personality, hobbies and preferences, past feedback, required skill set, work experience, etc. The factory manager inputs robot characteristic information (identification number, performance, work that can be performed, operating time, reliability) and work station requirements (required skills, operating time, work content). All of this data is stored in a database.

[0794] Preprocessing with emotion engine

[0795] The server uses an emotion engine to analyze the user's emotional response to the input data, which improves the reliability and consistency of the input information. For example, if the user shows positive emotions, the data will be rated as more reliable.

[0796] Data Preprocessing

[0797] The server preprocesses the individual and robot characteristic information, including the data obtained by the emotion engine. This preprocessing involves converting category values ​​into numerical values ​​and quantifying text data. The number of past work experiences is then calculated. Similar preprocessing is performed on the "customer characteristic information" and "workstation requirements," and the analysis results of the emotion engine are reflected.

[0798] Matching Score Calculation

[0799] The server calculates a matching score based on the preprocessed individual feature information, the robot feature information, the customer feature information, the business requirements, and the requirements of the work station. This score is calculated using a similarity calculation method such as cosine similarity, which quantifies how well each individual or robot matches the requirements of the customer or work station.

[0800] Selection of the best individuals and robots

[0801] The server selects the best individuals and robots based on the calculated matching scores. A list is created sorted by highest score, and candidates are filtered based on the specific customer's personality, hobbies, and work station requirements. An emotion engine can be used to further refine the filtering.

[0802] Specific examples

[0803] The user provides the following data as personal characteristic information:

[0804] Name: Taro

[0805] Age: 35

[0806] Gender: Male

[0807] Personality: introverted

[0808] Hobbies: Programming

[0809] Previous work experience: Systems engineer, project manager

[0810] In addition, the factory manager provides the following data as characteristic information of the robot:

[0811] Identification number: R123

[0812] Performance: High

[0813] Available work: Assembly, packaging

[0814] Operating time: 3000 hours

[0815] Reliability: 90%

[0816] The administrator provides the following data as requirements for the workstation:

[0817] Required skills: Assembly

[0818] Operating time: 2500 hours

[0819] Required work: Parts assembly

[0820] The server receives this information, analyzes it with an emotion engine, performs preprocessing, calculates a matching score, and selects the most suitable individual and robot.

[0821] Prompt Sentence Examples

[0822] Based on the data below, come up with an algorithm to optimally match robots and workstations, and implement it in Python.

[0823] Robot data (identification number, performance, skills, operating time, reliability)

[0824] Workstation data (skills required, uptime required, reliability required)

[0825] Consider also using a sentiment engine to assess the reliability of input data.

[0826] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0827] Step 1:

[0828] The user uses a terminal to input personal characteristic information (age, gender, personality, hobbies, past work experience). The terminal sends this information to the server and stores it in a database. This allows the system to obtain the necessary characteristic information.

[0829] Input: Personal characteristics information

[0830] Output: Personal characteristics stored in a database

[0831] Specific operation: The user enters the required information on the form input screen and clicks the "Submit" button. The device sends the input data in JSON format to the server's API.

[0832] Step 2:

[0833] Factory managers use terminals to input the robot's characteristic information (identification number, performance, tasks it can handle, operating hours, reliability). The terminals then send this information to the server and store it in a database. This allows the system to obtain the necessary robot characteristic information.

[0834] Input: Robot characteristics information

[0835] Output: Robot characteristics stored in a database

[0836] Specific operation: The administrator enters the robot details into the input form and presses the "Submit" button. The data sent from the terminal is processed by the server and stored in the database.

[0837] Step 3:

[0838] The server uses an emotion engine to perform emotion analysis on the data entered by users and administrators, which evaluates the reliability and consistency of the data.

[0839] Input: Input feature information

[0840] Output: Emotion analysis results

[0841] How it works: The emotion engine uses natural language processing (NLP) techniques to analyze the sentiment of the words and style contained in the input data and generate a confidence score, which is stored in a database.

[0842] Step 4:

[0843] The server performs preprocessing and quantifies the individual and robot feature information, including converting categorical values ​​and quantifying text data.

[0844] Input: Personal characteristic information, robot characteristic information

[0845] Output: Quantified feature information

[0846] Specific operation: Using Python libraries (e.g., pandas, scikit-learn), categorical data is converted to numerical values ​​and text data is vectorized. The calculation results are stored in a database as numerical data.

[0847] Step 5:

[0848] The server calculates a matching score based on the quantified individual characteristic information, customer characteristic information, business requirements, robot characteristic information, and work station requirements. This score calculation uses the cosine similarity calculation method.

[0849] Input: Quantified characteristic information, customer characteristic information, business requirements, work station requirements

[0850] Output: Matching score

[0851] Specific operation: Using existing data processing libraries (e.g., numpy, scipy), the cosine similarity is calculated and a matching score for each individual and robot is calculated. This score is then stored in a database.

[0852] Step 6:

[0853] The server selects the best individuals and robots based on the matching scores, creates a list sorted by the highest score, and presents it to the user and administrator.

[0854] Input: Matching score

[0855] Output: List of best individuals and robots

[0856] Specific operation: The server sorts the matching scores in descending order and lists the most suitable individuals and robots. This list is displayed on the user's and administrator's terminals.

[0857] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0858] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0859] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0860] [Third embodiment]

[0861] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0862] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0863] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0864] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0865] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0866] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0867] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0868] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0869] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0870] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0871] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0872] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0873] This invention is a human resources matching system for quickly and accurately selecting the most suitable human resources according to the customer's request. This system is implemented mainly by the following components.

[0874] Data Entry

[0875] The server receives "personal characteristic information" provided by the user. This information includes age, gender, personality, hobbies, past work experience, etc. It also receives "customer characteristic information" and "job requirements" provided by the customer. The customer characteristic information includes the customer's personality, hobbies and preferences, past feedback, etc., while the job requirements include the skill set, work experience, personality, hobbies and preferences, etc. required to perform a specific job.

[0876] Data Preprocessing

[0877] The server preprocesses the received "personal characteristic information." This preprocessing includes quantifying categorical values ​​(e.g., personality, hobbies) and text data. It also calculates the number of past work experiences. The same preprocessing is performed on "customer characteristic information."

[0878] Matching Score Calculation

[0879] The server calculates a matching score based on the preprocessed "personal characteristic information," "customer characteristic information," and "business requirements." This score calculation uses a machine learning algorithm and a similarity calculation method (e.g., cosine similarity).

[0880] Selection of the best individuals

[0881] The server selects the most suitable individual based on the calculated matching score, and then filters the candidates based on the specific customer's personality and hobbies and preferences to narrow down the most suitable candidates.

[0882] Specific examples

[0883] 1. Data Entry Example

[0884] The user provides the following data as personal characteristic information:

[0885] Name: Alice

[0886] Age: 28

[0887] Gender: Female

[0888] Personality: extroverted

[0889] Hobbies: Reading

[0890] Previous work experience: Engineer, Manager

[0891] The user provides the following data as customer characteristic information and business requirements.

[0892] Customer Name: Company A

[0893] Past feedback: Good communication

[0894] Job requirements: Age 30 or older, 5+ years of experience, extroverted personality, reading hobby

[0895] 2. Pretreatment

[0896] The server calculates the number of past work experiences of an individual, and in Alice's case it is "2".

[0897] The server converts category information such as "personality" and "hobbies" into numerical values.

[0898] 3. Calculating the Matching Score

[0899] The server calculates the similarity between Alice's information and the business requirements. At this time, Alice's information is quantified and compared with the business requirements.

[0900] 4. Selecting the best individuals

[0901] The server determines that Alice is the best candidate based on the calculated matching score, and after filtering, it confirms that Alice best meets the customer requirements.

[0902] This system allows users to efficiently and effectively select and dispatch personnel who are best suited to customer needs. This process is automated, with the server processing the data and presenting the results, significantly reducing the user's workload.

[0903] The processing flow will be explained below.

[0904] Step 1:

[0905] The server receives personal characteristic information from the user, including the individual's age, gender, personality, hobbies, and past work experience, and stores this information in a database.

[0906] Step 2:

[0907] The server receives customer characteristic information and job requirements from the user. The customer characteristic information includes the customer's personality, hobbies and preferences, and past feedback, while the job requirements include the required skill set, work experience, personality, hobbies and preferences, etc. This information is also stored in the database.

[0908] Step 3:

[0909] The server preprocesses the stored individual characteristic information. This preprocessing includes converting categorical values ​​(e.g., personality, hobbies) into numerical values ​​and calculating the number of past work experiences. For example, if the person has work experience such as "engineer" and "manager," the number is calculated to be "2."

[0910] Step 4:

[0911] The server also preprocesses the customer's characteristic information and business requirements, which quantifies the customer's personality and preferences, and expresses each item of the business requirements as a specific numerical value.

[0912] Step 5:

[0913] The server calculates a matching score based on the preprocessed individual feature information, the customer feature information, and the business requirements. This score is calculated using a similarity calculation method (e.g., cosine similarity), which quantifies how well each individual matches the customer's requirements.

[0914] Step 6:

[0915] The server sorts the list of individuals based on the calculated matching scores, creating a list sorted by highest score first.

[0916] Step 7:

[0917] The server filters individual candidates based on the specific customer's personality and preferences, narrowing down the candidates to the most suitable candidates.

[0918] Step 8:

[0919] The server presents the filtered list of optimal personnel to the user, who then makes a final selection based on the provided list and dispatches the appropriate personnel.

[0920] Step 9:

[0921] The user checks the list of optimal personnel provided by the server and selects the personnel who best meets the request. After further detailed checks and adjustments as necessary, the user is ready to dispatch the personnel to the customer.

[0922] Through these steps, users can quickly and accurately select and dispatch the personnel best suited to their client's requirements. This process is automated, significantly reducing the user's time and effort.

[0923] Example 1

[0924] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0925] With conventional talent matching systems, it was difficult to quickly and accurately select the talent that best met the customer's requirements. In particular, without preprocessing of input data or appropriate filtering, matching accuracy decreased, and inappropriate talent was often selected. In addition, the method of notifying the selection results was complicated, which significantly increased the user's workload.

[0926] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0927] In this invention, the server includes means for receiving personal characteristic information provided by the user, means for receiving customer characteristic information and business requirements, means for calculating a matching score based on the characteristic information quantified through preprocessing, means for selecting and filtering the most suitable individuals based on the calculated matching score, and means for notifying the user of the selection results. This makes it possible to efficiently and accurately select personnel who are most suited to the customer's requirements and significantly reduce the user's workload.

[0928] "Personal characteristic information" refers to specific attributes and data about a person, such as age, gender, personality, hobbies, and past work experience.

[0929] "Customer characteristic information" refers to attributes and data related to customers, such as their personality, hobbies and preferences, and past feedback.

