Information processing apparatus, information processing method, and program

Abstract

To support the utilization of training by business.SOLUTION: An information processor includes an acquisition part for acquiring input information from an employee, an extraction part for extracting learning contents of the employee in training on the basis of the input information, and an output part for outputting coaching card information on the basis of the information extracted by the extraction part.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] Patent Document 1 discloses a technology for maintaining a user's motivation. In Patent Document 1, goal information including a goal to be achieved by the user is set based on initial setting information including information about the user, and a comment is generated in response to the user's response to the goal information. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2023-136508 Summary of the Invention [Problem to be solved by the invention]

[0004] However, Patent Document 1 does not consider, for example, how to utilize training for employees for the purpose of developing human resources within a company in their actual work.

[0005] In view of the above-mentioned problems, an object of the present disclosure is to provide a technology that can support better utilization of training in work. [Means for solving the problem]

[0006] In a first aspect of the present disclosure, an information processing device is provided that has an acquisition unit that acquires input information from an employee, an extraction unit that extracts learning content of the employee based on the input information, and an output unit that outputs coaching card information based on the information extracted by the extraction unit.

[0007] In addition, a second aspect of the present disclosure provides an information processing method that acquires input information from an employee, extracts learning content of the employee based on the input information, and outputs coaching card information based on the extracted information.

[0008] In addition, a third aspect of the present disclosure provides a program that causes a computer to execute a process of acquiring input information from an employee, extracting learning content of the employee based on the input information, and outputting coaching card information based on the extracted information. [Effects of the Invention]

[0009] On the one hand, it can help employees make better use of the training in their work. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of an information processing apparatus according to an embodiment. [Figure 2] 1 is a diagram illustrating an example of the configuration of an information processing system according to an embodiment. [Figure 3] FIG. 1 is a diagram illustrating an example of a hardware configuration of an information processing apparatus according to an embodiment. [Figure 4] 10 is a flowchart illustrating an example of processing by the information processing apparatus according to the embodiment. [Figure 5] FIG. 10 is a diagram showing an example of coaching card information according to an embodiment. [Figure 6] FIG. 2 is a diagram illustrating an example of information stored in an employee DB (database) according to the embodiment. [Figure 7] FIG. 7 is a diagram showing an example of a display screen 701 for chatting when interactively extracting learning content and the like according to the embodiment. [Figure 8] FIG. 8 is a diagram showing an example of a display screen 801 for chatting when interactive coaching support is provided according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] The principles of the present disclosure will be described with reference to some exemplary embodiments. It should be understood that these embodiments are set forth for illustrative purposes only, to aid those skilled in the art in understanding and practicing the present disclosure, without implying any limitation on the scope of the disclosure. The disclosure described herein may be implemented in various ways other than those described below.

[0012] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0013] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Note that each drawing is merely an example for describing one or more embodiments. Each drawing may not relate to only one particular embodiment, but may also relate to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessarily required to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0014] (Embodiment 1) <Configuration> The configuration of an information processing device 10 according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the configuration of the information processing device 10 according to an embodiment. The information processing device 10 has an acquisition unit 11, an extraction unit 12, and an output unit 13. Each of these units may be realized by cooperation between one or more programs installed in the information processing device 10 and hardware such as a processor and memory of the information processing device 10.

[0015] The acquisition unit 11 acquires input information from employees reflecting on the training. The extraction unit 12 extracts the employee's learning content, etc., based on the input information acquired by the acquisition unit 11. The output unit 13 outputs coaching card information based on the learning content extracted by the extraction unit 12.

[0016] (Embodiment 2) <System configuration> Next, the configuration of the information processing system 1 according to the embodiment will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the information processing system 1 according to the embodiment. In the example of Fig. 2, the information processing system 1 includes an information processing device 10 and employee terminals 20A to 20C. Hereinafter, when there is no need to distinguish between the employee terminals 20A to 20C, they will simply be referred to as "employee terminal 20".

[0017] 2, the information processing devices 10 and employee terminals 20 are connected to each other so as to be able to communicate with each other via a network N. The number of information processing devices 10 and employee terminals 20 is not limited to that shown in the example of FIG.

