Information processing device, program, and information processing method

Abstract

This reduces the effort required to create appropriate evaluation criteria. [Solution] The information processing device comprises: an information acquisition unit that acquires information to be evaluated indicating the items to be evaluated; a guidance information acquisition unit that acquires guidance information including guidance items that determine the direction of the information to be generated; and a first supply unit that supplies the information to be evaluated and the guidance information to a generation unit, thereby generating intermediate information relating to the items to be evaluated in accordance with the direction determined by the guidance items.

Description

Technical Field

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

Background Art

[0002] When evaluating a certain matter, one or more evaluation criteria are generally provided, and the evaluation is generally performed based on whether or not these evaluation criteria are satisfied. For example, Patent Document 1 discloses a technique for evaluating a driver's driving skill based on predetermined evaluation criteria.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Generally, creating appropriate evaluation criteria requires establishing evaluation items without omission and determining whether each evaluation item can be appropriately evaluated. However, this work requires accurate and extensive knowledge about the matter to be evaluated, and is also time-consuming for creation and confirmation.

[0005] Therefore, the present invention has been made in view of the above points, and an object thereof is to reduce the labor of creating appropriate evaluation criteria.

Means for Solving the Problems

[0006] One aspect of the present invention is an information processing device comprising: an information acquisition unit that acquires information to be evaluated indicating items to be evaluated; a guidance information acquisition unit that acquires guidance information including guidance items that determine the direction of the information to be generated; and a first supply unit that supplies the information to be evaluated and the guidance information to a generation unit, thereby generating intermediate information relating to the items to be evaluated in accordance with the direction determined by the guidance items.

[0007] Furthermore, in one embodiment of the present invention, the induction items include at least one of knowledge or skills.

[0008] Furthermore, in one embodiment of the present invention, the information processing device further comprises a second supply unit that supplies the intermediate information to the generation unit to generate evaluation criteria for the items to be evaluated.

[0009] Furthermore, one aspect of the present invention is a program that causes a computer to execute: an information acquisition step of acquiring information to be evaluated that indicates items to be evaluated; a guidance information acquisition step of acquiring guidance information that includes guidance items that determine the direction of the information to be generated; and a first supply step of supplying the information to be evaluated and the guidance information to a generation unit so that intermediate information relating to the items to be evaluated is generated in accordance with the direction determined by the guidance items.

[0010] Furthermore, one aspect of the present invention is an information processing method comprising: an information acquisition step of acquiring information to be evaluated that indicates items to be evaluated; an information acquisition step of acquiring information that includes guidance items that determine the direction of the information to be generated; and a first supply step of supplying the information to be evaluated and the information that is guided to generate intermediate information relating to the items to be evaluated in accordance with the direction determined by the guidance items. [Effects of the Invention]

[0011] According to the present invention, the effort required to create appropriate evaluation criteria can be reduced. [Brief explanation of the drawing]

[0012] [Figure 1] This is a diagram illustrating the outline of an embodiment. [Figure 2] This is a block diagram illustrating an example configuration of the information processing system 1 according to the embodiment. [Figure 3] This figure shows an example of the process for generating intermediate information MI that is executed by the information processing device 10 according to the embodiment. [Figure 4] This figure shows an example of the process for generating evaluation criteria K that is executed by the information processing device 10 according to the embodiment. [Figure 5] This is a flowchart illustrating an example of the processing flow of the information processing device 10 according to the embodiment. [Figure 6] This figure shows a schematic example of the hardware configuration of the information processing device 90 applied to this embodiment. [Modes for carrying out the invention]

[0013] [overview] Figure 1 is a diagram illustrating the outline of the embodiment. The information processing device and program according to this embodiment generate intermediate information as a preliminary step in order to generate evaluation criteria that can appropriately evaluate the items to be evaluated. The intermediate information generated based on the items to be evaluated and the guiding questions (guiding items) for generating the evaluation criteria includes information about the evaluation criteria. Therefore, according to this embodiment, evaluation criteria can be easily generated from items to be evaluated that do not contain information about the evaluation criteria.

