Information processing system, program, and information processing method

Abstract

To provide an information processing system capable of digging deeper into the personality of a report writer by analyzing a document, particularly a report, from multiple angles. [Solution] According to one aspect of the present invention, there is provided an information processing system comprising a memory and a processor, the processor being configured to execute each of the following steps by reading a program recorded in the memory, wherein a first acquisition step acquires data of at least one report written in natural language, a determination step identifies an evaluation of the report based on the content of the report text, and a analysis step analyzes the personality of the report creator based on the content and evaluation of the report and a predetermined algorithm.

Description

[Technical field]

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

[0002] In recent years, research has been progressing on predicting the personality of a text writer by analyzing the text. For example, Patent Literature 1 discloses a technology for predicting the personality of a text writer by analyzing text posted on a social networking site. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-149196 A Summary of the Invention [Problem to be solved by the invention]

[0004] There is a need to advance this research further and to analyze in greater depth the personalities of the writers of texts.

[0005] In view of the above circumstances, the present invention provides an information processing system and the like that is capable of digging deeper into the personality of a report writer by analyzing a document, particularly a report, from multiple angles. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system comprising a memory and a processor, the processor being configured to execute each of the following steps by reading a program recorded in the memory: a first acquisition step acquiring data of at least one report written in a natural language; a determination step determining an evaluation of the report based on the content of the report text; and a analysis step analyzing the personality of the report creator based on the content and evaluation of the report and a predetermined algorithm.

[0007] According to this aspect, an information processing system or the like is provided that can dig deeper into the personality of the report creator by analyzing the report from multiple angles. [Brief description of the drawings]

[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1. [Diagram 2] 2 is a block diagram showing a hardware configuration of the server device 10. FIG. [Diagram 3] FIG. 2 is a block diagram showing the hardware configuration of a student terminal 20 and a teacher terminal 30. [Figure 4] 1 is a block diagram showing functions realized by a server device 10 (control unit 11), a student terminal 20 (control unit 21), and a teacher terminal 30 (control unit 31). [Diagram 5] 1 is a diagram showing an outline of a functional arrangement 50 provided in an information processing system 1 in this embodiment. [Figure 6] FIG. 2 is a diagram showing an overview of information processing (report analysis processing) executed by the information processing system 1. [Figure 7] FIG. 7 is a diagram showing further details of the process indicated in step S102 in FIG. 6. [Figure 8] FIG. 7 is a diagram showing further details of the process indicated in step S105 of FIG. 6. [Figure 9] This is an example of a report assignment given to students. [Figure 10] FIG. 1 is a diagram showing further details of each element derived by the Student analysis described above. [Figure 11] 13 is an example of a screen showing the analysis results of the Student analysis described above. [Figure 12] This is a screenshot showing the detailed results of a Student analysis. [Figure 13] FIG. 13 illustrates an update process for the prompt P1. [Figure 14] 13 is a sequence diagram showing matching between the derived student personality and the recruitment requirements of the recruiter. FIG. [Figure 15] This is an example screen showing a list of derived student personalities that will be shown to companies. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, embodiments of the present invention will be described. Note that various features shown in the following embodiments can be combined with each other.

[0010] That is, the information processing system of this embodiment is as follows. The information processing system includes a memory and a processor, and the processor performs the functions of the following components by reading out a program recorded in the memory. The first acquisition unit acquires data of at least one report written in a natural language. The specification unit specifies an evaluation of the report according to the content of the sentence in the report. The analysis unit analyzes the personality of the report creator based on the content and evaluation of the report and a predetermined algorithm.

[0011] Incidentally, a program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable recording medium, or may be provided so as to be downloadable from an external server, or may be provided so that the program is launched on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0012] In addition, in various information processing according to an embodiment, an input and an output according to the input can be realized. Here, as long as an output is obtained as a result of the input, the form of information referenced in such information processing (hereinafter referred to as reference information) is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a judgment formula such as a regression formula constructed by a statistical method), or may be a trained model that has previously trained the correlation between the input and the output, or may be a generation AI such as a large-scale language model or a visual language model that can output a desired result by inputting a prompt.

[0013] In one embodiment, the term "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In one embodiment, various information is handled, and this information is represented by, for example, physical values ​​of signal values ​​representing voltage and current, high and low signal values ​​as a binary bit collection consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be performed on the circuit in the broad sense.

[0014] Furthermore, a circuit in the broad sense is a circuit realized by at least appropriately combining a circuit, circuitry, a processor, and a memory. The processor may be a general-purpose processor or a dedicated circuit. In other words, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0015] 0. Scope of the present invention As described above, the present invention aims to dig deeper into the personality of a report writer by analyzing writing, particularly reports, from multiple angles. In this specification, the report writer is assumed to be a "student," the evaluator who evaluates the report or the supervisor who supervises the student is assumed to be a "teacher," and for ease of understanding, a university is assumed for the explanation. However, the relationship between the report writer and the evaluator (supervisor) is not limited to this, and may be, for example, a subordinate and superior belonging to an organization such as a company, or they may be friends.

[0016] [First embodiment] 1. Hardware Configuration This section describes the hardware configuration.

[0017] <Information Processing System 1> Fig. 1 is a configuration diagram showing an information processing system 1. The example of the information processing system 1 shown in Fig. 1 includes a communication line 2, a server device 10, a student terminal 20, and a teacher terminal 30. The server device 10, the student terminal 20, and the teacher terminal 30 are configured to be able to communicate with each other via the communication line 2. The connection between the server device 10, the student terminal 20, and the teacher terminal 30 may be wired or wireless.

[0018] The student terminal 20 is an information processing terminal used by a student S1. Here, the student S1 refers to a student belonging to, for example, an educational corporation, but in this specification, this student is defined as a student in a broad sense. In other words, it is not limited to students belonging to universities or technical colleges, but also includes students belonging to junior high schools, high schools, and elementary schools. It also includes students belonging to private schools (private schools, private schools, English conversation schools, cultural schools, etc.) that are not part of educational corporations.

[0019] The teacher terminal 30 is an information processing terminal used by the teacher T1. As described above, the student S1 is defined in a broad sense in this specification, so the teacher T1 is also defined as a teacher in a broad sense. In other words, the teacher T1 is not limited to a professional teacher who has a teaching license, but also includes a teacher who belongs to the private school described above.

[0020] Although Fig. 1 shows a single student terminal 20 and a single teacher terminal 30, the server device 10 of the information processing system 1 may provide, for example, a platform used by a plurality of teachers and a plurality of students. Such a platform may be a platform related to report analysis provided by the server device 10. Although not shown in Fig. 1, there may be an administrator of such a platform.

[0021] Although not shown in detail in Fig. 1, in addition to students S1 and teachers T1, teaching staff may also participate as users of the platform. Here, teaching staff are people who support the activities or work of students S1 and teachers T1, and may be organizations or their personnel who mediate interactions between students S1 and teachers T1.

[0022] In one embodiment, the information processing system 1 is composed of one or more devices or components. Therefore, the information processing system 1 can be an example of a system even if it is only the server device 10 or the terminals 20 and 30. More specifically, the information processing system 1 may include an element selected from the group consisting of the server device 10 and the terminals 20 and 30. Also, a plurality of server devices 10 or terminals 20 and 30 may be used. The unselected elements may not be included in the information processing system 1, but may be electrically connected to the selected elements as external elements. These components will be described below.

