Information processing systems, programs, and information processing methods

Abstract

We provide information processing systems that allow for a deeper understanding of the personality of a report writer by analyzing documents, especially reports, from multiple perspectives. [Solution] According to one aspect of the present invention, an information processing system is provided, comprising memory and a processor, wherein the processor is configured to perform the following steps by reading a program recorded in memory: in a first acquisition step, data of at least one report written in natural language is acquired; in an identification step, an evaluation of the report is identified according to the content of the report text; and in an analysis step, the personality of the report author is analyzed 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 Art]

[0002] In recent years, research on analyzing text to derive the personality of a text author has progressed. For example, Patent Document 1 discloses a technique for predicting the personality of a text author by analyzing text posted on social networking services. [Prior Art Literature] [Patent Literature]

[0003] [Patent Document 1] Japanese Unexamined Patent Publication No. 2020-149196 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] Further advancement of such research is demanded to more deeply analyze the personality of a text author.

[0005] In view of the above circumstances, the present invention aims to provide an information processing system and the like that can deeply dig into the personality of a report author by performing multifaceted analysis of text, particularly reports. [Means for Solving the Problem]

[0006] According to one aspect of the present invention, an information processing system is provided, comprising memory and a processor, wherein the processor is configured to perform the following steps by reading a program recorded in memory: in a first acquisition step, data of at least one report written in natural language is acquired; in a identification step, an evaluation of the report is identified according to the content of the report text; and in an analysis step, the personality of the report author is analyzed based on the content and evaluation of the report and a predetermined algorithm.

[0007] In this manner, an information processing system is provided that allows for a deeper understanding of the report writer's personality by analyzing the report from multiple perspectives. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram showing the configuration of Information Processing System 1. [Figure 2] This is a block diagram showing the hardware configuration of server device 10. [Figure 3] This block diagram shows the hardware configuration of student terminal 20 and teacher terminal 30. [Figure 4] This block diagram shows the 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). [Figure 5] This figure shows an overview of the functional arrangement 50 provided in the information processing system 1 in this embodiment. [Figure 6] This diagram shows an overview of the information processing (report analysis processing) performed by Information Processing System 1. [Figure 7] This figure shows further details of the process shown in step S102 in Figure 6. [Figure 8] This figure shows further details of the process shown in step S105 of Figure 6. [Figure 9] This is an example of a report assignment given to students by a Research Assistant (RA). [Figure 10] This figure shows further details of each element derived from the Student analysis mentioned above. [Figure 11] This is an example screen showing the results of the Student analysis described above. [Figure 12] This is an example screen showing detailed results of the student analysis. [Figure 13] This diagram shows the update process for prompt P1. [Figure 14] This sequence diagram illustrates the matching of the student's personality traits with the employer's job requirements. [Figure 15] This is an example screen showing a list of student personality traits derived from the assessment, presented to the company. [Modes for carrying out the invention]

[0009] Embodiments of the present invention will be described below. The various features shown in the embodiments below can be combined with each other.

[0010] In other words, the information processing system of this embodiment is as follows. The information processing system comprises memory and a processor, and the processor performs the functions of the following parts by reading programs stored in memory. The first acquisition unit acquires data from at least one report written in natural language. The specific department determines the evaluation of the report based on the content of the report's text. The analysis department analyzes the personality of the report's author based on the report's content and evaluation, as well as a predetermined algorithm.

[0011] Incidentally, the program for implementing the software according to one embodiment may be provided as a non-transitory computer-readable medium, may be provided to be downloadable from an external server, or may be provided such that the program is activated on an external computer to implement its functions in a client terminal (so-called cloud computing).

[0012] Furthermore, in various types of information processing according to one embodiment, input and output corresponding to the input can be realized. Here, as long as an output can be 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 determination expressions such as regression expressions constructed by statistical methods), may be a trained model obtained by pre-learning the correlation between inputs and outputs, or may be generative AI such as a large language model or a visual language model that can output desired results by inputting a prompt.

[0013] Furthermore, in one embodiment, the term "unit" may include, for example, a combination of hardware resources implemented by circuits in a broad sense and software information processing that can be specifically realized by these hardware resources. In addition, although various types of information are handled in one embodiment, these types of information are represented, for example, by physical values of signal values representing voltage and current, the magnitude of signal values as a binary bit aggregate composed of 0s or 1s, or quantum superposition (so-called quantum bits), and communication and calculation can be executed on a circuit in a broad sense.

[0014] Furthermore, a circuit in a broad sense is a circuit implemented by appropriately combining at least a circuit, circuitry, a processor, a memory, and the like. The processor may be a general-purpose processor or a dedicated circuit. That is, it includes an Application Specific Integrated Circuit (ASIC), a programmable logic device (for example, a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)), and the like.

[0015] 0. Scope of Application of the Present Invention As described above, the present invention aims to deeply analyze the personality of a report creator by comprehensively analyzing text, particularly a report. In the present specification, "a student" is assumed to be the report creator, "a teacher" is assumed to be an evaluator who evaluates the report or a supervisor who supervises the student, and the description is given assuming a university to facilitate understanding. However, the relationship between the report creator and the evaluator (supervisor) is not limited to this; for example, they may be a so-called subordinate and a supervisor 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> Figure 1 is a configuration diagram representing information processing system 1. The example of information processing system 1 shown in Figure 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 communicate with each other through 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] Student terminal 20 is an information processing terminal used by student S1. Here, student S1 refers to, for example, a student belonging to each school corporation, but in this specification, this student is defined as a student in a broad sense. That is, it is not limited to students belonging to universities or colleges of technology, but also includes students belonging to junior high schools and high schools, and children belonging to elementary schools. It also includes students belonging to private schools that are not included in school corporations (private cram schools, private schools, English conversation schools, cultural schools, etc.).

[0019] The teacher terminal 30 is an information processing terminal used by teacher T1. As stated above, in this specification, student S1 is used in a broad sense, so teacher T1 is also defined as a teacher in a broad sense. That is, teacher T1 is not limited to professional teachers who have a teaching license, but also includes teachers belonging to the private schools mentioned above.