[0018] Examples of the network N include, for example, the Internet, a mobile communication system, a wireless LAN (Local Area Network), a LAN, a bus, etc. Examples of the mobile communication system include, for example, a fifth generation mobile communication system (5G), a sixth generation mobile communication system (6G, Beyond 5G), a fourth generation mobile communication system (4G), a third generation mobile communication system (3G), etc.

[0019] The information processing device 10 is, for example, a device such as a server, a cloud server, a personal computer, a smartphone, etc. The information processing device 10 generates coaching card information including the learning content of the employee in the training, based on, for example, input information from the employee reflecting on the training.

[0020] The employee terminal 20 is, for example, a terminal such as a personal computer (PC), a smartphone, a tablet, or a wearable device that is used by an employee in his or her work activities.

[0021] <Hardware configuration> Fig. 3 is a diagram showing an example of the hardware configuration of an information processing device 10 according to an embodiment. In the example of Fig. 3, the information processing device 10 (computer 100) includes a processor 101, a memory 102, and a communication interface 103. These components may be connected via a bus or the like. The memory 102 stores at least a part of a program 104. The communication interface 103 includes an interface required for communication with other network elements.

[0022] When the program 104 is executed by the processor 101, memory 102, and the like in cooperation with each other, the computer 100 performs at least some of the processing of the embodiments of the present disclosure. The memory 102 may be of any type. As a non-limiting example, the memory 102 may be a non-transitory computer-readable storage medium. The memory 102 may also be implemented using any suitable data storage technology, such as semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory, and removable memory. Although only one memory 102 is shown in the computer 100, several physically different memory modules may exist in the computer 100. The processor 101 may be of any type. The processor 101 may include one or more of a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture, as a non-limiting example. The computer 100 may have multiple processors, such as application-specific integrated circuit chips that are time-slaved to a clock that synchronizes the main processor.

[0023] Embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device.

[0024] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, that execute on a target real or virtual processor or device to perform the processes or methods of the present disclosure. Program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or divided among program modules as desired in various embodiments. The machine-executable instructions of the program modules may be executed in local or distributed devices. In a distributed device, the program modules may be located in both local and remote storage media.

[0025] The program code for executing the methods of the present disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus. When the program code is executed by the processor or controller, the functions / acts in the flowcharts and / or implementing block diagrams are performed. The program code may be executed entirely on the machine, partly on the machine, as a standalone software package, partly on the machine and partly on a remote machine, or entirely on a remote machine or server.

[0026] The program can be stored and provided to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible recording media. Examples of non-transitory computer-readable media include magnetic recording media, magneto-optical recording media, optical disk media, and semiconductor memory. Magnetic recording media include, for example, flexible disks, magnetic tapes, and hard disk drives. Magneto-optical recording media include, for example, magneto-optical disks. Optical disk media include, for example, Blu-ray discs, CD (Compact Disc)-ROMs (Read Only Memory), CD-Rs (Recordable), and CD-RWs (Rewritable). Semiconductor memory includes, for example, solid-state drives, mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory). The program may also be provided to a computer by various types of temporary computer-readable media. Examples of temporary computer-readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire or an optical fiber, or via a wireless communication path.

[0027] <Processing> Next, an example of processing of the information processing device 10 according to the embodiment will be described with reference to Fig. 4 to Fig. 6. Fig. 4 is a flowchart showing an example of processing of the information processing device 10 according to the embodiment. Fig. 5 is a diagram showing an example of coaching card information according to the embodiment. Fig. 6 is a diagram showing an example of information stored in an employee DB (database) 601 according to the embodiment.

[0028] In step S101, the acquisition unit 11 acquires input information from an employee reflecting on the training. Here, the acquisition unit 11 may acquire, as input information, information ("reflection") such as what the employee learned in the training, how to apply the content learned in the training to actual work, and matters that the employee would like to learn further based on the training. The acquisition unit 11 may acquire the reflection as text data input by the employee through a chat interface, for example.

[0029] The acquisition unit 11 may automatically detect the end of the training in cooperation with, for example, a training schedule and attendance management system. When the acquisition unit 11 detects the end of the training, it may send an automatic message to the employee requesting them to input a review.