[0023] <Server device 10> Fig. 2 is a block diagram showing a hardware configuration of the server device 10. As shown in Fig. 2, the server device 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a communication bus 14. The control unit 11, the storage unit 12, and the communication unit 13 are electrically connected to each other inside the server device 10 via the communication bus 14.

[0024] <Control unit 11> The control unit 11 performs processing and control of the overall operation related to the server device 10. The control unit 11 is, for example, a central processing unit (CPU). The control unit 11 realizes various functions related to the server device 10 by reading out a predetermined program stored in the storage unit 12. That is, information processing by software stored in the storage unit 12 can be specifically realized by the control unit 11, which is an example of hardware, and executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and the server device 10 may have multiple control units 11 for each function. Also, the server device 10 may be configured with a combination of these.

[0025] <Storage section 12> The storage unit 12 stores various information defined by the above description. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the server device 10 executed by the control unit 11, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program calculations. The storage unit 12 stores various programs, variables, etc. related to the server device 10 executed by the control unit 11.

[0026] <Communications Division 13> The communication unit 13 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as LTE / 5G, BLUETOOTH (registered trademark) communication, etc. as necessary. In other words, it is more preferable to implement it as a collection of multiple communication means. In other words, the server device 10 may communicate various information from the outside via the communication unit 13 and the network.

[0027] The server device 10 may be in an on-premise form or in a cloud form. The server device 10 in a cloud form may provide the above-mentioned functions and processes in the form of, for example, SaaS (Software as a Service) or cloud computing.

[0028] <Student terminal 20 / Teacher terminal 30> Fig. 3 is a block diagram showing the hardware configuration of the student terminal 20 and the teacher terminal 30. As shown in Fig. 3A, the student terminal 20 includes a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, the storage unit 22, the communication unit 23, the input unit 24, and the output unit 25 are electrically connected via the communication bus 26 inside the student terminal 20. The explanation of the control unit 21, the storage unit 22, and the communication unit 23 will be omitted because they are the same as the explanation of each unit in the server device 10.

[0029] <Input section 24> The input unit 24 accepts an operation input made by a user. The operation input is transferred as a command signal to the control unit 21 via the communication bus 26. The control unit 21 may execute a predetermined control or calculation based on the transferred command signal as necessary. The input unit 24 may be included in the housing of the student terminal 20, or may be externally attached. For example, the input unit 24 may be implemented as a touch panel integrated with the output unit 25. When the input unit 24 is implemented as a touch panel, the user can input a tap operation, a swipe operation, or the like to the input unit 24. As the input unit 24, a switch button, a mouse, a track pad, a QWERTY keyboard, or the like can be adopted instead of a touch panel. In addition to the above-mentioned tactile input, voice input using a microphone is also possible.

[0030] <Output section 25> The output unit 25 displays a screen of a graphical user interface (GUI) that can be operated by the user. The output unit 25 may be included in the housing of the student terminal 20, or may be attached externally. Specifically, the output unit 25 may be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, or a plasma display. It is preferable that these display devices are implemented by selectively using them according to the type of the student terminal 20.

[0031] 3B, the teacher terminal 30 includes a control unit 31, a memory unit 32, a communication unit 33, an input unit 34, an output unit 35, and a communication bus 36. The control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 are electrically connected inside the teacher terminal 30 via the communication bus 36. The explanation of the control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 will be omitted because they are the same as the explanation of each unit in the student terminal 20.

[0032] 1 shows an example in which the various terminals are laptop PCs (Personal Computers), but in this embodiment, there are no particular limitations on the types of terminals of the student terminal 20 and the teacher terminal 30. In other words, the student terminal 20 and the teacher terminal 30 may each be various information processing terminals such as a desktop PC, a laptop PC, a smartphone, a tablet terminal, etc.

[0033] 2. Functional configuration 2.1 Overview In this section, an overview of the functional configuration of this embodiment will be described. Information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11 (a processor included in the information processing system 1).

[0034] FIG. 4 is a block diagram showing functions realized by the server device 10 (control unit 11), the student terminal 20 (control unit 21), and the teacher terminal 30 (control unit 31).

[0035] 4A, the server device 10 (control unit 11) includes a display control unit 111, an acquisition unit 112, a generation unit 113, an output unit 114, an identification unit 115, an analysis unit 116, a storage unit 117, an aggregation unit 118, an update unit 119, a memory management unit 120, and an artificial intelligence unit 121. The functions of each functional unit will be described below.

[0036] <Display control unit 111> The display control unit 111 is configured to be able to execute a display control step. In the display control step, the display control unit 111 is configured to display various information on various terminals. The display information may be information itself generated in a form that is visible to the user, such as a screen, an image, an icon, or text. In addition, such display control may be a signal transmitted from the display control unit 111 to the student terminal 20, and as a result, predetermined information may be displayed on the display unit of the various terminals. In the example of this embodiment, the display control unit 111 displays the analysis results of the report on each terminal. The specific contents displayed on the various terminals will be described later.

[0037] <Acquisition part 112> The acquisition unit 112 is configured to be able to execute an acquisition step. In the acquisition step, the acquisition unit 112 accepts various pieces of information. The route through which this information is acquired may be set arbitrarily, but as an example, the information may be acquired from various terminals, etc. related to the information processing system 1 of this embodiment. In this example of this embodiment, the acquisition unit 112 acquires data of at least one report written in a natural language. Details of the information acquired by the acquisition unit 112 will be described later.

[0038] <Generation unit 113> The generating unit 113 is configured to be able to execute a generating step. In the generating step, the generating unit 113 generates various information related to the information processing system 1. In the example of this embodiment, the generating unit 113 generates structured data that combines the contents and evaluation of the report into one piece of data. Details of this product will be described later.

[0039] <Output unit 114> The output unit 114 is configured to be able to execute an output step. In the output step, the output unit 114 outputs various information handled by the information processing system 1 in a predetermined manner. As an example, the output here may be output (insertion) of predetermined information in a predetermined area on the screen displayed by various terminals. In the example of this embodiment, the output unit 114 outputs the analysis results of the report on the display screen of each terminal. The specific manner of such output will be described later.

[0040] <Specific part 115> The identifying unit 115 is configured to be able to execute an identifying step. In the identifying step, the identifying unit 115 identifies the quality, evaluation, and the like of various information handled by the information processing system 1 in a predetermined manner. In the example of this embodiment, the identifying unit 115 identifies the evaluation of the report according to the content of the text of the report acquired by the information processing system 1 via the acquiring unit 112. A specific manner of identification will be described later.

[0041] <Analysis Department 116> The analysis unit 116 is configured to be able to execute an analysis step. In the analysis step, the analysis unit 116 executes various analyses on various pieces of information handled by the information processing system 1 using the artificial intelligence unit 121 described later. In the example of this embodiment, the analysis unit 116 analyzes the personality of the report creator based on the contents and evaluation of the report and a predetermined algorithm. The details will be described later.

[0042] <Storage section 117> The accumulation unit 117 is configured to be able to execute an accumulation step. In the accumulation step, the accumulation unit 117 accumulates various pieces of information handled by the information processing system 1 in the memory unit 12. In this embodiment, the accumulation unit 117 accumulates a plurality of analysis results derived by the analysis unit 116, which will be described later.