[0020] Although Figure 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 a platform used by, for example, multiple teachers and multiple students. Such a platform can be described as a report analysis platform provided by the server device 10. Although not shown in Figure 1, there may be an operator for such a platform.

[0021] Furthermore, although not shown in detail in Figure 1, in addition to students S1 and teachers T1, academic staff may also participate as users of the platform. Here, academic staff are those who support the activities or work of students S1 and teachers T1, and may be an organization or its representative that mediates interactions between students S1 and teachers T1.

[0022] In one embodiment, the information processing system 1 consists of one or more devices or components. Therefore, the information processing system 1 can be an example of a system even if it consists of a server device 10 or terminals 20, 30 alone. More specifically, the information processing system 1 may include elements selected from the group consisting of server devices 10 and terminals 20, 30. Alternatively, multiple server devices 10 or terminals 20, 30 may be used. 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> Figure 2 is a block diagram showing the hardware configuration of the server device 10. As shown in Figure 2, the server device 10 comprises 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 within 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 predetermined programs stored in the memory unit 12. That is, information processing by software stored in the memory unit 12 is concretely 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. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being a single unit, and the server device 10 may have multiple control units 11 for each function. The server device 10 may also be composed of a combination of these.

[0025] <Storage section 12> The storage unit 12 stores various types of information as defined above. This can be done, for example, as a storage device such as a solid-state drive (SSD) that stores various programs related to the server device 10 executed by the control unit 11, or as memory such as random access memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to 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 Department 13> The communication unit 13 preferably uses wired communication methods such as USB, IEEE1394, Thunderbolt®, and wired LAN network communication, but may also include wireless LAN network communication, mobile communication such as LTE / 5G, and Bluetooth® communication as needed. In other words, it is more preferable to implement it as a collection of these multiple communication methods. That is, 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 on-premises or in a cloud environment. A cloud-based server device 10 may provide the above-mentioned functions and processing in the form of, for example, SaaS (Software as a Service) or cloud computing.

[0028] <20 student terminals / 30 teacher terminals> Figure 3 is a block diagram showing the hardware configuration of the student terminal 20 and the teacher terminal 30. As shown in Figure 3A, the student terminal 20 comprises 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, storage unit 22, communication unit 23, input unit 24, and output unit 25 are electrically connected within the student terminal 20 via the communication bus 26. The explanation of the control unit 21, storage unit 22, and communication unit 23 is the same as the explanation of each part in the server device 10, so it is omitted.

[0029] <Input section 24> The input unit 24 receives operation input from the user. The operation input is transmitted to the control unit 21 via the communication bus 26 as a command signal. The control unit 21 can perform predetermined controls or calculations based on the transmitted command signal as needed. The input unit 24 may be included in the casing of the student terminal 20 or it may be an external component. 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 tap operations, swipe operations, etc. to the input unit 24. Instead of a touch panel, the input unit 24 can be a switch button, mouse, trackpad, QWERTY keyboard, etc. In addition to the tactile input described above, voice input using a microphone is also possible.

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

[0031] Furthermore, as shown in Figure 3B, the teacher-side terminal 30 comprises a control unit 31, a storage unit 32, a communication unit 33, an input unit 34, an output unit 35, and a communication bus 36. The control unit 31, storage unit 32, communication unit 33, input unit 34, and output unit 35 are electrically connected within the teacher-side terminal 30 via the communication bus 36. The descriptions of the control unit 31, storage unit 32, communication unit 33, input unit 34, and output unit 35 are the same as the descriptions of each part in the student-side terminal 20 and are therefore omitted.

[0032] Although Figure 1 shows an example where various terminals are laptop PCs (Personal Computers), the types of terminals used by the student terminal 20 and the teacher terminal 30 are not particularly limited in this embodiment. That is, the student terminal 20 and the teacher terminal 30 may be various information processing terminals such as desktop PCs, laptop PCs, smartphones, and tablet terminals.

[0033] 2. Functional Configuration 2.1 Overview This section describes the overview of the functional configuration of this embodiment. Information processing by software stored in the memory 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 (the processor provided by the information processing system 1).

[0034] Figure 4 is a block diagram showing the 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] As shown in Figure 4A, the server device 10 (control unit 11) comprises a display control unit 111, an acquisition unit 112, a generation unit 113, an output unit 114, a specific 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 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 the information itself that is generated in a manner that is visible to the user, such as a screen, image, icon, or text. In addition, such display control may involve the display control unit 111 transmitting a signal to the student terminal 20, resulting in predetermined information being displayed on the display units of the various terminals. In this embodiment, the display control unit 111 displays the analysis results of the report on each terminal. The specific content displayed on the various terminals will be explained later.

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

[0038] <Generation unit 113> The generation unit 113 is configured to execute the generation step. In the generation step, the generation unit 113 generates various information related to the information processing system 1. In this embodiment, the generation unit 113 generates structured data in which the report content and evaluation are combined into a single data. Details of this generated product will be described later.

[0039] <Output section 114> The output unit 114 is configured to execute the output step. In the output step, the output unit 114 outputs various types of information handled by the information processing system 1 in a predetermined manner. For example, the output here may be to output (insert) predetermined information into 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 identification unit 115 is configured to execute a specific step. In the specific step, the identification unit 115 identifies the quality, evaluation, etc., of various types of information handled by the information processing system 1 in a predetermined manner. In the example of this embodiment, the identification unit 115 identifies the evaluation of a report according to the content of the report text acquired by the information processing system 1 via the acquisition unit 112. The specific manner of identification will be described later.

[0041] <Analysis Department 116> The analysis unit 116 is configured to execute analysis steps. In the analysis steps, the analysis unit 116 performs various analyses on the various types of information handled by the information processing system 1 using the artificial intelligence unit 121, which will be described later. In this example, the analysis unit 116 analyzes the personality of the report's creator based on the report's content and evaluation, and a predetermined algorithm. The details will be described later.

[0042] <Storage Unit 117> The storage unit 117 is configured to perform the storage step. In the storage step, the storage unit 117 stores various types of information handled by the information processing system 1 in the memory unit 12. In this embodiment, the storage unit 117 stores multiple analysis results derived by the analysis unit 116, but this aspect will be described later.

