JP7293304B2 - Information processing device, information processing method and program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and a program that allow users to recognize their own strengths.

Patent Literature 1 mentions a problem in the prior art that although fans can pay sponsorship money to athletes, individual athletes cannot directly receive the sponsorship money. In Patent Document 1, a user management data storage unit that stores the amount of first value held by each user, a player management data storage unit that stores the amount of first value held by each player, and a player management data storage unit that stores the amount of first value held by each player, an updating unit that updates the amount of the first value held by the user based on the amount of the first value obtained by converting the amount of the second value; a value management unit that transfers at least part of the designated amount from the user's first value holding amount to a specific player's holding amount of the first value when receiving a request to transfer to the player; a determination unit that determines the amount of second value that can be received by a transferee designated for each player based on the amount of one value held and a coefficient determined for each player. is proposed.

Japanese Patent Application Laid-Open No. 2020-155023

In Patent Document 1, the approach is such that the individual athlete directly receives the sponsorship money. In response to this, the present invention provides an information processing apparatus and the like that can make a user recognize his or her own strengths when selecting a second career as an example. However, it should be noted that the present invention is not limited to users considering a second carrier.

An information processing device according to the present invention includes:
a reception unit that receives learning information or experience information of the user input from the input unit;
a determination unit that determines a user's strengths by applying learning information or experience information to the model;
an output unit that outputs the user's strengths;
may be provided.

In the information processing device according to the present invention,
The decision unit may derive multiple strengths about the user.

In the information processing device according to the present invention,
The reception unit receives the user's weaknesses input from the input unit,
Equipped with an association unit that associates weaknesses with strengths,
The output unit may output strengths associated with weaknesses.

In the information processing device according to the present invention,
Learning information or experiential information may include information from school days.

An information processing device according to the present invention includes:
a question unit that asks a plurality of questions to the user;
a creation unit that creates a user's autobiography from answers to questions;
with
The output unit may output an autobiography.

An information processing device according to the present invention includes:
A question part for asking a plurality of questions to the user,
The interrogator may query positive and negative elements for each predetermined time category.

An information processing device according to the present invention includes:
A question part for asking a plurality of questions to the user,
The judging section judges whether or not there is learning from the answers to the questions,
The questioning unit may ask a plurality of questions related to the content judged to be learned by the judging unit to acquire learning information or experience information.

An information processing device according to the present invention includes:
a comparison unit that compares the user's target carrier information and the user's strengths;
a selection unit that selects learning content to be recommended based on the result of comparison by the comparison unit;
may be provided.

An information processing device according to the present invention includes:
Equipped with a storage unit that stores changes in the user's strengths,
The output unit may output the transition of the user's strengths.

In the information processing device according to the present invention,
The determination unit may determine the strength for each time category of the personal history.

The information processing method according to the present invention comprises:
a step of receiving learning information or experience information of the user input from the input unit by the receiving unit;
determining the user's strengths by applying learned or experiential information to the model;
a step of outputting the user's strengths by an output unit;
may be provided.

A program according to the present invention comprises:
A program to be installed in an information processing device,
The information processing device on which the program is installed,
a reception function that receives the user's learning information or experience information input from the input unit;
A judgment function that judges the user's strengths by applying learning information or experience information to the model;
an output function that outputs the user's strengths;
may be provided.

ADVANTAGE OF THE INVENTION According to this invention, the information processing apparatus etc. which can make a user recognize one's strength can be provided.

FIG. 1 is a schematic diagram showing the configuration of an information processing apparatus according to an embodiment of the present invention. FIG. 2 is a diagram showing an example of information flow in the embodiment of the present invention. FIG. 3 is a diagram showing the concept of question contents according to time, category, and plus/minus difference in the embodiment of the present invention. FIG. 4 is a diagram showing an example of question content in the embodiment of the present invention. FIG. 5 is a diagram showing another example of question content in the embodiment of the present invention. FIG. 6 is a diagram showing still another example of question content in the embodiment of the present invention. FIG. 7 is a flow for explaining a mode of initial login according to the embodiment of the present invention. FIG. 8 is a flow for explaining aspects of the second and subsequent logins according to the embodiment of the present invention. FIG. 9 is a diagram showing an example of "history" displayed on the display unit in the embodiment of the present invention. FIG. 10 is a diagram showing an example of strength classification that can be used in the embodiment of the present invention.