[0043] <Collecting Section 118> The aggregation unit 118 is configured to be able to execute an aggregation step. In the aggregation step, the aggregation unit 118 aggregates, in a predetermined manner, a plurality of pieces of information acquired by the information processing system 1. In an example of the present embodiment, the aggregation unit 118 aggregates a plurality of report analysis results as teacher data, and this manner will be described later.

[0044] <Update section 119> The update unit 119 is configured to be able to execute an update step. In the update step, the update unit 119 updates the prompt of the artificial intelligence unit 121, which will be described later. In the example of this embodiment, the update unit 119 updates the artificial intelligence unit 121 based on the information aggregated by the aggregation unit 118 as teacher data, the details of which will be described later.

[0045] <Storage management section 120> The memory management unit 120 is configured to be able to execute a memory management step. In the memory management step, the memory management unit 120 manages various pieces of information to be stored that are related to the information processing system 1. Typically, the memory management unit 120 is configured to store information handled by the server device 10, various terminals, etc., in a memory area. This memory area is exemplified by, for example, a memory area (memory unit 12) provided in the server device 10 and memory areas of various devices, but this memory area does not necessarily have to be within the system shown in FIG. 1, and the memory management unit 120 can also manage various pieces of information to be stored in an external storage device, etc.

[0046] <Artificial Intelligence Department 121> The artificial intelligence unit 121 is configured to receive input from each functional unit and return an instructed output. The artificial intelligence used by the server device 10 in each functional unit may be a common one, or may be prepared individually for each functional unit.

[0047] The artificial intelligence unit 121 is an AI (Artificial Intelligence) equipped with learning models such as Transformers including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, GPT-3, GPT-4, and GPT-4о), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), and language models such as Recurrent Neural Networks (RNN), and may include generative AI and AI agents.

[0048] The language model is an example of a learning model based on a machine learning algorithm. Specific examples of machine learning algorithms include nearest neighbor methods, naive Bayes methods, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 121 can apply the above algorithms as appropriate.

[0049] The artificial intelligence unit 121 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data (training data). The training data is composed of a pair of input data for learning and output data (correct answer data). In addition, the language model may not only be one trained for a specific task, but also a general-purpose model that can be used for a wide range of tasks.

[0050] The artificial intelligence unit 121 may be a natural language model as the artificial intelligence, and may include a general-purpose natural language processing trained model such as a large-scale language model (LLM). The LLM is a learning model that has previously trained a large amount of large-scale data (for example, (i) web content on the Internet, or (ii) data accumulated in a specified database) composed of text data, etc., and can execute various language processing tasks by giving tasks. According to a given prompt, it can perform a wide range of natural language processing tasks such as grasping sentence patterns and contexts, answering questions, and generating sentences. Such a general-purpose learning model may include a language model that can handle various tasks without fine tuning by one-shot learning, few-shot learning, etc. In addition, the general-purpose learning model can also handle various tasks by zero-shot learning. The artificial intelligence used in each functional unit of the control unit 11 may be a separate learning model, or may be a common general-purpose learning model. The large-scale language model is a type of generative AI, and includes models provided by services such as OpenAI's GPT, Google's Gemini, and Microsoft's AzureAI Studio. Additionally, the artificial intelligence unit 121 can include any machine learning model, deep learning model, artificial intelligence model, etc. The artificial intelligence unit 121 may be constructed in a system external to the information processing system 1. Furthermore, the artificial intelligence unit 121 may be of an interactive type (which may be interpreted as a chat type or a conversation type) that alternately receives input for performing instructed output, and generates and outputs information.

[0051] The learning model included in the artificial intelligence unit 121 can perform additional learning by a method such as transfer learning or fine tuning. For example, the artificial intelligence unit 121 learns whether the output content has been modified by a user or the like. That is, the artificial intelligence unit 121 may perform additional learning and fine tuning, etc., based on modifications to the content output by the learning model. Also, for example, each time new data is registered, etc., the artificial intelligence unit 121 may perform additional learning and fine tuning, etc., using the new data as new teacher data. This improves the accuracy of information output from the learning model.

[0052] The learning model included in the artificial intelligence unit 121 may be a learning model (distilled model) obtained by knowledge distillation using an original trained model. In knowledge distillation, a trained model such as a large-scale language model is used as a teacher model, and the parameters of the student model are adjusted so that the output loss (Soft Target Loss) of the student model (distilled model) relative to the output (Soft Target) of the teacher model is reduced, thereby learning the student model, and the student model becomes a distilled model. In addition, the student model may be learned so that the output loss (Hard Target Loss) of the student model relative to the correct answer label (Hard Target) of the teacher data (combination of input data and output data of the learning model) is reduced. Compared to the original trained model (teacher model), the distilled model has a smaller number of parameters and a smaller processing load while having performance close to the trained model. Therefore, by using the distilled model, the cost of the information processing system 1 can be reduced.

[0053] For example, the learning model used in each functional unit may be a distilled model trained using a combination of input data and output data in a large-scale language model as training data. Furthermore, when the information processing system 1 is introduced, a large-scale language model may be used as the learning model used in each functional unit, and when training data from the large-scale language model is accumulated, a distilled model obtained by knowledge distillation using the training data may be used as the learning model used in each functional unit.

[0054] An AI agent may also be called an autonomous agent. An "AI agent" is a model that, when a target (goal, objective, etc.) such as "teach me XX" or a task such as "output XX" is input, breaks down the processing required to reach the goal or accomplish the task into subtasks, actions, etc., and collects and analyzes necessary data, generates and executes programs, etc. An AI agent aims at information or instructions input by a user, autonomously selects and executes tasks, actions, etc. according to the target, outputs information according to the target, and does not require intervention (operation input) from the user. In addition, an AI agent may autonomously learn to achieve a target by autonomously making and executing plans and evaluating the results of the execution. For example, an AI agent may be autonomously updated based on the results of the execution of subtasks (e.g., collected information, analysis results of information, etc.).

[0055] 2.2 Functional Configuration Details In this section, the functional configuration of this embodiment will be described in detail. Fig. 5 is a diagram showing an overview of a functional arrangement 50 provided in the information processing system 1 of this embodiment.

[0056] As shown in FIG. 5, the function arrangement 50 included in the information processing system 1 in the present embodiment is further classified into an LMS system 51 and an analysis system 52. Here, LMS is an abbreviation of "Learning Management System" and refers to an online system for managing, providing, and tracking education and training. That is, according to the LMS, it is possible to easily realize online the distribution of learning content, the progress management for each student, tests and evaluations, communication between students and teachers, the issuance of certification certificates, and the cooperation with external systems.

[0057] <LMS system 51> In the LMS system 51 in the example of the present embodiment, for example, there are subject management 511 for managing subjects that students can take, class management 512 for managing classes to which students belong, lecture management 514 for managing lectures that students can attend, attendance management 515 for managing students' attendance in lectures, assignment submission management 516 for managing whether students have submitted assignments, submitted assignment evaluation 517 which summarizes the evaluations of the assignments submitted by students, and feedback 518 which summarizes the feedback to students based on the evaluations. Thus, in the LMS in the example of the present embodiment, it is possible to manage the learning history, grade information, submitted assignment history, and behavioral data of students (report creators).