[0030] The acquisition unit 11 may, for example, send a message to the employee terminal 20 such as, "Mr. A, thank you for your hard work in today's training. Please reflect on the training content and enter what you learned and what you noticed. By entering your reflections, you can further enhance the effectiveness of the training." to encourage the employee to enter their reflections.

[0031] Next, the extraction unit 12 performs natural language processing on the input information acquired by the acquisition unit 11 (step S102). Here, the extraction unit 12 may perform, for example, morphological analysis, syntactic analysis, semantic analysis, etc. on the input information.

[0032] Next, the extraction unit 12 extracts action items and learning contents of the employee based on the natural language processing results of the input information (step S103). Here, the extraction unit 12 may extract action items and learning contents from the reflection using a method such as rule-based pattern matching or classification using a machine learning model. Here, the action items may be, for example, future actions or implementation items mentioned in the reflection. Furthermore, the learning contents may be realizations or lessons learned from the reflection.

[0033] Action items may be called by various names depending on the organization and usage context, such as tasks, action plans, next steps, action items, to-do items, improvement points, commitments, etc.

[0034] For example, suppose a reflection such as "Today's meeting was a lively discussion about a new project proposal. In particular, I learned about a method for visualizing ideas. I would like to prepare a project proposal by the next meeting and consult with my manager." is input. The extraction unit 12 may extract, for example, the part "I would like to prepare a project proposal by the next meeting and consult with my manager" as an action item. Furthermore, the extraction unit 12 may extract, for example, the part "I was able to learn about a method for visualizing ideas" as a learning content. Note that the extraction unit 12 may, for example, convert the extracted information into data in a structured format (for example, JSON format).

[0035] In addition, the extraction unit 12 may extract information indicating the training name, review date, review summary, learning content, details of the learning content, action items, progress of the action items, and the next action plan based on the results of natural language processing of the input information.

[0036] Next, the output unit 13 generates coaching card information based on the learning content and the like extracted by the extraction unit 12 (step S104). The output unit 13 may output the coaching card information in a format such as HTML (HyperText Markup Language) or PDF (Portable Document Format). The coaching card information is a document summarizing the main points of the reflection, and may also be data that promotes employee awareness and behavioral change.

[0037] Coaching card information may include information such as the date and summary of the reflection, learning content including insights and lessons learned during the reflection, related action items, progress on the action items, and next action plans and goals. Employees can check their own growth and progress by referring to the coaching card information. Managers can also refer to the coaching card information to appropriately conduct interviews with employees. Note that coaching card information may be called by various names depending on the organization and usage situation. Coaching card information may also be called a reflection sheet, training record, individual development plan (IDP), learning journal, skill development sheet, career progress card, performance tracker, growth record notebook, etc.

[0038] FIG. 5 shows an example of coaching card information according to an embodiment. In the example of FIG. 5, the content of the coaching card information is expressed in two columns: item and content. The item column includes the training name, review date, review summary, learning content, learning content details, action items, progress of action items, next action plan, etc. The content column is used to enter specific information corresponding to each item. This table format allows the content of the coaching card information to be structured and organized in an easy-to-read format.

[0039] The output unit 13 may record coaching card information and the like in the employee DB 601. In the example of FIG. 6, the employee DB 601 stores input information (reflection data), one or more action items, one or more learning contents, and coaching card information in association with a combination of an employee ID and training information. In addition, the employee ID of the manager and schedule information are stored in association with the employee ID. The training information is information about training that is the subject of reflection by the employee. The training information may include, for example, a training ID, which is identification information for the training, a training name, a training period, and the like. The manager's employee ID is the employee ID of the employee's manager (e.g., superior). The manager's employee ID may be set in advance, for example, by an operator of the information processing device 10.

[0040] The information recorded in the employee DB 601 may be used for various analyses, such as visualizing each employee's reflection trends (such as frequency and content trends), tracking and managing the progress of action items, classifying learning content and creating skill maps, and analyzing the utilization status of coaching card information and its impact on behavioral change. Machine learning and data mining techniques may be used for these analyses. For example, the information processing device 10 may analyze the content of the coaching card information using natural language processing to discover effective reflection patterns. The results of the analysis may be visualized in the form of a dashboard or report and used to develop human resource development measures and support individual employees.