[0930] "Job requirements" refer to the conditions that customers desire, such as the skill set, work experience, personality, hobbies, and preferences needed to perform a specific job.

[0931] "Matching score" refers to the numerical value of similarity calculated using machine learning algorithms and similarity calculation methods based on individual characteristic information, customer characteristic information, and business requirements.

[0932] "Preprocessing" refers to a series of processes that properly format, digitize, and vectorize received data before analyzing or calculating it.

[0933] "Filtering" refers to the process of narrowing down the individuals who best fit a particular criteria based on a calculated matching score.

[0934] "Notification" refers to the act of informing users of the selected results and other information via email, the system dashboard, etc.

[0935] This invention is a human resources matching system for quickly and accurately selecting the most suitable human resources according to the customer's needs. This system consists of a server, a terminal, and a user.

[0936] Hardware and Software Configuration

[0937] The server contains the database system (e.g., MySQL or MongoDB), the backend that executes the program logic (e.g., Python, Django, or Flask), and the machine learning algorithms (e.g., Scikit-learn, TensorFlow). The terminal consists of a web browser or application that provides the user interface and communicates with the server via HTTP requests.

[0938] Program processing explanation

[0939] 1. Data Entry

[0940] A user inputs personal characteristics information, such as name, age, sex, personality, hobbies, and past work experience, through a web form.

[0941] The customer inputs their characteristic information and business requirements, such as "more than 3 years of engineering experience, good communication skills," and sends this data to the server.

[0942] The server receives this information and stores it in a database.

[0943] 2. Data Preprocessing

[0944] The server retrieves the necessary data from the database and converts the categorical data into numerical values. For example, "Personality: Extroverted" is converted to the numerical value "1" and "Hobby: Reading" is converted to the numerical value "2."

[0945] The server vectorizes the text data using techniques such as TF-IDF. For example, it vectorizes "Past feedback: communication is good."

[0946] The server calculates the number of past work experiences and treats it as numerical data.

[0947] 3. Calculating the Matching Score

[0948] The server calculates a matching score based on the preprocessed data using a machine learning algorithm or a similarity calculation method. For example, it calculates the angle between the vectors of the individual and customer feature information using cosine similarity to calculate the similarity score.

[0949] The server stores the calculated matching scores in a database.

[0950] 4. Selecting the best individuals

[0951] The server selects the best individuals based on the calculated matching scores, sorts them by highest score, and filters them.

[0952] The server then further filters based on the specific customer's personality and preferences to narrow down the most suitable candidates.

[0953] Specific examples

[0954] Example of data entry:

[0955] The user enters "Name: XX, Age: 28, Gender: Female, Personality: Outgoing, Hobbies: Reading, Past Work Experience: Engineer, Manager."

[0956] The customer enters the following information: "Customer characteristics: personality, hobbies, preferences, past feedback; job requirements: age 30 or older, 5 or more years of engineering experience, personality: extrovert, hobby: reading."

[0957] Prompt Sentence Examples

[0958] "Select the best person to meet the client's business requirements. Consider the following information: client characteristics, business requirements, and personal characteristics."

[0959] This system allows users to efficiently and accurately select and dispatch personnel who are best suited to customer needs, significantly reducing the user's workload.

[0960] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0961] Step 1:

[0962] Data Entry

[0963] The user enters personal characteristic information into a web form and submits it.

[0964] Specifically, you enter information such as your name, age, gender, personality, hobbies, and past work experience.

[0965] The server receives the transmitted data and stores it in a database.

[0966] Input: Data entered by a user into a web form

[0967] Output: Personal characteristics stored in a database

[0968] The user also inputs and submits customer characteristic information and business requirements.

[0969] Specifically, you enter information such as the customer's personality, hobbies and preferences, past feedback, and required skill set.

[0970] The server also receives this data and stores it in a database.

[0971] Input: Customer characteristics and business requirements entered by the user

[0972] Output: Customer characteristics and business requirements stored in a database

[0973] Step 2:

[0974] Data Preprocessing

[0975] The server retrieves personal and customer characteristic information from a database.

[0976] Input: Personal and customer characteristics stored in the database

[0977] Output: Retrieved data

[0978] The server preprocesses the acquired data. First, it quantifies the category values.

[0979] For example, "Personality: Extroverted" is converted into a numerical value of "1" and "Hobby: Reading" is converted into a numerical value of "2".

[0980] Input: Acquired data (category information)

[0981] Output: digitized data

[0982] The server vectorizes the text data using TF-IDF.

[0983] For example, vectorize "Past feedback: Good communication."

[0984] Input: Text data

[0985] Output: Vectorized text data

[0986] The server calculates the number of past work experiences and treats it as numerical data.

[0987] Input: Previous work experience (text information)

[0988] Output: Quantified past work experience

[0989] Step 3:

[0990] Matching Score Calculation

[0991] The server calculates a matching score based on the pre-processed data.

[0992] The server uses machine learning algorithms (e.g., Random Forest or Support Vector Machine) and similarity calculation methods (e.g., cosine similarity).

[0993] Specifically, the angle between the feature information vectors of the individual and the customer is calculated using cosine similarity, and a similarity score is calculated.

[0994] Input: Preprocessed personal and customer characteristics

[0995] Output: The calculated matching score

[0996] The server stores the calculated matching scores in a database.

[0997] Input: The calculated matching score

[0998] Output: Matching scores stored in a database

[0999] Step 4:

[1000] Selection of the best individuals

[1001] The server selects the best individual based on the calculated matching score.

[1002] Sorting is done by highest score and selecting the most suitable individual.

[1003] Input: Matching scores stored in the database

[1004] Output: Selection of the best individual

[1005] The server performs further filtering based on the characteristics and preferences of the particular customer.

[1006] Input: Selected personal data and customer characteristics

[1007] Output: Best candidates after filtering

[1008] The server notifies the user of the selection results by email or by displaying the results on the system dashboard.

[1009] Input: Best candidates after filtering

[1010] Output: Selection result notified to the user

[1011] This system efficiently and accurately selects the personnel best suited to the customer's requirements, significantly reducing the user's workload.

[1012] (Application example 1)

[1013] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1014] In the security services industry, a challenge is quickly and accurately selecting security personnel who meet customer requirements. With conventional personnel matching systems, it takes time to select highly suitable security personnel and there are also limitations to the accuracy of the matching. This makes it difficult to provide security services efficiently and effectively.

[1015] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1016] In this invention, the server includes means for receiving personal characteristic information provided by a user, means for receiving customer characteristic information and business requirements provided by a user, means for calculating a matching score between the individual and the customer based on the individual characteristic information, the customer characteristic information and business requirements, means for selecting an optimal individual based on the matching score, means for selecting an optimal security officer based on security service requirements, and means for outputting information on the selected security officer, thereby enabling security officers suitable for security services to be selected quickly and accurately.

[1017] 1. "Personal characteristic information" refers to characteristic information related to an individual, such as age, gender, personality, hobbies, and past work experience.

[1018] 2. "Customer characteristic information" refers to characteristic information related to a customer, such as the customer's personality, hobbies and preferences, and past feedback.

[1019] 3. "Job requirements" refer to the skill sets, work experience, personality traits, hobbies, and other conditions necessary to perform a specific job.

[1020] 4. "Matching score" refers to a similarity score calculated based on personal characteristic information, customer characteristic information, and business requirements.

[1021] 5. "Security services" means services that provide security, guarding, and surveillance.

[1022] 6. "Security Officer" means an individual selected to perform security service duties.

[1023] 7. "Outputting information" means displaying, notifying, or transmitting calculated results or selected data to another system.

[1024] The system for carrying out the present invention is for quickly and accurately selecting security personnel in the field of security services in response to customer requests. The system is mainly composed of the following components:

[1025] Data Entry

[1026] The server receives "personal characteristic information" provided by the user. This information includes age, gender, personality, hobbies, past work experience, etc. It also receives "customer characteristic information" and "job requirements" provided by the user. Customer characteristic information includes the customer's personality, hobbies and preferences, past feedback, etc., while job requirements include the skill set, work experience, personality, hobbies and preferences, etc. required to perform a specific job.

[1027] Data Preprocessing

[1028] The server preprocesses the received "personal characteristic information." This preprocessing includes quantifying categorical values ​​(e.g., personality, hobbies) and text data. It also calculates the number of past work experiences. The same preprocessing is performed on "customer characteristic information."

[1029] Matching Score Calculation

[1030] The server calculates a matching score based on the preprocessed "personal characteristic information," "customer characteristic information," and "business requirements." This score calculation uses a machine learning algorithm or a similarity calculation method (e.g., cosine similarity).

[1031] Selection of the best individuals

[1032] The server selects the most suitable individual based on the calculated matching score. Furthermore, filtering is performed based on the specific customer's personality and hobbies and preferences to narrow down the most suitable security personnel. During this selection process, filtering specific to the security service requirements is also performed.

[1033] Output of information

[1034] The server outputs information about the selected security officer to the terminal, including the reason for the selection and detailed characteristic information about the security officer.

[1035] For example, if the following data is entered:

[1036] Personal characteristic information

[1037] Name: Security Officer A

[1038] Age: 35

[1039] Gender: Male

[1040] Personality: extroverted

[1041] Hobbies: Reading

[1042] Previous work experience: 10 years

[1043] Customer characteristics and business requirements

[1044] Customer Name: Customer Company B

[1045] Past feedback: Good communication

[1046] Job requirements: 8+ years of experience, outgoing personality, reading hobby

[1047] Based on this data, the server determines that security officer A is the best candidate and outputs that information.

[1048] An example of a prompt sentence to be input to a specific generative AI model is as follows:

[1049] Write a program to select the best security officer for a customer based on user-input data. Receive personal and customer characteristics as input data, calculate the cosine similarity based on the data, and use a method to select the best candidate.

[1050] In this way, it becomes possible to quickly and accurately select security personnel suitable for security services.

[1051] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1052] Step 1:

[1053] The server receives personal characteristic information provided by the user as input. This information includes age, gender, personality, hobbies, past work experience, etc., and is important data for identifying an individual. Each piece of data is in text or numerical format. The server stores this data in temporary storage.

[1054] Step 2:

[1055] The server receives as input the customer characteristics and job requirements provided by the user, including the customer's personality, hobbies and preferences, past feedback, and the skill set required for a particular job. This data is also stored in temporary storage.

[1056] Step 3:

[1057] The server preprocesses the individual's characteristic information. Preprocessing includes quantifying category values, quantifying text data, and quantifying past work experience. For example, "Personality: Extroverted" is quantified, and "Past work experience: 10 years" is treated as a number. This ensures that all data is in a unified format. The output is preprocessed numerical data.

[1058] Step 4:

[1059] The server also preprocesses customer characteristic information and business requirements, converting categorical values ​​into numbers and quantifying text data, and standardizing the data format. The output is preprocessed numerical data.