[0058] <Analysis system 52> The analysis system 52 is a group of functional units for analyzing the assignments submitted by students. In the example of the present embodiment, the analysis system 52 is further classified into a BI function system 52a and an analysis function system 52b. Here, BI is an abbreviation of "Business Intelligence" and is a general term for technologies and processes for enterprises and organizations to collect and analyze data and support decision-making. In particular, it is used for business strategies, business improvement, and learning analysis in educational institutions.

[0059] By using a BI tool, it is possible to visualize a huge amount of data and support business improvement and strategy planning. Representative functions include data collection and integration, data visualization, data analysis, report creation and sharing, etc. When this BI tool is adopted in an educational institution such as a university, it is possible to manage and analyze various information related to students in cooperation with the above-mentioned LMS. That is, in this embodiment, the analysis system 52 acquires education-related data including at least one of the report creator's learning history, grade information, submitted assignment history, and behavior data by referring to the learning management system (LMS) of the report creator, that is, the organization to which the student belongs, that is, the university, and analyzes the personality using this education-related data. According to this embodiment, it is possible to perform an accurate analysis that takes into account not only the content of the report but also the learning history, etc.

[0060] In the example of this embodiment, the BI function system 52a includes a plurality of dashboards 52a1 to 52a4 and subject evaluation data 52a5. Here, the dashboard refers to a tool that visualizes a lot of information to assist intuitive understanding. That is, the BI function system 52a in this embodiment includes a teacher dashboard 52a1 in which learning information for teachers is visualized, a subject / class / lecture dashboard 52a2 in which the learning status of each subject is visualized, a student dashboard 52a3 in which the learning progress status of each student is visualized, and a submitted assignment dashboard 52a4 in which the submission status of assignments is visualized. The subject evaluation data 52a5 is data including evaluation criteria used for evaluating the grades of students. By inputting the information summarized in these dashboards and the subject evaluation data 52a5 together into the analysis function system 52b, it becomes possible to perform report analysis, which will be described in detail later.

[0061] The analysis function system 52b includes a submitted assignment evaluation function 52b1 and a student analysis function 52b2. The submitted assignment evaluation function 52b1 is a function for evaluating the assignment report submitted by the student according to the content of the text, and the student analysis function 52b2 is a function for analyzing the personality of the student according to the evaluation of the report and its content. Further details of these functions will be described later.

[0062] 3. Information processing method In this section, an information processing method of the server device 10 will be described. This information processing method may be executed as each step by each unit of the server device 10. Note that the various features described in this section can be combined with each other as long as no technical contradiction occurs.

[0063] As described above, the information processing system 1 includes at least one processor (e.g., control unit 11), and the processor is configured to execute the following steps by reading a program recorded in a memory. In other words, the information processing method includes the steps of the information processing system 1. From another perspective, the program causes a computer to execute the steps of the information processing system 1. FIG. 6 is a diagram showing an overview of information processing (report analysis processing) executed by the information processing system 1. Details of the processing related to each step in FIG. 6 will be described below.

[0064] First, in step S101, the acquisition unit 112 of the control unit 11 acquires data on at least one report R1 submitted by a student S1 and written in a natural language. The acquisition unit 112 acquires data on the report R1. Here, "written in a natural language" basically means "written in a language that humans can understand," regardless of the type of language.

[0065] In step S102, the identification unit 115 identifies an evaluation of the report according to the content of the sentences in the report. More specifically, the identification unit 115 identifies an evaluation of the report R1 according to the accuracy of the sentences in the report. The accuracy here includes the logic, persuasiveness, clarity of expression, and / or appropriateness of vocabulary of the sentences in the report. According to this embodiment, it is possible to evaluate the accuracy of the sentences in the report from various viewpoints. Further details of step S102 will be described with reference to FIG. 7 below.

[0066] In step S103, the generating unit 113 generates structured data SR1 in which the report contents and evaluations are combined into one data. Here, "structuring the report contents and evaluations into one data" refers to packaging the report contents and evaluations for one report so that they can be linked to each other and managed in a centralized manner, rather than managing them independently. According to this aspect, the number of analysis targets is increased compared to when only the report contents are the analysis target, and more detailed analysis is possible. In this embodiment, the report R1 includes multiple reports created by the same creator, and the generating unit 113 generates structured data SR1 in which the contents of the multiple reports R1 and the corresponding evaluations are combined in a chronological order. According to this aspect, analysis can be performed while taking into account the characteristics of the report creator that change over time. This structured data combined in a chronological order may be in a so-called json (JavaScript Object Notation) format. Here, the "json method" refers to a format for structuring and describing data, and is a format for expressing data using pairs of "key" and "value", which is easy for both humans and computers to read and is often used when structuring data.

[0067] In step S104, the generation unit 113 combines the generated structured data SR1 with a prompt P1 of a large-scale language model (LLM) held by the artificial intelligence unit 121. This process makes it possible to construct the structured data SR1 in a state that can be analyzed by the analysis unit 116 in the next step. Here, the prompt P1 is a prompt for personality analysis, and is used to perform personality analysis of the learner. Specifically, the prompt P1 is input to the LLM with the structured data SR1 attached, and the learner's personality tendencies, behavioral patterns, inclinations, etc. are analyzed. By applying the prompt P1, it becomes possible to evaluate the learner's characteristics from multiple angles and provide individually optimized feedback.

[0068] In step S105, the analysis unit 116 analyzes the personality of the report creator based on the content and evaluation of the structured data SR1 (structured report) and a predetermined algorithm (for example, an algorithm using the prompt P1). More specifically, a Student analysis, which will be described later, is executed to derive an analysis result AR1. According to this embodiment, a multifaceted analysis is possible compared to a case where the personality of the report creator is analyzed based only on either the quality or the content of the report, and a more in-depth personality can be derived. Further details of step S105 will be described with reference to FIG. 8.

[0069] As used herein, student analysis refers to a process of analyzing four characteristics, namely, "personal branding profile," "orientation," "behavioral characteristics," and "basic personality information," based on report data submitted by students. Here, "personal branding profile" refers to information that clarifies the individuality and strengths of students and differentiates them from others. "Orientation" refers to an analysis of the direction of a learner's interests and concerns and the motivation for their actions. "Behavioral characteristics" refers to an evaluation of a learner's behavioral patterns and decision-making tendencies. "Basic personality information" refers to an estimation of a learner's personality tendencies based on psychological theories. Further details of these four characteristics will be described later.

[0070] Alternatively, without distinguishing between step S104 and step S105, the analysis unit 116 may assign the structured data SR1 to the prompt P1, input the LLM prompt with the structured data SR1 assigned thereto into a large scale language model (LLM), and analyze the personality of the creator.

