Management system and management program

Abstract

The objective is to provide a management system and management program that can provide useful information regarding the subject. [Solution] The system comprises an acquisition means for acquiring multiple opinion pieces of information that show the subjective views of a subject, a grouping means for dividing the multiple opinion pieces of information acquired by the acquisition means into multiple groups based on predetermined criteria, and a management means for managing the multiple opinion pieces of information acquired by the acquisition means based on the multiple groups divided by the grouping means, wherein each of the multiple subject-related pieces of information is information that combines a first word information corresponding to the subject and a second word information corresponding to the predicate, and further comprises an identification means for identifying emotion information that shows the feelings of the subject regarding each of the multiple subject-related pieces of information acquired by the acquisition means, and the grouping means divides the multiple subject-related pieces of information acquired by the acquisition means into multiple groups based on predetermined criteria and the emotion information identified by the identification means.

Description

Technical Field

[0001] The present invention relates to a management system and a management program.

Background Art

[0002] Conventionally, there has been known a technique for performing various processes on the content posted by a user regarding a target (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, there has been a demand for a technique for providing useful information regarding a target.

[0005] The present invention has been made in view of the above facts, and an object thereof is to provide a management system and a management program capable of providing useful information regarding a target.

Means for Solving the Problems

[0006] In order to solve the above-described problems and achieve the object, the management system according to claim 1 includes an acquisition unit that acquires a plurality of pieces of target-related information indicating the subjectivity of a target person regarding a target or facts regarding the target, a grouping unit that divides the plurality of pieces of target-related information acquired by the acquisition unit into a plurality of groups based on a predetermined criterion, and a management unit that manages the plurality of pieces of target-related information acquired by the acquisition unit based on the plurality of groups divided by the grouping unit.

[0007] The management system according to claim 2 is the management system according to claim 1, wherein each of the plurality of object-related pieces of information acquired by the acquisition means is information that combines a first word piece corresponding to a subject and a second word piece corresponding to a predicate.

[0008] The management system according to claim 3 is the management system according to claim 1, wherein the plurality of object-related information acquired by the acquisition means at least indicates the subjective opinion of the subject with respect to the object, the management system further comprises identification means for identifying emotion information indicating the subject's feelings with respect to each of the plurality of object-related information acquired by the acquisition means, and the grouping means divides the plurality of object-related information acquired by the acquisition means into a plurality of groups based on predetermined criteria and the emotion information identified by the identification means.

[0009] The management system according to claim 4 is the management system according to claim 1, further comprising a generation means that generates name information indicating the name of each of the multiple groups divided into the grouping means, based on the object-related information belonging to each of the multiple groups divided into the grouping means, and the management means manages the multiple object-related information acquired by the acquisition means based on the multiple groups divided into the grouping means and the name information generated by the generation means.

[0010] The management system according to claim 5 is the management system according to claim 4, further comprising a selection means for selecting one or more candidate category information from a plurality of candidate category information based on a plurality of groups divided by the grouping means and name information generated by the generation means, wherein the plurality of candidate category information is information indicating a plurality of candidate categories that are candidates to be set as categories representing each of the plurality of groups divided by the grouping means, and the management means manages a plurality of target-related information acquired by the acquisition means based on the plurality of groups divided by the grouping means, name information generated by the generation means and one or more candidate category information selected by the selection means.

[0011] The management program described in claim 6 causes a computer to function as: an acquisition means for acquiring multiple pieces of subject-related information that indicate the subject's subjective opinion of the subject or facts about the subject; a grouping means for dividing the multiple pieces of subject-related information acquired by the acquisition means into multiple groups based on predetermined criteria; and a management means for managing the multiple pieces of subject-related information acquired by the acquisition means based on the multiple groups divided by the grouping means. [Effects of the Invention]

[0012] According to the management system described in claim 1 and the management program described in claim 6, by dividing multiple object-related information into multiple groups based on predetermined criteria and managing multiple object-related information based on these groups, for example, it is possible to manage object-related information on a group basis, thereby making it possible to provide useful information regarding the object.

[0013] According to the management system described in claim 2, each of the multiple object-related pieces of information is a combination of a first word piece corresponding to the subject and a second word piece corresponding to the predicate. Therefore, for example, appropriate information can be used as object-related information, making it possible to provide useful information regarding the object.

[0014] According to the management system described in claim 3, by dividing multiple subject-related pieces of information into multiple groups based on predetermined criteria and emotional information, it is possible to appropriately group them, for example, by taking emotions into consideration, thereby making it possible to provide useful information about the subject.

