Job suggestion system
The job suggestion system uses GPT to generate questions about user gender and strengths, creating unique fictional jobs in katakana, addressing the lack of occupation proposals that utilize user strengths and enhancing engagement.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- DENTSU INC
- Filing Date
- 2024-12-26
- Publication Date
- 2026-07-08
AI Technical Summary
Conventional systems fail to propose imaginary occupations that utilize a user's strengths in a pre-specified field, such as the nursing care field, and lack variety in job title generation.
A job suggestion system using an existing learning model like GPT generates questions about user gender and strengths in a cheerful style, and creates fictional job titles in katakana, avoiding simple conversions and incorporating user dreams to suggest new occupations.
The system easily proposes futuristic and varied fictional jobs that leverage user strengths, providing a cool impression and engaging experience, especially for elementary school students.
Smart Images
Figure 2026113785000001_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to an occupation proposal system that proposes imaginary occupations to users.
Background Art
[0002] Conventionally, various educational devices have been proposed. For example, a system that provides educational content for career formation has been proposed for working people or those who are about to become working people (see, for example, Patent Document 1).
[0003] According to this conventional device, as part of career formation, it is possible to provide educational content that can be recommended based on the user's desired career interest area, or to provide an "image of what one wants to be" derived from the educational content viewed by the user.
Prior Art Documents
Patent Documents
[0004]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0005] However, in the above-described conventional device, it is not assumed to propose imaginary occupations (new occupations in the future). In particular, a system that can propose an imaginary occupation (new occupation in the future) that makes use of what the user is good at in a pre-specified occupation field (for example, the nursing care field) has not been proposed so far.
[0006] The present invention has been made in view of the above problems, and an object thereof is to provide an occupation proposal system that can propose an imaginary occupation that makes use of what the user is good at in a pre-specified occupation field.
Means for Solving the Problems
[0007] The present invention provides a job suggestion system that suggests fictional jobs to a user, and includes: a question generation unit that, upon receiving a job suggestion request from the user, causes an existing learning model to generate a question in a predetermined style that asks the user about their gender and areas of expertise; a question answer processing unit that outputs the question generated by the existing learning model to the user and receives the user's answer to the question; a fictional job generation unit that, based on the user's gender and areas of expertise included in the user's answer, causes the existing learning model to generate information about a fictional job in a predetermined occupational field; and a user suggestion processing unit that outputs the information about the fictional job generated by the existing learning model to the user.
[0008] In this configuration, when a user requests a job suggestion, an existing learning model (such as GPT) is used to generate a question asking the user about their "gender" and "strengths," using a pre-specified writing style (for example, a cheerful and engaging style), and output it to the user. When the user provides an answer to the question, the existing learning model (such as GPT) is used to generate information about a fictional job (a new job of the future) in a pre-specified occupational field (for example, the nursing care field) based on the "gender" and "strengths" included in the answer, and output it to the user. In this way, by using an existing learning model, it is possible to easily suggest a fictional job (a new job of the future) that utilizes the user's strengths in a pre-specified occupational field (for example, the nursing care field).
[0009] Furthermore, in the occupation suggestion system of the present invention, the fictional occupation generation unit may cause the existing learning model to generate the occupation name of the fictional occupation in katakana, and may also prohibit the inclusion of a katakana expression that is simply a katakana conversion of the occupation field in the katakana expression of the occupation name.
[0010] This configuration generates fictional job titles in katakana, giving users a "futuristic and cool impression" of those jobs (fictional jobs). In this case, the katakana representation of the job title cannot include a katakana representation of the job field, thus preventing the generation of similar job titles and increasing the variety of job titles that can be generated.
[0011] Furthermore, in the occupation suggestion system of the present invention, the occupation field is the nursing care field, and it may be prohibited to include the katakana expression "care" in the katakana expression of the occupation name.