Embodiments of an information processing apparatus and an information processing method according to the present invention will be described below. The present embodiment also provides a program that, when installed in a computer such as a personal computer, enables the computer to execute the information processing method of the present embodiment, and a recording medium that records the program.

The information processing apparatus of the present embodiment is, for example, a server, and may be installed in any location, and a cloud environment may be used. The information processing apparatus according to the present embodiment may be composed of one device or may be composed of a plurality of devices. Further, when the information processing apparatus 1 is composed of a plurality of devices, each device does not need to be installed in the same space such as the same room, and may be installed in different rooms, different buildings, different regions, or the like.

The information processing apparatus of this embodiment is generated by installing a program, for example. This program may be delivered by e-mail, may be obtained by logging in after accessing a predetermined URL, or may be recorded on a recording medium. A program according to this embodiment is used to generate an information processing apparatus described below, and a recording medium according to this embodiment is used to record the program. Further, the information processing method of this embodiment is carried out by an information processing apparatus in which the above program is installed.

As shown in FIG. 1, the information processing apparatus 1 of the present embodiment includes a reception unit 10 that receives learning information or experience information of a user input from an input unit 120 of a user terminal 100, and a You may have the judgment part 20 which judges a user's strength by applying to a model, and the output part 90 which outputs a user's strength.

The information processing device 1 may have a communication unit 5 capable of communicating with the user terminal 100 . The communication unit 5 may communicate with the user terminal 100 multiple times (including transmission/reception and writing to the server) so that the reception unit 10 receives multiple pieces of information from the user. The information processing device 1 may have a storage unit 60 that stores various information.

The user terminal 100 may be a smart phone, a tablet terminal, a PC, or the like. When the user terminal 100 is a smartphone, a tablet terminal, or the like, the touch panel screen has the functions of both the display unit 110 and the input unit 120, and functions as an input display unit. Access to the information processing apparatus 1 from the user terminal 100 may be performed by reading a QR code (registered trademark) by the user terminal 100 such as a smartphone.

The determination unit 20 has an artificial intelligence function, and may generate a determination model by performing machine learning using learning information. In this case, the determination unit 20 may determine the adoption variables (elements) to be used and their coefficients (weights) by machine learning technology so that the probability of the target event occurring is most likely from past performance data. good. Various models can be used in machine learning, for example, a tree model or other models may be used.

Information based on past cases may be used as learning information. For example, a user's learning information and experience information may be used as input information, and the user's strengths determined in the past by career consultants may be used as output information, and machine learning may be performed to generate a determination model. The generated judgment model may be stored in the storage unit 60 . Also, a judgment model prepared in advance may be stored in the storage unit 60 .

The determination unit 20 may derive one strength for each user, or may derive a plurality of strengths. For example, 3 to 5 strengths may be derived for the user, and the output unit 90 may output the results. By deriving a plurality of strengths in this way, it is useful in that the strengths of the user can be grasped from a plurality of viewpoints. Information output by the output unit 90 is displayed on the display unit 110 of the user terminal 100 . The determination unit 20 may derive a plurality of strengths by calculating an evaluation value for each strength element prepared in advance and selecting a plurality of strength elements in descending order of evaluation values.

The accepting unit 10 may accept the user's weaknesses input from the input unit 120 . The information processing device 1 may have an associating unit 70 that associates the input weaknesses with the user's strengths. Then, the output unit 90 may output the strengths associated with the weaknesses by the association unit 70 . By associating weaknesses with strengths in this way, weaknesses can be converted into strengths (see FIG. 5). In other words, by outputting as a strength the user's characteristic that the user has recognized as a weakness, the user can change his/her own view. The associating unit 70 may have an artificial intelligence function, or may associate weaknesses with strengths by using an association model generated in advance. Information based on past cases may also be used as learning information when an association model is generated by an artificial intelligence function. For example, machine learning may be performed to generate an association model using information about weaknesses perceived by the user as input information and strengths that career consultants have linked to the weaknesses in the past as output information.