[0014] [Embodiment] The information processing apparatus, program, and information processing method according to this embodiment will be described in detail below with reference to the attached drawings, with reference to preferred embodiments. In the drawings, identical or similar parts are denoted by the same or similar reference numerals. This embodiment is not limited to these embodiments and includes various modifications or improvements. In other words, the components described below include those that can be easily imagined by a person skilled in the art, and those that are substantially the same, and the components described below can be combined as appropriate. Furthermore, this embodiment may include various omissions, substitutions, or modifications of components without departing from the spirit of the present invention.

[0015] In all the figures used to illustrate the embodiments, components having the same function are given the same reference numerals, and repeated explanations are omitted. Furthermore, in this application, "based on XX" means "based on at least XX," and includes cases where it is based on other elements in addition to XX. Also, "based on XX" is not limited to cases where XX is used directly, but also includes cases where it is based on XX after calculations or processing have been performed on it. Furthermore, "based on XX" may include XX itself. "XX" is any element (for example, any information). Embodiments of the present invention will now be described with reference to the drawings.

[0016] [Example of an information processing system configuration] Figure 2 is a block diagram illustrating an example configuration of an information processing system 1 according to an embodiment. The information processing system 1 comprises an information processing device 10, a user terminal 20, and a generation device 30. One user terminal 20 may be connected to one information processing device 10, or multiple user terminals 20 may be connected.

[0017] The information processing apparatus 10, the user terminal 20, and the information processing apparatus 10 and the generation apparatus 30 are communicably connected via a network NW (network NW1, network NW2). The network NW may be a network using wireless communication or a network using wired communication. The network NW may be configured using, for example, the Internet, or may be configured using a local area network (LAN). The network NW may be configured by combining a plurality of networks.

[0018] [Configuration example of information processing apparatus] The information processing apparatus 10 includes an arithmetic unit 11 and a storage unit 12.

[0019] The arithmetic unit 11 includes a central processing unit (CPU), operates based on programs and data stored in the storage unit 12, and provides various functions.

[0020] The storage unit 12 is configured by, for example, a hard disk drive or a semiconductor memory (flash memory, RAM, ROM), etc., and stores various types of information such as programs and data read by the arithmetic unit 11. Note that the storage unit 12 may be realized by a virtual storage device such as a cloud server outside the information processing apparatus 10.

[0021] [Configuration example of user terminal] The user terminal 20 is, for example, an information processing apparatus such as a personal computer, a tablet, or a smartphone. The user terminal 20 includes a user terminal display unit 21, a user terminal operation unit 22, a user terminal arithmetic unit 23, and a user terminal storage unit 24.

[0022] The user terminal display unit 21 includes, for example, a liquid crystal display and displays various images. In the following description, the user terminal display unit 21 displaying an image is also referred to as presenting an image to the user. The user is, for example, a person who uses the information processing apparatus 10.

[0023] The user terminal operation unit 22 may, for example, be equipped with a touch panel to detect user operations. Alternatively, the user terminal operation unit 22 may acquire user operation information from input devices such as a keyboard or mouse.

[0024] The user terminal processing unit 23 (not shown) is equipped with a central processing unit and operates based on programs and data stored in the user terminal storage unit 24 (not shown), providing various functions.

[0025] The user terminal storage unit 24 is composed of, for example, a hard disk drive or semiconductor memory, and stores various types of information, such as programs and data read by the user terminal processing unit 23. The user terminal storage unit 24 may also be implemented by a virtual storage device, such as a cloud server, located outside the user terminal 20.

[0026] [Example of a generating device configuration] The generation device 30 represents an AI that has been pre-trained using natural language, images, or audio. The generation device 30 may be built by the user or it may be built externally (for example, an LLM (Large Language Model)). If built by the user, the generation device 30 may be provided within the information processing device 10. Hereinafter, supplying information to the generation device 30 to generate desired information will be simply referred to as "generating". The generation device 30 may also be called a generation unit.