[0012] This configuration allows for a "futuristic and cool impression" of fictional occupations in the caregiving field to be conveyed to users. In this case, the inclusion of the katakana word "care" in the occupational name is prohibited, which prevents the generation of similar occupational names and increases the variety of generated occupational names.
[0013] Furthermore, in the occupation suggestion system of the present invention, when the question generation unit receives an occupation suggestion request from the user, it may cause the existing learning model to generate a question in the pre-specified style that asks the user about their gender, strengths, and future dreams, and the fictional occupation generation unit may cause the existing learning model to generate information about a fictional occupation in the pre-specified occupational field based on the user's gender, strengths, and future dreams included in the user's response.
[0014] In this configuration, when a user requests a job suggestion, an existing learning model (such as GPT) is used to generate a question asking the user about their "gender," "strengths," and "future dreams," using a pre-specified writing style (for example, a cheerful and engaging style). When the user provides answers to the questions, the existing learning model (such as GPT) is used to generate information about a fictional job (a new job of the future) in a pre-specified occupational field (for example, the nursing care field) based on the "gender," "strengths," and "future dreams" included in the answer, and this information is output to the user.
[0015] The present invention relates to a method performed in a job suggestion system that proposes fictitious occupations to a user, the method comprising: receiving a job suggestion request from the user, causing an existing learning model to generate a question in a predetermined style that asks the user about their gender and areas of expertise; outputting the question generated by the existing learning model to the user and receiving the user's answer to the question; causing the existing learning model to generate information about fictitious occupations in a predetermined occupational field based on the user's gender and areas of expertise included in the user's answer; and outputting the information about fictitious occupations generated by the existing learning model to the user.
[0016] This method, as with the system described above, also receives a job suggestion request from a user. Using an existing learning model (such as GPT), a question asking the user about their "gender" and "strengths" is generated in a pre-specified style (for example, a style that keeps the conversation light and engaging) and output to the user. Upon receiving the user's answer to the question, the existing learning model (such as GPT) is used to generate information about a hypothetical job (a new future job) in a pre-specified occupational field (for example, the nursing care field) based on the "gender" and "strengths" included in the answer, and this information is output to the user. In this way, by using an existing learning model, it is possible to easily suggest a hypothetical job (a new future job) that utilizes the user's strengths in a pre-specified occupational field (for example, the nursing care field).
[0017] The program of the present invention is a program executed in a job suggestion system that suggests fictitious occupations to a user, wherein the program, upon receiving a job suggestion request from the user, causes an existing learning model to generate a question sentence in a predetermined style that asks the user about their gender and strengths; outputs the question sentence generated by the existing learning model to the user and receives the user's answer to the question sentence; causes the existing learning model to generate information about fictitious occupations in a predetermined occupational field based on the user's gender and strengths included in the user's answer; and outputs the information about fictitious occupations generated by the existing learning model to the user.
[0018] Even with this program, similar to the above system, when receiving a career proposal request from a user, using an existing learning model (such as GPT, etc.), a question text for asking the user about "gender" and "what they are good at" is generated in a pre-specified style (such as a style that makes the conversation enjoyable in a bright tone, etc.) and output to the user. When receiving an answer from the user to the question, using an existing learning model (such as GPT, etc.), based on the "gender" and "what they are good at" included in the answer, information about fictional careers (future new careers) in a pre-specified career field (such as the nursing field, etc.) is generated and output to the user. In this way, by using an existing learning model, it is possible to easily propose fictional careers (future new careers) that make use of what the user is good at in a pre-specified career field (such as the nursing field, etc.).
Advantages of the Invention
[0019] According to the present invention, it is possible to easily propose fictional careers that make use of what the user is good at in a pre-specified career field.
