User evaluation method

Abstract

To provide a method for multilaterally evaluating the skill of registered personnel.SOLUTION: In a user evaluation method for evaluating a user, a system executes an input information receiving step of receiving input information including information on a biography of the user, a question output step of creating a question based on the input information using the input information and outputting the question, a response receiving step of receiving response information from the user regarding the question, and a user analysis step of analyzing a feature of the user based on the input information and the response information and obtaining analysis information of the user.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] This invention relates to a user evaluation method, etc. More specifically, this invention relates to a method that can evaluate registered personnel from multiple perspectives, taking into consideration not only input information used in recruiting activities but also answers to questions based on the input information. [Background technology]

[0002] Japanese Patent Publication No. 7457191 describes a human resources management support system, a human resources management support method, and a program. This human resources management support system acquires attribute parameters for a target person, including attribute values ​​in a first category and attribute values ​​in a second category. Next, at least one label including information based on the attribute values ​​in the first category and a dependent parameter representing the state of the first category based on the attribute values ​​in the second category is assigned to the target person's information. Then, the target person's information is individually displayed in a manner in which the label has been assigned.

[0003] The above-mentioned human resource management support systems are excellent at managing human resource information. However, it is difficult for these systems to assess a candidate's skills from multiple perspectives. Furthermore, this system makes it difficult for employees to objectively self-assess their skill proficiency, and registered employees themselves cannot understand what they need to study to improve their evaluation. This system also makes it difficult to evaluate the future potential of registered employees. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 7457191 Summary of the Invention [Problem to be solved by the invention]

[0005] Therefore, there is a need for a method that can evaluate the skills of registered personnel from multiple perspectives. There is also a need for a method that can objectively evaluate skill proficiency and provide registered personnel with learning guidelines. Furthermore, there is a need for a method that can evaluate the future potential of registered personnel. [Means for solving the problem]

[0006] The present invention is based on the finding that the above-mentioned problems can be solved by creating questions based on information input by users (registered personnel) and having them answer the questions, thereby objectively evaluating registered personnel and analyzing the skills and learning content they will need for the future. In other words, the present invention solves at least one of the above-mentioned problems.

[0007] The user evaluation method for evaluating a user described in this specification includes an input information receiving step, a question outputting step, an answer receiving step, and a user analysis step. The input information receiving step is a step of receiving input information including information about the user's career history. The input information preferably includes input information of the user's resume. The input information preferably includes the user's qualification information and information about the user's evaluations from others. The question output step is a step of using input information to create a question based on the input information and outputting the question. The question output step preferably includes a step of obtaining the question by inputting the input information into a first trained model, which is a trained model by machine learning that outputs a question based on the input information. The answer receiving step is a step of receiving answer information from the user regarding the question. The user analysis step is a step of analyzing user characteristics based on the input information and response information to obtain user analysis information. The user analysis information is preferably a non-fungible token (NFT). The user analysis information preferably includes an evaluation of the user's current situation and an evaluation of the user's future ability growth. The user analysis information preferably includes a step of obtaining user analysis information by inputting the input information and response information into a second trained model, which is a trained model by machine learning that evaluates the user based on the input information and response information.

[0008] In a preferred embodiment of the above-described user evaluation method, the input information includes information regarding the user's desired occupation, and the user's analysis information includes information regarding the skills required for role models related to the desired occupation and information regarding the user's current situation regarding the required skills.

[0009] In a preferred embodiment of the above-described user evaluation method, the input information includes information regarding the user's desired occupation, and the user's analysis information includes information regarding what the user should learn in the future with respect to role models related to the desired occupation and projects that the user should preferably experience in the future. [Effects of the Invention]

[0010] The above method evaluates users based not only on the information entered by the user but also on their responses to custom-made questions, allowing for a multifaceted evaluation of the skills of registered personnel. Similarly, this method can provide objective assessments of skill proficiency and learning guidelines for registered personnel. Furthermore, this method can evaluate the future potential of registered personnel. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a block diagram illustrating the configuration of a user evaluation system for implementing a user evaluation method. [Figure 2] FIG. 2 is a flow chart showing each step of the user evaluation method. [Figure 3]Figure 3 shows an example of building a trained model and an example of using the trained model. DETAILED DESCRIPTION OF THE INVENTION

[0012] The following describes embodiments of the present invention with reference to the drawings. The present invention is not limited to the embodiments described below, and also includes appropriate modifications of the embodiments below within the scope obvious to those skilled in the art.