[0015] According to the management system described in claim 4, by managing multiple object-related information based on multiple groups and the name information of those groups, for example, it is possible to manage object-related information on a group basis while taking the name information into consideration, thereby making it possible to provide useful information regarding the object.

[0016] According to the management system described in claim 5, by managing a plurality of target-related information based on a plurality of groups, the name information of the groups, and the selected candidate category information, for example, it is possible to manage the target-related information in units of groups in consideration of the name information and the candidate category information, so that it is possible to provide useful information regarding the target.

Brief Description of Drawings

[0017] [Figure 1] It is a block diagram functionally showing the information system according to this embodiment. [Figure 2] It is a diagram illustrating submission-related information. [Figure 3] It is a diagram illustrating opinion-related information. [Figure 4] It is a flowchart of information management processing [Figure 5] It is an explanatory diagram of information management processing. [Figure 6] It is a flowchart of grouping-related processing. [Figure 7] It is an explanatory diagram of opinion information and feature amounts. [Figure 8] It is an explanatory diagram of a group. [Figure 9] It is an explanation of the selection of setting category information.

Mode for Carrying Out the Invention

[0018] Hereinafter, with reference to the accompanying drawings, embodiments of the management system and the management program according to this invention will be described in detail. First, after explaining [I] the basic concept of the embodiment, [II] the specific content of the embodiment will be described, and finally, [III] modifications to the embodiment will be described. However, the present invention is not limited by the embodiments.

[0019] 〔I〕Basic Concept of the Embodiment First, the basic concepts of the embodiments will be explained. The embodiments relate to a management system and a management program. The management system according to the present invention is a system for managing target-related information, and the concept includes, for example, a dedicated system for managing target-related information, or a system realized by implementing a function for managing target-related information on a system used for general purposes (for example, a server computer (including a cloud computer), a personal computer, a tablet terminal, etc.).

[0020] "Subject-related information" refers to information related to the subject, and is a concept that includes, for example, information that shows the subjective views of the subject, or information that shows facts about the subject.

[0021] "Target-related information" is, for example, information that combines information corresponding to the subject (first-word information) and information that corresponds to the predicate (a phrase corresponding to the aforementioned subject) (second-word information). The number of subjects and predicates included in one piece of target-related information is arbitrary. Furthermore, as a variation, "target-related information" is not limited to information that combines this first-word information and second-word information, but may also be composed of information that indicates any word.

[0022] "Target-related information" is a concept that includes, for example, text information such as characters or image information.

[0023] "Subject" refers to the object or objective reality of the subject's perception or facts, and includes concepts such as products (for example, a specific application program, hats, shoes, etc.), services, and things (for example, things other than products, including people or animals, such as monuments in tourist areas, company employees, pets, etc.).

[0024] The term "target person" refers to anyone who has their own opinion about the target, such as a person who uses the target (user, employer, supervisor, customer, owner, etc.).

[0025] "Information that shows the subjective views of the subject" refers to information that shows the subject's thoughts (opinions) about the subject, and is a concept that includes, for example, information that shows the subject's perception, feelings, or evaluation of the subject.

[0026] "Information that shows facts about the subject" refers to information that shows matters related to the subject, and is a concept that includes, for example, information that shows the quality, progress, or status of the subject.

[0027] The embodiments described below will illustrate and explain the case in which the "target" is a predetermined application program and the "target-related information" is text information that shows the subjective opinion of the target person regarding the target.

[0028] [II] Specific details of the embodiment Next, the specific details of the embodiment will be described.

[0029] (composition) First, the configuration of the information system according to this embodiment will be described. Figure 1 is a block diagram that functionally illustrates the information system according to this embodiment.

[0030] The information system 100 is a system that includes a management system, and for example, comprises a terminal device 1 and a server device 2.

[0031] (Configuration - Terminal device) The terminal device 1 in Figure 1 is a device used by various users, such as a tablet terminal or a smartphone, and one example of such a device includes a communication unit 11, a touchpad 12, a display 13, a recording unit 14, and a control unit 15.

[0032] Note that other terminal devices, such as a personal computer, can also be used as terminal device 1. Furthermore, the number of terminal devices 1 is arbitrary, but in this embodiment, the configuration shown in Figure 1 will be used for explanation.