[0071] FIG. 7 is a diagram showing further details of the process shown in step S102 in FIG. 6. The process in step S102 in FIG. 6 is described as "determining the evaluation of report R1 according to the accuracy of the sentences in report R1", but in this embodiment, this evaluation is performed on a five-point scale. In step S102A, the specification unit 115 uses the assignment R1 submitted by the student, the prompt P2 for the five-point scale evaluation, and the evaluation criterion EC1 to determine the accuracy of the sentences in report R1 and to specify the evaluation of the report. The evaluation criterion EC1 here is, for example, an "evaluation index for learning evaluation" called a rubric, and executes a process of, for example, judging the above-mentioned "logic, persuasiveness, clarity of expression, and / or appropriateness of vocabulary of the sentences in the report" on a four-point scale (excellent, good, average, needs improvement), and giving a five-point scale as a comprehensive evaluation. More specifically, the evaluation criteria for "logic" can be "consistency of the argument and appropriateness of the logical flow," "persuasiveness" can be "presence or absence of specific examples or evidence to support the argument," "clarity of expression" can be "accuracy of sentence structure and grammar," and "appropriateness of vocabulary" can be "whether appropriate words and technical terms are used."

[0072] As a result of step S102A, an evaluation result ER1 is given to the report R1. In step S102B, the identification unit 115 further identifies the evaluation using sentiment analysis. Here, sentiment analysis refers to a technology that determines emotions such as positive, negative, and neutral from text data. Specific methods include a loose-based method that calculates an impression score using a word dictionary, a machine learning method that learns past data and determines emotions, and a deep learning method that uses an advanced natural language processing model, but any method may be used. According to this embodiment, it is possible to perform an evaluation that takes into account the creator's emotions and opinions. As a result of the analysis in step S102B, the analysis unit 116 derives an analysis result AR2. This analysis result AR2 includes a five-point evaluation of the report R1, the evaluation reason, and the result of the sentiment analysis. In step S103 of FIG. 6, a plurality of analysis results AR2 derived for a plurality of reports are structured and become structured data SR1.

[0073] Figure 8 is a diagram showing further details of the process shown in step S105 in Figure 6. In Figure 6, step S105 simply involves inputting the prompt P1 to which the structured data SR1 (the integrated result of the analysis results AR2) has been added into the LLM for analysis, but this step is more specifically divided into steps S105A to S105C.

[0074] First, in step S105A, a prompt P1A for analyzing a basic profile to which structured data SR1 has been added is input to the LLM, and an analysis result AR3 of the basic profile is derived. Here, the analysis result AR3 of the basic profile includes the aforementioned tendencies and behavioral characteristics.

[0075] In step S105B, the self-branding prompt P1B with the basic profile analysis result AR3 is input to the LLM, leading to the self-branding analysis result AR4. The self-branding analysis result AR4 includes the above-mentioned personal branding profile in addition to the basic profile analysis result AR3.

[0076] In parallel with the above process, in step S105C, a basic personality analysis is performed on the analysis result AR3 of the basic profile by a predetermined algorithm logic AL1, and an analysis result AR5 is derived. The analysis result AR5 of the basic personality analysis includes the above-mentioned basic personality information. In this embodiment, this algorithm logic AL1 may be a psychological characteristic analysis model. A representative model that can be adopted is the Big Five theory. The Big Five theory is a psychological model that represents human personality traits by five main factors and evaluates an individual's personality based on the strength of each element. More specifically, the five main factors are "openness (a tendency to be curious and actively seek new experiences. The more creative a person is, the higher the score, and the more conservative a person is), "conscientiousness (a tendency to have a strong sense of self-control and a strong sense of responsibility. The more planned and cautious a person is, the higher the score, and the lower the impulsive and unplanned a person is), "extroversion (a tendency to be sociable and energetic. The higher the score is for people who prefer to interact with others, and the lower the score is for people who are introverted), "cooperativeness (a tendency to be considerate and to cooperate with others. The higher the score is for people with high empathy, and the lower the score is for people who are competitive and self-centered), and "neuroticism (indicates how sensitive a person is to stress and negative emotions. The higher the score is for people who are mentally unstable, and the lower the score is for people who are emotionally stable)." In this embodiment, the algorithm logic AL1 quantifies the learner's personality traits based on the Big Five theory, and derives the personality by combining it with the analysis results of the report. In other words, it can be said that the analysis unit 116 analyzes the personality using a psychological trait analysis model. According to this embodiment, it is possible to perform an analysis that takes into account a psychological perspective, such as the Big Five. In addition, it is possible to perform a more detailed analysis of the learner's personality from a psychological perspective, including their thinking tendencies and behavioral patterns, rather than merely analyzing the characteristics of the text.

[0077] 6 is an analysis result AR1 obtained by integrating these analysis results AR4 and AR5. Moreover, the analysis result AR1 may further be integrated with the analysis result AR2 of sentiment analysis.

[0078] In the above, the Big Five theory has been cited as the psychological trait analysis method used in this embodiment, but the model that can be adopted is not limited to this, and various well-known models can be adopted, such as the HEXACO model, which is an extension of the Big Five theory and evaluates six traits, the MBTI model, which classifies 16 types of personalities, the Enneagram, which classifies into nine personalities, the 16PF, which analyzes personality by measuring 16 factors, and the DISC theory, which classifies behavioral traits into four categories.

[0079] In this way, the analysis unit 116 calculates a first analysis result (e.g., analysis result AR3) using a first analysis model (e.g., a model into which prompt P1A is input) on the contents of structured data SR1, and analyzes the personality using a second analysis model different from the first analysis model (e.g., a model into which prompt P1B is input) for the first analysis result. The first analysis result includes a basic profile of the creator. According to this embodiment, it becomes possible to gradually grasp the personality analysis results of the report creator.

[0080] 9 is an example of a report assignment RA given to a student. In this embodiment, the contents of the report submitted by the learner are designed for the purpose of analyzing the learner's thinking tendency, behavioral characteristics, inclinations, and personal branding. These report assignments are classified into, for example, the following six categories, and different analyses are applied according to each category.

[0081] 1. Tasks that encourage self-awareness and self-analysis These tasks are aimed at analyzing the learner's "self-understanding" and "ability to express oneself" and evaluating the depth and consistency of self-awareness. Examples of such tasks include the following in Figure 9: "Introduce yourself and describe how you felt (200 characters or less)," "Describe what characteristics you have. Explain in positive terms (200 characters or less)," and "Refine your 'reason for enrolling in this university' in your first report (200 characters or less)." For these task examples, the learner's orientation and behavioral characteristics are extracted by basic profile analysis using prompt P1A, and the positive / negative tendencies of the text are evaluated by sentiment analysis.

[0082] 2. Issues that question the decision-making process These tasks aim to evaluate the learner's "information gathering ability, logical thinking ability, and planning ability" when making decisions. Examples of such tasks include "What would you like to consider or research when choosing a program or laboratory (400 characters or less)" and "What career path do you envision for the future? Think about it while taking into consideration your own characteristics and the characteristics of students studying at this university (400 characters or less)" as shown in Figure 9. For these task examples, the learner's decision-making patterns are extracted through basic profile analysis using prompt P1A, and the logical structure of the decision-making is evaluated using a rubric evaluation (logic and persuasiveness).

[0083] 3. Tasks that test behavioral habits and planning These tasks aim to evaluate the learner's "time management ability, self-regulation ability, and planning ability." Examples of such tasks include "Based on the contents of your time-use record book, list the aspects of your lifestyle that you would like to continue or improve in the future (400 characters or less)" and "Describe what you would like to challenge in your university life (400 characters or less)" in Figure 9. For these tasks, the learner's behavioral characteristics are extracted through basic profile analysis using prompt P1A, and the way in which planning is expressed is analyzed through rubric evaluation (appropriateness of vocabulary, clarity of expression).