[0013] FIG. 1 is a block diagram illustrating the configuration of a user evaluation system for implementing a user evaluation method. As shown in FIG. 1, this system 1 includes an input information receiving unit 3, a question output unit 5, a response receiving unit 7, a user analysis unit 9, and an analysis information output unit 11. This system 1 includes a computer. Preferably, the computer is a quantum computer. Quantum computers are publicly known, as described in, for example, Japanese Patent Publication Nos. 7422647, 7401825, 7466478, and 7329806. Using a quantum computer as the computing platform for system 1 enables rapid extraction and evaluation of technical skills, consisting of a large number of items, from information such as resumes and engineer input. Using a quantum computer as the computing platform for system 1 enables rapid and accurate extraction of the most suitable candidates for a hiring company's requirements from a large number of resumes, on the scale of one million people. The input information receiving unit 3, the question output unit 5, the answer receiving unit 7, and the user analysis unit 9 are elements for executing the input information receiving process, the question output process, the answer receiving process, and the user analysis process, respectively. The analysis information output unit 11 is an element for executing the analysis information output process. In this specification, a user or a company refers to a terminal owned or accessible by a user, depending on the context, and a company refers to a terminal owned or accessible by a company.

[0014] The user evaluation in the user evaluation method or system is, for example, an evaluation by a person currently recruiting (a student, a job seeker, or a job seeker), and can be used as an evaluation of a potential employer or as a self-evaluation. This evaluation may be used as one element of a (digital) resume. This evaluation may also be used as common information for use by multiple employers.

[0015] A computer has an input unit, an output unit, a control unit, a calculation unit, and a memory unit, and each element is connected by a bus or the like to enable the exchange of information. For example, the memory unit may store a program or various information. When predetermined information is input from the input unit, the control unit reads the program stored in the memory unit. The control unit then reads the information stored in the memory unit as appropriate and transmits it to the calculation unit. The control unit also transmits the input information to the calculation unit as appropriate. The calculation unit performs calculation processing using the various received information and stores it in the memory unit. The control unit reads the calculation results stored in the memory unit and outputs them from the output unit. In this way, various processes and steps are executed. Each unit or means executes these various processes. A computer may have a processor, and the processor may realize various functions and steps. A computer may be standalone. A computer may have some of its functions distributed between a server and a terminal. In this case, it is preferable that the server and the terminal can exchange information via a network such as the Internet or an intranet. The computer may include a processor and a memory coupled to the processor. The memory may store instructions that, when executed by the processor, cause the computer to perform various processes or function as various elements. The computer may be provided with various training data to construct a learning model and perform various calculations through machine learning. In this case, the computer may perform various analyses using a learning model created through machine learning and deep learning in AI (artificial intelligence). This improves the accuracy of machine learning.

[0016] FIG. 2 is a flow chart showing the steps of the user evaluation method. As shown in FIG. 2, the method includes an input information receiving step (S101), a question output step (S102), an answer receiving step (S103), and a user analysis step (S104). This method is executed by a computer. In this method, a processor storing a program causes the computer to execute each step based on instructions from the program. For example, if the system 1 uses a quantum computer, the present invention can provide an optimization algorithm based on quantum annealing for personnel matching. This algorithm aims to find the optimal match between specific job seeker data and job requirements, and can achieve processing speed and efficiency that are unattainable with conventional digital computers.

[0017] Input information receiving step (S101) The input information receiving process is a process in which the input information receiving unit 3 receives input information including information about the user's career. For example, the user or a person evaluating the user opens a registration screen and inputs the necessary information into a computer or the user's terminal using a pointing device. Examples of pointing devices are a keyboard, a mouse, a touch panel, and voice input. When a user inputs input information into the user's terminal, the input information is output from the user's terminal to the system 1. The input information receiving unit 3 of the system 1 receives the input information output from the user's terminal. The input information is then stored in a memory unit as appropriate and input to the input information receiving unit 3. The input information receiving unit 3 receives this input information and stores it in a memory unit as appropriate. The input information is usually digital information that can be used by a computer but is incomprehensible to humans.