[0033] (Configuration - Terminal Equipment - Communication Unit) The communication unit 11 is a communication means for communicating with external devices (for example, the server device 2). The specific type and configuration of this communication unit 11 are arbitrary, but it can be configured using, for example, a known communication circuit.

[0034] (Configuration - Terminal device - Touchpad) The touchpad 12 is an operating means that receives various operation inputs from the user when pressed by the user's finger or the like. The specific configuration of the touchpad 12 is arbitrary, but for example, a known one equipped with an operation position detection means such as a resistive type or a capacitive type can be used.

[0035] (Configuration - Terminal device - Display) The display 13 is a display means that displays various images based on the control of the control unit 15. The specific configuration of the display 13 is arbitrary, but for example, a known liquid crystal display or an organic EL display, or other flat panel display, can be used. The touch pad 12 and the display 13 may also be superimposed on each other to form an integrated touch panel.

[0036] (Configuration - Terminal device - Recording unit) The recording unit 14 is a recording means for recording programs and various data necessary for the operation of the terminal device 1, and can be configured using, for example, flash memory (the same applies to the recording units of other devices).

[0037] (Configuration - Terminal device - Control unit) The control unit 15 is a control means for controlling the terminal device 1, and specifically, it is a computer comprising a CPU, various programs interpreted and executed on the CPU (including basic control programs such as the OS and application programs launched on the OS to realize specific functions), and internal memory such as RAM for storing programs and various data (the control units of other devices are similar). In particular, the program according to this embodiment is installed on the terminal device 1 via any recording medium or network, thereby substantially constituting each part of the control unit 15 (the control units of other devices are similar). The processing of each part of this control unit 15 will be described later.

[0038] (Configuration - Server Equipment) The server device 2 in Figure 1 is a management system and includes, for example, a communication unit 21, a recording unit 22, and a control unit 23.

[0039] (Configuration - Server device - Communications unit) The communication unit 21 is a communication means for communicating with an external device (for example, terminal device 1 or other device not shown). The specific type and configuration of this communication unit 21 are arbitrary, but for example, it can be configured in the same way as the communication unit 11.

[0040] (Configuration - Server device - Recording unit) The recording unit 22 is a recording means for recording programs and various data necessary for the operation of the server device 2, and stores, for example, information related to posts and information related to opinions.

[0041] (Configuration - Server device - Recording unit - Post-related information) Figure 2 is an example of post-related information. "Post-related information" refers to information posted by the target user, and as shown in Figure 2, it is information that links together, for example, product name information, date information, and post content information. Note that the information specifically described in Figure 2 is included for explanatory purposes only (the same applies to Figure 3, which will be discussed later).

[0042] ===Product name information=== The product name information in Figure 2 indicates the name of the product (the specified application program referred to as the "target" above) (e.g., "AAA" in Figure 2).

[0043] ===Date Information=== The date information in Figure 2 indicates the date the post was made by the subject (e.g., "March 1, 2024" in Figure 2).

[0044] ===Post Content Information=== The post content information in Figure 2 represents information that shows the content of information posted by the target user, and is a concept that includes, for example, one or more pieces of target-related information (in Figure 2, "The app crashes easily, you have to pay to use it, the image quality is good, and..." etc.).

[0045] ===Explanation of each piece of information=== Furthermore, the information at the top of Figure 2 indicates that, regarding a product named "AAA," the subject made a post on March 1, 2024, stating, "The app crashes easily, you have to pay to use it...the image quality is good, and..."

[0046] While there is actually a lot more information about posts related to "AAA" than what is shown in Figure 2, we will mainly focus on the information shown in this figure for this explanation.

[0047] Furthermore, the method for storing this posted content information is arbitrary. For example, the information may be stored by the administrator entering it into server device 2, or the information may be recorded in one or more external DBs (databases), and server device 2 may periodically access these external DBs to retrieve and store the information.

[0048] (Configuration - Server device - Recording unit - Opinion-related information) Figure 3 illustrates opinion-related information. "Opinion-related information" refers to information about the subjective opinions of the subjects, and as shown in Figure 3, it is information that links together, for example, product name information, date information, opinion information, post content information, sentiment information, sentiment likelihood information, group name information, group likelihood information, representative opinion flag information, and set category information.

[0049] ===Product name information, date information, and post content information=== Note that the product name information, date information, and post content information in Figure 3 are the same information as the information with the same name in Figure 2.