[0027] [Functions of the information processing device] The calculation unit 11 includes, as its functional units, a communication unit 110, an operation reception unit 111, a display control unit 112, a target information acquisition unit 113, a guidance information acquisition unit 114, a first supply unit 115, an intermediate information acquisition unit 116, a second supply unit 117, an evaluation criterion acquisition unit 118, and an evaluation unit 119. Each of these functional units may be implemented using electronic circuits as needed. Furthermore, each functional unit does not have to be included in a single device, and the information processing device 10 may be configured from multiple devices.

[0028] The communications unit 110 communicates information with the user terminal 20.

[0029] The operation reception unit 111 receives various operations performed on the user terminal 20. The operation reception unit 111 activates each part of the calculation unit 11 according to the various operations received.

[0030] The display control unit 112 controls the display on the user terminal 20. Specifically, the display control unit 112 generates the screen to be displayed on the user terminal display unit 21 and transmits it to the user terminal 20 via the communication unit 110. The user terminal 20 displays the screen generated by the display control unit 112.

[0031] [Function of information processing device: Generation of intermediate information] Figure 3 shows an example of the process for generating intermediate information MI executed by the information processing device 10 according to the embodiment. The information processing device 10 can generate intermediate information MI, which serves as the basis for generating the evaluation criterion K, through the processes executed by the functional units from the target information acquisition unit 113 to the intermediate information acquisition unit 116.

[0032] The target information acquisition unit 113 acquires the evaluation target information AI. The target information acquisition unit 113 may, for example, acquire the evaluation target information AI that the user has entered into the user terminal 20. The evaluation target information AI is information that indicates the evaluation target item A. The evaluation target item A is an item that is to be evaluated, and whether or not the evaluation target item A is met is evaluated (judged) based on some evaluation criteria. The evaluation target item A includes various things such as arbitrary items such as "safe driving," "healthy lifestyle," or "completion of work," as well as necessary propositions (~should) that indicate what should be done, and recommended propositions (~it would be good) that recommend doing. The user may, for example, input evaluation target information AI indicating evaluation target item A such as "safe driving" by operating the user terminal operation unit 22. The target information acquisition unit 113 acquires the evaluation target information AI "How to drive safely."

[0033] The guidance information acquisition unit 114 acquires guidance information II. For example, the guidance information acquisition unit 114 may acquire guidance information II entered by the user to the user terminal 20, or it may acquire guidance information II that has been set in advance and stored in the storage unit 12. Guidance information II is information used when generating information related to evaluation criteria K, and it is information that determines the direction of the generated information. The direction determined by guidance information II may be one or more. Each direction determined by guidance information II is called a guidance item I. That is, guidance information II contains information indicating one or more guidance items I. Information on the determined direction is, for example, information on matters required when evaluating evaluation target item A. Guidance information II and guidance items I may also be called guidance questions.

[0034] Guidance Information II may have different guidance items I depending on the intended use of evaluation criteria K, or at least some guidance items I may be set in common. For example, Guidance Information II in Figure 3 includes a first guidance item I1, "knowledge," and a second guidance item I2, "skills." This causes the generation device 30 to generate directional information such as the knowledge required for evaluation item A and the skills required for evaluation item A. Guidance items I such as "knowledge" and "skills" often serve as criteria when achieving something. By including at least one of "knowledge" or "skills" as guidance item I, evaluation criteria K for various evaluation item A can be generated without differentiating guidance Information II for each application. In addition, guidance items I such as "process" and "environment" may be set depending on the application. By including "process" as guidance item I, evaluation criteria K that takes into account the procedure for carrying out things can be generated. By including "environment" as guidance item I, evaluation criteria K that includes the environment required when achieving evaluation item A can be generated.