[1060] Step 5:

[1061] The server calculates a matching score based on the preprocessed individual feature information, customer feature information, and business requirements. This score is calculated using similarity calculation methods such as machine learning algorithms and cosine similarity. Specifically, the degree of compatibility between an individual and a customer is quantified by calculating the cosine similarity between feature vectors. The output is a matching score.

[1062] Step 6:

[1063] The server selects the best individuals based on the matching scores. First, it lists the calculated matching scores and sorts them by highest score. Then it performs filtering specific to the security service requirements to narrow down the best security officers. The output is a list of selected individuals.

[1064] Step 7:

[1065] The server outputs information about the selected security officer to the terminal. This information includes the name, age, gender, past work experience, and reasons for the selection of the best candidate. The terminal displays this information on the screen or in a notification message. The user checks this information and makes the final decision on whether to actually dispatch the security officer.

[1066] For example, you can issue prompts to the server using the following:

[1067] Write a program to select the best security officer for a customer based on user-input data. Receive personal and customer characteristics as input data, calculate the cosine similarity based on the data, and use a method to select the best candidate.

[1068] Through the above process, it becomes possible to quickly and accurately select an appropriate security officer for security services.

[1069] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1070] This invention is a talent matching system for quickly and accurately selecting the most suitable talent in response to customer requests. This system achieves highly accurate matching by incorporating an emotion engine that recognizes the user's emotions. Detailed embodiments of the system are described below.

[1071] Data Entry

[1072] The server receives personal characteristic information from the user. The received information includes the individual's age, gender, personality, hobbies, and past work experience. This information is stored in a database. The server also receives customer characteristic information and job requirements from the user. The customer characteristic information includes the customer's personality, hobbies and preferences, and past feedback, and the job requirements include the required skill set, work experience, personality, hobbies and preferences, etc. This information is also stored in a database.

[1073] Preprocessing with emotion engine

[1074] The server uses an emotion engine to recognize the user's emotions, thereby improving the reliability and consistency of input information. The emotion engine analyzes the user's emotional reactions to the characteristic information and business requirements entered by the user and incorporates this data into preprocessing.

[1075] Data Preprocessing

[1076] The server preprocesses the individual's characteristic information, including the data obtained by the emotion engine. This preprocessing includes quantifying categorical values ​​(e.g., personality, hobbies) and text data. The number of past work experiences is also calculated. The same preprocessing is performed on the "customer's characteristic information," and the analysis results of the emotion engine are reflected.

[1077] Matching Score Calculation

[1078] The server calculates a matching score based on the preprocessed individual feature information, the customer feature information, and the business requirements. This score is calculated using a similarity calculation method (e.g., cosine similarity), which quantifies how well each individual matches the customer's requirements.

[1079] Selection of the best individuals

[1080] The server sorts the list of individuals based on the calculated matching score. A list sorted by highest score is created, and individual candidates are filtered based on the personality and hobbies of the specific customer. An emotion engine can be used to further refine the filtering.

[1081] Specific examples

[1082] 1. Data Entry Example

[1083] The user provides the following data as personal characteristic information:

[1084] Name: Alice

[1085] Age: 28

[1086] Gender: Female

[1087] Personality: extroverted

[1088] Hobbies: Reading

[1089] Previous work experience: Engineer, Manager

[1090] The user provides the following data as customer characteristic information and business requirements.

[1091] Customer Name: Company A

[1092] Past feedback: Good communication

[1093] Job requirements: Age 30 or older, 5+ years of experience, extroverted personality, reading hobby

[1094] 2. Preprocessing by the emotion engine

[1095] The server analyzes the input data from the user using an emotion engine. For example, if the user's emotion at the time of input is positive, it is evaluated as a factor that increases the reliability of the data.

[1096] 3. Data Preprocessing

[1097] The server calculates the number of past work experiences of each individual, and in Alice's case, it sets it to "2." It also quantifies category information such as "personality" and "hobbies."

[1098] 4. Calculating the Matching Score

[1099] The server calculates the similarity between Alice's information and the business requirements. At this time, Alice's information is quantified and compared with the business requirements.

[1100] 5. Selecting the best individuals

[1101] The server determines that Alice is the best candidate based on the calculated matching score, and also takes into account data from the sentiment engine to confirm that Alice best meets the customer requirements.

[1102] This system allows users to quickly and accurately select and dispatch the personnel best suited to their client's requirements. Furthermore, the use of an emotion engine improves the reliability of input data, resulting in more accurate matching. This process is automated, significantly reducing the user's workload.

[1103] The processing flow will be explained below.

[1104] Step 1:

[1105] The server receives personal characteristic information from the user. The received information includes the individual's age, gender, personality, hobbies, and past work experience. This information is stored in a database. For example, when information about an individual named Alice is provided, that information is sent to the server in digital format.

[1106] Step 2:

[1107] The server receives customer characteristic information and business requirements from the user. Customer characteristic information includes the customer's personality, hobbies and preferences, and past feedback, while business requirements include the required skill set, work experience, personality, hobbies and preferences, etc. This information is also stored in the database. For example, the business requirements and characteristic information of Company A are entered into the server.

[1108] Step 3:

[1109] The server uses an emotion engine to analyze the personal characteristic information entered by the user. For example, it recognizes the user's emotional state (positive, negative, etc.) at the time of input and adds that information to the input data. The results of this analysis are used to evaluate the reliability of the data and correct it.

[1110] Step 4:

[1111] The server preprocesses the individual's characteristic information, including the data analyzed by the emotion engine. This preprocessing includes converting categorical values ​​(e.g., personality, hobbies) into numerical values ​​and calculating the number of past work experiences. For example, Alice's personality trait "extroverted" is converted to the numerical value "1," and her hobby "reading" is converted to the numerical value "2."

[1112] Step 5:

[1113] The server also preprocesses customer characteristic information and business requirements, including data analyzed by the emotion engine. This quantifies the customer's personality and hobbies and preferences, and each item in the business requirements is expressed as a specific numerical value. For example, Company A's requirement "extroverted personality" is converted to the numerical value "1," and "hobby reading" is converted to the numerical value "2."

[1114] Step 6:

[1115] The server calculates a matching score based on the preprocessed individual characteristic information, customer characteristic information, and business requirements. A similarity calculation method (e.g., cosine similarity) is used to calculate this score. This quantifies the degree to which each individual matches the customer requirements. For example, Alice's information is compared with Company A's business requirements to generate a matching score.

[1116] Step 7:

[1117] The server sorts the list of individuals based on the calculated matching scores, creating a list sorted by highest score first. For example, Alice, Bob, Charlie might be listed in descending order of scores.

[1118] Step 8:

[1119] The server filters individual candidates based on the specific customer's personality and hobbies and preferences. This narrows down the candidates to the most suitable. The filtering process also takes into account the analysis results of the emotion engine. For example, Alice is narrowed down as the most suitable candidate.

[1120] Step 9:

[1121] The server presents the filtered list of optimal candidates to the user. The user makes a final selection based on the provided list and prepares to dispatch the appropriate candidate. For example, Alice's detailed information is displayed to the user, and the user can decide whether to dispatch her to the customer.

[1122] These steps enable users to quickly and accurately select and dispatch the best personnel for their customer requirements. This process, combined with the emotion engine, improves the reliability of input data and achieves more accurate matching.

[1123] Example 2

[1124] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1125] Conventional talent matching systems lacked the reliability and consistency of input data, making it difficult to quickly and accurately select the talent most suited to customer requirements. Furthermore, data processing was performed without taking the user's emotional state into consideration, making it difficult to achieve highly accurate matching. This resulted in increased user effort and hindered efficient talent selection.

[1126] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1127] In this invention, the server includes means for receiving personal characteristic information provided by the user, means for receiving customer characteristic information and business requirements provided by the user, means for calculating a matching score based on the personal characteristic information, customer characteristic information and business requirements, means for selecting the most suitable individual based on the matching score, means for analyzing the user's emotions using an emotion engine and improving the reliability and consistency of input data, means for reflecting the analysis results of the emotion engine in preprocessing, and means for reflecting the user's emotional state in calculations based on the preprocessed data. This enables highly accurate matching and significantly reduces the user's workload.

[1128] "Individual characteristic information" is attribute information about a specific individual, such as age, gender, personality, hobbies, and past work experience.

[1129] "Customer characteristic information" is attribute information about a specific customer, such as the customer's personality, hobbies and preferences, and past feedback.

[1130] "Job requirements" are the conditions necessary to perform a specific job, such as the necessary skill set, work experience, personality, hobbies, and preferences.

[1131] The "matching score" is a numerical representation of the compatibility between an individual and a customer, calculated based on the individual's characteristic information, the customer's characteristic information, and business requirements.

[1132] An "emotion engine" is a technology used to analyze a user's emotional response to input data, improving reliability and consistency.

[1133] "Preprocessing" refers to the process of making the collected raw data easier to analyze, and includes converting categorical values ​​into numerical values ​​and quantifying text data.

[1134] "Filtering" is the process of sorting data based on specific conditions and extracting only useful information.

[1135] "Reliability" refers to the degree of accuracy and consistency of data.

[1136] "Consistency" indicates that the data follows certain rules or patterns.

[1137] This invention is a talent matching system for quickly and accurately selecting the best talent according to customer needs. This system achieves highly accurate matching by combining an emotion engine that recognizes the user's emotions.

[1138] First, the server receives personal characteristic information (age, gender, personality, hobbies, past work experience) provided by the user and stores it in the database. The server also receives customer characteristic information (personality, hobbies and preferences, past feedback) and job requirements (required skill set, work experience, personality, hobbies and preferences) and stores them in the database.

[1139] The server then analyzes the user's emotions using an emotion engine, which analyzes the emotional response to the input data to improve reliability and consistency. For example, if the user's emotion at the time of input is positive, it is evaluated as a factor that increases the reliability of the data.

[1140] In the data preprocessing stage, the server performs preprocessing on the collected data to make it easier to analyze. This includes quantifying categorical information such as personality and hobbies, and work experience. The analysis results from the emotion engine are also reflected here, and a reliability score for the data is calculated.

[1141] The server then calculates a matching score based on the preprocessed data. This calculation uses a similarity calculation method such as cosine similarity. As a result, the degree of match between the individual's characteristic information, the customer's characteristic information, and the business requirements is quantified.

[1142] Finally, the server generates a list of candidates based on the calculated matching scores. This list is sorted by highest score and filtered based on the personality and preferences of the specific customer. An emotion engine can be used to further refine the filtering.

[1143] Specific examples

[1144] 1. Data Entry Example

[1145] The user provides the following data as personal characteristic information:

[1146] Name: Individual A

[1147] Age: 28

[1148] Gender: Female

[1149] Personality: extroverted

[1150] Hobbies: Reading

[1151] Previous work experience: Engineer, Manager

[1152] The user provides the following data as customer characteristic information and business requirements.