[0018] The input information preferably includes the user's resume. The resume input information preferably includes one or more of the following: name, current address, telephone number, email address, educational background, work history, motivation for applying, health status, and information about dependents. The input information preferably further includes the user's qualifications and evaluations of the user from others. Examples of qualifications include information about various public or private qualification exams, such as the Eiken, TOEIC, and administrative scrivener exams. Examples of evaluations from others include evaluations from the internship company if the user was an intern, or evaluations from the company if the user was employed there. Inputting information about the user's working conditions at a company makes it possible to objectively evaluate the user. Furthermore, by creating questions based on this information, it is possible to evaluate the user's skill acquisition and personality (e.g., whether the user is the type who tries to understand or the type who simply follows instructions) at the internship or employment company. Another example of input information is information about an unexcused absence on an interview day. When a job interview is conducted using the system 1, a user who has previously been absent without permission is likely to be absent from the interview without permission and is likely to be selfish. Therefore, by accumulating information on absences without permission, such users can be appropriately evaluated as selfish personnel. Note that information on absences without permission is stored in the memory of the system 1, and although it is not accessible to users, it is preferable that it be accessible to companies (that meet certain conditions).

[0019] The input information may include the user's desired job type. Examples of the desired job type include one or more of: clerical work, research, human resources, accounting, legal affairs, intellectual property, general affairs, planning, general affairs, career track, general employee, part-time, and casual work. As will be described later, the machine learning unit uses various input information as training data to build a trained model, and therefore can obtain appropriate questions and analytical information for any input information.

[0020] Question output process (S102) The question output process is a process in which the question output unit 5 uses input information to create a question based on the input information and outputs the question. For example, the question output unit 5 receives the input information from the input information receiving unit 3. Alternatively, the question output unit 5 may read the input information from a storage unit. The question output unit 5 uses the input information to create a question based on the input information. A known method may be appropriately adopted as the method in which the question output unit 5 uses the input information to create a question based on the input information. For example, the question output unit 5 may extract keywords from words included in the input information and read or create a question using the extracted keywords. Such keywords may be appropriately stored in the storage unit. Then, the question output unit 5 may match the words included in the input information with the keywords to obtain the keywords necessary for the question. The question output unit 5 may store questions associated with the keywords and output a question associated with the obtained keywords.

[0021] The question output step preferably includes a step of creating a question using artificial intelligence. An example of the artificial intelligence is ChatGPT (registered trademark). For example, the question output step includes a step of obtaining a question by inputting input information into the first trained model 23.

[0022] FIG. 3 shows an example of constructing a trained model and an example of using the trained model. The first trained model 23 is a trained model generated by machine learning that outputs questions based on input information. For example, the system 1 includes a first machine learning unit 21. The system 1 inputs various pieces of input information and corresponding example questions to the first machine learning unit 21 as training data with answers. The first machine learning unit 21 then performs machine learning to obtain the first trained model 23. The accuracy of the first trained model 23 increases the more input information and example questions are input. Also, for example, certain input information is input to the trained model 23, and evaluation information indicating whether the obtained question is appropriate is fed back to the first machine learning unit 21. In this way, the first machine learning unit 21 can improve the accuracy of the first trained model 23. The question output unit 5 inputs input information to the first learning unit 21. The first learning unit 21 then creates questions based on the input information. The question output unit 5 may store the created question in a storage unit as appropriate.

[0023] For example, if the input information includes a history of part-time work at a patent office and a desired occupation in the intellectual property department, the question output unit 5 inputs this input information into the first trained model 23, and a question about intellectual property is output. By having the user answer this question, the system 1 can analyze the user's aptitude and how the user has performed in part-time work. Furthermore, if the question is a written question, analyzing the written answer can analyze the user's proficiency, level of understanding, ability to express, and the like. Furthermore, by using the part-time work history and level of understanding, the system 1 can predict the user's future abilities.

[0024] The question output unit 5 outputs a question. The question output unit 5 may display the question on a display unit (such as a monitor) of the system 1. Furthermore, the question output unit 5 may output question display information to the user's terminal so that the display unit of the user's terminal can display the question.