[0041] Next, when a specific action item is extracted by the extraction unit 12, the output unit 13 sends a meeting proposal (a meeting notification) to the employee and the manager (step S105). The notification may include the purpose of the meeting (to consult about the execution of the action item), related reflection content, and coaching card information. In the above-mentioned reflection example, the output unit 13 may determine that a meeting between the employee and the manager is necessary based on the specific action item "I would like to consult with the manager."

[0042] Next, the output unit 13 sets the date of the meeting in cooperation with the schedule management system, and when each participant approves their participation, the output unit 13 confirms the meeting schedule and registers it in the schedule calendar of each participant (step S106). Here, the output unit 13 may cooperate with, for example, a cloud service for schedule management, search for participants' free time, and propose the most suitable date and time.

[0043] Employees and managers can use coaching card information and other information during interviews. This improves the quality and efficiency of interviews, bringing benefits to both employees and managers. In other words, it improves the quality of person-to-person communication and makes it easier to change employee behavior.

[0044] (Example of a use case) Below is an example of a use case where an employee has taken a training course on "marketing." After taking the training course, the employee can enter their reflections through the chat interface. For example, they could enter, "I took the marketing training course and gained a deeper understanding of the importance of customer segmentation. I was particularly impressed by how they identified evangelists. I would like to utilize customer segmentation in future strategy planning."

[0045] The extraction unit 12 may apply morphological analysis, syntactic analysis, semantic analysis, etc. to the input text data. This allows the structure and meaning of the sentence to be understood and converted into a format that can be processed mechanically. The extraction unit 12 extracts keywords such as "customer segmentation" and "evangelist" and analyzes the relationships between them.

[0046] Then, the extraction unit 12 may extract action items and learning content from the review content based on the analysis result. In this example, "We would like to utilize customer segmentation in future policy planning" is extracted as an action item, and "The importance of customer segmentation" and "How to identify evangelists" are extracted as learning content. The extraction result is saved as structured data in JSON format or the like.

[0047] The output unit 13 may propose a meeting between the employee and the manager when the action item is extracted. The purpose of the meeting may be to discuss the formulation of a policy utilizing customer segmentation. The notification of the meeting proposal may include a review related to the action item.

[0048] The output unit 13 may check the schedules of the employee and manager, search for available times for both parties, and propose the optimal date and time. For example, it may propose "next Monday from 10:00 to 11:00 is available for both parties." If both parties approve the proposed date and time, the meeting is confirmed and registered in their respective calendars.

[0049] The output unit 13 may also generate coaching card information that summarizes the review content and the extracted learning content. The coaching card information may include the training title "Marketing," the review date and summary, details of the learning content "The Importance of Customer Segmentation" and "How to Identify Evangelists," a related action item "Planning Measures Using Customer Segmentation" and its progress, and a next action plan. The output unit 13 may output the generated coaching card information in, for example, PDF format and distribute it to employees or managers.

[0050] The output unit 13 may also accumulate (record) the reflection data, action items, learning content, coaching card information, and the like generated during the series of activities. The accumulated data may be used for various analyses. For example, the data may be used to analyze the reflection content of all participants in a marketing training program to identify trends in topics with high levels of understanding and frequently extracted action items. The effectiveness of the training may also be evaluated by analyzing how the coaching card information is used and its impact on subsequent policy planning. In this way, by utilizing natural language processing and machine learning technologies to support the entire process from taking the training program to reflection, implementing the action plan, and follow-up, it is possible to maximize the effectiveness of the training and promote behavioral change in employees.

[0051] (An example of interactive response generation) Input information on the employee's reflection on the training may be acquired using interactive response generation. The extraction unit 12 may use, for example, a language model. The extraction unit 12 may generate an interactive response to the input text data of the reflection using, for example, a pre-trained language model. This enables, for example, interactive and flexible reflection support. Furthermore, it is possible to realize detailed support tailored to the reflection of each employee.