[1153] Customer Name: Customer A

[1154] Past feedback: Good communication

[1155] Job requirements: Age 30 or older, 5+ years of experience, extroverted personality, reading hobby

[1156] 2. Preprocessing by the emotion engine

[1157] The server analyzes the input data from the user using an emotion engine. For example, if the user's emotion at the time of input is positive, it is evaluated as a factor that increases the reliability of the data.

[1158] 3. Data Preprocessing

[1159] The server calculates the number of past work experiences, and sets the number to "2" in the case of Individual A. It also quantifies category information such as "personality" and "hobbies."

[1160] 4. Calculating the Matching Score

[1161] Based on the business requirements, the server calculates the degree of similarity with the information of person A. At this time, person A's information is quantified and compared with the business requirements.

[1162] 5. Selecting the best individuals

[1163] Based on the calculated matching score, the server determines that Person A is the best candidate. Data from the emotion engine is also taken into account to confirm that Person A best meets the customer requirements.

[1164] Prompt Sentence Examples

[1165] "Please register Individual A, a 28-year-old extroverted female engineer whose hobby is reading."

[1166] "Looking for someone over 30, with at least 5 years of experience, who is extroverted and enjoys reading."

[1167] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1168] Step 1:

[1169] Data Entry

[1170] The server receives personal characteristic information (name, age, gender, personality, hobbies, past work experience) provided by the user. The input data is sent to the server via an HTTP request. The server stores the received data in a database. It also receives customer characteristic information (personality, hobbies and preferences, past feedback) and job requirements (required skill set, work experience, personality, hobbies and preferences) and stores them in the database.

[1171] Specific operation example: When a user enters personal and customer characteristic information into a web form and presses the submit button, the information is sent to the server, which processes this data using Python and stores it in a database (e.g., MySQL).

[1172] Input: User-entered personal and customer characteristics information

[1173] Output: Feature information stored in a database

[1174] Step 2:

[1175] Preprocessing with emotion engine

[1176] The server sends the acquired feature information to the emotion engine to analyze the user's emotional state. The emotion engine determines the emotional response (positive, negative, neutral, etc.) based on the input data. This result is used as additional information to improve the reliability and consistency of the data.

[1177] Specific operation example: The server calls the API for the emotion engine and sends the user's characteristic information. The emotion engine returns the analysis results, and the server stores the results in a database.

[1178] Input: Feature information

[1179] Output: Analysis results by the emotion engine

[1180] Step 3:

[1181] Data Preprocessing

[1182] The server preprocesses the collected data, including the analysis results of the emotion engine. This preprocessing includes quantifying categorical information such as personality and hobbies, quantifying past work experience, and calculating a reliability score for the data. This facilitates the subsequent calculation of matching scores.

[1183] Specific example: Using Python's pandas library, the collected data is processed as a data frame. Categorical information and text data are converted into numerical data, and the number of work experiences is calculated.

[1184] Input: Feature information including the analysis results of the emotion engine

[1185] Output: Preprocessed data

[1186] Step 4:

[1187] Matching Score Calculation

[1188] The server calculates a matching score based on the preprocessed individual and customer characteristic information and business requirements. The similarity calculation uses, for example, cosine similarity. The calculated matching score quantifies the degree of agreement between the individual and customer requirements.

[1189] Specific example: Using the scikit-learn library, calculate the cosine similarity between vectors of preprocessed data. The calculation results are stored in a database.

[1190] Input: Preprocessed individual and customer characteristics information

[1191] Output: Matching score

[1192] Step 5:

[1193] Selection of the best individuals

[1194] The server generates a candidate list based on the calculated matching scores. It sorts the candidates by highest score and filters them based on the characteristics and hobbies of specific customers. It also takes into account the results of the emotion engine to create an even more accurate candidate list.

[1195] Specific example of operation: Using an SQL query, data is retrieved from the database in descending order of matching score, a list reflecting the results of sentiment analysis is generated, and then provided to the user.

[1196] Input: Matching score

[1197] Output: A list of the best candidates

[1198] (Application example 2)

[1199] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1200] Conventional talent matching systems have issues with the reliability and consistency of input information because they do not take into account user emotional data. Also, in factory management using robots, there is a problem with the inability to quickly and accurately allocate appropriate robots.

[1201] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving individual characteristic information provided by a user; means for receiving customer characteristic information and business requirements provided by a user; means for calculating a matching score between the individual and the customer based on the individual characteristic information, the customer characteristic information, and the business requirements; means for selecting the most suitable individual based on the matching score; means for analyzing the user's emotional response using an emotion engine and evaluating the reliability of the data based on the analysis; and means for a factory manager to input robot characteristic information and work station requirements using a smart device and match robots with work stations based on the input. This enables highly accurate personnel matching that takes user emotional data into account and efficient deployment of robots in the factory.

[1202] "User emotional response" refers to the psychological state or feelings a user exhibits when entering information.

[1203] The "matching score" is a numerical representation of the degree of match between the individual's characteristic information, the customer's characteristic information, and the business requirements.

[1204] An "emotion engine" is a system that analyzes user emotions in response to input data and evaluates the reliability and consistency of that data.

[1205] "Smart devices" refers to electronic devices with internet connectivity, such as smartphones, tablets, smart glasses, and head-mounted displays.

[1206] "Robot characteristic information" includes information such as the robot's identification number, performance, tasks that it can handle, operating time, and reliability.

[1207] "Work station" refers to a location within a factory where a specific task is performed.

[1208] A "factory manager" is a person in charge of managing work and robots within the factory.

[1209] The present invention is a system for matching human resources and robots with consideration of the user's emotions. Specific embodiments will be described below.

[1210] Data Entry

[1211] First, the server receives personal characteristic information provided by the user. This information includes age, gender, personality, hobbies, past work experience, etc. The user also inputs customer characteristic information and work requirements. This includes the customer's personality, hobbies and preferences, past feedback, required skill set, work experience, etc. The factory manager inputs robot characteristic information (identification number, performance, work that can be performed, operating time, reliability) and work station requirements (required skills, operating time, work content). All of this data is stored in a database.

[1212] Preprocessing with emotion engine

[1213] The server uses an emotion engine to analyze the user's emotional response to the input data, which improves the reliability and consistency of the input information. For example, if the user shows positive emotions, the data will be rated as more reliable.

[1214] Data Preprocessing

[1215] The server preprocesses the individual and robot characteristic information, including the data obtained by the emotion engine. This preprocessing involves converting category values ​​into numerical values ​​and quantifying text data. The number of past work experiences is then calculated. Similar preprocessing is performed on the "customer characteristic information" and "workstation requirements," and the analysis results of the emotion engine are reflected.

[1216] Matching Score Calculation

[1217] The server calculates a matching score based on the preprocessed individual feature information, the robot feature information, the customer feature information, the business requirements, and the requirements of the work station. This score is calculated using a similarity calculation method such as cosine similarity, which quantifies how well each individual or robot matches the requirements of the customer or work station.

[1218] Selection of the best individuals and robots

[1219] The server selects the best individuals and robots based on the calculated matching scores. A list is created sorted by highest score, and candidates are filtered based on the specific customer's personality, hobbies, and work station requirements. An emotion engine can be used to further refine the filtering.

[1220] Specific examples

[1221] The user provides the following data as personal characteristic information:

[1222] Name: Taro

[1223] Age: 35

[1224] Gender: Male

[1225] Personality: introverted

[1226] Hobbies: Programming

[1227] Previous work experience: Systems engineer, project manager

[1228] In addition, the factory manager provides the following data as characteristic information of the robot:

[1229] Identification number: R123

[1230] Performance: High

[1231] Available work: Assembly, packaging

[1232] Operating time: 3000 hours

[1233] Reliability: 90%

[1234] The administrator provides the following data as requirements for the workstation:

[1235] Required skills: Assembly

[1236] Operating time: 2500 hours

[1237] Required work: Parts assembly

[1238] The server receives this information, analyzes it with an emotion engine, performs preprocessing, calculates a matching score, and selects the most suitable individual and robot.

[1239] Prompt Sentence Examples

[1240] Based on the data below, come up with an algorithm to optimally match robots and workstations, and implement it in Python.

[1241] Robot data (identification number, performance, skills, operating time, reliability)

[1242] Workstation data (skills required, uptime required, reliability required)

[1243] Consider also using a sentiment engine to assess the reliability of input data.

[1244] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1245] Step 1:

[1246] The user uses a terminal to input personal characteristic information (age, gender, personality, hobbies, past work experience). The terminal sends this information to the server and stores it in a database. This allows the system to obtain the necessary characteristic information.

[1247] Input: Personal characteristics information

[1248] Output: Personal characteristics stored in a database

[1249] Specific operation: The user enters the required information on the form input screen and clicks the "Submit" button. The device sends the input data in JSON format to the server's API.

[1250] Step 2:

[1251] Factory managers use terminals to input the robot's characteristic information (identification number, performance, tasks it can handle, operating hours, reliability). The terminals then send this information to the server and store it in a database. This allows the system to obtain the necessary robot characteristic information.

[1252] Input: Robot characteristics information

[1253] Output: Robot characteristics stored in a database

[1254] Specific operation: The administrator enters the robot details into the input form and presses the "Submit" button. The data sent from the terminal is processed by the server and stored in the database.

[1255] Step 3:

[1256] The server uses an emotion engine to perform emotion analysis on the data entered by users and administrators, which evaluates the reliability and consistency of the data.

[1257] Input: Input feature information

[1258] Output: Emotion analysis results

[1259] How it works: The emotion engine uses natural language processing (NLP) techniques to analyze the sentiment of the words and style contained in the input data and generate a confidence score, which is stored in a database.

[1260] Step 4:

[1261] The server performs preprocessing and quantifies the individual and robot feature information, including converting categorical values ​​and quantifying text data.

[1262] Input: Personal characteristic information, robot characteristic information

[1263] Output: Quantified feature information

[1264] Specific operation: Using Python libraries (e.g., pandas, scikit-learn), categorical data is converted to numerical values ​​and text data is vectorized. The calculation results are stored in a database as numerical data.

[1265] Step 5:

[1266] The server calculates a matching score based on the quantified individual characteristic information, customer characteristic information, business requirements, robot characteristic information, and work station requirements. This score calculation uses the cosine similarity calculation method.

[1267] Input: Quantified characteristic information, customer characteristic information, business requirements, work station requirements

[1268] Output: Matching score

[1269] Specific operation: Using existing data processing libraries (e.g., numpy, scipy), the cosine similarity is calculated and a matching score for each individual and robot is calculated. This score is then stored in a database.

[1270] Step 6:

[1271] The server selects the best individuals and robots based on the matching scores, creates a list sorted by the highest score, and presents it to the user and administrator.