[0043] <Aggregation section 118> The aggregation unit 118 is configured to execute the aggregation step. In the aggregation step, the aggregation unit 118 aggregates multiple pieces of information acquired by the information processing system 1 in a predetermined manner. In the example of this embodiment, the aggregation unit 118 aggregates multiple report analysis results as training data, but this manner will be described later.

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

[0045] <Storage management section 120> The memory management unit 120 is configured to execute the memory management step. In the memory management step, the memory management unit 120 manages various types of information to be stored 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 the memory area (storage unit 12) of the server device 10 or the memory areas of various devices, but this memory area does not necessarily have to be within the system shown in Figure 1, and the memory management unit 120 can also manage to store various types of information in external storage devices, etc.

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

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

[0048] The language model is an example of a learning model using a machine learning algorithm. Specific machine learning algorithms include nearest neighbors, naive Bayes, 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 consists of pairs of input data and output data (correct answer data) for training. Furthermore, the language model may not only be one trained for a specific task, but also a general-purpose model that can be used universally for a wide range of tasks.

[0050] The artificial intelligence unit 121 may be a natural language model, or it may include a general-purpose pre-trained model for natural language processing, such as a Large Language Model (LLM). An LLM is a pre-trained model that has learned a large amount of data in advance, such as text data (e.g., (i) web content on the internet, or (ii) data stored in a predetermined database), and can perform various language processing tasks when given a task. It can perform a wide range of natural language processing tasks, such as understanding sentence patterns and context, responding to questions, and generating sentences, according to given prompts. Such a general-purpose pre-trained model may include language models that can handle various tasks without fine-tuning using One-shot Learning or Few-shot Learning. Furthermore, a general-purpose pre-trained model can also handle various tasks using Zero-shot Learning. The artificial intelligence used in each functional unit of the control unit 11 may be a separate pre-trained model, or it may be a common general-purpose pre-trained model. A large 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 Azure AI Studio. Furthermore, the artificial intelligence unit 121 may include any machine learning model, deep learning model, artificial intelligence model, etc. The artificial intelligence unit 121 may be built on a system outside of the information processing system 1. Also, the artificial intelligence unit 121 may be interactive (which may be rephrased as chat type or conversation type) in which it alternately receives input to produce an instructed output and generates and outputs information.

[0051] The learning model included in the artificial intelligence unit 121 can undergo additional learning through methods such as transfer learning or fine-tuning. For example, the artificial intelligence unit 121 learns whether or not the output content has been modified by a user or the like. In other words, the artificial intelligence unit 121 may perform additional learning and fine-tuning based on the modifications made to the content output by the learning model. Also, for example, whenever new data is registered, the artificial intelligence unit 121 may perform additional learning and fine-tuning using this as new training data. This improves the accuracy of the 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 the original trained model. In knowledge distillation, a trained model, such as a large-scale language model, is used as the teacher model, and the parameters of the student model are adjusted so that the output loss of the student model (distilled model) relative to the output (Soft Target Loss) of the teacher model is small. The student model is then trained, and this student model becomes the distilled model. Alternatively, the student model may be trained so that the output loss of the student model relative to the correct labels (Hard Target) of the teacher data (combinations of input and output data of the learning model) is small. Compared to the original trained model (teacher model), the distilled model has similar performance to the trained model but with fewer parameters and a lower processing load. Therefore, using a distilled model can reduce the cost of the information processing system 1.

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

[0054] An AI agent may also be called an autonomous agent. An "AI agent" is a model that, upon input of a goal (objective, purpose, etc.) such as "teach me about XX" or a task such as "output XX," breaks down the processes necessary to reach the goal or accomplish the task into subtasks, actions, etc., and performs necessary data collection and analysis, program generation and execution, etc. The AI ​​agent takes the information and instructions input by the user as its goal, autonomously selects and executes tasks and actions according to the goal, outputs information according to the goal, and does not require user intervention (operation input). Furthermore, the AI ​​agent may autonomously plan and execute, evaluate the execution results itself, and autonomously learn in order to achieve the goal. For example, the AI ​​agent may autonomously update itself based on the execution results of subtasks (e.g., collected information, results of information analysis, etc.).

[0055] 2.2 Detailed Functional Configuration This section will describe the details of the functional configuration of this embodiment. Figure 5 is a diagram showing an overview of the functional arrangement 50 provided in the information processing system 1 in this embodiment.

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

[0057] <LMS系51> The LMS system 51 in the example of the present embodiment includes, for example, subject management 511 that manages subjects that students can take, class management 512 that manages classes to which students belong, lecture management 514 that manages lectures that students can take, attendance management 515 that manages student attendance at lectures, assignment submission management 516 that manages whether students have submitted assignments, submitted assignment evaluation 517 that is a collection of evaluations for assignments submitted by students, and feedback 518 that is a collection of feedback to students based on evaluations. As described above, in the LMS according to the example of the present embodiment, it is possible to manage the learning history, grade information, submitted assignment history, and behavior data of students (report creators).

[0058] <分析系52> The analysis system 52 is a group of functional units for analyzing 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 for "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 utilized for corporate management strategy, business improvement, learning analysis in educational institutions, and the like.

[0059] Using BI tools makes it possible to visualize vast amounts of data and support business improvement and strategic planning. Typical functions include data collection and integration, data visualization, data analysis, and report creation and sharing. When this BI tool is adopted in an educational institution such as a university, it becomes possible to manage and analyze various information about students in conjunction with the aforementioned LMS. In other words, in this embodiment, the analysis system 52 obtains educational data including at least one of the following from the report creator's learning history, grade information, submitted assignment history, and behavioral data by referring to the report creator, i.e., the organization to which the student belongs, i.e., the university's learning management system (LMS), and uses this educational data to analyze personality. With this configuration, accurate analysis that takes into account not only the content of the report but also the learning history, etc., becomes possible.