[0025] Response receiving step (S103) The answer receiving process is a process in which the answer receiving unit 7 receives answer information from the user regarding the question. In the question output process (S102), the question is displayed on the display unit. The user inputs the answer to the question into the system 1 or the user's terminal. If the answer is input using the pointing device of the system 1, the answer receiving unit 7 receives the input answer information. If the answer is input into the user's terminal, information regarding the answer is output from the user's terminal to the system 1. The answer receiving unit 7 of the system 1 receives information regarding the answer output from the user's terminal. The answer may be a written answer to the question.

[0026] User analysis step (S104) The user analysis step is a step in which the user analysis unit 9 analyzes user characteristics based on the input information and response information to obtain user analysis information. The user analysis information is preferably a non-fungible token (NFT). By converting the user analysis information into an NFT, information about the user is accumulated and cannot be tampered with, making it possible to obtain user information over time. Japanese Patent Nos. 7043672 and 7398145 describe management systems for non-fungible tokens (NFTs). This invention may also appropriately use the non-fungible token (NFT) management methods described in these patent documents.

[0027] The user analysis information preferably includes an evaluation of the user's current state and an evaluation of the user's future ability growth. The user analysis information preferably includes a step of obtaining the user analysis information by inputting the input information and the response information into a second trained model, which is a trained model by machine learning that evaluates the user based on the input information and the response information.

[0028] For example, artificial intelligence may be used to analyze the user. An example of the artificial intelligence is ChatGPT (registered trademark). For example, the system 1 includes a second machine learning unit 31. The system 1 inputs various pieces of input information and answer information, as well as corresponding user analysis information, as training data with answers to the second machine learning unit 31. The second machine learning unit 31 then performs machine learning to obtain a second trained model 33. The more input information, answer information, and analysis information the second trained model 33 receives, the higher its accuracy becomes. For example, certain input information and answer information may be input to the trained model 33, and evaluation information indicating whether the obtained analysis information is appropriate is fed back to the second machine learning unit 31. In this way, the second machine learning unit 31 can improve the accuracy of the second trained model 33. The question output unit 5 inputs the input information and answer information to the second learning unit 31. The second learning unit 31 then creates user analysis information based on the input information and answer information. The user analysis unit 9 may store the created user analysis information in a memory unit as appropriate. The user analysis process may be performed in the same manner as the question output process. If the input information or answer information includes a sentence, the system 1 may include an element for analyzing whether the sentence was created by a computer, such as artificial intelligence. The system 1 preferably stores the analysis results regarding whether the sentence was created by a human or a computer in a memory unit and provides them to the company. Whether the sentence was created by a computer can be analyzed by constructing a learning model and inputting the sentence into the learned model. If the sentence was created by a human, the system 1 may analyze the accuracy of the sentence (subject, predicate, object), store the analysis results, and provide them to the company.

[0029] It is not easy to measure a person's abilities in a multifaceted and fair manner through document screening or a short interview alone. It is particularly difficult to evaluate practical aspects, and the evaluation tends to be influenced by the impression made during the interview, leading to a bias toward those who are easy to interview. This invention re-evaluates the user based on the user's response information, allowing for an appropriate evaluation of the user.

[0030] The user analysis information may include the user's skill proficiency. The user analysis information may also include information about what the user should learn and the skills and qualifications that the user should acquire. The user analysis information may also include information about how the user should improve their skills. In this case, the first and second trained models may be used that have been trained using the user's skill proficiency and the content that the user should learn as training data (with answers). For example, even an engineer user may not be able to properly grasp their current level of skill proficiency. Furthermore, such users cannot see their future goals and do not know where to head or what to learn. Furthermore, such users have a lot to do and do not know where to start, making it difficult for them to grow. This method can obtain the above-mentioned user analysis information, allowing it to appropriately address these issues.

[0031] It is preferable that user analysis information includes an image of the skills a user will have after a certain period of time has passed since joining the company. It is also important for employers to know whether users can grow. Therefore, it is useful to have an image of not only their current skills but also what they will be like several years after joining the company. In this case, the first and second trained models can be trained using past users and their post-employment status and evaluations (e.g., leaving after a certain number of years, becoming a valuable asset, being promoted, obtaining qualifications, etc.) as training data (with responses). This method can obtain the user analysis information described above, thereby addressing these challenges appropriately.