[1272] Input: Matching score

[1273] Output: List of best individuals and robots

[1274] Specific operation: The server sorts the matching scores in descending order and lists the most suitable individuals and robots. This list is displayed on the user's and administrator's terminals.

[1275] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1276] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1277] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1278] [Fourth embodiment]

[1279] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1280] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1281] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1282] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1283] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1284] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1285] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1286] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1287] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1288] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1289] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1290] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1291] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1292] This invention is a human resources matching system for quickly and accurately selecting the most suitable human resources according to the customer's request. This system is implemented mainly by the following components.

[1293] Data Entry

[1294] The server receives "personal characteristic information" provided by the user. This information includes age, gender, personality, hobbies, past work experience, etc. It also receives "customer characteristic information" and "job requirements" provided by the customer. The customer characteristic information includes the customer's personality, hobbies and preferences, past feedback, etc., while the job requirements include the skill set, work experience, personality, hobbies and preferences, etc. required to perform a specific job.

[1295] Data Preprocessing

[1296] The server preprocesses the received "personal characteristic information." This preprocessing includes quantifying categorical values ​​(e.g., personality, hobbies) and text data. It also calculates the number of past work experiences. The same preprocessing is performed on "customer characteristic information."

[1297] Matching Score Calculation

[1298] The server calculates a matching score based on the preprocessed "personal characteristic information," "customer characteristic information," and "business requirements." This score calculation uses a machine learning algorithm and a similarity calculation method (e.g., cosine similarity).

[1299] Selection of the best individuals

[1300] The server selects the most suitable individual based on the calculated matching score, and then filters the candidates based on the specific customer's personality and hobbies and preferences to narrow down the most suitable candidates.

[1301] Specific examples

[1302] 1. Data Entry Example

[1303] The user provides the following data as personal characteristic information:

[1304] Name: Alice

[1305] Age: 28

[1306] Gender: Female

[1307] Personality: extroverted

[1308] Hobbies: Reading

[1309] Previous work experience: Engineer, Manager

[1310] The user provides the following data as customer characteristic information and business requirements.

[1311] Customer Name: Company A

[1312] Past feedback: Good communication

[1313] Job requirements: Age 30 or older, 5+ years of experience, extroverted personality, reading hobby

[1314] 2. Pretreatment

[1315] The server calculates the number of past work experiences of an individual, and in Alice's case it is "2".

[1316] The server converts category information such as "personality" and "hobbies" into numerical values.

[1317] 3. Calculating the Matching Score

[1318] The server calculates the similarity between Alice's information and the business requirements. At this time, Alice's information is quantified and compared with the business requirements.

[1319] 4. Selecting the best individuals

[1320] The server determines that Alice is the best candidate based on the calculated matching score, and after filtering, it confirms that Alice best meets the customer requirements.

[1321] This system allows users to efficiently and effectively select and dispatch personnel who are best suited to customer needs. This process is automated, with the server processing the data and presenting the results, significantly reducing the user's workload.

[1322] The processing flow will be explained below.

[1323] Step 1:

[1324] The server receives personal characteristic information from the user, including the individual's age, gender, personality, hobbies, and past work experience, and stores this information in a database.

[1325] Step 2:

[1326] The server receives customer characteristic information and job requirements from the user. The customer characteristic information includes the customer's personality, hobbies and preferences, and past feedback, while the job requirements include the required skill set, work experience, personality, hobbies and preferences, etc. This information is also stored in the database.

[1327] Step 3:

[1328] The server preprocesses the stored individual characteristic information. This preprocessing includes converting categorical values ​​(e.g., personality, hobbies) into numerical values ​​and calculating the number of past work experiences. For example, if the person has work experience such as "engineer" and "manager," the number is calculated to be "2."

[1329] Step 4:

[1330] The server also preprocesses the customer's characteristic information and business requirements, which quantifies the customer's personality and preferences, and expresses each item of the business requirements as a specific numerical value.

[1331] Step 5:

[1332] The server calculates a matching score based on the preprocessed individual feature information, the customer feature information, and the business requirements. This score is calculated using a similarity calculation method (e.g., cosine similarity), which quantifies how well each individual matches the customer's requirements.

[1333] Step 6:

[1334] The server sorts the list of individuals based on the calculated matching scores, creating a list sorted by highest score first.

[1335] Step 7:

[1336] The server filters individual candidates based on the specific customer's personality and preferences, narrowing down the candidates to the most suitable candidates.

[1337] Step 8:

[1338] The server presents the filtered list of optimal personnel to the user, who then makes a final selection based on the provided list and dispatches the appropriate personnel.

[1339] Step 9:

[1340] The user checks the list of optimal personnel provided by the server and selects the personnel who best meets the request. After further detailed checks and adjustments as necessary, the user is ready to dispatch the personnel to the customer.

[1341] Through these steps, users can quickly and accurately select and dispatch the personnel best suited to their client's requirements. This process is automated, significantly reducing the user's time and effort.

[1342] Example 1

[1343] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1344] With conventional talent matching systems, it was difficult to quickly and accurately select the talent that best met the customer's requirements. In particular, without preprocessing of input data or appropriate filtering, matching accuracy decreased, and inappropriate talent was often selected. In addition, the method of notifying the selection results was complicated, which significantly increased the user's workload.

[1345] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1346] In this invention, the server includes means for receiving personal characteristic information provided by the user, means for receiving customer characteristic information and business requirements, means for calculating a matching score based on the characteristic information quantified through preprocessing, means for selecting and filtering the most suitable individuals based on the calculated matching score, and means for notifying the user of the selection results. This makes it possible to efficiently and accurately select personnel who are most suited to the customer's requirements and significantly reduce the user's workload.

[1347] "Personal characteristic information" refers to specific attributes and data about a person, such as age, gender, personality, hobbies, and past work experience.

[1348] "Customer characteristic information" refers to attributes and data related to customers, such as their personality, hobbies and preferences, and past feedback.

[1349] "Job requirements" refer to the conditions that customers desire, such as the skill set, work experience, personality, hobbies, and preferences needed to perform a specific job.

[1350] "Matching score" refers to the numerical value of similarity calculated using machine learning algorithms and similarity calculation methods based on individual characteristic information, customer characteristic information, and business requirements.

[1351] "Preprocessing" refers to a series of processes that properly format, digitize, and vectorize received data before analyzing or calculating it.

[1352] "Filtering" refers to the process of narrowing down the individuals who best fit a particular criteria based on a calculated matching score.

[1353] "Notification" refers to the act of informing users of the selected results and other information via email, the system dashboard, etc.

[1354] This invention is a human resources matching system for quickly and accurately selecting the most suitable human resources according to the customer's needs. This system consists of a server, a terminal, and a user.

[1355] Hardware and Software Configuration

[1356] The server contains the database system (e.g., MySQL or MongoDB), the backend that executes the program logic (e.g., Python, Django, or Flask), and the machine learning algorithms (e.g., Scikit-learn, TensorFlow). The terminal consists of a web browser or application that provides the user interface and communicates with the server via HTTP requests.

[1357] Program processing explanation

[1358] 1. Data Entry

[1359] A user inputs personal characteristics information, such as name, age, sex, personality, hobbies, and past work experience, through a web form.

[1360] The customer inputs their characteristic information and business requirements, such as "more than 3 years of engineering experience, good communication skills," and sends this data to the server.

[1361] The server receives this information and stores it in a database.

[1362] 2. Data Preprocessing

[1363] The server retrieves the necessary data from the database and converts the categorical data into numerical values. For example, "Personality: Extroverted" is converted to the numerical value "1" and "Hobby: Reading" is converted to the numerical value "2."

[1364] The server vectorizes the text data using techniques such as TF-IDF. For example, it vectorizes "Past feedback: communication is good."

[1365] The server calculates the number of past work experiences and treats it as numerical data.

[1366] 3. Calculating the Matching Score

[1367] The server calculates a matching score based on the preprocessed data using a machine learning algorithm or a similarity calculation method. For example, it calculates the angle between the vectors of the individual and customer feature information using cosine similarity to calculate the similarity score.

[1368] The server stores the calculated matching scores in a database.

[1369] 4. Selecting the best individuals

[1370] The server selects the best individuals based on the calculated matching scores, sorts them by highest score, and filters them.

[1371] The server then further filters based on the specific customer's personality and preferences to narrow down the most suitable candidates.

[1372] Specific examples

[1373] Example of data entry:

[1374] The user enters "Name: XX, Age: 28, Gender: Female, Personality: Outgoing, Hobbies: Reading, Past Work Experience: Engineer, Manager."

[1375] The customer enters the following information: "Customer characteristics: personality, hobbies, preferences, past feedback; job requirements: age 30 or older, 5 or more years of engineering experience, personality: extrovert, hobby: reading."

[1376] Prompt Sentence Examples

[1377] "Select the best person to meet the client's business requirements. Consider the following information: client characteristics, business requirements, and personal characteristics."

[1378] This system allows users to efficiently and accurately select and dispatch personnel who are best suited to customer needs, significantly reducing the user's workload.

[1379] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1380] Step 1:

[1381] Data Entry

[1382] The user enters personal characteristic information into a web form and submits it.

[1383] Specifically, you enter information such as your name, age, gender, personality, hobbies, and past work experience.

[1384] The server receives the transmitted data and stores it in a database.

[1385] Input: Data entered by a user into a web form

[1386] Output: Personal characteristics stored in a database

[1387] The user also inputs and submits customer characteristic information and business requirements.

[1388] Specifically, you enter information such as the customer's personality, hobbies and preferences, past feedback, and required skill set.

[1389] The server also receives this data and stores it in a database.

[1390] Input: Customer characteristics and business requirements entered by the user

[1391] Output: Customer characteristics and business requirements stored in a database

[1392] Step 2:

[1393] Data Preprocessing

[1394] The server retrieves personal and customer characteristic information from a database.

[1395] Input: Personal and customer characteristics stored in the database

[1396] Output: Retrieved data

[1397] The server preprocesses the acquired data. First, it quantifies the category values.

[1398] For example, "Personality: Extroverted" is converted into a numerical value of "1" and "Hobby: Reading" is converted into a numerical value of "2".

[1399] Input: Acquired data (category information)

[1400] Output: digitized data

[1401] The server vectorizes the text data using TF-IDF.

[1402] For example, vectorize "Past feedback: Good communication."

[1403] Input: Text data

[1404] Output: Vectorized text data

[1405] The server calculates the number of past work experiences and treats it as numerical data.

[1406] Input: Previous work experience (text information)

[1407] Output: Quantified past work experience

[1408] Step 3:

[1409] Matching Score Calculation

[1410] The server calculates a matching score based on the pre-processed data.

[1411] The server uses machine learning algorithms (e.g., Random Forest or Support Vector Machine) and similarity calculation methods (e.g., cosine similarity).

[1412] Specifically, the angle between the feature information vectors of the individual and the customer is calculated using cosine similarity, and a similarity score is calculated.