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

[0061] The analysis function system 52b includes the submitted assignment evaluation function 52b1 and the student analysis function 52b2. The submitted assignment evaluation function 52b1 is a function that evaluates assignment reports submitted by students according to the content of the writing, and the student analysis function 52b2 is a function that analyzes the student's personality based on the above evaluation of the report and its content. Further details of these functions will be described later.

[0062] 3. Information Processing Methods This section describes the information processing method of the server device 10. This information processing method may be executed by each part of the server device 10 as individual steps. The various features described in this section can be combined with each other as long as they do not create technical inconsistencies.

[0063] As described above, the information processing system 1 comprises at least one processor (for example, a control unit 11), and the processor is configured to execute the following steps by reading a program stored in memory. In other words, such an information processing method comprises each step of the information processing system 1. From another perspective, such a program causes a computer to execute each step of the information processing system 1. Figure 6 is a diagram illustrating the overview of the information processing (report analysis processing) performed by the information processing system 1. The details of the processing related to each step in Figure 6 will be described below.

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

[0065] In step S102, the identification unit 115 determines the evaluation of the report according to the content of the report's text. More specifically, the identification unit 115 determines the evaluation of report R1 according to the accuracy of the report's text. Accuracy here includes the logical coherence, persuasiveness, clarity of expression, and / or appropriateness of vocabulary in the report's text. This configuration makes it possible to evaluate the accuracy of the report's text from various perspectives. Further details of step S102 will be explained using Figure 7 below.

[0066] In step S103, the generation unit 113 generates structured data SR1, which combines the report content and evaluation into a single data set. Here, "structuring the report content and evaluation into a single data set" means that, rather than managing the content and evaluation of a single report independently, they are linked together and packaged for centralized management. This approach allows for a more detailed analysis compared to analyzing only the report content, as it increases the number of data points to be analyzed. In this embodiment, report R1 specifically includes multiple reports created by the same author, and the generation unit 113 generates structured data SR1 by combining the content of multiple reports R1 and their corresponding evaluations in chronological order. This approach allows for analysis that also takes into account the characteristics of the report author that change over time. This chronologically combined structured data may be in so-called JSON (JavaScript Object Notation) format. Here, "JSON format" refers to a format for structuring and describing data, which uses "key" and "value" pairs to represent data. It is easy for both humans and computers to read and is frequently used when structuring data.

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

[0068] In step S105, the analysis unit 116 analyzes the personality of the report author based on the content and evaluation of the structured data SR1 (structured report) and a predetermined algorithm (for example, an algorithm using prompt P1). More specifically, it performs the Student analysis described later and derives the analysis result AR1. This configuration allows for a more multifaceted analysis compared to analyzing the report author's personality based solely on either the quality or content of the report, and enables the deriving of a more in-depth personality. Further details of step S105 will be explained with reference to Figure 8.

[0069] In this specification, "Student Analysis" refers to the process of analyzing four characteristics—"Personal Branding Profile," "Orientation," "Behavioral Characteristics," and "Basic Personality Information"—based on report data submitted by students. Here, "Personal Branding Profile" refers to information used to clarify a student's individuality and strengths and differentiate them from others. "Orientation" is an analysis of the learner's interests, directions of concern, and motivations for behavior. "Behavioral Characteristics" is an evaluation of the learner's behavioral patterns and decision-making tendencies. "Basic Personality Information" is an estimation of the learner's personality tendencies based on psychological theories. Further details of these four characteristics will be described later.

[0070] Alternatively, steps S104 and S105 may be omitted, and the analysis unit 116 may assign structured data SR1 to prompt P1, input the LLM prompt with structured data SR1 assigned to it into the Large-Scale Language Model (LLM), and analyze the personality of the creator.

[0071] Figure 7 shows further details of the process shown in step S102 in Figure 6. In Figure 6, the process in step S102 was to "determine the evaluation of Report R1 according to the accuracy of the writing in Report R1," but in this embodiment, this evaluation is performed on a 5-point scale. In step S102A, the identification unit 115 uses the assignment R1 submitted by the student, the prompt P2 for the 5-point evaluation, and the evaluation criterion EC1 to determine the accuracy of the writing in Report R1 and to determine the evaluation of the report. The evaluation criterion EC1 here is, for example, an "evaluation index for learning assessment" called a rubric, and performs a process such as judging the "logic, persuasiveness, clarity of expression, and / or appropriateness of vocabulary of the report" on a 4-point scale (excellent, good, average, needs improvement) and giving a 5-point evaluation as an overall evaluation. More specifically, criteria for evaluating "logical reasoning" can include "consistency of the argument and appropriateness of the logical flow," criteria for evaluating "persuasiveness" can include "the presence or absence of specific examples or evidence to support the argument," criteria for evaluating "clarity of expression" can include "accuracy of sentence structure and grammar," and criteria for evaluating "appropriate vocabulary" can include "whether appropriate words and technical terms are used."

[0072] In step S102A, an evaluation result ER1 is assigned to the result report R1. Then, in step S102B, the identification unit 115 further identifies the evaluation using sentiment analysis. Here, sentiment analysis refers to the technique of determining emotions such as positive, negative, and neutral from text data. Specific methods include loose-based methods that calculate impression scores using a word dictionary, machine learning methods that learn from past data to determine emotions, and deep learning methods that utilize advanced natural language processing models; any of these methods may be used. With this approach, it becomes possible to perform evaluations that also take into account the emotions and opinions of the creator. As a result of the analysis in step S102B, the analysis unit 116 derives the analysis result AR2. This analysis result AR2 includes a 5-point rating for report R1, the reason for the evaluation, and the result of the sentiment analysis. In step S103 of Figure 6, multiple analysis results AR2 derived for multiple reports are structured and become structured data SR1.

[0073] Figure 8 shows further details of the process shown in step S105 of Figure 6. In Figure 6, step S105 simply involves inputting a prompt P1 with structured data SR1 (the integrated result of analysis result AR2) into the LLM for analysis, but this step can be divided into more detailed steps S105A to S105C.

[0074] First, in step S105A, a prompt P1A for basic profile analysis, which is assigned structured data SR1, is input to the LLM, and the basic profile analysis result AR3 is derived. Here, the basic profile analysis result AR3 includes the orientation and behavioral characteristics mentioned above.