Based on the user's answer input from the input unit 120, the determination unit 20 may determine the weakness of the user. Also in this case, the user's weaknesses may be determined by applying the user's learning information or experience information to the determination model. A method of generating a judgment model for weaknesses can employ the same mode as described for strengths.

Learning information or experience information may include information during school days, information after graduation, information after becoming a member of society, and the like. The information about student days may include information about elementary school days, information about junior high school days, information about high school days, information about college days, and the like (see FIG. 3).

The information processing apparatus 1 may have a questioning unit 30 that asks a plurality of questions to the user, and a creating unit 80 that creates the user's personal history from answers to the questions. Questions from the question unit 30 and answers from users may be provided in a chatbot format. However, it is not limited to such a mode, and answers to questions may be input in the form of answering questionnaires from a PC. An example of an autobiography is shown in FIG.

When the chatbot format is adopted, information from the user is collected by repeating questions to the user and answers from the user multiple times. At this time, the information required to create the user's personal history may be collected, and the information related to strengths may be dug deeper to obtain more in-depth information. The number of repetitions of questions and answers is not particularly limited, but is about 50 to 200 times as an example. The output format of the personal history output unit 90 is not particularly limited, but as an example, it may be in a format that can be shown to others, for example, it may be output in a format that can be submitted as part of a resume. . Adopting such a mode is advantageous in that it is possible to provide personal histories in job hunting, for example.

For the content of questions in the chatbot format, question content (conversation know-how) given by career consultants may be used as learning information, and a question model generated by machine learning may be used. As the information used as the learning information, a plurality of questions asked by the career consultant in the past and the user's answers thereto may be used. As an example, the question section 30 may perform machine learning using a plurality of questions as input information and answers to the questions as output information. In addition, a question model may be generated by storing the user's actual answers to questions from the question unit 30 in the storage unit 60, and performing machine learning by the question unit 30 using combinations of questions and answers. , the question model may be generated by using the question and the answer to the question as input information and the next question actually asked by the career consultant in the past as output information. The generated question model may be stored in the storage unit 60 . Further, a question model prepared in advance may be stored in the storage unit 60 . The question unit 30 may ask questions according to a scenario, and the storage unit 60 may store answer pattern examples when the scenario branches according to an answer from the user. In this case, the question may be changed according to the user's answer, and the user's strengths may be learned while creating the user's personal history.

The questioning unit 30 selects a predetermined number (for example, 5 to 10) of important events/episodes for in-depth questions from among the events/episodes in the user's personal history, and focuses on the selected events. You can ask questions. By asking questions about events and episodes flatly, it is possible to prevent the omission of important events and episodes that the person is not aware of when diagnosing their strengths.

The questioning unit 30 may evaluate the value of the events heard from the user as learning information, select a predetermined number of events in descending order of value, and ask questions intensively. An answer may be evaluated by applying it to a question model. The question model may be generated by using, as learning information, evaluations (values as learning information) of a plurality of answers given by a career consultant in the past. As an example, the question section 30 may perform machine learning using an answer from the user as input information and an evaluation of the answer (value as learning information) as output information. In addition, the question unit 30 asks the user whether or not he/she learned something about the event/episode, and if the user answers that he or she has learned something, asks the user an in-depth question about the event/episode (multiple questions). may be performed).

For example, as shown in Fig. 4, questions to be asked when digging deeper include, "Please tell me the details of the items answered as '...' in XX," and "How are you doing at that time?" Did you feel that?”, “You answered that the event has led you to where you are now. You may ask. As for the answer to the question, the option "I don't know" may be prepared. If the user selects the option "I don't know", the question may be skipped and the next item shown in FIG. 4 may be asked again.

Based on the answers thus obtained, the determination unit 20 functioning as a strengths analysis engine may guess the strengths. In this case, the strength information of the user may be acquired by applying the answer obtained by the determination unit 20 to the determination model. It should be noted that if there is no answer when digging deep, the user may be prompted to input the strengths that the user considers. In this case, the output unit 90 may output the personal history, and the user may determine the strength after viewing the personal history.