[0035] The first supply unit 115 generates intermediate information MI by supplying the evaluation target information AI and guidance information II to the generation device 30. The evaluation target information AI and guidance information II may be supplied as separate and independent pieces of information, or they may be supplied as a single piece of information containing the two pieces of information (for example, a single piece of text information containing the two pieces of information). The generation device 30 generates intermediate information MI based on the evaluation target information AI and guidance information II. The intermediate information acquisition unit 116 acquires the intermediate information MI generated by the generation device 30. The first supply unit 115 and the intermediate information acquisition unit 116 may together be referred to as the intermediate information generation unit.

[0036] Intermediate information (MI) is directional information defined by each guiding item (I), and is related to the evaluation target (A). Intermediate information (MI) may be generated as one or more from one guiding item (I), or as one or more from multiple guiding items (I). Furthermore, intermediate information (MI) generated from two different guiding items (I) may be combined into one, or kept separate for each guiding item (I). To generate appropriate evaluation criteria (K), it is desirable to comprehensively understand the matters that may be required for evaluation, such as the achievement or truth / false determination of the evaluation target (A). Therefore, it is desirable that multiple intermediate information (MI) be generated from a single guiding item (I).

[0037] The relationship between evaluation item A, evaluation criterion K, and intermediate information MI will be explained below using the concept of cosine similarity, which indicates the similarity between two pieces of information placed in a vector space, as an example. Here, evaluation item A is assumed not to contain information about one or more evaluation items a included in evaluation criterion K. That is, the cosine similarity between evaluation item A and evaluation criterion K is 90 degrees (=0), and it is difficult to generate evaluation criterion K from only the information included in evaluation item A and to accurately evaluate evaluation item A.

[0038] Therefore, as a preliminary step before generating evaluation criteria K from evaluation item A, intermediate information MI is generated, which has a cosine similarity of 45 degrees (=1 / √2) with evaluation item A. Since intermediate information MI contains information about evaluation item A, it can be generated from evaluation item A. Furthermore, the cosine similarity between intermediate information MI and evaluation criteria K is also 45 degrees, and since intermediate information MI contains information about evaluation criteria K, evaluation criteria K can be generated from intermediate information MI.

[0039] In this way, by inserting intermediate information MI, which contains information similar to both the evaluation item A and the evaluation criterion K, it is possible to generate the evaluation criterion K from the evaluation item A. In order to gradually increase the similarity of information between the intermediate information MI and the evaluation criterion K, guiding item I, which determines the direction of the generated information, is important.

[0040] Furthermore, the cosine similarity between evaluation item A and intermediate information MI, and between intermediate information MI and evaluation criterion K, is not limited to 45 degrees. Any angle other than 0 degrees (=1), 90 degrees (=0), 180 degrees (=-1), and 270 degrees (=0) is acceptable.

[0041] Furthermore, the number of intermediate information MI generated between the evaluation item A and the evaluation criterion K does not have to be one; there may be multiple. Specifically, after generating the first intermediate information MI from the evaluation item A, the second intermediate information MI (cosine similarity 60 degrees) may be generated by supplying the first intermediate information MI (cosine similarity 30 degrees) in addition to the evaluation item AI and the guidance information II, or by substituting it for at least one of the evaluation item AI or the guidance information II.

[0042] Let's specifically explain an example of the intermediate information MI that will be generated. If the evaluation item A is "safe driving" and the guidance item I is "knowledge" and "skills" (see Figure 3), the generator 30 may be input with "What knowledge and skills are necessary to perform safe driving?". Based on this information, the generator 30 generates a knowledge list MI1, which is intermediate information MI indicating the knowledge necessary to perform safe driving, and a skills list MI2, which is intermediate information MI indicating the skills necessary to perform safe driving. The knowledge list MI1 may include knowledge items M1 such as, for example, obeying the speed limit (first knowledge item M11), slowing down before a curve (second knowledge item M12), giving way to pedestrians (third knowledge item M13), and not driving under the influence of alcohol (fourth knowledge item M14). Furthermore, Skill List MI2 may also include Skill Items M2, such as holding a driver's license (Skill Item 1 M21), applying the brakes accurately in an emergency (Skill Item 2 M22), verbal communication during actions such as turning, starting, and stopping (Skill Item 3 M23), and coming to a complete stop (Skill Item 4 M24).