[0075] In step S105B, the self-branding prompt P1B, which is assigned the basic profile analysis result AR3, is entered into the LLM, and the self-branding analysis result AR4 is derived. The self-branding analysis result AR4 includes the personal branding profile described above, in addition to the basic profile analysis result AR3.

[0076] Furthermore, in parallel with the above processing, in step S105C, the analysis result AR3 of the basic profile is subjected to a basic personality analysis by a predetermined algorithm logic AL1, and the analysis result AR5 is derived. The analysis result AR5 of the basic personality analysis includes the basic personality information mentioned above. In this embodiment, this algorithm logic AL1 may be a psychological trait 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 with five main factors and evaluates an individual's personality based on the strength of each element. More specifically, these five main factors are "openness (a tendency to be highly curious and actively seek new experiences; higher scores indicate higher creativity, lower scores indicate lower conservatism)," "conscientiousness (a tendency to be highly self-managing and responsible; higher scores indicate higher planning and cautious personalities, lower scores indicate lower impulsive and unplanned personalities)," "extraversion (a tendency to be sociable and energetic; higher scores indicate higher social interaction, lower scores indicate lower introversion)," "agreeableness (a tendency to be caring and cooperative; higher scores indicate higher empathy, lower scores indicate lower competitive and self-centered personalities)," and "neuroticism (indicates how sensitive one is to stress and negative emotions; higher scores indicate higher emotional instability, lower scores indicate lower emotional stability)." In this embodiment, the algorithmic logic AL1 quantifies the learner's personality traits based on the Big Five personality theory and derives the personality by combining them with the analysis results of the report. In other words, the analysis unit 116 analyzes personality using a psychological trait analysis model. This approach makes it possible to conduct analyses that incorporate psychological perspectives, such as the Big Five personality traits. Furthermore, it goes beyond mere textual analysis, enabling a more precise analysis of learners' thinking tendencies and behavioral patterns from a psychological standpoint.

[0077] The analysis result AR1 in Figure 6 is a combination of the analysis results AR4 and AR5. Furthermore, the sentiment analysis result AR2 may also be further integrated into the analysis result AR1.

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

[0079] In this manner, the analysis unit 116 uses a first analysis model (for example, a model into which prompt P1A is input) on the content of structured data SR1 to calculate a first analysis result (for example, analysis result AR3), and then uses a second analysis model (for example, a model into which prompt P1B is input), which is different from the first analysis model, on the first analysis result to analyze personality. The first analysis result includes the creator's basic profile. With this configuration, it becomes possible to grasp the personality analysis results of the report creator step by step.

[0080] Figure 9 shows an example of a student report assignment (RA). In this embodiment, the content of the reports submitted by learners is designed to analyze the learners' thinking tendencies, behavioral characteristics, orientations, and personal branding. These report assignments are classified into six categories, for example, and different analyses are applied to each category.

[0081] 1. Tasks to promote self-awareness and self-analysis This assignment aims to analyze learners' "self-understanding" and "self-expression abilities" and to evaluate the depth and consistency of their self-awareness. Examples of such assignments include "Introduce yourself and describe what you felt (within 200 characters)," "Describe your own characteristics. Explain them in positive terms (within 200 characters)," and "Refine your initial report's 'Reasons for enrolling in this university' (within 200 characters)." For these example assignments, learners' orientations and behavioral characteristics are extracted through basic profile analysis using Prompt P1A, and the positive and negative tendencies of their writing are evaluated through sentiment analysis.

[0082] 2. Issues that question the decision-making process This assignment aims to evaluate learners' "information gathering ability, logical thinking ability, and planning ability" when making decisions. Examples of such assignments include "What would you like to consider and research when choosing a program or research lab (within 400 characters)?" and "What kind of career path are you considering in the future? Please consider your own characteristics and the characteristics of a student studying at this university (within 400 characters)." For these example assignments, learners' decision-making patterns will be extracted through basic profile analysis using Prompt P1A, and the logical structure of their decisions will be evaluated using rubric assessment (logical reasoning and persuasiveness).

[0083] 3. Tasks that assess behavioral habits and planning skills This task aims to evaluate learners' "time management ability, self-regulation ability, and planning ability." Examples of such tasks include "Based on the contents of your daily time log, list aspects of your daily habits that you would like to continue and aspects that you would like to improve (within 400 characters)" and "Describe what you would like to challenge yourself with during your university life (within 400 characters)," as shown in Figure 9. For these tasks, learners' behavioral characteristics are extracted through basic profile analysis using prompt P1A, and their methods of expressing planning ability are analyzed through rubric evaluation (appropriateness of vocabulary and clarity of expression).

[0084] 4. Challenges related to communication skills This assignment aims to assess learners' "cooperativeness, social adaptability, and leadership." Examples of such assignments include "How will you improve your communication skills in your future student life (within 400 characters)?" and "Describe how you would like to develop your 'teamwork skills,' a fundamental skill for working professionals (within 200 characters)," as shown in Figure 9. For these example assignments, learners' cooperativeness and leadership will be analyzed using self-branding analysis with prompt P1B, and their psychological tendencies regarding relationship building with others will be evaluated using sentiment analysis.

[0085] 5. Tasks that assess adaptability to the external environment and application of learning. The task is designed to assess learners' "adaptability to the environment and ability to absorb new knowledge." Examples of such tasks include, as shown in Figure 9, "What do you want to apply from today's lecture to your future student life (within 400 characters)?" and "As a student at this university, how do you want to engage with technology in response to technological changes (within 200 characters)?" For these example tasks, learners' learning application abilities are analyzed using self-branding analysis with prompt P1B, and sentiment analysis is used to evaluate whether learners "positively absorb knowledge" or "have resistance to it."

[0086] 6. Tasks that assess leadership and problem-solving skills This task aims to assess how learners demonstrate leadership, problem-solving skills, and judgment. Examples of such tasks, though not shown in Figure 9, include: "Describe how you would demonstrate leadership when working on a team project (within 400 characters)," and "Explain, with specific examples, how you would respond when faced with a difficult situation (within 400 characters)." These tasks are assessed using self-branding analysis with prompt P1B to evaluate leadership characteristics, and problem-solving abilities are measured using rubric assessment (logical reasoning and persuasiveness).