The storage unit 60 may store a plurality of strength elements constituting strengths, descriptions of strengths, and the like. The determination unit 20 may evaluate the value of each strength element based on the user's response, and determine that the strength element with the high evaluation value is the strength of the user. As an example, the determination unit 20 may determine strengths by performing natural language processing. A vector derived by creating a vector of words included in the answers from the user and adding each vector of the answers regarding strengths. It is also possible to determine what the user's strengths are based on the strength elements closest to , or a combination of a predetermined number of strength elements selected in order of closestness. A description of strengths may be prepared for each of the positive and negative histories. In addition, the description of the strengths may include, for example, how the corresponding strengths can be used after employment. Moreover, from the viewpoint of facilitating identification by AI, each strength element may be MECE (Mutually Exclusive Collectively Exhaustive). However, the present invention is not limited to this, and each strength element may overlap. Further, the determination unit 20 may perform natural language processing using Watson (registered trademark) provided by IBM (registered trademark) or the like. It should be noted that weaknesses may also be determined in the same way, and the determination unit 20 may determine weaknesses by performing natural language processing. It is also possible to determine what the user's weakness is from the combination of the weakness element closest to the vector derived by adding each vector or the combination of a predetermined number of weakness elements selected from the closest order. Also, as an example, 1000 or more strength concepts that define strengths may be prepared and stored in the storage unit 60 . Then, after performing natural language processing on the answers input by the user, it reclassifies them into a plurality of corresponding strength concepts, and combines or weights the corresponding strength concepts (the weight applied to the strength concepts is determined in advance). may be input by the user.), the determining unit 20 may determine the strength of the user. Similarly, 1,000 or more weak concepts may be prepared as an example, and natural language processing is performed on the answers input by the user, and then reclassified into a plurality of corresponding weak concepts. The determination unit 20 may determine the strength of

Strengths are the qualities of wanting to do or achieve something (executive ability), the qualities of wanting to influence people (influence), the qualities of fostering relationships with people (human relationship building ability), and the ability to deal with information and situations. It may include multiple elements divided into categories such as analytic qualities (strategic thinking). Execution ability may include strength elements such as desire for achievement, arrangement, conviction, fairness, prudence, discipline, goal orientation, sense of responsibility, and recovery orientation. Influence may include strength elements such as directiveness, communication, competitiveness, optimism, self-confirmation, ego, sociability, and activeness. Relationship-building abilities may include strengths factors such as adaptability, destiny orientation, empathy, harmony, inclusion, individualization, positivity, and intimacy. Strategic thinking may include strengths such as analysis orientation, origin orientation, future orientation, ideas, collectivity, introspection, desire to learn, and strategic nature.

In addition, as elements of strengths, there are “reason” and “sensitivity” as “types of abilities to emphasize” (horizontal axis), and “change” and “adaptation” as “response to external environment” (vertical axis). Strengths may be categorized along these axes (see FIG. 10).

The output unit 90 may output the strength obtained by the determination unit 20 to request confirmation from the user (see FIG. 5). If the user gives a negative answer to the output strengths, the user may be prompted to input the strengths that the user considers (see FIG. 6). Also at this time, the output unit 90 may output the personal history, and the user may determine the strength after viewing the personal history. Also, strengths associated with the user's weaknesses (strengths converted from weaknesses) may be output (see FIG. 5).

The user information may be collected by asking questions from the question section 30, or may be collected by the user's input according to a format prepared in advance. The user information may include gender, age, date of birth, educational background, work history, and the like. If the user is an athlete, his/her competition history/activity history, activity start time, activity end time, etc. may be collected as user information. Also, a nickname may be input as the user information, and in this case, operations on the information processing apparatus 1 may be performed using the nickname. A tutorial function on basic usage may be provided, and in this case, users can be expected to become familiar with how to use the chatbot.