[1413] Input: Preprocessed personal and customer characteristics

[1414] Output: The calculated matching score

[1415] The server stores the calculated matching scores in a database.

[1416] Input: The calculated matching score

[1417] Output: Matching scores stored in a database

[1418] Step 4:

[1419] Selection of the best individuals

[1420] The server selects the best individual based on the calculated matching score.

[1421] Sorting is done by highest score and selecting the most suitable individual.

[1422] Input: Matching scores stored in the database

[1423] Output: Selection of the best individual

[1424] The server performs further filtering based on the characteristics and preferences of the particular customer.

[1425] Input: Selected personal data and customer characteristics

[1426] Output: Best candidates after filtering

[1427] The server notifies the user of the selection results by email or by displaying the results on the system dashboard.

[1428] Input: Best candidates after filtering

[1429] Output: Selection result notified to the user

[1430] This system efficiently and accurately selects the personnel best suited to the customer's requirements, significantly reducing the user's workload.

[1431] (Application example 1)

[1432] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1433] In the security services industry, a challenge is quickly and accurately selecting security personnel who meet customer requirements. With conventional personnel matching systems, it takes time to select highly suitable security personnel and there are also limitations to the accuracy of the matching. This makes it difficult to provide security services efficiently and effectively.

[1434] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1435] In this invention, the server includes means for receiving personal characteristic information provided by a user, means for receiving customer characteristic information and business requirements provided by a user, means for calculating a matching score between the individual and the customer based on the individual characteristic information, the customer characteristic information and business requirements, means for selecting an optimal individual based on the matching score, means for selecting an optimal security officer based on security service requirements, and means for outputting information on the selected security officer, thereby enabling security officers suitable for security services to be selected quickly and accurately.

[1436] 1. "Personal characteristic information" refers to characteristic information related to an individual, such as age, gender, personality, hobbies, and past work experience.

[1437] 2. "Customer characteristic information" refers to characteristic information related to a customer, such as the customer's personality, hobbies and preferences, and past feedback.

[1438] 3. "Job requirements" refer to the skill sets, work experience, personality traits, hobbies, and other conditions necessary to perform a specific job.

[1439] 4. "Matching score" refers to a similarity score calculated based on personal characteristic information, customer characteristic information, and business requirements.

[1440] 5. "Security services" means services that provide security, guarding, and surveillance.

[1441] 6. "Security Officer" means an individual selected to perform security service duties.

[1442] 7. "Outputting information" means displaying, notifying, or transmitting calculated results or selected data to another system.

[1443] The system for carrying out the present invention is for quickly and accurately selecting security personnel in the field of security services in response to customer requests. The system is mainly composed of the following components:

[1444] Data Entry

[1445] The server receives "personal characteristic information" provided by the user. This information includes age, gender, personality, hobbies, past work experience, etc. It also receives "customer characteristic information" and "job requirements" provided by the user. Customer characteristic information includes the customer's personality, hobbies and preferences, past feedback, etc., while job requirements include the skill set, work experience, personality, hobbies and preferences, etc. required to perform a specific job.

[1446] Data Preprocessing

[1447] The server preprocesses the received "personal characteristic information." This preprocessing includes quantifying categorical values ​​(e.g., personality, hobbies) and text data. It also calculates the number of past work experiences. The same preprocessing is performed on "customer characteristic information."

[1448] Matching Score Calculation

[1449] The server calculates a matching score based on the preprocessed "personal characteristic information," "customer characteristic information," and "business requirements." This score calculation uses a machine learning algorithm or a similarity calculation method (e.g., cosine similarity).

[1450] Selection of the best individuals

[1451] The server selects the most suitable individual based on the calculated matching score. Furthermore, filtering is performed based on the specific customer's personality and hobbies and preferences to narrow down the most suitable security personnel. During this selection process, filtering specific to the security service requirements is also performed.

[1452] Output of information

[1453] The server outputs information about the selected security officer to the terminal, including the reason for the selection and detailed characteristic information about the security officer.

[1454] For example, if the following data is entered:

[1455] Personal characteristic information

[1456] Name: Security Officer A

[1457] Age: 35

[1458] Gender: Male

[1459] Personality: extroverted

[1460] Hobbies: Reading

[1461] Previous work experience: 10 years

[1462] Customer characteristics and business requirements

[1463] Customer Name: Customer Company B

[1464] Past feedback: Good communication

[1465] Job requirements: 8+ years of experience, outgoing personality, reading hobby

[1466] Based on this data, the server determines that security officer A is the best candidate and outputs that information.

[1467] An example of a prompt sentence to be input to a specific generative AI model is as follows:

[1468] Write a program to select the best security officer for a customer based on user-input data. Receive personal and customer characteristics as input data, calculate the cosine similarity based on the data, and use a method to select the best candidate.

[1469] In this way, it becomes possible to quickly and accurately select security personnel suitable for security services.

[1470] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1471] Step 1:

[1472] The server receives personal characteristic information provided by the user as input. This information includes age, gender, personality, hobbies, past work experience, etc., and is important data for identifying an individual. Each piece of data is in text or numerical format. The server stores this data in temporary storage.

[1473] Step 2:

[1474] The server receives as input the customer characteristics and job requirements provided by the user, including the customer's personality, hobbies and preferences, past feedback, and the skill set required for a particular job. This data is also stored in temporary storage.

[1475] Step 3:

[1476] The server preprocesses the individual's characteristic information. Preprocessing includes quantifying category values, quantifying text data, and quantifying past work experience. For example, "Personality: Extroverted" is quantified, and "Past work experience: 10 years" is treated as a number. This ensures that all data is in a unified format. The output is preprocessed numerical data.

[1477] Step 4:

[1478] The server also preprocesses customer characteristic information and business requirements, converting categorical values ​​into numbers and quantifying text data, and standardizing the data format. The output is preprocessed numerical data.

[1479] Step 5:

[1480] The server calculates a matching score based on the preprocessed individual feature information, customer feature information, and business requirements. This score is calculated using similarity calculation methods such as machine learning algorithms and cosine similarity. Specifically, the degree of compatibility between an individual and a customer is quantified by calculating the cosine similarity between feature vectors. The output is a matching score.

[1481] Step 6:

[1482] The server selects the best individuals based on the matching scores. First, it lists the calculated matching scores and sorts them by highest score. Then it performs filtering specific to the security service requirements to narrow down the best security officers. The output is a list of selected individuals.

[1483] Step 7:

[1484] The server outputs information about the selected security officer to the terminal. This information includes the name, age, gender, past work experience, and reasons for the selection of the best candidate. The terminal displays this information on the screen or in a notification message. The user checks this information and makes the final decision on whether to actually dispatch the security officer.

[1485] For example, you can issue prompts to the server using the following:

[1486] Write a program to select the best security officer for a customer based on user-input data. Receive personal and customer characteristics as input data, calculate the cosine similarity based on the data, and use a method to select the best candidate.

[1487] Through the above process, it becomes possible to quickly and accurately select an appropriate security officer for security services.

[1488] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1489] This invention is a talent matching system for quickly and accurately selecting the most suitable talent in response to customer requests. This system achieves highly accurate matching by incorporating an emotion engine that recognizes the user's emotions. Detailed embodiments of the system are described below.

[1490] Data Entry

[1491] The server receives personal characteristic information from the user. The received information includes the individual's age, gender, personality, hobbies, and past work experience. This information is stored in a database. The server also receives customer characteristic information and job requirements from the user. The customer characteristic information includes the customer's personality, hobbies and preferences, and past feedback, and the job requirements include the required skill set, work experience, personality, hobbies and preferences, etc. This information is also stored in a database.

[1492] Preprocessing with emotion engine

[1493] The server uses an emotion engine to recognize the user's emotions, thereby improving the reliability and consistency of input information. The emotion engine analyzes the user's emotional reactions to the characteristic information and business requirements entered by the user and incorporates this data into preprocessing.

[1494] Data Preprocessing

[1495] The server preprocesses the individual's characteristic information, including the data obtained by the emotion engine. This preprocessing includes quantifying categorical values ​​(e.g., personality, hobbies) and text data. The number of past work experiences is also calculated. The same preprocessing is performed on the "customer's characteristic information," and the analysis results of the emotion engine are reflected.

[1496] Matching Score Calculation

[1497] The server calculates a matching score based on the preprocessed individual feature information, the customer feature information, and the business requirements. This score is calculated using a similarity calculation method (e.g., cosine similarity), which quantifies how well each individual matches the customer's requirements.

[1498] Selection of the best individuals

[1499] The server sorts the list of individuals based on the calculated matching score. A list sorted by highest score is created, and individual candidates are filtered based on the personality and hobbies of the specific customer. An emotion engine can be used to further refine the filtering.

[1500] Specific examples

[1501] 1. Data Entry Example

[1502] The user provides the following data as personal characteristic information:

[1503] Name: Alice

[1504] Age: 28

[1505] Gender: Female

[1506] Personality: extroverted

[1507] Hobbies: Reading

[1508] Previous work experience: Engineer, Manager

[1509] The user provides the following data as customer characteristic information and business requirements.

[1510] Customer Name: Company A

[1511] Past feedback: Good communication

[1512] Job requirements: Age 30 or older, 5+ years of experience, extroverted personality, reading hobby

[1513] 2. Preprocessing by the emotion engine

[1514] The server analyzes the input data from the user using an emotion engine. For example, if the user's emotion at the time of input is positive, it is evaluated as a factor that increases the reliability of the data.

[1515] 3. Data Preprocessing

[1516] The server calculates the number of past work experiences of each individual, and in Alice's case, it sets it to "2." It also quantifies category information such as "personality" and "hobbies."

[1517] 4. Calculating the Matching Score

[1518] The server calculates the similarity between Alice's information and the business requirements. At this time, Alice's information is quantified and compared with the business requirements.

[1519] 5. Selecting the best individuals

[1520] The server determines that Alice is the best candidate based on the calculated matching score, and also takes into account data from the sentiment engine to confirm that Alice best meets the customer requirements.

[1521] This system allows users to quickly and accurately select and dispatch the personnel best suited to their client's requirements. Furthermore, the use of an emotion engine improves the reliability of input data, resulting in more accurate matching. This process is automated, significantly reducing the user's workload.

[1522] The processing flow will be explained below.

[1523] Step 1:

[1524] The server receives personal characteristic information from the user. The received information includes the individual's age, gender, personality, hobbies, and past work experience. This information is stored in a database. For example, when information about an individual named Alice is provided, that information is sent to the server in digital format.

[1525] Step 2:

[1526] The server receives customer characteristic information and business requirements from the user. Customer characteristic information includes the customer's personality, hobbies and preferences, and past feedback, while business requirements include the required skill set, work experience, personality, hobbies and preferences, etc. This information is also stored in the database. For example, the business requirements and characteristic information of Company A are entered into the server.