[0032] Analysis information output process (S105) The analysis information output step is a step in which the analysis information output unit 11 outputs the analysis information of the user. The analytical information output unit 11 receives the user's analytical information from the user analysis unit 9. Alternatively, the analytical information output unit 11 reads the user's analytical information from the storage unit. Then, the analytical information output unit 11 outputs the user's analytical information. The analytical information output unit 11 may display the user's analytical information on a display unit (such as a monitor) of the system 1. Alternatively, the analytical information output unit 11 may output the user's analytical information to the user's terminal so that the display unit of the user's terminal can display the user's analytical information. For example, if another user (e.g., a terminal of a company's recruiter) requests it, the analytical information may be output to a third party's terminal according to the user's request. When outputting the analytical information, it is preferable to protect the information using quantum cryptography (technology using a quantum cryptographic key). This technology can maintain the confidentiality and integrity of data even against potential threats using quantum computers.

[0033] In a preferred embodiment of the above user evaluation method, the input information includes information about the user's desired occupation, and the user's analysis information includes information about the skills required for a role model related to the desired occupation and information about the user's current situation regarding the required skills. A role model related to the desired occupation refers to, for example, a model staff member in the desired occupation. For example, if the desired occupation is the intellectual property department, an example of a role model would be an intellectual property department member. Furthermore, the required skills for the role model are skills that a model staff member in the desired occupation would desirably acquire. For example, if the desired occupation is an intellectual property department member, an example of the required skills would be knowledge of patent law, and other examples of the required skills would be the ability to organize information and coordination skills. Examples of content that the user should study in the future include the Intellectual Property Skills Test and related website information if the user is a student, and in-company training, related website information, examination institutions, etc. if the user is a company employee. Examples of projects that the user should experience in the future include an in-company project if the user is a company employee, and an internship if the user is a student. Thus, in a preferred embodiment of the above user evaluation method, the input information includes information about the user's desired occupation, and the user's analysis information includes information about what the user should learn in the future with respect to role models related to the desired occupation and about projects the user should experience in the future. These are input as training data to the second machine learning unit 31, and the second trained model 33 reflects the training data, allowing for appropriate output.

[0034] The above method evaluates users based not only on the information entered by the user but also on their responses to custom-made questions, allowing for a multifaceted evaluation of the skills of registered personnel. Similarly, this method can provide objective assessments of skill proficiency and learning guidelines for registered personnel. Furthermore, this method can evaluate the future potential of registered personnel. [Industrial Applicability]

[0035] This invention can be used in the recruitment industry, the examination industry, etc. This invention can also be used in personnel planning / training of employees, reskilling (career change guidance following restructuring), etc. [Explanation of symbols]

[0036] 1. User Rating System 3. Input information receiving section 5 Question output section 7. Response Receipt Department 9. User Analysis Department 11 Analysis information output section 21 First Machine Learning Department 23 First trained model 31 Second Machine Learning Department 33 Second trained model

Claims

1. A user evaluation method for evaluating a user, comprising: an input information receiving step of receiving input information including information about the user's career history; a question output step of using the input information to create a question based on the input information and outputting the question; an answer receiving step of receiving answer information from the user regarding the question; a user analysis step of analyzing the characteristics of the user based on the input information and the response information to obtain analysis information of the user; A method comprising:

2. 10. The method of claim 1, wherein the user analytics information is a non-fungible token (NFT).

3. The method of claim 1 , wherein the input information comprises a resume input information of the user.

4. The method of claim 1 , wherein the input information includes the user's qualification information and the user's reputation information from others.

5. The method of claim 1 , wherein the user analysis information includes an assessment of the user's current state and an assessment of the user's future performance growth.

6. 2. The method of claim 1, wherein the question output process includes a process of obtaining the question by inputting the input information into a first trained model, which is a trained model using machine learning that outputs a question based on input information.

7. 2. The method of claim 1, wherein the user analysis information includes a step of obtaining the user analysis information by inputting the input information and the response information into a second trained model, the second trained model being a machine learning trained model that evaluates the user based on the input information and the response information.

8. 2. The method according to claim 1, wherein the input information includes information about the user's desired occupation; The method, wherein the user's analysis information includes information about skills required for role models related to the desired job type and information about the user's current situation regarding the required skills.

9. 2. The method according to claim 1, wherein the input information includes information about the user's desired occupation; The method, wherein the user analysis information includes information regarding what the user should learn in the future and projects the user should preferably experience in the future, relative to role models related to the desired job type.

Images