[0050] ===Opinion information=== The opinion information in Figure 3 is the aforementioned subject-related information (information that shows the subject's subjective opinion about the subject), and for example, it is information that shows the subject's thoughts (also called "opinions") about the subject (in Figure 3, "The image quality is good," etc.). The opinion information in Figure 3 is information that shows the opinion indicated by the posted content information.

[0051] In this embodiment, the opinion information represents a single opinion. "A single opinion" may be interpreted as, for example, a single sentence containing a combination of one or more subjects and one or more predicates corresponding to those subjects, or it may be interpreted as a unit of opinion defined according to any other arbitrary rule.

[0052] As an alternative, information showing two or more opinions may be used as opinion information in Figure 3.

[0053] ===Emotional information=== The emotional information in Figure 3 represents the emotions of the subject related to the opinion indicated by the opinion information.

[0054] While the specific content of the emotional information is arbitrary, this embodiment describes cases where, for example, "positive" indicates a forward-looking, affirmative, or positive emotion; "negative" indicates a backward-looking, negative, or passive emotion (i.e., the opposite of "positive"); and "neutral" indicates the absence of emotion or an emotion other than "positive" or "negative."

[0055] ===Emotional Likelihood Information=== The sentiment likelihood information in Figure 3 indicates the likelihood (reliability) of sentiment information associated with opinion information. Specifically, it indicates the reliability of the sentiment information related to the opinion expressed by the opinion information.

[0056] The specific content of the sentiment likelihood information is arbitrary, but in this embodiment, for example, it is explained as being represented by a numerical value in the range of 0 to 1, where a higher confidence level corresponds to a larger value (the same applies to the group likelihood information described later).

[0057] ===Group Name Information=== The group name information in Figure 3 is information (name information) that indicates the name of the group to which the opinion information belongs when the opinion information is grouped together (in Figure 3, the name of the group to which the opinion information in the first row of the drawing belongs is "The image quality is good and desirable," and the name of the group to which the opinion information in the second row of the drawing belongs is "There is strong pressure to charge," etc.).

[0058] ===Group Likelihood Information=== The group likelihood information in Figure 3 indicates the likelihood (reliability) of the group to which the opinion information belongs. Specifically, it indicates the likelihood that the opinion information belongs to the group corresponding to the group name information (i.e., the degree of suitability of the group to which the opinion information belongs).

[0059] ===Representative Opinion Flag Information=== The representative opinion flag information in Figure 3 indicates whether the opinion shown in the opinion information is a representative opinion or not (in Figure 3, "TRUE" indicates that it is a representative opinion and "FALSE" indicates that it is not a representative opinion).

[0060] "Representative opinion" is a concept that, for example, represents a predetermined number of opinions (for example, one, two, or three, etc.) that represent the entire group, based on one or more opinions expressed by one or more opinion pieces belonging to that group.

[0061] ===Settings Category Information=== The setting category information in Figure 3 indicates the category of the group indicated by the group name information. Since opinion information belongs to a group, the setting category information can also be interpreted as indicating the category of the opinions belonging to that group. More specifically, this setting category information indicates the category corresponding to one or more candidate categories selected from a predetermined set of candidate categories (categories that can be set).

[0062] ===Explanation of each piece of information=== Furthermore, the information at the top of Figure 3 shows that, regarding the product named "AAA," an opinion piece corresponding to a post made by a user on March 1, 2024, stating "The app crashes easily, you have to pay to use it..., I think the image quality is good. And...", is "The image quality is good." It also shows that the emotion corresponding to this opinion piece, "The image quality is good," is "positive," and the emotion likelihood information is "0.9" (relatively high confidence). It also shows that the name of the group to which this opinion piece belongs is "The image quality is good and desirable," and the group likelihood information is "0.9" (indicating that the "The image quality is good and desirable" group is relatively suitable to include "The image quality is good"). It also shows that the opinion piece represents a representative opinion. Finally, it shows that the category represented by the "The image quality is good and desirable" group (i.e., the category of "The image quality is good" belonging to the "The image quality is good and desirable" group) is "UI" (User Interface).

[0063] Furthermore, while the method for storing this opinion-related information is arbitrary, it can be stored, for example, by performing the information management process described later.

[0064] (Configuration - Server device - Control unit) The control unit 23 is a control means for controlling the server device 2. Functionally, the control unit 23 includes, for example, acquisition means, grouping means, management means, identification means, generation means, and selection means.

[0065] ===Acquisition method=== The means of acquisition refers to the means of acquiring multiple pieces of subject-related information that indicate the subject's subjective opinion or facts about the subject.