[0043] Furthermore, for the generation device 30 to generate intermediate information MI, it is necessary that the generation device 30 has previously learned information regarding evaluation target item A and evaluation criterion K, and that it is able to acquire such information. In the case of large-scale language models such as LLM, this is often not a problem as they retain publicly available knowledge. However, when using a generation device 30 created by a user, it is desirable that it be trained using documents related to evaluation target item A, or that it be configured to be easily referenced. For example, documents related to evaluation target item A may be input as guidance information II.

[0044] [Function of information processing device: Generation of evaluation criteria] Figure 4 shows an example of the process for generating evaluation criteria K executed by the information processing device 10 according to the embodiment. The information processing device 10 can generate evaluation criteria K by executing the processes from the second supply unit 117 to the evaluation unit 119.

[0045] The second supply unit 117 generates evaluation criteria K by supplying evaluation target information AI and intermediate information MI to the generation device 30. The evaluation target information AI and intermediate information MI may be supplied independently or together, similar to the evaluation target information AI and guidance information II. The generation device 30 generates evaluation criteria K based on the evaluation target information AI and intermediate information MI. The evaluation criteria acquisition unit 118 acquires the evaluation criteria K generated by the generation device 30. The second supply unit 117 and the evaluation criteria acquisition unit 118 may together be referred to as the evaluation criteria generation unit. Note that generating evaluation criteria K is synonymous with generating one or more evaluation items a that constitute evaluation criteria K, and when these are not distinguished, it is simply referred to as generating evaluation criteria K.

[0046] Evaluation Criterion K is a standard that can be used to evaluate the achievement or truthfulness of the evaluation target A. Evaluation Criterion K may be generated one by one from each item included in the intermediate information MI (for example, each knowledge item M1 and skill item M2), or multiple items may be generated, or one or more items may be generated from multiple guidance items I. Evaluation Criterion K is generated in the same way as when intermediate information MI is generated from the evaluation target information AI and guidance information II. Evaluation Criterion K may also be called conformity conditions or conformity requirements.

[0047] Let's explain in detail an example of the evaluation criteria K that will be generated. When generating evaluation criteria K from the intermediate information MI generated in Figure 3 (see Figure 4), the generation device 30 may receive evaluation target information AI, which is "What are the evaluation criteria for evaluating that A has been done?", and intermediate information MI (knowledge list MI1 and skill list MI2) as input. Based on the input intermediate information MI, the generation device 30 generates evaluation criteria K by, for example, integrating the intermediate information MI, extracting a part of the intermediate information MI, or generating new evaluation criteria. Evaluation Criterion K may include evaluation items a such as "Drive at a safe speed (Evaluation Item 1 a1)" generated based on obeying the speed limit (Evaluation Item 1 M11), "Perform safety checks (Evaluation Item 2 a2)" generated based on verbal communication during actions such as curves, starting, and stopping (Evaluation Item 3 M23) and making temporary stops (Evaluation Item 4 M24), "Drive with the correct posture (Evaluation Item 3 a3)" generated based on the correct application of the emergency brakes (Evaluation Item 2 M22), and "Do not drive under the influence of alcohol (Evaluation Item 4 a4)," which is the same as Evaluation Item 4 M14.

[0048] Furthermore, the first supply unit 115 that generates intermediate information MI and the second supply unit 117 that generates evaluation criteria K may generate information using the same generation device 30, or they may generate information using different generation devices.