Brief Explanation of the Drawings
[0020] [Figure 1] It is a block diagram showing the configuration of the career proposal system in an embodiment of the present invention. [Figure 2] It is a diagram showing an output example from the career proposal system (an example of generating information about fictional careers generated by an existing learning model). [Figure 3] It is a sequence diagram for explaining the operation of the career proposal system in an embodiment of the present invention. Hereinafter, the occupation proposal system according to the embodiment of the present invention will be described with reference to the drawings. In this embodiment, the case of an occupation proposal system used in classes for elementary school students and the like will be exemplified. The occupation proposal system of this embodiment has a function of generating information on fictional occupations using an existing learning model. This function is realized by a program stored in the memory area of the occupation proposal system or the like.
[0022] The configuration of the occupation proposal system according to the embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing the configuration of the occupation proposal system according to this embodiment. As shown in FIG. 1, the occupation proposal system 1 is connected to the user device 2 via a network N such as the Internet. In this embodiment, the occupation proposal system 1 is configured by, for example, a cloud server device. Further, the user device 2 is configured by, for example, a computer device, and includes an input unit 3 such as a keyboard and a mouse, and a display unit 4 such as a display.
[0023] An occupation proposal request from the user is input from the input unit 3 of the user device 2. For example, by clicking the "Create!" button displayed on the display unit 4 of the user device 2, an occupation proposal request from the user is input. The occupation proposal request input to the user device 2 is sent to the occupation proposal system 1.
[0024] The occupation proposal system 1 includes an input unit 5, an output unit 6, a storage unit 7, and a control unit 8. Various information input by the input unit 3 of the user device 2 is input to the input unit 5. Information (information sent to the user device 2) generated by the occupation proposal system 1 is output from the output unit 6. The storage unit 7 stores various information (data) and programs for proposing fictional occupations to the user. The control unit 8 has a function of proposing fictional occupations to the user, and includes a question sentence generation unit 80, a question answer processing unit 81, a fictional occupation generation unit 82, and a user proposal processing unit 83 as functional blocks therefor.
[0025] The question generation unit 80, upon receiving a job suggestion request from a user, has the function of having an existing learning model (such as GPT (Generative Pre-trained Transformer)) generate questions asking the user about their "gender," "strengths," and "future dreams," in a pre-specified style. The pre-specified style includes, but is not limited to, a "style that keeps the conversation going in a cheerful tone."
[0026] More specifically, the question generation unit 80 has the function of generating prompts that cause an existing learning model (e.g., GPT) to generate questions that ask the user about their "gender," "strengths," and "future dreams," while conducting a conversation with a hospitable, fun, and cheerful tone, much like a cast member at an amusement park. The question generation unit 80 also has the function of inputting the generated prompts into the existing learning model (e.g., GPT) and receiving the questions generated by the existing learning model (e.g., GPT) as a response to that input. In this way, the question generation unit 80 uses the existing learning model (e.g., GPT) to generate questions that ask the user about their "gender," "strengths," and "future dreams."
[0027] The question answering processing unit 81 has the function of outputting question sentences generated by an existing learning model (e.g., GPT) to the user. When a question sentence is sent from the job suggestion system 1 to the user device 2, the user device 2 inputs an answer to that question sentence. The question answering processing unit 81 has the function of receiving the answer to the question sentence entered by the user.
[0028] The fictional occupation generation unit 82 has a function to generate information about fictional occupations in a pre-specified occupational field using an existing learning model (e.g., GPT) based on the "gender," "strengths," and "future dreams" included in the user's response. In this case, the fictional occupation generation unit 82 causes the existing learning model (e.g., GPT) to generate the occupation name of the fictional occupation in katakana, and prohibits the inclusion of a katakana expression that is simply a katakana conversion of the occupational field in the katakana expression of the occupation name. In this embodiment, the occupational field is "nursing care," and the inclusion of the katakana expression "care" in the katakana expression of the occupation name is prohibited.
[0029] More specifically, the fictional occupation generation unit 82 has a function to generate prompts that cause an existing learning model (such as GPT) to generate a new occupation in the "nursing care field" by combining the "gender," "strengths," and "future dreams" included in the user's response. Furthermore, the fictional occupation generation unit 82 has a function to generate prompts that cause an existing learning model (such as GPT) to generate a cool and exciting "occupation name (in katakana)" that evokes a sense of the future for the generated new occupation in the "nursing care field." In this case, the inclusion of the katakana expression "care" in the occupation name is prohibited.