[0066] Furthermore, for example, each of the multiple object-related pieces of information acquired by the acquisition means is information that combines a first-word piece of information corresponding to the subject and a second-word piece of information corresponding to the predicate. Also, for example, each of the multiple object-related pieces of information acquired by the acquisition means at least indicates the subjective opinion of the subject regarding the object.

[0067] ===Methods of Grouping=== A grouping means is a means of dividing multiple object-related pieces of information acquired by an acquisition means into multiple groups based on predetermined criteria. For example, the grouping means divides multiple object-related pieces of information acquired by an acquisition means into multiple groups based on predetermined criteria and emotion information identified by an identification means.

[0068] ===Management means=== The management means is a means for managing multiple object-related information acquired by the acquisition means based on multiple groups divided by the grouping means. For example, the management means manages multiple object-related information acquired by the acquisition means based on multiple groups divided by the grouping means and name information generated by the generation means. For example, the management means manages multiple object-related information acquired by the acquisition means based on multiple groups divided by the grouping means, name information generated by the generation means and one or more candidate category information selected by the selection means.

[0069] ===Specific means=== Identification means are means of identifying emotional information that indicates the emotions of a subject with respect to each of the multiple pieces of subject-related information acquired by the acquisition means.

[0070] ===Generation means=== The generation means is a means for generating name information indicating the name of each of the multiple groups that have been divided into multiple groups, based on the object-related information belonging to each of the multiple groups that have been divided into multiple groups.

[0071] ===Selection Methods=== The selection means is a means for selecting one or more candidate category information from among multiple candidate category information based on the multiple groups divided by the grouping means and the name information generated by the generation means. The multiple candidate category information refers to information indicating multiple candidate categories that are candidates to be set as categories representing each of the multiple groups divided by the grouping means.

[0072] The specific processes that each measure performs will be described later.

[0073] (process) Next, we will explain the information management processes performed by the information system 100. Figure 4 is a flowchart of the information management processes (in the following descriptions of each process, the step will be abbreviated as "S"), and Figure 5 is an explanatory diagram of the information management processes. Figure 5 shows an overview of the processes.

[0074] "Information management processing" refers to the process of managing opinion-related information, and is, for example, a process executed by server device 2. The timing of execution of this information management processing is arbitrary, but for example, it will be started when the user performs the following predetermined operation, and the explanation will begin from the point when it starts.

[0075] Furthermore, we will explain the case where, in the post-related information shown in Figure 2, a large amount of information is already stored in addition to the information specifically illustrated at the top. We will also explain some of the elements in Figure 5 with corresponding reference numerals.

[0076] ===SA1=== In SA1 in Figure 4, the control unit 23 of the server device 2 acquires opinion information. Specifically, although it is arbitrary, for example, it acquires post content information in the post-related information in Figure 2, and then acquires opinion information based on the acquired post content information.

[0077] For example, a method using a pre-trained opinion-related model may be employed.

[0078] An "opinion-related trained model" is a model that, when input content information for a post is given, outputs opinion information corresponding to that post content information. This opinion-related trained model is a model that has been pre-trained to output opinion information that combines first-word information corresponding to the subject and second-word information corresponding to the predicate, as information indicating the subject's opinion on the subject, with respect to the input post content information. For example, this is recorded in the recording unit 22.

[0079] The opinion information output here will, for example, basically be information corresponding to sentences (sentences containing a subject and predicate) contained in the text indicated by the input post content information. More specifically, it is expected to include the sentence itself contained in the input post content information, or information indicating the sentence corresponding to that sentence. In other words, it is expected that in addition to the sentence contained in the post content information, sentences with similar meanings corresponding to that sentence will also be included in the opinion information. Furthermore, it is expected that the opinion-related trained model will output only one opinion or two or more opinion pieces depending on the content of the input post content information.

[0080] ==Processing== In this method, the control unit 23 acquires post content information from the post-related information shown in the figure and inputs this post content information to the opinion-related trained model. In this case, the opinion-related trained model outputs one or more opinion pieces corresponding to the input post content information, and the control unit 23 identifies and acquires these outputted opinion pieces.

[0081] Then, by performing the above process on all post content information included in the post-related information in Figure 2, multiple opinion pieces of information are obtained.