The personal history created by the creating unit 80 may be output together with the strengths (see FIG. 9). By outputting strengths together with personal histories in this way, the user can comprehend the reasons for being judged as strengths, making it easier to understand the reasons. It is also beneficial in that it enables you to clearly state the reasons for your own strengths when, for example, finding a job or changing jobs. The user may check his/her own history and strengths, and use the results to conduct mentoring such as counseling with a third party (see FIG. 2). Then, the result of the interview with the mentoring may be stored in the storage unit 60 and used as information for machine learning. Also, as shown in FIG. 9, personal histories may be output together with not only strengths but also weaknesses. This weakness may be a weakness input by the user himself or may be a weakness determined by the determination unit 20 . It should be noted that the user may input strengths that he/she considers himself/herself. In this case, it should be noted that the strength determined and output by the determination unit 20 may result in the same content as the strength input by the user himself/herself.

The questioning unit 30 may ask about positive and negative factors for each predetermined time category. Alternatively, instead of asking questions, the user may input positive and negative factors for each predetermined time category. Each predetermined time category means each era such as elementary school, junior high school, high school, and college. Also, a plurality of time categories may be grouped together, for example, elementary school age and junior high school age may be grouped together as elementary and junior high school age. Examples of positive elements (plus history) include feeling joy, achievement, challenges, successful experiences, hard work, and good encounters. Negative elements (negative history) include, for example, feelings of sadness, frustration, suffering, failure experiences, dislikes, painful experiences, and the like. As for the questions in the question section 30, when the user looks back on the content of his or her experience, the user may be asked if there is anything that is connected to the present or if there is anything that has been learned. In addition, questions may be asked or input may be prompted about positive and negative elements in club activities.

Questions (typically, questions about positive factors and negative factors) from the question section 30 may be divided into categories. For example, categories related to learning such as studies, qualifications, and examinations; categories related to extracurricular activities such as extracurricular activities, lessons, and volunteer activities; categories related to work and part-time jobs; It may be performed by dividing the categories related to the actions taken toward the dream (see FIG. 3). Moreover, after dividing into such categories, the user may input positive elements and negative elements for each category.

The determination unit 20 may determine the strength for each time category of personal history (see FIG. 9). For example, based on the learning information or experience information in each of elementary school days, junior high school days, high school days, and university days, the strengths determined by the determination part 20 are associated with the learning information or experience information that is the basis, and the output part 90 may be output.

The determination unit 20 may determine the presence or absence of learning from the answers to the questions. The questioning unit 30 may ask a plurality of questions related to the content determined by the determining unit 20 as learning to acquire learning information or experience information. By asking a plurality of questions in relation to the content determined to be learned in this way, it is beneficial in that it is possible to dig deeper and acquire learned information. The judgment model used by the judging section 20 may be used to judge the presence or absence of learning. In other words, the determination unit 20 may determine the presence or absence of learning by applying the answers to the questions to the determination model. For example, the determination unit 20 may perform machine learning using, as learning information, information determined by a career consultant as learning based on learning information or experience information of the user.

Also in this case, the judgment model is not limited to the aspect in which it is generated by machine learning. Judgment may be made on the content, the content of weaknesses, the presence or absence of learning, and so on.

The information processing apparatus 1 includes a comparison unit 40 that compares user's target career information (career path) with the user's strengths, and a selection unit 45 that receives the comparison result of the comparison unit 40 and selects recommended study content. , may have The carrier information may be input from the input unit 120 of the user terminal 100 by the user. Career information may be specific occupations and positions in occupations. Further, the career information may be a job type of a specific company. Candidate study contents are stored in the storage unit 60, and the selection unit 45 may select study contents for imparting necessary strengths to target career information from among a plurality of candidate study contents. Alternatively, the learning content may be selected by the selection unit 45 automatically searching on the WEB. As an example, assuming that career information (career path) targeted by the user has a strength A required, the selection unit 45 may read learning content for compensating for the strength A from the storage unit 60. The above search may be performed automatically. There are various levels of learning content, ranging from low-specialty general learning content to highly-specialized learning content.