[0087] As described above, the "List of Example Report Assignments" in this embodiment serves as a standard for comprehensively evaluating learners' thinking tendencies, decision-making abilities, behavioral habits, cooperativeness, and adaptability to the environment. Furthermore, the information processing system 1 according to this embodiment enables more precise personality analysis by combining the analytical methods applied to each of these report assignments.

[0088] Figure 10 shows further details of each element derived from the Student analysis mentioned above. A. Personal Branding Profile As shown in Figure 10, a personal branding profile can be summarized as "the core for differentiating one's value as a person and effectively communicating it to others," and it comprises "tagline" and "USP." A "tagline" is a phrase for conveying one's identity in an impressive way, such as "Robot Explorer." "USP" stands for "Unique Selling Proposition," and refers to a short statement that presents a unique strength or value proposition that differentiates oneself from competitors. A concrete example would be a short statement such as "I have loved robots since childhood and have dedicated myself to robotics research at university."

[0089] B. Intentionality As shown in Figure 10, orientation can be summarized as "a keyword indicating the direction one is currently heading," and its components include "objects of interest" and "sources of motivation." "Objects of interest" are things or themes that one wants to know about, do, or get involved with, such as "robots, programming, abacus, psychology, travel." "Sources of motivation" are the driving force, motivation, or source of comfort when taking action, such as "monetary rewards, the desire for growth, contact with new cultures, pet cats."

[0090] C. Behavioral characteristics Behavioral characteristics, as shown in Figure 10, can be summarized as "the source of behavioral patterns and tendencies that characterize how one behaves," and their constituent elements include "values ​​and means that are valued" and "values ​​that are valued." "Values ​​that are valued as instruments" are values ​​that are valued as means to achieve a goal, for example, "Rokeach's instrumental values." Here, "Rokeach's instrumental values" are one of the human values ​​proposed by psychologist Milton Rokeach, and refer to values ​​related to "how to live." More specifically, values ​​such as "honesty," "responsibility," "courage," "independence," "tolerance," "creativity," "diligence," and "discipline" are examples. "Values ​​that are valued" are the ideal state or values ​​that one ultimately wants to reach, for example, "Rokeach's terminal values." "Rokeach's terminal values" are also one of the human values ​​proposed by psychologist Milton Rokeach, and refer to values ​​related to "what kind of life one ultimately wants to live." More specifically, these include "happiness," "freedom," "self-expression," "love," "social recognition," "peace," "harmony," and "prosperity."

[0091] D. Basic personality information Basic personality information, as shown in Figure 10, can be summarized as "basic personality information based on insights from personality psychology," and its components include "BIG5," "universal talent value traits," and "personality risk." "BIG5" refers to the Big Five personality theory described above, and its explanation will be omitted. "Universal talent value traits" are personal characteristics that are valued in the workplace, such as leadership and autonomy, which are rated on a 5-point scale. "Personality risk" refers to the potential for negative impact on work, such as lack of GRIT or mental vulnerability, which are rated on a 5-point scale.

[0092] Figure 11 is an example screen showing the analysis results of the Student Analysis described above. This example screen is displayed on display unit D1, which is an example of the output unit 35 of the teacher's terminal 30. Display unit D1 displays a list RL of the results of the Student Analysis performed on multiple students. The results list RL includes the update date and time of the analysis results, the student's photo, and each of the items that make up the Student Analysis results as explained in Figure 10. The teacher can refer to this list and select any item to view more detailed information about that item.

[0093] Figure 12 shows an example screen illustrating the detailed results of the Student Analysis. This screen is displayed, for example, on display unit D2, which is an example of the output unit 25 of the student terminal 20. The symbols assigned to each area on this screen correspond to the items used in the Student Analysis, as explained in Figure 10, and their respective details are omitted here.

[0094] In this manner, the display control unit 111 in the information processing system 1 displays a screen that allows the creator to understand the analyzed personality. With this configuration, the report creator can understand their own personality as objectively analyzed, which can lead to changes in their future behavior or serve as a guide for their actions. In this embodiment, this example screen was 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] Figure 13 shows the update process for prompt P1. First, in step S201, Student analysis is performed to derive the analysis result AR1, similar to the embodiment described in Figure 6.

[0096] In the Student analysis of step S201, the analysis result AR1 was output as a single result in the embodiment shown in Figure 6. However, in the Student analysis of this embodiment, the Student analysis is performed multiple times from different perspectives, and an analysis result AR6 containing multiple versions of the results is output (step S202). The perspective here can be changed, for example, by weighting the items of the Student analysis described in Figure 10. Note that the processing in 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 multiple Student analyses, output in step S202, to the report's creator, accepts the creator's selection, and stores it. The creator's choice of which version to select from the multiple versions may be subjective or may be based on predetermined criteria. Furthermore, this version selection may be made not by the report's creator, but by the report's supervisor (e.g., the supervising teacher).

[0098] In step S204, the aggregation unit 118 of the control unit 11 receives the multiple selected analysis results AR7 stored by the storage unit 117 and aggregates them into a single analysis result AR8. In other words, the processing in steps S201 to S203 is performed for multiple report creators, accumulating multiple "selected analysis results AR7," which the aggregation unit 118 then aggregates into an analysis result AR8, which is a "collection of selected analysis results AR7."

[0099] Then, the update unit 119 of the control unit 11 receives the analysis results AR8 aggregated from the aggregation unit 118 and updates the prompt P1 using these analysis results AR8 as training data. This update method involves analyzing the selected analysis results AR7 from perspectives such as what kind of response patterns are likely to be selected as "appropriate," how sentiment analysis and sentence structure characteristics are influencing the results, and which parts of the prompt P1 used for evaluation are having the strongest influence. The instructions and conditions of the prompt P1 are then adjusted and improved to enable more accurate adjustments.