[0082] Here, for example, the post content information shown in Figure 2, "The app crashes easily, you have to pay to use it..., I think the image quality is good. And...", is retrieved, and this retrieved post content information is input into the opinion-related trained model. Then, if the opinion-related trained model outputs opinion information such as "The image quality is good" (see Figure 3) and "The app crashes easily", these "The image quality is good" and "The app crashes easily" are identified and retrieved as opinion information.

[0083] In the explanatory diagram in Figure 5, this process will result in obtaining opinion information 81-83, etc., based on the posted content information 91, etc.

[0084] ==Variations== Furthermore, variations may include configuring the system to process data using a generative model stored outside the server device 2 (such as a GPT (Generative Pretrained Transformer) model that outputs corresponding response information when query information is input), or configuring the system to process data using a predetermined algorithm without using a model (the same applies to SA2 described later).

[0085] Furthermore, as a predetermined algorithm, for example, an algorithm may be applied that decomposes the posted content information into sentence units, determines whether each sentence unit contains a predetermined word or not to determine whether it is a sentence expressing the subject's opinion on the subject, and obtains sentences expressing the subject's opinion on the subject as opinion information.

[0086] ===SA2=== In SA2 in Figure 4, the control unit 23 of the server device 2 identifies emotion information and emotion likelihood information for each opinion information acquired in SA1.

[0087] For example, a method using a pre-trained model related to emotions may be employed.

[0088] A "pre-trained emotion-related model" is a model that, when given an opinion piece of input, outputs emotion information and emotion likelihood information corresponding to that opinion piece of input. This pre-trained emotion-related model is a model that has been pre-trained to output emotion information ("positive," "negative," or "neutral") indicating the subject's emotion corresponding to the opinion expressed by the input opinion piece of input, and emotion likelihood information (a numerical value ranging from 0 to 1, with higher confidence levels indicating greater confidence), and is recorded, for example, in the recording unit 22.

[0089] ==Processing== In this method, the control unit 23 selects one opinion from the opinion information acquired by SA1 and inputs that opinion to the emotion-related trained model. In this case, the emotion-related trained model outputs emotion information indicating the emotion corresponding to the input opinion information and emotion likelihood information related to that emotion information, and the control unit 23 acquires and identifies the outputted emotion information and emotion likelihood information.

[0090] Then, by performing the above processing on all opinion information obtained in SA1, the sentiment information and sentiment likelihood information corresponding to all opinion information are identified.

[0091] Here, for example, if SA1 acquires opinion information such as "The image quality is good" (see Figure 3) or "The app crashes easily," first, "The image quality is good" is selected and input into the emotion-related trained model. Then, if the emotion-related trained model outputs "Positive" and "0.9" as emotion information and emotion likelihood information, these "Positive" and "0.9" are acquired and identified as the emotion information and emotion likelihood information corresponding to "The image quality is good." The same process is then performed for "The app crashes easily," etc.

[0092] In the explanatory diagram in Figure 5, this process identifies, for example, emotional information 71-73 based on opinion information 81-83.

[0093] ===SA3=== In SA3 shown in Figure 4, the control unit 23 of the server device 2 executes grouping-related processing. Figure 6 is a flowchart of the grouping-related processing.

[0094] "Grouping-related processing" refers to processing for dividing opinion information into groups (grouping), and in this embodiment, for example, it includes processing for dividing multiple opinion pieces obtained in SA1 into multiple groups based on predetermined criteria and sentiment information identified in SA2.

[0095] ===SB1=== In SB1 of Figure 6, the control unit 23 of the server device 2 acquires opinion information that has been identified as "positive" as emotion information in SA2 from the opinion information acquired in SA1 of Figure 4. Then, in SB2 to SB5 below, processing is performed on this "positive" opinion information.

[0096] Here, for example, among the "Image quality is good" (see Figure 3) and "The app crashes easily" obtained in SA1, "Image quality is good" and others are considered "positive," so we will retrieve these "Image quality is good" and others.

[0097] ===SB2=== In SB2 in Figure 6, the control unit 23 of the server device 2 identifies the feature quantities of the "positive" opinion information acquired in SB1.

[0098] "Features" are a concept related to AI (Artificial Intelligence) or machine learning, and specifically, they are quantitative numerical representations of data characteristics that can be identified, for example, using a predetermined embedding model.

[0099] Specifically, although optional, for example, the control unit 23 applies the opinion information acquired by SB1 to a predetermined Embedding model, thereby acquiring and identifying numerical vector information of a predetermined number of dimensions representing the aforementioned opinion information transformed by the model as a feature.