The selection unit 45 has an artificial intelligence function, and may generate a selection model by performing machine learning using learning information. Information based on past cases may be used as learning information. For example, data (past data) on services and efforts actually advanced by a career consultant who has seen personal history data may be used as learning information. As an example, the selection unit 45 may perform machine learning using personal history data as input information and learning content such as services and efforts actually advanced as output information. The selection model may retrieve data on other users who have similar careers to the user and utilize it as a role model. Whether or not a user has a similar carrier may be determined by the selection unit 45 comparing the user information of the target user and the user information of a plurality of other users. When the user is an athlete, the selection unit 45 may match the user with the reference user by using the content of the competition, the position in the competition, the educational background, and the like. As an example, the selection unit 45 selects learning content learned by socially successful users who are similar in competition content, position in the competition, educational background, etc. good too.

When the selection unit 45 adopts a mode in which learning contents are provided, the user can grasp what he/she needs to learn to obtain the necessary strengths, and the user can obtain the necessary strengths without the intervention of a career consultant. It is beneficial in that it can automatically propose initiatives to promote growth.

Changes in strengths of individual users may be stored in the storage unit 60 and output by the output unit 90 . The user may read out the transition of his/her strength from the storage unit 60 and check it. By adopting such a mode, it becomes possible to confirm the transition (growth) of the user's strengths based on new information such as learning information from learning content or experience information. Therefore, the user can easily recognize the degree of growth and status of the user. Statistical models may be used to evaluate user growth.

In order for the user to easily access the information processing apparatus 1, the information processing apparatus 1 functions as a mentor who keeps close to the user, such as a chat function for casual conversation, a function for estimating the user's intention emotion and counseling, etc. may have Such a function may be realized by the question section 30, for example. In order to implement the chat function, the storage unit 60 may store conversation response example sentence data. The questioning section 30 may determine the intended emotion (emotional value) of the user, and the questioning section 30 may determine the counseling action from the emotional value.

In order to realize the function as a mentor, the question section 30 may generate a mentor model by performing machine learning using learning information. For generation of the mentor model, the career consultant may use, as learning information, chats with a plurality of users in the past and content of counseling, and the mentor model may be generated by machine learning.

The storage unit 60 stores a plurality of pieces of user information, and the user information of each user may be managed and stored in association with identification information such as a user ID. By entering the user ID and password on the login screen, the user can read the user information associated with the user, and can check information such as personal history, strengths, weaknesses, and transitions of strengths and weaknesses. good too. When the recommended learning content is used, it may be automatically stored in the storage unit 60 as learning information or experience information. By doing so, the user information may be updated.

The user is not particularly limited, but examples include athletes, entertainers, and artists. Taking an athlete as an example, it may be difficult to develop a career after retiring as an athlete. According to this aspect, it is possible to convey one's own strengths to such athletes, which can be useful in forming a second career.

An example of an information processing method by the information processing apparatus 1 according to this embodiment will be described with reference to FIGS. 7 and 8. FIG.

First, the user accesses the information processing apparatus 1 from the user terminal 100, inputs user information and a password, and logs in (see S1 and S2 in FIG. 7).

When the user logs in in this way, the screen transitions to a chat screen, and the chat screen is displayed on the display unit 110 of the user terminal 100 (see S3 and S4 in FIG. 7 and FIGS. 4 to 6). At this time, the context for the first call is read from the storage unit 60, and the bot API (Application Programming Interface) is read (see S10 and S11 in FIG. 7). Then, the question from the question section 30 is displayed on the display section 110 of the user terminal 100 as an utterance by the bot (see S20 in FIG. 7).

At this time, after the log is saved in the storage unit 60 such as a database, the user inputs an answer from the input unit 120, the bot API is read, and the question from the question unit 30 regarding the answer is made again. (See S21 to S24 in FIG. 7).

After that, the above contents are repeated.

In the second and subsequent logins, instead of the above context for the first call, the context at the time of the previous termination is read, and the conversation screen showing the contents of the conversation so far is restored (S31 in FIG. 8). and S32). After that, the steps are the same as those described above (see S33 to S44 in FIG. 8).

Note that each member such as the reception unit 10, the output unit 90, the comparison unit 40, the selection unit 45, the determination unit 20, the question unit 30, the association unit 70, the creation unit 80, etc. of the present embodiment includes one or a plurality of IC It may be implemented by a chip, an electronic module, or the like, or may be implemented by a circuit configuration.