[1527] Step 3:

[1528] The server uses an emotion engine to analyze the personal characteristic information entered by the user. For example, it recognizes the user's emotional state (positive, negative, etc.) at the time of input and adds that information to the input data. The results of this analysis are used to evaluate the reliability of the data and correct it.

[1529] Step 4:

[1530] The server preprocesses the individual's characteristic information, including the data analyzed by the emotion engine. This preprocessing includes converting categorical values ​​(e.g., personality, hobbies) into numerical values ​​and calculating the number of past work experiences. For example, Alice's personality trait "extroverted" is converted to the numerical value "1," and her hobby "reading" is converted to the numerical value "2."

[1531] Step 5:

[1532] The server also preprocesses customer characteristic information and business requirements, including data analyzed by the emotion engine. This quantifies the customer's personality and hobbies and preferences, and each item in the business requirements is expressed as a specific numerical value. For example, Company A's requirement "extroverted personality" is converted to the numerical value "1," and "hobby reading" is converted to the numerical value "2."

[1533] Step 6:

[1534] The server calculates a matching score based on the preprocessed individual characteristic information, customer characteristic information, and business requirements. A similarity calculation method (e.g., cosine similarity) is used to calculate this score. This quantifies the degree to which each individual matches the customer requirements. For example, Alice's information is compared with Company A's business requirements to generate a matching score.

[1535] Step 7:

[1536] The server sorts the list of individuals based on the calculated matching scores, creating a list sorted by highest score first. For example, Alice, Bob, Charlie might be listed in descending order of scores.

[1537] Step 8:

[1538] The server filters individual candidates based on the specific customer's personality and hobbies and preferences. This narrows down the candidates to the most suitable. The filtering process also takes into account the analysis results of the emotion engine. For example, Alice is narrowed down as the most suitable candidate.

[1539] Step 9:

[1540] The server presents the filtered list of optimal candidates to the user. The user makes a final selection based on the provided list and prepares to dispatch the appropriate candidate. For example, Alice's detailed information is displayed to the user, and the user can decide whether to dispatch her to the customer.

[1541] These steps enable users to quickly and accurately select and dispatch the best personnel for their customer requirements. This process, combined with the emotion engine, improves the reliability of input data and achieves more accurate matching.

[1542] Example 2

[1543] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1544] Conventional talent matching systems lacked the reliability and consistency of input data, making it difficult to quickly and accurately select the talent most suited to customer requirements. Furthermore, data processing was performed without taking the user's emotional state into consideration, making it difficult to achieve highly accurate matching. This resulted in increased user effort and hindered efficient talent selection.

[1545] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1546] In this invention, the server includes means for receiving personal characteristic information provided by the user, means for receiving customer characteristic information and business requirements provided by the user, means for calculating a matching score based on the personal characteristic information, customer characteristic information and business requirements, means for selecting the most suitable individual based on the matching score, means for analyzing the user's emotions using an emotion engine and improving the reliability and consistency of input data, means for reflecting the analysis results of the emotion engine in preprocessing, and means for reflecting the user's emotional state in calculations based on the preprocessed data. This enables highly accurate matching and significantly reduces the user's workload.

[1547] "Individual characteristic information" is attribute information about a specific individual, such as age, gender, personality, hobbies, and past work experience.

[1548] "Customer characteristic information" is attribute information about a specific customer, such as the customer's personality, hobbies and preferences, and past feedback.

[1549] "Job requirements" are the conditions necessary to perform a specific job, such as the necessary skill set, work experience, personality, hobbies, and preferences.

[1550] The "matching score" is a numerical representation of the compatibility between an individual and a customer, calculated based on the individual's characteristic information, the customer's characteristic information, and business requirements.

[1551] An "emotion engine" is a technology used to analyze a user's emotional response to input data, improving reliability and consistency.

[1552] "Preprocessing" refers to the process of making the collected raw data easier to analyze, and includes converting categorical values ​​into numerical values ​​and quantifying text data.

[1553] "Filtering" is the process of sorting data based on specific conditions and extracting only useful information.

[1554] "Reliability" refers to the degree of accuracy and consistency of data.

[1555] "Consistency" indicates that the data follows certain rules or patterns.

[1556] This invention is a talent matching system for quickly and accurately selecting the best talent according to customer needs. This system achieves highly accurate matching by combining an emotion engine that recognizes the user's emotions.

[1557] First, the server receives personal characteristic information (age, gender, personality, hobbies, past work experience) provided by the user and stores it in the database. The server also receives customer characteristic information (personality, hobbies and preferences, past feedback) and job requirements (required skill set, work experience, personality, hobbies and preferences) and stores them in the database.

[1558] The server then analyzes the user's emotions using an emotion engine, which analyzes the emotional response to the input data to improve reliability and consistency. For example, if the user's emotion at the time of input is positive, it is evaluated as a factor that increases the reliability of the data.

[1559] In the data preprocessing stage, the server performs preprocessing on the collected data to make it easier to analyze. This includes quantifying categorical information such as personality and hobbies, and work experience. The analysis results from the emotion engine are also reflected here, and a reliability score for the data is calculated.

[1560] The server then calculates a matching score based on the preprocessed data. This calculation uses a similarity calculation method such as cosine similarity. As a result, the degree of match between the individual's characteristic information, the customer's characteristic information, and the business requirements is quantified.

[1561] Finally, the server generates a list of candidates based on the calculated matching scores. This list is sorted by highest score and filtered based on the personality and preferences of the specific customer. An emotion engine can be used to further refine the filtering.

[1562] Specific examples

[1563] 1. Data Entry Example

[1564] The user provides the following data as personal characteristic information:

[1565] Name: Individual A

[1566] Age: 28

[1567] Gender: Female

[1568] Personality: extroverted

[1569] Hobbies: Reading

[1570] Previous work experience: Engineer, Manager

[1571] The user provides the following data as customer characteristic information and business requirements.

[1572] Customer Name: Customer A

[1573] Past feedback: Good communication

[1574] Job requirements: Age 30 or older, 5+ years of experience, extroverted personality, reading hobby

[1575] 2. Preprocessing by the emotion engine

[1576] The server analyzes the input data from the user using an emotion engine. For example, if the user's emotion at the time of input is positive, it is evaluated as a factor that increases the reliability of the data.

[1577] 3. Data Preprocessing

[1578] The server calculates the number of past work experiences, and sets the number to "2" in the case of Individual A. It also quantifies category information such as "personality" and "hobbies."

[1579] 4. Calculating the Matching Score

[1580] Based on the business requirements, the server calculates the degree of similarity with the information of person A. At this time, person A's information is quantified and compared with the business requirements.

[1581] 5. Selecting the best individuals

[1582] Based on the calculated matching score, the server determines that Person A is the best candidate. Data from the emotion engine is also taken into account to confirm that Person A best meets the customer requirements.

[1583] Prompt Sentence Examples

[1584] "Please register Individual A, a 28-year-old extroverted female engineer whose hobby is reading."

[1585] "Looking for someone over 30, with at least 5 years of experience, who is extroverted and enjoys reading."

[1586] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1587] Step 1:

[1588] Data Entry

[1589] The server receives personal characteristic information (name, age, gender, personality, hobbies, past work experience) provided by the user. The input data is sent to the server via an HTTP request. The server stores the received data in a database. It also receives customer characteristic information (personality, hobbies and preferences, past feedback) and job requirements (required skill set, work experience, personality, hobbies and preferences) and stores them in the database.

[1590] Specific operation example: When a user enters personal and customer characteristic information into a web form and presses the submit button, the information is sent to the server, which processes this data using Python and stores it in a database (e.g., MySQL).

[1591] Input: User-entered personal and customer characteristics information

[1592] Output: Feature information stored in a database

[1593] Step 2:

[1594] Preprocessing with emotion engine

[1595] The server sends the acquired feature information to the emotion engine to analyze the user's emotional state. The emotion engine determines the emotional response (positive, negative, neutral, etc.) based on the input data. This result is used as additional information to improve the reliability and consistency of the data.

[1596] Specific operation example: The server calls the API for the emotion engine and sends the user's characteristic information. The emotion engine returns the analysis results, and the server stores the results in a database.

[1597] Input: Feature information

[1598] Output: Analysis results by the emotion engine

[1599] Step 3:

[1600] Data Preprocessing

[1601] The server preprocesses the collected data, including the analysis results of the emotion engine. This preprocessing includes quantifying categorical information such as personality and hobbies, quantifying past work experience, and calculating a reliability score for the data. This facilitates the subsequent calculation of matching scores.

[1602] Specific example: Using Python's pandas library, the collected data is processed as a data frame. Categorical information and text data are converted into numerical data, and the number of work experiences is calculated.

[1603] Input: Feature information including the analysis results of the emotion engine

[1604] Output: Preprocessed data

[1605] Step 4:

[1606] Matching Score Calculation

[1607] The server calculates a matching score based on the preprocessed individual and customer characteristic information and business requirements. The similarity calculation uses, for example, cosine similarity. The calculated matching score quantifies the degree of agreement between the individual and customer requirements.

[1608] Specific example: Using the scikit-learn library, calculate the cosine similarity between vectors of preprocessed data. The calculation results are stored in a database.

[1609] Input: Preprocessed individual and customer characteristics information

[1610] Output: Matching score

[1611] Step 5:

[1612] Selection of the best individuals

[1613] The server generates a candidate list based on the calculated matching scores. It sorts the candidates by highest score and filters them based on the characteristics and hobbies of specific customers. It also takes into account the results of the emotion engine to create an even more accurate candidate list.

[1614] Specific example of operation: Using an SQL query, data is retrieved from the database in descending order of matching score, a list reflecting the results of sentiment analysis is generated, and then provided to the user.

[1615] Input: Matching score

[1616] Output: A list of the best candidates

[1617] (Application example 2)

[1618] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1619] Conventional talent matching systems have issues with the reliability and consistency of input information because they do not take into account user emotional data. Also, in factory management using robots, there is a problem with the inability to quickly and accurately allocate appropriate robots.

[1620] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving individual characteristic information provided by a user; means for receiving customer characteristic information and business requirements provided by a user; means for calculating a matching score between the individual and the customer based on the individual characteristic information, the customer characteristic information, and the business requirements; means for selecting the most suitable individual based on the matching score; means for analyzing the user's emotional response using an emotion engine and evaluating the reliability of the data based on the analysis; and means for a factory manager to input robot characteristic information and work station requirements using a smart device and match robots with work stations based on the input. This enables highly accurate personnel matching that takes user emotional data into account and efficient deployment of robots in the factory.

[1621] "User emotional response" refers to the psychological state or feelings a user exhibits when entering information.

[1622] The "matching score" is a numerical representation of the degree of match between the individual's characteristic information, the customer's characteristic information, and the business requirements.