[0049] According to the generated evaluation criteria K, the item to be evaluated A can be appropriately evaluated. For example, a user may evaluate the item to be evaluated A using the evaluation criteria K, or the evaluation unit 119 of the information processing device 10 or an external evaluation unit (e.g., artificial intelligence not shown) may be given the item to be evaluated A, situational information indicating the situation of the item to be evaluated A, and the evaluation criteria K to perform the evaluation. Below, an example of the evaluation of the item to be evaluated A will be specifically explained by illustrating the evaluation process performed by the evaluation unit 119.

[0050] In the above description, an example was given in which the second supply unit 117 generates evaluation criteria K by supplying evaluation target information AI and intermediate information MI to the generation device 30. However, this embodiment is not limited to this example. The second supply unit 117 can generate evaluation criteria K even without supplying evaluation target information AI. For example, the second supply unit 117 can generate evaluation criteria K by supplying intermediate information MI that indicates the evaluation process of evaluation target item A. Specifically, if evaluation target item A is "safe driving" and guidance item I is "evaluation process", the first supply unit 115 inputs "What is the process for evaluating safe driving?" to the generation device 30, causing it to generate a process list for evaluating safe driving, such as "vehicle inspection before driving" and "monitoring of driving behavior". The second supply unit 117 generates check items for each process, such as "vehicle inspection" and "checking the condition of the tires," by instructing the output of items to check for processes within the process of evaluating safe driving, such as "What items should be checked in the vehicle inspection before driving?". The second supply unit 117 generates the check items for each step in the process of evaluating safe driving. The information generated in this way covers the check items for each step in the multiple processes that evaluate the evaluation target item A, and is fully usable as evaluation criterion K.

[0051] The evaluation unit 119 acquires, for example, an evaluation item A called "safe driving," situational information about the driver while driving, and an evaluation criterion K for "safe driving." The situational information may include, for example, information that can be used to understand the situation, such as whether the driver has a pre-existing medical condition, and text, images, videos, and audio indicating the driving situation. The evaluation unit 119 determines the degree of fit by comparing the situation indicated by the situational information with each evaluation item a. The degree of fit may be, for example, the degree to which the information indicated by the situational information satisfies the evaluation criterion K. The degree of fit may be, for example, the ratio of the number of evaluation items a that meet the criterion to the total number of each evaluation item a, or the sum of the values ​​calculated for each evaluation item a, or these values ​​with a predetermined calculation applied. The evaluation unit 119 may evaluate that the condition is met if the degree of fit is above a predetermined threshold, and evaluate that the condition is not met if the degree of fit is below the threshold, or it may output the degree of fit itself as the evaluation result, or it may output the result after performing a predetermined calculation, etc.

[0052] The information processing device 10 may share the evaluation results of the evaluation unit 119 with the user via the user terminal 20, or may perform various processes based on the evaluation results.

[0053] [Information Processing System Processing Flow] Figure 5 is a flowchart illustrating an example of the processing flow of the information processing device 10 according to the embodiment. The target information acquisition unit 113 acquires the information to be evaluated AI (step S101). The guidance information acquisition unit 114 acquires guidance information II, which includes guidance items I that determine the direction of the information to be generated (step S102). The first supply unit 115 generates intermediate information MI based on the information to be evaluated AI and the guidance information II, and acquires it using the intermediate information acquisition unit 116 (step S103). If intermediate information MI is to be generated repeatedly (step S104; Yes), the first supply unit 115 supplies the generated intermediate information MI and generates further intermediate information MI (step S103). If the generation of intermediate information MI is sufficient and repeated generation is not performed (step S104; No), the second supply unit 117 generates evaluation criteria K based on the information to be evaluated AI and the intermediate information MI, and acquires it using the evaluation criteria acquisition unit 118 (step S105). The evaluation unit 119 evaluates item A based on the evaluation criteria K and the situation information (step S106).