The above description of the embodiment and the disclosure of the drawings are only examples for explaining the invention described in the scope of claims, and the description of the embodiment and the disclosure of the drawings described above constitute the scope of the claims. The claimed invention is not limited.

Various models can be used in the machine learning of this embodiment. When machine learning is performed, past performance may typically be used, and a model is generated using past performance data as learning information. Appropriate output can then be obtained by applying this model to the information of the target user or information obtained from the user.

1 information processing device 10 reception unit 20 determination unit 30 question unit 40 comparison unit 45 selection unit 60 storage unit 70 association unit 80 creation unit 90 output unit 120 input unit

Claims (12)

a reception unit that receives learning information and experience information of the user input from the input unit;
a determination unit that determines a user's strengths by applying learning information and experience information to a model;
an output unit that outputs the user's strengths;
with
The information processing device , wherein the learning information and the experience information include information from school days . a user's learning information or experience information input from the input unit, and a reception unit that receives the user's weaknesses;
a determination unit that determines a user's strengths by applying learning information or experience information to the model;
an association unit that associates weaknesses with strengths;
an output unit that outputs the strengths of the user determined by the determination unit and the strengths associated with the weaknesses;
An information processing device. a reception unit that receives learning information or experience information of the user input from the input unit;
a determination unit that determines a user's strengths by applying learning information or experience information to the model;
an output unit that outputs the user's strengths;
a question unit that asks a plurality of questions to the user;
a creation unit that creates a user's autobiography from answers to questions;
with
The output unit is an information processing device that outputs personal histories. a reception unit that receives learning information or experience information of the user input from the input unit;
a determination unit that determines a user's strengths by applying learning information or experience information to the model;
an output unit that outputs the user's strengths;
a question unit that asks a plurality of questions to the user ;
with
The inquiry unit is an information processing device that asks about positive elements and negative elements for each predetermined time category. a reception unit that receives learning information or experience information of the user input from the input unit;
a determination unit that determines a user's strengths by applying learning information or experience information to the model;
an output unit that outputs the user's strengths;
a question unit that asks a plurality of questions to the user ;
with
The judging section judges whether or not there is learning from the answers to the questions,
The information processing device, wherein the questioning unit asks a plurality of questions related to the content judged to be learned by the judging unit to obtain learning information or experience information . a reception unit that receives learning information or experience information of the user input from the input unit;
a determination unit that determines a user's strengths by applying learning information or experience information to the model;
an output unit that outputs the user's strengths;
a comparison unit that compares the user's target carrier information and the user's strengths;
a selection unit that selects learning content to be recommended based on the result of comparison by the comparison unit;
An information processing device. a reception unit that receives learning information or experience information of the user input from the input unit;
a determination unit that determines a user's strengths by applying learning information or experience information to the model;
an output unit that outputs the user's strengths;
a storage unit that stores changes in the user's strengths ;
with
The output unit is an information processing device that outputs changes in user's strengths. a reception unit that receives learning information or experience information of the user input from the input unit;
a determination unit that determines a user's strengths by applying learning information or experience information to the model;
an output unit that outputs the user's strengths;
with
The judgment unit is an information processing device that judges strengths for each time category of personal history. The information processing apparatus according to any one of claims 1 to 8 , wherein the determination unit derives a plurality of strengths regarding the user. 10. The information processing apparatus according to any one of claims 2 to 9 , wherein the learning information or experience information includes information from school days. a step of receiving learning information and experience information of the user input from the input unit by the receiving unit;
a judgment unit judging the user's strengths by applying learning information and experience information to the model;
a step of outputting the user's strengths by an output unit;
with
The information processing method , wherein the learning information and the experience information include information from school days . A program to be installed in an information processing device,
Information processing equipment installed with the program
a reception function that receives the user's learning information and experience information input from the input unit;
A judgment function that judges the user's strengths by applying learning information and experience information to the model;
an output function that outputs the user's strengths;
with
The program , wherein the learning information and the experiential information include information from school days .

Images