[0052] Here, a language model according to an embodiment will be described. A language model is a machine learning model (also called a generative model) that inputs a language and outputs a language. A language model learns the relationships between words in a sentence, and generates related strings related to a target string from the target string. By using a language model that has learned sentences and passages from various contexts, it is possible to generate related strings with appropriate content related to the target string. When a prompt (query) including instructions regarding a response is input, the language model outputs an answer corresponding to the prompt.

[0053] The learning method of the language model is not particularly limited, and as an example, the language model may be learned to output at least one sentence including an input string. Specifically, the language model may be a Generative Pretrained-Transformer (GPT) that outputs a sentence including an input string by predicting a string that is likely to follow the input string. Furthermore, the language model may be, for example, a Text-to-Text Transfer Transformer (T5), a Bidirectional Encoder Representations from Transformers (BERT), a Robustly optimized BERT approach (RoBERTa), or an Efficiently Learning an Encoder that Classifies Token Replacements Accurately (ELECTRA).

[0054] The extraction unit 12 may ask the employee additional questions about the action items and learning contents to be extracted from the reflection text data. When the extraction unit 12 receives a response from the employee, the extraction unit 12 may ask more in-depth questions based on the information, thereby interactively extracting the action items and learning contents as shown in FIG.

[0055] FIG. 7 is a diagram illustrating an example of a chat display screen 701 when interactively extracting learning content, etc., according to an embodiment. When an employee inputs learnings and realizations gained from training as text data, the extraction unit 12 may analyze the content of the text data and estimate the employee's level of understanding and interests. The extraction unit 12 may then ask specific questions to further deepen the employee's reflection. In the example of FIG. 7 , the extraction unit 12 asks, "You said that the method for identifying evangelists was impressive. What specific points did you find useful?" This question is intended to help the employee digest the training content in their own way and draw out hints for applying it to practice. After the employee answers the question, the extraction unit 12 may analyze the answer and ask more in-depth questions. The extraction unit 12 may repeat this process to interactively deepen the employee's reflection.

[0056] The extraction unit 12 may also automatically extract action items (matters that should be put into actual action) and learning contents (obtained knowledge and skills) from the chat contents (text data) of the employees, thereby enabling the employees to organize their own reflections and clarify specific next steps.

[0057] The extraction unit 12 may also mention new realizations or issues that arise from the employee's reflection. In the above example, by mentioning points such as "data collaboration with other departments" and "strengthening customer orientation throughout the organization," the extraction unit 12 broadens the employee's perspective and encourages the employee to reflect from a broader perspective.

[0058] As described above, interactive exchanges between the extraction unit 12 and employees realize two-way, deep introspection rather than simply one-way reflection. The extraction unit 12 appropriately interprets what employees say and asks questions and makes suggestions according to the context, thereby effectively drawing out employees' awareness and supporting their continuous growth.

[0059] The extraction unit 12 may also generate flexible responses according to the context by referring to information such as past review data and related documents, etc. This makes it possible to handle a variety of review patterns that are relatively difficult to handle with fixed rule-based processing.

[0060] The language model used by the extraction unit 12 can be fine-tuned specifically for the review support task to enable more advanced processing. Specifically, the extraction unit 12 can improve the accuracy of extracting action items and learning contents by additionally learning excellent past review cases as training data. The extraction unit 12 may use, for example, a model trained by machine learning using combinations of past input information and learning contents as training data.

[0061] (Example of providing support to administrators) The information processing device 10 may assist managers in understanding the content of employee reflections and further strengthening their coaching for more effective meetings. The output unit 13 may use the coaching card information to respond to questions from managers using natural language processing technology. The output unit 13 may be implemented, for example, using a large-scale language model. Fine-tuning the large-scale language model specifically for the coaching dialogue task enables the generation of more natural and contextual responses. Furthermore, the manager may continuously improve the model by feeding back insights gained from interactions to the model. For example, if the manager evaluates that "this example question would be better if it were more specific," the manager may add that evaluation to the model as learning data. This allows the model to incorporate organization-specific coaching know-how.

[0062] The output unit 13 may generate coaching option information in addition to the coaching card information. The coaching option information is information that indicates a plurality of coaching directions and specific advice options based on the employee's learning content and extracted action items.