[0030] Furthermore, the fictional occupation generation unit 82 has a function to generate prompts that cause an existing learning model (such as GPT) to generate an "explanatory text" that explains, in an appealing way, why the newly generated occupation in the "nursing care field" is a wonderful occupation with social significance. In addition, the fictional occupation generation unit 82 has a function to generate prompts that cause an existing learning model (such as GPT) to generate a "reasoning text" that explains, in an interesting and thorough manner, how the "skills" included in the user's response will be utilized in the newly generated occupation in the "nursing care field".
[0031] Furthermore, the fictional occupation generation unit 82 has a function to generate prompts that cause an existing learning model (such as GPT) to generate images that are characteristic of each occupation and are also surprising, for the newly generated occupations in the "nursing care field". These images are, for example, images of people (people in their 20s) that are included in the "gender" of the user's response.
[0032] The fictional occupation generation unit 82 has the function of inputting the generated prompt into an existing learning model (e.g., GPT) and receiving the "occupation name," "description," "reason statement," and "image" generated by the existing learning model (e.g., GPT) as a response to that input. In this way, the fictional occupation generation unit 82 generates information about fictional occupations ("occupation name," "description," "reason statement," and "image") using the existing learning model (e.g., GPT).
[0033] The user suggestion processing unit 83 has a function to output information on fictional occupations generated by an existing learning model (e.g., GPT) to the user device 2. When the information on fictional occupations generated by an existing learning model (e.g., GPT) is sent from the occupation suggestion system 1 to the user device 2, it is displayed on the display unit 4 of the user device 2.
[0034] Figure 2 shows an example of generating information about a fictional occupation using an existing learning model (e.g., GPT). As shown in Figure 2, the information about a fictional occupation includes the "occupation name," "description," "reason statement," and "image."
[0035] When generating information for a fictional occupation in the "caregiving field," if the user's response includes "male" for "gender," "talent" for "drawing train route maps," and "future dream" for "train driver," the "occupation name" generated by an existing learning model (e.g., GPT) might be something like "train navigator." In this case, the "description" generated by an existing learning model (e.g., GPT) might be something like, "Train navigators provide train driving simulations and brain exercises using route maps in elderly care facilities. They teach seniors the joy of driving using train driving simulators and improve cognitive function with games using route maps. This brings joy to elderly people who love trains and increases their daily enjoyment." Furthermore, "reason statements" generated by existing learning models (such as GPT) might include phrases like, "The reason Train Navigator is needed is to provide seniors with new hobbies and stimulation. Train driving simulations allow seniors to experience the thrill and enjoyment of driving, and route map games help activate the brain. You can use your passion for trains and route map drawing skills to help seniors discover new forms of entertainment."
[0036] Furthermore, if the user's response includes "male" for "gender," "history" for "areas of expertise," and "future dream" for "to live a comfortable life," the "job title" generated by an existing learning model (e.g., GPT) might be something like "History Comfort Guide." In this case, the "explanatory text" generated by an existing learning model (e.g., GPT) might be something like, "For someone like you who is good at history and wants to live a comfortable life, there is a job called History Comfort Guide. This job involves supporting the comfortable lives of the elderly in nursing homes by telling them history stories. You can use your knowledge of history to provide a pleasant environment while making the elderly enjoy themselves." Also, the "reasoning text" generated by an existing learning model (e.g., GPT) might be something like, "Being a History Comfort Guide is an important job that enriches the hearts of the elderly and supports their comfortable lives. Your knowledge of history will allow the elderly to enjoy interesting stories and provide a comfortable environment, enabling them to live more relaxed lives. This unique combination is what energizes everyone."