[0100] In this embodiment, the analysis unit 116 in the information processing system 1 calculates multiple analysis results AR6 by applying prompt P1 from multiple different perspectives when analyzing the personality of the report creator. The storage unit 117 stores one analysis result selected by the creator from the multiple analysis results. The aggregation unit 118 aggregates the multiple analysis results selected by multiple different creators as training data. The update unit 119 updates prompt P1 based on the training data. With this configuration, the system can autonomously and continuously learn the analysis results, and an improvement in the accuracy of the prompts can be expected.

[0101] [Second Embodiment] The above describes a first embodiment in which a student's personality is derived by analyzing a report they have created. The following describes a second embodiment in which this analyzed personality is utilized.

[0102] Specifically, in this embodiment, the analyzed student personality is provided to organizations such as companies and university seminars that are engaged in recruitment activities, thereby facilitating matching between organizations and students.

[0103] Figure 14 is a sequence diagram illustrating the matching of the derived student personality with the job requirements of the employer. First, in steps S301 and S302, as described in the above embodiment, the student creates and submits a report, and the system analyzes and stores the personality.

[0104] Next, in step S303, the recruiting party presents the recruitment requirements to the system. Here, recruitment requirements are the requirements for recruiting personnel with the skills and aptitudes sought by an organization such as a company or university. These include job titles and positions for companies, research themes and specialized fields for university seminars, and, as requirements common to both, desired skills and abilities (work skills, academic aptitude, technical skills, etc.), desired candidate profile (personality elements such as teamwork, leadership, and critical thinking), eligibility requirements, and application conditions.

[0105] In step S304, the system matches students based on the student's personality derived from the report submitted by the student and the job requirements presented by the recruiting party. This matching process may be performed by the analysis unit 116 of the system's control unit 11.

[0106] The matching process begins by determining the student's interests and aptitudes based on their personality traits and behavioral characteristics. This is then compared with the job requirements provided by the recruiting organization to narrow down the number of organizations the student is likely to be interested in. If the student possesses the behavioral characteristics that meet the requirements of the organization, a match can be determined.

[0107] In steps S305 and S306, the system provides the calculated matching information to both the students and the recruiting parties. Then, in steps S307 and S308, the students and recruiting parties take actions based on the provided matching information, such as students applying to recruiting parties or recruiting parties scouting students.

[0108] Figure 15 shows an example screen displaying a list of student personalities derived from the company's analysis. This example assumes the company is in a free trial period. The student's name is displayed in column C1 for convenience, but this part is personal information and is therefore hidden. The student's affiliation is displayed in column C2. Details of the affiliation (e.g., faculty, department, seminar name, etc.) are displayed in column C3, but this part is also hidden during the trial period. A brief character assessment of the student is displayed in column C4. This is the "tagline" mentioned earlier. The student's interests are displayed in column C5. From column C6, 167 onwards, the student's behavioral characteristics are displayed along with their rank. Column C8 is a paid feature that allows for more detailed display of personality information and anonymous messaging to students.

[0109] To summarize this embodiment, the acquisition unit 112 in the information processing system 1 further acquires requirement information related to job requirements. Furthermore, the output unit 114 outputs personnel matching information regarding the suitability of job seekers and personnel based on the analyzed personality and requirement information. With this configuration, it becomes possible to propose appropriate careers to creators based on their characteristics, and it becomes possible to introduce to employers individuals with the characteristics desired by the employer from among many report creators.

[0110] By adopting a system like the one in this embodiment, companies can receive analyzed personality information on students from universities. This allows them to receive not only subjective evaluations from the applicants but also objective evaluations from the supervising university, enabling them to make decisions based on these evaluations and conduct more efficient recruitment activities. This is also a significant advantage for students.

[0111] On the other hand, the information provider (the university) can provide companies with information about students' characteristics, and by receiving a commission from the companies in return for providing this information, the university can generate a significant source of income.

[0112] [others] With respect to the information processing system 1 according to the above embodiment, the following configurations may be adopted.

[0113] At least one of the devices included in the information processing system 1 may be located outside of Japan. For example, the server device 10 or the server may be located outside of Japan, while the terminals 20 and 30 are located within Japan. Similarly, a user may access the server device 10 located within Japan from outside of Japan using their terminals 20 and 30. This configuration allows for a more convenient user experience through various management methods.

[0114] In one embodiment, a functional unit implemented by the control unit 11 of the server device 10 is described, but at least a part of this may be implemented as a functional unit implemented by another server. Alternatively, it may be implemented as a functional unit implemented by the control unit 21 of the student terminal 20 or the control unit 31 of the teacher terminal 30. Furthermore, the various types of information described in the above example may be stored not only in the storage unit 12 of the server device 10, but also distributedly on other external devices using blockchain technology or the like.

[0115] The product may be provided in any of the following embodiments.

[0116] (1) An information processing system comprising memory and a processor, wherein the processor is configured to perform the following steps by reading a program recorded in the memory, the first acquisition step being to acquire data of at least one report written in natural language, the identification step being to identify an evaluation of the report according to the content of the report's text, and the analysis step being to analyze the personality of the report's author based on the content of the report, the evaluation, and a predetermined algorithm.

[0117] This approach allows for a more multifaceted analysis of the report writer's personality compared to analyzing the report's quality or content alone, enabling a deeper understanding of their personality.

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

[0119] This approach makes it possible to grasp the results of the personality analysis of the report writer in a step-by-step manner.

[0120] (3) An information processing system as described in (1) above, wherein in the generation step, structured data is generated by combining the contents of the report and the evaluation into a single data, and in the analysis step, a prompt with the structured data is input into a large-scale language model to analyze the personality of the creator.

[0121] This approach allows for a more detailed analysis compared to focusing solely on the report's content, as it expands the scope of analysis.

[0122] (4) An information processing system as described in (3) above, wherein the report includes multiple reports created by the same creator, the generation step generates structured data which combines the contents of the multiple reports and the corresponding evaluations in chronological order, and the analysis step inputs the prompts to which the structured data is attached into the large-scale language model to analyze the personality of the creator.

[0123] This approach allows for analysis that takes into account the characteristics of the report writer, which change over time.