[1623] An "emotion engine" is a system that analyzes user emotions in response to input data and evaluates the reliability and consistency of that data.

[1624] "Smart devices" refers to electronic devices with internet connectivity, such as smartphones, tablets, smart glasses, and head-mounted displays.

[1625] "Robot characteristic information" includes information such as the robot's identification number, performance, tasks that it can handle, operating time, and reliability.

[1626] "Work station" refers to a location within a factory where a specific task is performed.

[1627] A "factory manager" is a person in charge of managing work and robots within the factory.

[1628] The present invention is a system for matching human resources and robots with consideration of the user's emotions. Specific embodiments will be described below.

[1629] Data Entry

[1630] First, the server receives personal characteristic information provided by the user. This information includes age, gender, personality, hobbies, past work experience, etc. The user also inputs customer characteristic information and work requirements. This includes the customer's personality, hobbies and preferences, past feedback, required skill set, work experience, etc. The factory manager inputs robot characteristic information (identification number, performance, work that can be performed, operating time, reliability) and work station requirements (required skills, operating time, work content). All of this data is stored in a database.

[1631] Preprocessing with emotion engine

[1632] The server uses an emotion engine to analyze the user's emotional response to the input data, which improves the reliability and consistency of the input information. For example, if the user shows positive emotions, the data will be rated as more reliable.

[1633] Data Preprocessing

[1634] The server preprocesses the individual and robot characteristic information, including the data obtained by the emotion engine. This preprocessing involves converting category values ​​into numerical values ​​and quantifying text data. The number of past work experiences is then calculated. Similar preprocessing is performed on the "customer characteristic information" and "workstation requirements," and the analysis results of the emotion engine are reflected.

[1635] Matching Score Calculation

[1636] The server calculates a matching score based on the preprocessed individual feature information, the robot feature information, the customer feature information, the business requirements, and the requirements of the work station. This score is calculated using a similarity calculation method such as cosine similarity, which quantifies how well each individual or robot matches the requirements of the customer or work station.

[1637] Selection of the best individuals and robots

[1638] The server selects the best individuals and robots based on the calculated matching scores. A list is created sorted by highest score, and candidates are filtered based on the specific customer's personality, hobbies, and work station requirements. An emotion engine can be used to further refine the filtering.

[1639] Specific examples

[1640] The user provides the following data as personal characteristic information:

[1641] Name: Taro

[1642] Age: 35

[1643] Gender: Male

[1644] Personality: introverted

[1645] Hobbies: Programming

[1646] Previous work experience: Systems engineer, project manager

[1647] In addition, the factory manager provides the following data as characteristic information of the robot:

[1648] Identification number: R123

[1649] Performance: High

[1650] Available work: Assembly, packaging

[1651] Operating time: 3000 hours

[1652] Reliability: 90%

[1653] The administrator provides the following data as requirements for the workstation:

[1654] Required skills: Assembly

[1655] Operating time: 2500 hours

[1656] Required work: Parts assembly

[1657] The server receives this information, analyzes it with an emotion engine, performs preprocessing, calculates a matching score, and selects the most suitable individual and robot.

[1658] Prompt Sentence Examples

[1659] Based on the data below, come up with an algorithm to optimally match robots and workstations, and implement it in Python.

[1660] Robot data (identification number, performance, skills, operating time, reliability)

[1661] Workstation data (skills required, uptime required, reliability required)

[1662] Consider also using a sentiment engine to assess the reliability of input data.

[1663] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1664] Step 1:

[1665] The user uses a terminal to input personal characteristic information (age, gender, personality, hobbies, past work experience). The terminal sends this information to the server and stores it in a database. This allows the system to obtain the necessary characteristic information.

[1666] Input: Personal characteristics information

[1667] Output: Personal characteristics stored in a database

[1668] Specific operation: The user enters the required information on the form input screen and clicks the "Submit" button. The device sends the input data in JSON format to the server's API.

[1669] Step 2:

[1670] Factory managers use terminals to input the robot's characteristic information (identification number, performance, tasks it can handle, operating hours, reliability). The terminals then send this information to the server and store it in a database. This allows the system to obtain the necessary robot characteristic information.

[1671] Input: Robot characteristics information

[1672] Output: Robot characteristics stored in a database

[1673] Specific operation: The administrator enters the robot details into the input form and presses the "Submit" button. The data sent from the terminal is processed by the server and stored in the database.

[1674] Step 3:

[1675] The server uses an emotion engine to perform emotion analysis on the data entered by users and administrators, which evaluates the reliability and consistency of the data.

[1676] Input: Input feature information

[1677] Output: Emotion analysis results

[1678] How it works: The emotion engine uses natural language processing (NLP) techniques to analyze the sentiment of the words and style contained in the input data and generate a confidence score, which is stored in a database.

[1679] Step 4:

[1680] The server performs preprocessing and quantifies the individual and robot feature information, including converting categorical values ​​and quantifying text data.

[1681] Input: Personal characteristic information, robot characteristic information

[1682] Output: Quantified feature information

[1683] Specific operation: Using Python libraries (e.g., pandas, scikit-learn), categorical data is converted to numerical values ​​and text data is vectorized. The calculation results are stored in a database as numerical data.

[1684] Step 5:

[1685] The server calculates a matching score based on the quantified individual characteristic information, customer characteristic information, business requirements, robot characteristic information, and work station requirements. This score calculation uses the cosine similarity calculation method.

[1686] Input: Quantified characteristic information, customer characteristic information, business requirements, work station requirements

[1687] Output: Matching score

[1688] Specific operation: Using existing data processing libraries (e.g., numpy, scipy), the cosine similarity is calculated and a matching score for each individual and robot is calculated. This score is then stored in a database.

[1689] Step 6:

[1690] The server selects the best individuals and robots based on the matching scores, creates a list sorted by the highest score, and presents it to the user and administrator.

[1691] Input: Matching score

[1692] Output: List of best individuals and robots

[1693] Specific operation: The server sorts the matching scores in descending order and lists the most suitable individuals and robots. This list is displayed on the user's and administrator's terminals.

[1694] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1695] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1696] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1697] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1698] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1699] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1700] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1701] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1702] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1703] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1704] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1705] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1706] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1707] 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.

[1708] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1709] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1710] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1711] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1712] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1713] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1714] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1715] The following is further disclosed regarding the above embodiment.

[1716] (Claim 1)

[1717] means for receiving personal characteristic information provided by a user;

[1718] means for receiving customer characteristics information and business requirements provided by a user;

[1719] a means for calculating a matching score between the individual and the customer based on the individual's characteristic information, the customer's characteristic information, and business requirements;

[1720] The system includes a means for selecting the best individual based on the matching score.

[1721] (Claim 2)

[1722] The system according to claim 1 , further comprising means for preprocessing and quantifying the individual characteristic information.

[1723] (Claim 3)

[1724] The system of claim 1 , further comprising: means for filtering the individual candidates based on the customer characteristic information.

[1725] "Example 1"

[1726] (Claim 1)

[1727] means for receiving personal characteristic information provided by a user;

[1728] means for receiving customer characteristics information and business requirements provided by a user;

[1729] a means for calculating a matching score between the individual and the customer based on the individual's characteristic information, the customer's characteristic information, and business requirements;

[1730] means for calculating the matching score based on the individual characteristic information and customer characteristic information that have been digitized after preprocessing;

[1731] A means for selecting and filtering the most suitable individuals based on the matching scores;

[1732] The system includes a means for notifying the user of the selection result.

[1733] (Claim 2)

[1734] The system according to claim 1 , further comprising a preprocessing means for converting the individual characteristic information and the customer characteristic information into numerical values ​​and vectorizing text data.

[1735] (Claim 3)

[1736] 10. The system of claim 1, further comprising means for calculating the matching score using a machine learning algorithm or similarity calculation technique.

[1737] "Application Example 1"

[1738] (Claim 1)

[1739] means for receiving personal characteristic information provided by a user;

[1740] means for receiving customer characteristics information and business requirements provided by a user;

[1741] a means for calculating a matching score between the individual and the customer based on the individual's characteristic information, the customer's characteristic information, and business requirements;

[1742] means for selecting the most suitable individual based on the matching score;

[1743] A means for selecting the most suitable security personnel based on the requirements of the security service;

[1744] The system includes a means for outputting information about the selected security officer.

[1745] (Claim 2)

[1746] The system according to claim 1 , further comprising means for preprocessing and quantifying the individual characteristic information.

[1747] (Claim 3)

[1748] The system of claim 1 , further comprising: means for filtering the individual candidates based on the customer characteristic information.

[1749] "Example 2: Combining Emotion Engines"

[1750] (Claim 1)

[1751] means for receiving personal characteristic information provided by a user;

[1752] means for receiving customer characteristics information and business requirements provided by a user;

[1753] A means for calculating a matching score based on the individual characteristic information, the customer characteristic information, and the business requirements;

[1754] a means for selecting the best individuals based on the matching scores;

[1755] A means for analyzing user emotions using an emotion engine to improve the reliability and consistency of input data;

[1756] a means for reflecting the analysis result of the emotion engine in preprocessing;

[1757] The system includes means for incorporating a user's emotional state into the calculation based on the preprocessed data.

[1758] (Claim 2)

[1759] 10. The system of claim 1, further comprising means for preprocessing and quantifying the individual's characteristic information.

[1760] (Claim 3)

[1761] 10. The system of claim 1, further comprising means for filtering individual candidates based on customer characteristic information.

[1762] "Application example 2 when combining emotion engines"

[1763] (Claim 1)

[1764] means for receiving personal characteristic information provided by a user;

[1765] means for receiving customer characteristics information and business requirements provided by a user;

[1766] a means for calculating a matching score between the individual and the customer based on the individual's characteristic information, the customer's characteristic information, and business requirements;

[1767] means for selecting the most suitable individual based on the matching score;

[1768] a means for analyzing a user's emotional response using an emotion engine and assessing the reliability of the data based thereon;

[1769] A means for factory managers to input robot characteristic information and work station requirements using smart devices and then match the robot with the work station based on the input information.

[1770] A system including:

[1771] (Claim 2)

[1772] The system according to claim 1 , further comprising means for preprocessing and quantifying the individual characteristic information and the robot characteristic information.

[1773] (Claim 3)

[1774] The system of claim 1 , further comprising means for filtering the individual candidates and optimal robots based on the customer characteristic information and work station requirements. [Explanation of symbols]

[1775] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving personal characteristic information provided by a user; means for receiving customer characteristic information and business requirements provided by a user; a means for calculating a matching score between the individual and the customer based on the individual characteristic information, the customer characteristic information, and business requirements; and means for selecting the best individuals based on the matching scores.

2. The system according to claim 1 , further comprising means for preprocessing and quantifying the individual characteristic information.

3. The system of claim 1 , further comprising means for filtering the individual candidates based on the customer characteristic information.

Images