[0037] The operation of the job suggestion system 1, configured as described above, will be explained with reference to the sequence diagram in Figure 3.
[0038] When proposing a fictional occupation (a new occupation of the future) using the occupation suggestion system 1 of this embodiment, the first operation performed is to click the "Create!" button on the user device 2 (S1). Then, an occupation suggestion request is sent from the user device 2 to the occupation suggestion system 1 (S2).
[0039] When the job suggestion system 1 receives a job suggestion request, it causes an existing learning model (e.g., GPT) to generate a question sentence in a pre-specified style that asks the user about their "gender," "strengths," and "future dreams." Specifically, the job suggestion system 1 generates a prompt (S3) that causes the existing learning model (e.g., GPT) to generate a question sentence that asks the user about their "gender," "strengths," and "future dreams," inputs the generated prompt into the existing learning model (e.g., GPT), and receives the question sentence generated by the existing learning model (e.g., GPT) as a response to that input (S4).
[0040] The job suggestion system 1 sends a question generated by an existing learning model (e.g., GPT) to the user (S5). The display unit 4 of the user device 2 displays the question received from the job suggestion system 1 (S6), and the user input unit 3 of the user device 2 inputs the answer to that question (S7). The input answer is sent from the user device 2 to the job suggestion system 1 (S8).
[0041] When the job suggestion system 1 receives a response from the user device 2, it causes an existing learning model (e.g., GPT) to generate information about a fictional job in a pre-specified occupational field based on the "gender," "strengths," and "future dreams" included in the response. Specifically, the job suggestion system 1 generates a prompt (S9) that causes the existing learning model (e.g., GPT) to generate a new job in the "nursing care field" by combining the "gender," "strengths," and "future dreams" included in the user's response. The generated prompt is input into the existing learning model (e.g., GPT), and in response to that input, the system receives information about the fictional job ("job name," "description," "reason," and "image") generated by the existing learning model (e.g., GPT) (S10).
[0042] Information about a fictional occupation ("occupation name," "description," "reason statement," and "image") generated by an existing learning model (e.g., GPT) is transmitted from the occupation suggestion system 1 to the user device 2 (S11) and displayed on the display unit 4 of the user device 2 (S12). In this way, a fictional occupation (a new occupation for the future) is suggested.
[0043] According to this embodiment of the occupation suggestion system 1, upon receiving an occupation suggestion request from a user, a question asking the user about their "gender," "strengths," and "future dreams" is generated using an existing learning model (e.g., GPT), in a pre-specified style (e.g., "a style that keeps the conversation going in a cheerful tone"), and output to the user. The "style that keeps the conversation going in a cheerful tone" is suitable for children, such as elementary school students.
[0044] In this embodiment, when the system receives an answer to a question from the user, it uses an existing learning model (such as GPT) to generate information about a fictional occupation (a new future occupation) in a pre-specified occupational field (such as the nursing care field) based on the "gender," "strengths," and "future dreams" included in the answer, and outputs this information to the user.
[0045] Thus, according to the occupation suggestion system 1 of this embodiment, by using an existing learning model (such as GPT), it is possible to easily suggest a fictional occupation (a new occupation of the future) that utilizes the user's strengths in a pre-specified occupational field (such as the nursing care field).
[0046] Furthermore, in this embodiment, since the job titles of fictional occupations in the "nursing care field" are generated in katakana, it is possible to give users a "futuristic and cool impression" of those occupations (fictional occupations). In this case, the inclusion of the katakana expression "care," which is simply a katakana conversion of the occupation field, is prohibited in the katakana expression of the job titles in the "nursing care field," thus preventing the generation of similar job titles and increasing the variety of generated job titles.
[0047] Although embodiments of the present invention have been described above by example, the scope of the present invention is not limited to these, and modifications and alterations can be made within the scope described in the claims depending on the purpose.
[0048] For example, the above description described the case where the predetermined occupational field is the "nursing care field," but the present invention is not limited to this and can be similarly implemented in other occupational fields (for example, the "agriculture field" or the "construction work field").