[0084] 4. Issues with communication skills This task aims to evaluate the learner's "cooperativeness, social adaptability, and leadership." Examples of such tasks include "How would you like to improve your communication skills in your future student life (400 characters or less)," and "Describe how you would like to improve your 'ability to work in a team', a basic skill for working in society (200 characters or less)." For these example tasks, the learner's cooperativeness and leadership are analyzed through self-branding analysis using prompt P1B, and psychological tendencies regarding building relationships with others are evaluated through sentiment analysis.

[0085] 5. Tasks that test adaptability to external environments and application of learning This task aims to evaluate the learner's "ability to adapt to the environment and absorb new knowledge." Examples of such tasks include "What would you like to apply to your future student life from today's lecture (400 characters or less)" and "As a student at this university, how would you like to be involved in technological changes (200 characters or less)" in response to these task examples. These task examples are analyzed for the learner's ability to apply learning through self-branding analysis using prompt P1B, and an evaluation is made of whether the learner "absorbs knowledge positively" or "is resistant" through sentiment analysis.

[0086] 6. Leadership and problem-solving skills These tasks are aimed at evaluating how learners demonstrate "leadership, problem-solving ability, and judgment." Examples of such tasks, not shown in Figure 9, include "Describe how you would demonstrate leadership when working on a team project (400 characters or less)," and "When faced with a difficult situation, explain with concrete examples how you would respond (400 characters or less)." For these task examples, leadership characteristics are evaluated through a self-branding analysis using prompt P1B, and problem-solving ability is measured through a rubric evaluation (logic and persuasiveness).

[0087] As described above, the "list of report assignment examples" in this embodiment serves as a criterion for evaluating a learner's thinking tendency, decision-making ability, behavioral habits, cooperativeness, and environmental adaptability from multiple angles. In addition, the information processing system 1 according to this embodiment enables more precise personality analysis by combining analysis methods applied to each of these report assignments.

[0088] FIG. 10 is a diagram showing further details of each element derived by the Student analysis described above. A. Personal Branding Profile As shown in Figure 10, a personal branding profile is, in a word, "the core for differentiating the value of one's talent and effectively communicating it to others," and its components are a "tagline" and a "USP." A "tagline" is a phrase that conveys one's identity in an impressive way, such as "robot explorer." "USP" is an abbreviation for "Unique Selling Proposition," and refers to a short sentence that presents a unique strength or value proposition that differentiates one from competitors. A specific example is a short sentence such as "I have loved robots since I was a child, and I am passionate about robotics research at university."

[0089] B. Intentionality As shown in Figure 10, orientation is, in a word, "keywords that indicate the current direction," and its components include "interests" and "sources of motivation." "Interests" are things or themes that one wants to know about, do, or be involved in, such as "robots, programming, abacus, psychology, travel." "Sources of motivation" are things that serve as the driving force, motivation, or healing when taking action, such as "monetary compensation, desire for growth, contact with a new culture, pet cats."

[0090] C. Behavioral characteristics As shown in Figure 10, behavioral characteristics are, in a word, "sources of behavioral patterns and tendencies that characterize how we behave," and include "valued means" and "valued end values" as components. "Values ​​valued means" are values ​​that are valued as a means to achieve a goal, for example, "Rokeach's instrumental values." Here, "Rokeach's instrumental values" is one of the human values ​​proposed by psychologist Milton Rokeach, and refers to values ​​related to "how to live." More specifically, values ​​include "sincerity," "responsibility," "courage," "independence," "tolerance," "creativity," "hard work," and "discipline." "End values ​​valued" are ideal states or values ​​that one ultimately wants to reach, for example, "Rokeach's terminal values." "Rokeach's terminal values" is one of the human values ​​proposed by psychologist Milton Rokeach, and refers to values ​​related to "what kind of life do we ultimately want to live?" More specifically, these include "happiness," "freedom," "self-expression," "love," "social acceptance," "peace," "harmony," and "prosperity."

[0091] D. Basic personality information As shown in Figure 10, basic personality information is, in a word, "basic personality information based on the findings of personality psychology," and its components include the "BIG5," "universal human resource value traits," and "personality risk." "BIG5" refers to the descriptive Big Five theory, and an explanation is omitted here. "Universal human resource value traits" are personal traits evaluated in a job, such as leadership and autonomy, rated on a five-point scale. "Personality risk" refers to the possibility of a negative impact on work, such as a lack of grit and mental vulnerability, rated on a five-point scale.

[0092] Fig. 11 is an example of a screen showing the analysis results of the Student analysis described above. This example screen is displayed, for example, on the display unit D1, which is an example of the output unit 35 of the teacher's terminal 30. A list of results RL of the Student analysis performed on multiple students is displayed on the display unit D1. The result list RL includes the update date and time of the analysis results, photos of the students, and each of the items constituting the Student analysis results described in Fig. 10. The teacher can refer to this list and select any item to check more detailed information about that item.

[0093] Fig. 12 is an example of a screen showing the detailed results of the Student analysis. This screen is displayed, for example, on the display unit D2, which is an example of the output unit 25 of the student terminal 20. The symbols attached to each area on this screen correspond to each item used in the Student analysis described in Fig. 10, and the details of each are omitted.

[0094] In this way, the display control unit 111 in the information processing system 1 displays a screen that allows the creator of the report to understand the analyzed personality. According to this embodiment, the creator of the report can understand his / her own personality that has been objectively analyzed, and can make changes to his / her future actions or use the results as a guide for actions. Note that, in this embodiment, this screen example has been described as being displayed on the display unit D2 of the student terminal 20, but it may also be displayed on the display unit D1 of the teacher terminal 30.

[0095] 13 is a diagram showing the update process of the prompt P1. First, in step S201, the Student analysis is executed to derive the analysis result AR1, as in the embodiment described in FIG.

[0096] Here, in the Student analysis in step S201, the analysis result AR1 is output as one result in the embodiment of Fig. 6, but in the Student analysis in this embodiment, the Student analysis is performed multiple times from different viewpoints, and an analysis result AR6 including multiple versions of the results is output (step S202). The viewpoint here can be changed by weighting the items of the Student analysis described in Fig. 10, for example. The processes of steps S201 and S202 may be performed by the analysis unit 116.

[0097] In step S203, the storage unit 117 of the control unit 11 displays the analysis results including the multiple Student analyses output in step S202 to the creator of the report, and accepts and stores one selection made by the creator. The version selected by the creator from the multiple versions may be subjective, or may be selected according to a predetermined criterion. In addition, the version selection may be made not by the creator of the report, but by the supervisor of the report creator (e.g., a teacher in charge of supervision).

[0098] In step S204, aggregation unit 118 of control unit 11 accepts the multiple selected analysis results AR7 accumulated by accumulation unit 117, and aggregates them into one analysis result AR8. That is, the processes of steps S201 to S203 are performed for multiple report creators, multiple "selected analysis results AR7" are accumulated, and aggregation unit 118 aggregates them into analysis result AR8, which is a "collection of selected analysis results AR7".