[0063] For example, when the extracted learning content is "the importance of customer segmentation," the output unit 13 may generate the following coaching options: (1) Consider in detail how customer segmentation can be used in actual business operations. (2) Strengthen data collaboration with other departments and promote the collection and analysis of customer data. (3) Develop measures to increase customer orientation throughout the organization.

[0064] Managers can hold meetings with employees while referring to these coaching options. Each option may be accompanied by more detailed explanations and advice. By providing information on coaching options in this way, managers can efficiently select the optimal coaching direction for each employee, enabling more detailed coaching. Furthermore, by holding multiple discussions based on the options, it becomes easier to develop specific action plans together with employees.

[0065] The output unit 13 may answer a question from the manager as shown in FIG. 8. FIG. 8 is a diagram showing an example of a chat display screen 801 when interactive coaching support according to the embodiment is provided. In the example of FIG. 8, a question such as "What is the employee's awareness of the problem behind this action item?" is input by the manager. The output unit 13 may analyze the contents of the coaching card information and past review data, etc., to understand the intent of the question and then generate an appropriate answer.

[0066] The output unit 13 may also provide hints for questions that a manager should ask employees in a meeting. For example, suppose a manager inputs a request such as, "I would like to discuss improving employee motivation in this meeting." The output unit 13 may analyze the content of the coaching card information and output (present) example questions such as, "What are the barriers to putting into practice what you learned in the training?" or "Why not ask about your future career vision?"

[0067] This allows managers to attend meetings with a deeper understanding of their employees' situations. Furthermore, rather than simply reading the coaching card information, managers can resolve any questions they may have about it and identify areas that need further digging, thereby improving the quality of meetings.

[0068] <Other> It is not easy to apply the content of training to actual work and lead to behavioral change. Traditionally, employee reflections have often been conducted according to standardized templates, which tended to lack flexibility. Furthermore, there was not enough of a system in place to utilize the content of reflections to improve work.

[0069] On the other hand, according to the present disclosure, coaching card information including information on the learning content, etc. is generated based on input information from employees reflecting on the training. This can, for example, help employees better utilize the training in their work.

[0070] <Modification> The output unit 13 may analyze the interview results and provide feedback. The output unit 13 may generate useful information for at least one of the employee and the manager by performing information processing on the interview results. For example, the output unit 13 may generate more effective feedback by transcribing the audio of the interview and summarizing and analyzing it using a language model. The output unit 13 may use a language model to understand the content of the interview, extract important points, and generate a summary. Furthermore, the output unit 13 may suggest advice or areas for improvement to the manager or employee, taking into account the context of the interview. For example, the output unit 13 may notify the employee or manager of advice such as "You need to improve your communication skills" or "Setting specific goals is effective."

[0071] The output unit 13 may also perform emotion analysis on the voice data to estimate the emotional state of the interview participant. For example, the output unit 13 may extract prosodic features (pitch, volume, speed, etc.) of the voice of the interview participant and classify the emotion using a machine learning model (e.g., support vector machine or convolutional neural network).

[0072] Alternatively, the output unit 13 may estimate stress and emotions with higher accuracy by also analyzing biological information (heart rate, electrodermal activity, body temperature, etc.) acquired using a wearable device. For example, a decrease in heart rate variability (HRV) or an increase in electrodermal activity (EDA) can be used as an indicator of a stress state.

[0073] The output unit 13 may analyze this data in chronological order to visualize at what point in the interview the participants' emotions or stress levels changed. Specifically, a graph may be generated that measures time on the horizontal axis and emotional intensity or stress levels on the vertical axis, with topics of the interview and important events overlaid on the graph. This allows the output unit 13 to visually grasp the participants' reactions to specific topics or questions. For example, the output unit 13 may generate specific insights such as "The stress level rose when the topic of performance evaluation came up." By providing such an integrated analysis of emotion analysis and vital data, the output unit 13 can evaluate the quality of the interview, leading to more effective communication and human resource development.