[0049] Furthermore, while the above explanation described an example where information about a fictional occupation is generated based on "gender," "strengths," and "future dreams," "future dreams" are not necessarily required. According to the present invention, it is also possible to generate information about a fictional occupation based on "gender" and "strengths."
[0050] Furthermore, although the above explanation described an example in which the question generation unit 80 and the fictional occupation generation unit 82 are implemented as separate functions, the question generation unit 80 and the fictional occupation generation unit 82 may also be implemented together as a single function (for example, "Question / Fictional Occupation Generation Unit"). [Industrial applicability]
[0051] As described above, the occupation suggestion system according to the present invention has the effect of easily suggesting a fictional occupation (a new occupation of the future) that utilizes the user's strengths in a pre-specified occupational field (for example, the nursing care field), and is useful for use in lessons for elementary school students, etc. [Explanation of symbols]
[0052] 1. Career Suggestion System 2. User devices 3. Input section 4 Display 5 Input section 6 Output section 7 Memory section 8 Control Unit 80 Question generation section 81 Question Answering Processing Section 82 Fictional Occupation Generation Department 83 User Proposal Processing Unit
Claims
1. This is a job suggestion system that proposes fictional occupations to users. Upon receiving a job suggestion request from the user, the system includes a question generation unit that uses an existing learning model to generate question sentences in a pre-specified style that ask the user about their gender and areas of expertise, A question answering processing unit that outputs a question sentence generated by the existing learning model to the user and receives an answer to the question sentence entered by the user, A fictional occupation generation unit causes the existing learning model to generate information about fictional occupations in a pre-specified occupational field based on the user's gender and areas of expertise included in the user's response, A user suggestion processing unit that outputs information about fictional occupations generated by the aforementioned existing learning model to the user, A job suggestion system equipped with the following features.
2. The fictional occupation generation unit uses the existing learning model, The occupation suggestion system according to claim 1, which generates a katakana representation of the occupation name of the fictitious occupation, and prohibits including a katakana representation of the occupation field that is simply converted into katakana in the katakana representation of the occupation name.
3. The occupational suggestion system according to claim 2, wherein the occupational field is the nursing care field, and the inclusion of the katakana expression "care" in the katakana expression of the occupational name is prohibited.
4. When the question generation unit receives a job suggestion request from the user, it causes the existing learning model to generate a question asking the user about their gender, strengths, and future dreams, in the pre-specified style. The occupation suggestion system according to claim 1, wherein the fictional occupation generation unit causes the existing learning model to generate information on fictional occupations in the pre-specified occupational field based on the user's gender, strengths, and future dreams included in the user's response.
5. A method implemented in a job suggestion system that proposes fictional occupations to users, The aforementioned method, Upon receiving a job suggestion request from the user, the existing learning model is instructed to generate a question asking the user about their gender and areas of expertise, using a pre-specified writing style. The steps include outputting a question sentence generated by the existing learning model to the user and receiving an answer to the question sentence entered by the user, The steps include: causing the existing learning model to generate information about a fictitious occupation in a pre-specified occupational field based on the user's gender and areas of expertise included in the user's response; The steps include outputting information about fictional occupations generated by the existing learning model to the user, Methods that include...
6. A program that runs in a job suggestion system that proposes fictional occupations to users, The aforementioned program is installed on the computer of the job suggestion system. Upon receiving a job suggestion request from the user, the existing learning model is instructed to generate a question asking the user about their gender and areas of expertise, using a pre-specified writing style. The process includes outputting a question sentence generated by the existing learning model to the user and receiving the user's answer to the question sentence, Based on the user's gender and areas of expertise included in the user's response, the existing learning model is instructed to generate information about a fictional occupation in a pre-specified occupational field. The process involves outputting information about fictional occupations generated by the aforementioned existing learning model to the user, A program that executes something.