[0124] (5) An information processing system according to any one of (1) to (4) above, wherein the specific step identifies the evaluation according to the accuracy of the text of the report, and the accuracy includes the logicality, persuasiveness, clarity of expression, and / or appropriateness of the vocabulary of the text of the report.

[0125] This approach makes it possible to evaluate the accuracy of the report's writing from various perspectives.

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

[0127] This approach makes it possible to conduct evaluations that also take into account the creator's feelings and opinions.

[0128] (7) An information processing system according to any one of (1) to (6) above, wherein the analysis step involves analyzing the personality using a psychological trait analysis model.

[0129] This approach allows for a more precise analysis of learners' thinking tendencies and behavioral patterns from a psychological perspective, going beyond mere textual analysis.

[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 following: learning history, grade information, submitted assignment history, and behavioral data of the author of the report, is acquired by referring to a learning management system of the organization to which the author of the report belongs, and in the analysis step, the personality is analyzed using the education-related data.

[0131] This approach allows for accurate analysis that takes into account not only the content of the report but also learning history and other factors.

[0132] (9) An information processing system according to any one of (1) to (8) above, wherein the display control step further displays a screen in which the creator can grasp the analyzed personality.

[0133] In this manner, the report writer will gain an objective understanding of their own personality, which will enable them to make changes to their future behavior or use it as a guide for their 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 to analyze 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, multiple analysis results selected by multiple different creators are aggregated as training data; and in the update step, the predetermined algorithm is updated based on the training data.

[0135] In this configuration, the system can autonomously and continuously learn from the analysis results, and an improvement in the accuracy of prompts can be expected.

[0136] (11) An information processing system described in any one of (1) to (10) above, wherein in a third acquisition step, requirements information relating to job requirements is acquired, and in an output step, personnel matching information relating to the suitability of job applicants and personnel is output based on the analyzed personality and the requirements information.

[0137] This approach makes it possible to propose appropriate career paths to creators based on their characteristics, and to introduce job seekers to individuals with the desired characteristics from among many report creators.

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

[0139] In this manner, it can be implemented as a program.

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

[0141] This embodiment can be implemented as an information processing method. Of course, this is not always the case.

[0142] Finally, while various embodiments relating to this disclosure have been described, these are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of Symbols]

[0143] 1: Information Processing System 10: Server device 11: Control Unit 111: Display Control Unit 112: Acquisition Department 113 :Generation part 114: Output section 115: Specific part 116:Analysis Department 117: Storage Unit 118: Aggregation Department 119: Update section 120: Memory management department 121: Artificial Intelligence Department 12: Storage section 13: Communications Department 14: Communications bus 2: Communication lines 20: Student terminal 21: Control Unit 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communications bus 30: Teacher's terminal 31: Control Unit 32: Storage section 33: Communications Department 34: Input section 35: Output section 36: Communications 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: Data for subject evaluation 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 Results P1: Prompt P2: Prompt R1: Report RA: Report assignment RL: Results List S1: Student SR1: Structured data T1:Teacher

Claims

1. An information processing system, The system comprises memory and a processor, the processor being configured to perform the following steps by reading a program stored in the memory: In the first acquisition step, data from at least one report written in natural language is acquired. In a specific step, the evaluation of the report is determined according to the content of the report's text. In the analysis step, the personality of the report's creator is analyzed based on the contents of the report, the evaluation, and a predetermined algorithm. Information processing system.

2. In the information processing system described in claim 1, In the aforementioned analysis step, the first analysis model is used on the contents of the report to calculate the first analysis result, and the personality is analyzed using a second analysis model, which is different from the first analysis model, on the first analysis result, and here, The first analysis results mentioned above include the basic profile of the creator, Information processing system.

3. In the information processing system described in claim 1, Furthermore, in the generation step, structured data is generated by combining the contents of the report and the evaluation into a single data set. In the analysis step, the prompt with the structured data is input into a large-scale language model to analyze the personality of the creator. Information processing system.

4. In the information processing system described in claim 3, The aforementioned report includes multiple reports created by the same author, In the generation step, the structured data is generated by combining the contents of the multiple reports and the corresponding evaluations in chronological order. In the analysis step, the prompt with the structured data attached is input to the large-scale language model to analyze the personality of the creator. Information processing system.

5. In the information processing system described in claim 1, In the aforementioned specific step, the evaluation is identified according to the accuracy of the text in the report, The accuracy of the information processing system includes the logical coherence, persuasiveness, clarity of expression, and / or appropriateness of vocabulary in the report.

6. In the information processing system described in claim 1, In the aforementioned specific step, sentiment analysis is further used to identify the evaluation. Information processing system.

7. In the information processing system described in claim 1, In the aforementioned analysis step, the personality is analyzed using a psychological trait analysis model. Information processing system.

8. In the information processing system described in claim 1, Furthermore, in the second acquisition step, education-related data including at least one of the following—the author's learning history, grade information, submitted assignment history, and behavioral data—is acquired by referring to the learning management system of the organization to which the author of the report belongs. In the aforementioned analysis step, the personality is analyzed using the education-related data. Information processing system.

9. In the information processing system described in claim 1, Furthermore, in the display control step, a screen is displayed that allows the creator to understand the analyzed personality. Information processing system.

10. In the information processing system described in claim 1, In the aforementioned analysis step, when analyzing the personality of the creator, the predetermined algorithm is applied from multiple different perspectives to calculate multiple analysis results. In the accumulation step, one analysis result selected by the creator from the multiple analysis results is accumulated. In the aggregation step, multiple analysis results selected by different creators are aggregated as training data. In the update step, the predetermined algorithm is updated based on the training data. Information processing system.

11. In the information processing system described in claim 1, Furthermore, in the third acquisition step, we obtain requirement information regarding the job requirements, Furthermore, in the output step, the information processing system outputs personnel matching information regarding the suitability of job seekers and personnel based on the analyzed personality and requirements information.

12. It is a program, The computer is made to perform each step of the analysis system described in any one of claims 1 to 11. program.

13. Information processing method, Each step of the information processing system according to any one of claims 1 to 11 is provided. Information processing methods.

Images