[0099] The update unit 119 of the control unit 11 then receives the analysis result AR8 aggregated from the aggregation unit 118, and updates the prompt P1 using this analysis result AR8 as teacher data. As a method of updating, the analysis result AR7 selected from the perspective of, for example, what kind of answer pattern is likely to be selected as "appropriate", how the sentiment analysis and sentence structure features affect it, which part of the prompt P1 used in the evaluation has a strong influence, etc. is analyzed, and the instructions and conditions of the prompt P1 are adjusted to improve the adjustment so that it can be made more accurate.

[0100] To summarize this embodiment, the analysis unit 116 in the information processing system 1 applies the prompt P1 from multiple different perspectives when analyzing the personality of a report creator to calculate multiple analysis results AR6. The accumulation unit 117 accumulates one analysis result selected by the creator from the multiple analysis results. The aggregation unit 118 aggregates the multiple analysis results selected by the different creators as teacher data. The update unit 119 updates the prompt P1 based on the teacher data. According to this embodiment, the system autonomously and continuously learns the analysis results, and the accuracy of the prompts can be expected to improve.

[0101] [Second embodiment] In the above, a first embodiment has been described in which a student's personality is derived by analyzing a report written by the student. In the following, a second embodiment will be described in which the analyzed personality is used.

[0102] Specifically, in this embodiment, the analyzed personalities of students are provided to organizations engaged in job hunting, such as companies and university seminars, in order to facilitate matching between organizations and students.

[0103] 14 is a sequence diagram showing matching between the derived personality of a student and the recruitment requirements of the recruiter. First, in steps S301 and S302, as described in the above embodiment, the student creates and submits a report, and the personality is analyzed and accumulated by the system.

[0104] Next, in step S303, the recruiting party presents the recruitment requirements to the system. Here, the recruitment requirements are requirements for hiring personnel with the skills and aptitudes required by organizations such as companies and universities, and include job types and positions for companies, research themes and specialized fields of seminars for university seminars, and common requirements for both, such as desired skills and abilities (business skills, academic knowledge, technical ability, etc.), desired personality (personality elements such as cooperation, leadership, and thinking ability), application qualifications, application conditions, etc.

[0105] In step S304, the system performs matching between the personality of the student derived from the report submitted by the student and the job requirements presented by the recruiting side. This matching process may be performed by the analysis unit 116 of the control unit 11 of the system.

[0106] The matching process first determines what fields the student is interested in and suitable for based on the inclinations and behavioral characteristics contained in the student's personality.Then, by comparing the job requirements provided by the employer, it narrows down the organizations that the student may be interested in.If it is determined that the student has behavioral characteristics that match the requirements of the organization, it can determine that the two are a good match.

[0107] In steps S305 and S306, the system provides the calculated matching information to the student and the recruiting party, respectively. Then, in steps S307 and S308, the student and the recruiting party take action based on the provided matching information, such as the student applying to the recruiting party or the recruiting party scouting the student.

[0108] FIG. 15 is an example of a screen showing a list of the derived student personalities shown to the company. Note that this screen example assumes that the company is in a so-called free trial period. In column C1, the student's name is displayed for convenience, but this part is also personal information and is hidden. In column C2, the affiliation is displayed. In column C3, details of the affiliation (e.g., faculty, department, seminar name, etc.) are displayed, but this part is also hidden during the trial period. In column C4, a brief character evaluation of the student is displayed. This is the "tagline" mentioned above. In column C5, the student's interests are displayed. In columns C6, 167 and onwards, the student's behavioral characteristics are displayed together with a rank. Although column C8 is a paid feature, it is a column that displays the personality in more detail and allows the user to send anonymous messages to the student.

[0109] To summarize this embodiment, the acquisition unit 112 in the information processing system 1 further acquires requirement information related to the job requirements. Furthermore, the output unit 114 outputs talent matching information related to the compatibility between the job target and the talent based on the analyzed personality and requirement information. According to this embodiment, it is possible to suggest an appropriate career to the creator based on the characteristics, and it is possible to introduce to the recruiter a person who has the characteristics desired by the recruiter from among many report creators.

[0110] By adopting a system like this embodiment, companies can receive analyzed personality information about students from universities, and can make decisions based on not only the subjective evaluation of the students who are applicants, but also the objective evaluation of the universities that supervise them, making it possible to carry out more efficient recruitment activities. This is also a great advantage for students.

[0111] On the other hand, the information provider (university) will be able to provide companies with student characteristics, and in return will receive commission from the companies, which will become a major source of income for the university.

[0112] [others] The information processing system 1 according to the above embodiment may be configured as follows.

[0113] At least one of the devices included in the information processing system 1 may be installed outside Japan. For example, the server device 10 or a server may be installed outside Japan, and the terminals 20 and 30 may be installed inside Japan. Similarly, a user may access the server device 10 installed inside Japan from outside Japan using his or her own terminal 20 or 30. According to such an embodiment, a more convenient experience can be provided to the user through various management forms.

[0114] In one embodiment, the functional units realized by the control unit 11 of the server device 10 are described, but at least a part of them may be implemented as functional units realized by other servers. Alternatively, they may be implemented as functional units realized by the control unit 21 of the student terminal 20 or the control unit 31 of the teacher terminal 30. Furthermore, the various information described in the above example may be stored not only in the storage unit 12 of the server device 10 but also in a distributed manner in other external devices using block chain technology or the like.

[0115] It may be provided in any of the following ways:

[0116] (1) An information processing system comprising a memory and a processor, the processor being configured to execute each of the following steps by reading a program recorded in the memory: a first acquisition step acquiring data of at least one report written in a natural language; a determination step determining an evaluation of the report based on the content of the report's text; and a analysis step analyzing the personality of the report's creator based on the content of the report and the evaluation and a predetermined algorithm.

[0117] According to such an embodiment, a more multifaceted analysis is possible than when the personality of a report creator is analyzed based solely on either the quality or content of the report, making it possible to derive a more in-depth personality.

[0118] (2) In the information processing system described in (1) above, in the analysis step, a first analysis result is calculated using a first analysis model on the contents of the report, and a second analysis model different from the first analysis model is used on the first analysis result to analyze the personality, wherein the first analysis result includes a basic profile of the creator.

[0119] According to this embodiment, it becomes possible to understand the personality analysis results of the report creator in stages.

[0120] (3) An information processing system according to (1) above, further comprising: in the generation step, generating structured data in which the content of the report and the evaluation are combined into a single piece of data; and in the analysis step, inputting the prompt to which the structured data has been added into a large-scale language model to analyze the personality of the creator.

[0121] According to this embodiment, the analysis targets are increased compared to when only the contents of the report are the subject of analysis, making it possible to perform a more detailed analysis.

[0122] (4) In the information processing system described in (3) above, the report includes multiple reports created by the same creator, and in the generation step, structured data is generated by combining the contents of the multiple reports and the evaluations corresponding to each report in chronological order, and in the analysis step, the prompts to which the structured data has been added are input into the large-scale language model to analyze the personality of the creator.

[0123] According to this embodiment, analysis can be performed taking into account the characteristics of the report creator that change over time.

[0124] (5) An information processing system according to any one of (1) to (4) above, wherein in the identification step, the evaluation is identified according to the accuracy of the report's writing, and the accuracy includes the logic, persuasiveness, clarity of expression, and / or appropriateness of vocabulary of the report's writing.

[0125] According to this embodiment, it becomes possible to evaluate the accuracy of the report text from various viewpoints.