[0100] Figure 7 is an explanatory diagram of opinion information and features. Here, for example, in SB1, we will explain by illustrating the case where opinion information such as "The image quality is good," "The addition of new functions has improved work efficiency," and "The new design is very easy to use" is obtained.

[0101] In this case, when each opinion information is applied to a predetermined Embedding model and converted into numerical vector information such as [-0.28, 0.31, -0.35, -0.40, 0.15, -0.05] as exemplified in Figure 7, these [-0.28, 0.31, -0.35, -0.40, 0.15, -0.05] etc. are obtained and identified as features of each opinion information.

[0102] ===SB3=== In SB3 of Figure 6, the control unit 23 of the server device 2 groups the "positive" opinion information acquired in SB1 based on the features identified in SB2.

[0103] Specifically, although optional, the control unit 23, for example, groups opinion information where the feature quantities are similar (i.e., similar in meaning) into the same group. Note that this grouping criterion may be interpreted as corresponding to a "predetermined criterion."

[0104] In detail, points corresponding to the numerical vector information, which are features identified by SB2, are placed in space, and the opinion information of each point corresponding to a point cloud that is located close to each other and has a density higher than a predetermined value is grouped into the same group. By processing in this way, opinion information with similar features (i.e., similar meanings) is grouped into the same group. As for the method to realize this process, a method using a predetermined clustering model may be applied, or other methods may be applied.

[0105] Figure 8 is an explanatory diagram of the groups. Here, for example, if the feature quantities such as "The image quality is good" and "The new design is very easy to use" in Figure 7 are relatively close to each other (i.e., they are feature points that are placed relatively close to each other when placed in space), and the feature quantity such as "The addition of new functions has increased work efficiency" is relatively far from the aforementioned feature quantity (i.e., it is a feature point that is placed relatively far away when placed in space), then, as shown in Figure 8, the opinion information such as "The image quality is good" and "The new design is very easy to use" will be grouped together into the same group, and the opinion information such as "The addition of new functions has increased work efficiency" will be grouped into a different group from the aforementioned group.

[0106] In practice, however, it is expected that the data may be grouped into other groups besides the two mentioned above, depending on the number of opinion pieces, the variability or density of each feature, etc.

[0107] In the explanatory diagram in Figure 5, this process results in grouping opinion information 81, 83, etc., into the same group.

[0108] ==Variations== As a variation, the distance between each feature may be calculated and the opinion information whose calculated distance is less than or equal to a predetermined distance may be grouped together, or grouping may be done using any other arbitrary method.

[0109] ===SB4=== In SB4 in Figure 6, the control unit 23 of the server device 2 identifies group likelihood information for each opinion information grouped in SB3.

[0110] Specifically, although it is arbitrary, for example, the control unit 23 calculates the distance (i.e., the difference) between the reference feature quantity of each group grouped by SB3 and the feature quantity of each opinion information, and identifies the group likelihood information based on the calculated distance.

[0111] A "reference feature" is the central feature among the opinion information features belonging to each group. For example, it is a concept that indicates the feature corresponding to the center when each feature is arranged in space. Alternatively, it can be interpreted as the feature of opinion information that has the shortest sum of distances between it and other features.

[0112] In more detail about the processing, for example, the shorter the calculated distance (i.e., the smaller the difference in features), the closer it is to the central reference feature and the higher the confidence level, so the group likelihood information is identified to have a large value. For example, the group likelihood information may be identified using various types of information (mathematical formulas, transformation tables, or thresholds, etc.) that show the relationship between distance and group likelihood information.

[0113] Here, for example, if the distance between the reference feature of the group to which "The image quality is good" belongs in Figure 8 and the feature of "The image quality is good" is relatively small (the difference is relatively small), then "The image quality is good" is considered to belong to a relatively high degree of appropriateness as that group (the group grouped by SB3), and the group likelihood information is assigned as "0.9".

[0114] ===SB5=== In SB5 of Figure 6, the control unit 23 of the server device 2 identifies the representative opinion flag information for each opinion information grouped in SB3.

[0115] Specifically, although optional, for example, from the opinion information belonging to each group grouped in SB3, a predetermined number of opinion information can be selected as opinion information indicating representative opinions, and "TRUE" can be identified as the representative opinion flag information for the selected opinion information, while "FALSE" can be identified as the representative opinion flag information for opinion information other than the selected opinion information (i.e., opinion information indicating opinions other than representative opinions).