[0074] <Variation 2> The information processing device 10 may be a device contained in a single housing, but the information processing device 10 of the present disclosure is not limited to this. Each unit of the information processing device 10 may be realized, for example, by cloud computing configured with one or more computers. Furthermore, the information processing device 10 and the employee terminal 20 may be housed in the same housing and configured as an integrated information processing device. Furthermore, at least a portion of the processing of each functional unit of the information processing device 10 may be executed by the employee terminal 20. Such information processing devices 10 are also included as examples of the "information processing device" of the present disclosure.

[0075] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0076] Some or all of the above embodiments may also be described as, but are not limited to, the following appendices. Note that some or all of the elements (e.g., configurations and functions) described in each appendix dependent on appendix 1 may also be dependent on independent appendices in other categories in a similar dependency relationship. Some or all of the elements described in any appendix may be applied to various hardware, software, recording means for recording software, systems, and methods. (Appendix 1) an acquisition unit that acquires input information on the training review from employees; an extraction unit that extracts the learning content of the employee in the training based on the input information; an output unit that outputs coaching card information based on the information extracted by the extraction unit; An information processing device having the above. (Appendix 2) the extraction unit extracts information indicating a training name, a review date, a review summary, learning content, details of learning content, action items, progress of the action items, and a next action plan based on a result of natural language processing of the input information; 10. The information processing device according to claim 1. (Appendix 3) the extraction unit generates questions for extracting the action items and the learning content based on the input information, and extracts the action items and the learning content based on the employee's answers to the questions; 3. The information processing device according to claim 2. (Appendix 4) The extraction unit uses a machine-learned model using a combination of past input information and learning content as training data. 3. The information processing device according to claim 1 or 2. (Appendix 5) the extraction unit extracts a specific action item for the employee by natural language processing based on the input information, and sends a notification of a meeting based on the specific action item to the employee and the employee's manager; 3. The information processing device according to claim 1 or 2. (Appendix 6) The event notice includes the coaching card information. 6. The information processing device according to claim 5. (Appendix 7) the output unit uses the coaching card information to respond to a question from the manager using a natural language processing technique. 6. The information processing device according to claim 5. (Appendix 8) the output unit uses the coaching card information to present examples of questions that the manager should ask the employee in the meeting; 8. The information processing device according to claim 7. (Appendix 9) Obtain training reflection input from employees, extracting the employee's learning content from the training based on the input information; Outputting coaching card information based on the extracted information. Information processing methods. (Appendix 10) Obtain training reflection input from employees, extracting the employee's learning content from the training based on the input information; outputting coaching card information based on the learning content; A program that causes a computer to perform a process. [Explanation of symbols]

[0077] 1. Information Processing Systems 10. Information processing equipment 11 Acquisition Department 12 Extraction part 13 Output section 20 Employee terminals

Claims

1. an acquisition unit that acquires input information on the training review from employees; an extraction unit that extracts the learning content of the employee in the training based on the input information; an output unit that outputs coaching card information based on the information extracted by the extraction unit; An information processing device having the above.

2. the extraction unit extracts information indicating a training name, a review date, a review summary, learning content, details of learning content, action items, progress of the action items, and a next action plan based on a result of natural language processing of the input information; The information processing device according to claim 1 .

3. the extraction unit generates questions for extracting the action items and the learning content based on the input information, and extracts the action items and the learning content based on the employee's answers to the questions; The information processing device according to claim 2 .

4. The extraction unit uses a machine-learned model using a combination of past input information and learning content as training data.

3. The information processing device according to claim 1.

5. the extraction unit extracts a specific action item for the employee by natural language processing based on the input information, and sends a notification of a meeting based on the specific action item to the employee and the employee's manager; 3. The information processing device according to claim 1.

6. The event notice includes the coaching card information. The information processing device according to claim 5 .

7. the output unit uses the coaching card information to respond to a question from the manager using a natural language processing technique. The information processing device according to claim 5 .

8. the output unit uses the coaching card information to present examples of questions that the manager should ask the employee in the meeting; The information processing device according to claim 7 .

9. Obtain training reflection input from employees, extracting the employee's learning content from the training based on the input information; Outputting coaching card information based on the extracted information. Information processing methods.

10. Obtain training reflection input from employees, extracting the employee's learning content from the training based on the input information; outputting coaching card information based on the learning content; A program that causes a computer to perform a process.

Images