[0054] [Summary of Embodiments] According to the embodiment described above, the information processing device 10 includes: a target information acquisition unit 113 that acquires evaluation target information AI indicating evaluation target item A; a guidance information acquisition unit 114 that acquires guidance information II including guidance items I that determine the direction of the information to be generated; and a first supply unit 115 that supplies the evaluation target information AI and guidance information II to a generation device 30, causing it to generate intermediate information MI related to evaluation target item A in accordance with the direction determined by guidance items I. For evaluation target item A, it is extremely difficult to generate evaluation criteria K from information on evaluation target item A alone, and the creation of evaluation criteria K has generally been done by humans. However, collecting information that constitutes appropriate evaluation criteria K and creating evaluation criteria K has been time-consuming and laborious. By generating intermediate information MI in the embodiment, the information that constitutes evaluation criteria K can be collected easily and quickly. Based on this information, the mechanical generation of evaluation criteria K from evaluation target item A, which was considered difficult in principle, can be easily realized. Furthermore, since the information processing device 10 according to this embodiment can generate intermediate information MI simply by setting the evaluation target item A and the guidance item I, the generation of intermediate information MI can be realized at low cost.

[0055] Furthermore, according to the embodiment described above, the guidance item I includes at least one of knowledge or skills. When evaluating whether or not a certain evaluation target A has been achieved, or when evaluating whether or not a person possesses knowledge or abilities above a predetermined standard, it is common to require specific knowledge or specific skills. With guidance information II in which guidance item I includes at least one of knowledge or skills, it is possible to generate appropriate intermediate information MI, and consequently appropriate evaluation criteria K, for various evaluation target A without separately adjusting guidance information II.

[0056] Furthermore, according to the embodiment described above, the information processing device 10 further includes a second supply unit 117 that supplies intermediate information MI to the generation device 30 to generate evaluation criteria K for the item to be evaluated A. According to the information processing device 10 of the embodiment, evaluation criteria K required for evaluating item to be evaluated A can be generated from item to be evaluated A. There is almost no operation required by the user in this creation process, and evaluation criteria K that are not included in the information of item to be evaluated A can be mechanically generated from item to be evaluated A. This makes it easy to mechanically generate evaluation criteria K from item to be evaluated A, which was previously considered difficult in principle. Therefore, the effort and time required to generate evaluation criteria K can be significantly reduced. In addition, since the information processing device 10 of the embodiment can generate evaluation criteria K simply by setting the item to be evaluated AI and guidance information II, the generation of evaluation criteria K can be realized at low cost.

[0057] As described above, the effort, time, and cost involved in creating evaluation criteria have been reduced, but further benefits can be obtained by utilizing this embodiment with artificial intelligence. In recent years, natural language processing technologies such as LLM have advanced, making it possible to obtain information in a conversational format with artificial intelligence. Here, general artificial intelligence generates answers based on user questions. Therefore, if the user question does not include evaluation criteria for evaluating the items to be evaluated, it is difficult to generate an answer that takes into account the items not included in the question, and an inaccurate answer may be generated. By using the information processing device 10 according to this embodiment to generate answers, the artificial intelligence can generate evaluation criteria K or intermediate information MI that serves as the basis for generating evaluation criteria K from a user question in which evaluation criteria K is not indicated, and then appropriately evaluate and answer. Therefore, with the information processing device 10, it is possible to easily and quickly improve the accuracy of the answers of artificial intelligence.

[0058] [Example Hardware Configuration] Figure 6 is a schematic diagram of an example hardware configuration of an information processing device 90 applied to this embodiment. The information processing device 90 comprises a processor 91, main memory 92, communication interface 93, auxiliary storage device 94, input / output interface 95, and internal bus 96. The processor 91, main memory 92, communication interface 93, auxiliary storage device 94, and input / output interface 95 are connected to each other via the internal bus 96 so as to be able to communicate with each other. The information processing device 90 may be applied to, for example, an information processing device 10. In this case, for example, the communication unit 110 may be configured using the communication interface 93. For example, the storage unit 12 may be configured using the auxiliary storage device 94. Also, the functional unit shown in the arithmetic unit 11 may be configured using the processor 91 and the main memory 92.