[0126] (6) In the information processing system according to any one of (1) to (5) above, in the identification step, the evaluation is identified further using sentiment analysis.

[0127] According to this embodiment, it is possible to perform an evaluation that takes into account the creator's feelings and opinions.

[0128] (7) In the information processing system according to any one of (1) to (6) above, in the analyzing step, the personality is analyzed using a psychological characteristic analysis model.

[0129] According to such an embodiment, it becomes possible to not only simply analyze the characteristics of a sentence, but also to analyze a learner's thinking tendencies and behavioral patterns more precisely from a psychological perspective.

[0130] (8) An information processing system according to any one of (1) to (7) above, wherein in a second acquisition step, education-related data including at least one of the report creator's learning history, grade information, submitted assignment history, and behavioral data is acquired by referring to a learning management system in an organization to which the report creator belongs, and in the analysis step, the personality is analyzed using the education-related data.

[0131] According to this embodiment, it is possible to perform an accurate analysis that takes into account not only the contents of the report but also the learning history and the like.

[0132] (9) In the information processing system according to any one of (1) to (8) above, in the display control step, a screen is displayed that enables the creator to understand the analyzed personality.

[0133] According to such an embodiment, the writer of the report will be able to grasp his / her own personality through an objective analysis, and will be able to make changes to his / her future actions or use the results as a guide for his / her actions.

[0134] (10) An information processing system according to any one of (1) to (9) above, wherein in the analysis step, the predetermined algorithm is applied from multiple different perspectives when analyzing the personality of the creator to calculate multiple analysis results, in the storage step, one analysis result selected by the creator from the multiple analysis results is stored, in the aggregation step, the multiple analysis results selected by the different creators are aggregated as teacher data, and in the update step, the predetermined algorithm is updated based on the teacher data.

[0135] According to this embodiment, the system will autonomously and continuously learn from the analysis results, which is expected to improve the accuracy of prompts.

[0136] (11) An information processing system according to any one of (1) to (10) above, further comprising, in a third acquisition step, acquiring requirement information relating to the job requirements, and, in an output step, outputting human resource matching information relating to the compatibility between the job target and the human resource based on the analyzed personality and the requirement information.

[0137] According to such an embodiment, it becomes possible to suggest appropriate careers to report creators based on their characteristics, and it becomes possible for recruiters to be introduced to people who possess the characteristics desired by the recruiting party from among many report creators.

[0138] (12) A program that causes a computer to execute each step of the analysis system described in any one of (1) to (11) above.

[0139] According to this embodiment, it can be implemented as a program.

[0140] (13) An information processing method comprising each step of the information processing system according to any one of (1) to (11) above.

[0141] According to this aspect, the present invention can be implemented as an information processing method. Of course, this is not the case.

[0142] Finally, although various embodiments according to the present disclosure have been described, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiment can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments and their modifications are included within the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0143] 1: Information processing system 10: Server device 11: Control section 111: Display control unit 112: Acquisition Department 113 :Generation part 114: Output section 115: Specific part 116:Analysis Department 117: Storage unit 118: Aggregation section 119:Update section 120: Memory management department 121: Artificial Intelligence Department 12: Storage section 13: Communications Department 14: Communication bus 2: Communication lines 20: Student terminal 21: Control section 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communication bus 30: Teacher's terminal 31: Control section 32: Storage section 33: Communications Department 34: Input section 35: Output section 36: Communication bus 50:Functional arrangement 51:LMS system 511: Subject management 512: Class Management 514: Lecture management 515: Attendance management 516: Assignment submission management 517: Evaluation of submitted assignments 518: Feedback 52: Analysis system 52a: BI function system 52a1: Teacher Dashboard 52a2: Lecture Dashboard 52a3: Student Dashboard 52a4: Submission Dashboard 52a5: Subject evaluation data 52b:Analysis function system 52b1: Submitted assignment evaluation function 52b2 :Analysis function AL1: Algorithmic Logic AR1:Analysis results AR2:Analysis results AR3:Analysis results AR4:Analysis results AR5:Analysis results AR6:Analysis results AR7:Analysis results AR8:Analysis results C1: Column C2: Column C3: Column C4: Column C5: Column C6: Column C7: Column C8: Column D1:Display section D2: Display section ER1: Evaluation result P1 : Prompt P2: Prompt R1 : Report RA: Report assignment RL :Result List S1: Student SR1 : Structured Data T1:Teacher

Claims

1. An information processing system, The method includes the steps of: In a first acquisition step, data of at least one assignment report written in a natural language is acquired; In the identification step, an evaluation of the assignment report is identified according to the accuracy of the sentences in the assignment report; In the generating step, structured data is generated by combining the content of the assignment report and the evaluation into one piece of data; In the analysis step, the prompt combined with the structured data is input to a large-scale language model to analyze the personality of the writer of the assignment report. Information processing system.

2. 2. The information processing system according to claim 1, In the analysis step, a first analysis result is calculated by using a first analysis model on the contents of the assignment report, and a second analysis model different from the first analysis model is used on the first analysis result to analyze the personality, The first analysis result includes a basic profile of the creator. Information processing system.

3. 2. The information processing system according to claim 1, The subject report includes a plurality of subject reports created by the same creator; In the generating step, the structured data is generated by combining the contents of the multiple assignment reports and the evaluations corresponding to each of the multiple assignment reports in a chronological order; In the analyzing step, the prompt combined with the structured data is input to the large-scale language model to analyze the personality of the creator. Information processing system.

4. 2. The information processing system according to claim 1, An information processing system, wherein the accuracy includes logic, persuasiveness, clarity of expression, and / or appropriateness of vocabulary of the writing of the project report.

5. 2. The information processing system according to claim 1, The identifying step further includes identifying the evaluation using sentiment analysis. Information processing system.

6. 2. The information processing system according to claim 1, In the analyzing step, the personality is analyzed using a psychological characteristic analysis model. Information processing system.

7. 2. The information processing system according to claim 1, In a second acquisition step, education-related data including at least one of the creator's learning history, grade information, submitted assignment history, and behavioral data is acquired by referring to a learning management system in an organization to which the creator of the assignment report belongs; In the analyzing step, the personality is analyzed using the education-related data. Information processing system.

8. 2. The information processing system according to claim 1, Furthermore, in the display control step, a screen that enables the creator to understand the analyzed personality is displayed. Information processing system.

9. 2. The information processing system according to claim 1, In the analyzing step, the large-scale language model is applied from a plurality of different perspectives when analyzing the personality of the creator to calculate a plurality of analysis results; In the storing step, one analysis result selected by the creator from the plurality of analysis results is stored; In the aggregating step, a plurality of analysis results selected by the plurality of different creators are aggregated as training data; In the updating step, the prompts of the large-scale language model are updated based on the training data. Information processing system.

10. 2. The information processing system according to claim 1, In the third acquisition step, requirement information regarding the job requirements is acquired, Furthermore, in an output step, the information processing system outputs personnel matching information regarding compatibility between the job target and personnel based on the analyzed personality and the requirement information.

11. A program, A method for causing a computer to execute each step of the analysis system according to any one of claims 1 to 10, program.

12. 1. An information processing method, comprising: The information processing system according to any one of claims 1 to 10, Information processing methods.

Images