[0059] Furthermore, the target information acquisition unit 113 to evaluation unit 119 of the information processing device 10 may be implemented by the user terminal calculation unit 23 of the user terminal 20. In this case, the functions performed by the storage unit 12 may be implemented by the user terminal storage unit 24 or a cloud server, etc.

[0060] The information processing device 10 may be implemented using multiple information processing devices. For example, the information processing device 10 may be implemented using a device such as a cloud. The arithmetic unit 11 and the storage unit 12 may each be implemented in different information processing devices. For example, in the information processing device 10, the evaluation target information AI, guidance information II, intermediate information MI, evaluation criteria K, situation information, etc., may be stored in a distributed manner across multiple information processing devices.

[0061] Furthermore, the entirety or a part thereof of the functions of each part of the information processing device 10 in the above-described embodiment may be realized by recording a program for realizing these functions on a computer-readable recording medium, having a computer system read the program recorded on this recording medium, and executing it. The term "computer system" here includes hardware such as an operating system and peripheral devices.

[0062] Furthermore, "computer-readable recording media" refers to portable media such as flexible disks, magneto-optical disks, ROMs, and CD-ROMs, as well as recording units such as hard disks built into computer systems. In addition, "computer-readable recording media" may include those that dynamically hold programs for a short period of time, such as communication lines used when transmitting programs over networks such as the Internet or communication lines such as telephone lines, and those that hold programs for a certain period of time, such as volatile memory inside computer systems that act as servers or clients in such cases. Moreover, the above-mentioned program may be for the purpose of realizing some of the functions described above, and may also be able to realize the above-mentioned functions in combination with programs already recorded in the computer system.

[0063] Although one embodiment of this invention has been described in detail above with reference to the drawings, the specific configuration is not limited to that described above, and various design changes can be made without departing from the spirit of this invention. Furthermore, the configurations described in each embodiment and example above may be combined. [Explanation of Symbols]

[0064] 1...Information processing system, 10...Information processing device, 11...Calculation unit, 110...Communication unit, 111...Operation reception unit, 112...Display control unit, 113...Target information acquisition unit, 114...Guidance information acquisition unit, 115...First supply unit, 116...Intermediate information acquisition unit, 117...Second supply unit, 118...Evaluation criteria acquisition unit, 119...Evaluation unit, 12...Storage unit, 20...User terminal, 21...User terminal display unit, 22...User terminal operation unit, 23...User terminal calculation unit, 24...User terminal storage unit, 30...Generator, A...Evaluation target item, AI...Evaluation target information, I...Guidance item, II...Guidance information, a...Evaluation item, MI...Intermediate information, K...Evaluation criteria

Claims

1. A target information acquisition unit that acquires evaluation target information indicating the items to be evaluated, A guidance information acquisition unit acquires guidance information that includes guidance items that determine the direction of the information to be generated, A first supply unit supplies the evaluation target information and the guidance information to the generation unit, thereby generating intermediate information regarding the evaluation target items in accordance with the direction determined by the guidance items. An information processing device equipped with the following features.

2. The aforementioned induction items include at least one of knowledge or skills. The information processing apparatus according to claim 1.

3. A second supply unit generates evaluation criteria for the items to be evaluated by supplying the aforementioned intermediate information to the generation unit. The information processing apparatus according to claim 1 or claim 2, further comprising:

4. On the computer, A step to acquire target information that indicates the items to be evaluated, A guidance information acquisition step involves acquiring guidance information that includes guidance items that determine the direction of the information to be generated, A first supply step involves supplying the evaluation target information and the guidance information to the generation unit to generate intermediate information regarding the evaluation target items in accordance with the direction determined by the guidance items, A program that executes the command.

5. A step to acquire target information that indicates the items to be evaluated, A guidance information acquisition step involves acquiring guidance information that includes guidance items that determine the direction of the information to be generated, A first supply step involves supplying the evaluation target information and the guidance information to the generation unit to generate intermediate information regarding the evaluation target items in accordance with the direction determined by the guidance items, An information processing method having

Images