[0116] Here, for example, regarding the comments "The image quality is good" and "The new design is very easy to use" in Figure 8, which belong to the same group, if "The image quality is good" is selected as the representative opinion and "The new design is very easy to use" is not selected as the representative opinion, then "TRUE" is identified as the representative opinion flag for "The image quality is good" and "FALSE" is identified as the representative opinion flag for "The new design is very easy to use".

[0117] In the explanatory diagram of Figure 5, the processing here converts, for example, opinion information 81 into opinion information indicating representative opinion 81A.

[0118] The method for selecting opinion information to represent representative opinions is arbitrary, but for example, the following method may be used, or other methods may be used.

[0119] For example, each opinion piece belonging to each group is broken down into words, and the importance of each word is determined (the degree of importance is determined according to the frequency of occurrence of the word within the group, with higher frequency indicating higher importance). Then, from among the words of all opinion pieces belonging to the group, a predetermined number (e.g., 2 or 3) of words with the aforementioned high importance are identified as group-side important words. Next, for each opinion piece belonging to the group, a predetermined number (e.g., 2 or 3) of words with the aforementioned high importance are identified as opinion piece-side important words. Next, the similarity between the aforementioned group-side important words and opinion piece-side important words is determined, and opinion pieces corresponding to a predetermined number (e.g., 2 or 3) of opinion piece-side important words with the highest similarity may be selected as opinion pieces representing the representative opinion.

[0120] Furthermore, the similarity between the aforementioned group-side important words and opinion-side important words may be determined, for example, by converting each word into numerical vector information using a predetermined model, and then determining the similarity based on the difference or distance between these numerical vector information.

[0121] ==Variations== As a variation, for example, one could focus on the group likelihood information identified in SB4 and select a predetermined number of opinion pieces from each group with the highest group likelihood information values ​​to represent the representative opinion. Alternatively, other methods may be applied.

[0122] ===SB6=== In SB6 of Figure 6, the control unit 23 of the server device 2 acquires opinion information that has been identified as "negative" as emotion information in SA2 from the opinion information acquired in SA1 of Figure 4. Then, in SB7 to SB10 below, processing is performed on this "negative" opinion information.

[0123] Note that the processing of SB7 to SB10 is the same as that of SB2 to SB5, so only an overview will be provided.

[0124] ===SB7=== In SB7 in Figure 6, the control unit 23 of the server device 2 identifies the feature quantities of the "negative" opinion information acquired in SB6.

[0125] ===SB8=== In SB8 of Figure 6, the control unit 23 of the server device 2 groups the "negative" opinion information acquired in SB6 based on the features identified in SB7.

[0126] ===SB9=== In SB9 in Figure 6, the control unit 23 of the server device 2 identifies group likelihood information for each opinion information grouped in SB8.

[0127] ===SB10=== In SB10 of Figure 6, the control unit 23 of the server device 2 identifies the representative opinion flag information for each opinion information grouped in SB8. Then, it returns the grouping-related processing shown in Figure 6.

[0128] ===SA4=== In SA4 in Figure 4, the control unit 23 of the server device 2 generates group name information indicating the names of each group grouped in SA3 (specifically SB3 and SB8 in Figure 6).

[0129] Specifically, although optional, the control unit 23 processes the data using a generative model stored outside the server device 2 (such as a GPT (Generative Pretrained Transformer) model that outputs response information indicating the answer corresponding to the query information when query information is input).

[0130] ==Processing== In detail, the control unit 23 acquires opinion information belonging to each group, and also acquires emotion information corresponding to each group. Then, it communicates with an external source to input query information, which includes the acquired opinion information and instruction information (information indicating an instruction to generate and output the name of the group to which the input opinion information belongs, taking into account the emotion indicated by the input emotion information), into the generation model.

[0131] The generation model then outputs group name information corresponding to the input opinion information and sentiment information as response information corresponding to the inquiry information, and the control unit 23 acquires this group name information by communicating with an external source, and uses the acquired group name information as the group name information generated for the aforementioned group.

[0132] Furthermore, the aforementioned instruction information includes not only emotional information but also information indicating a predetermined naming convention for group names; in other words, it includes information that has been pre-adjusted and created to obtain appropriate group name information. In addition, since emotional information is included in the instruction information, it is possible to obtain appropriate group name information that takes emotions into consideration.

[0133] Furthermore, regarding the emotional information included in the instruction information, when generating group name information for groups grouped in SB3 in Figure 6, the "positive" emotional information identified in SA2 will be used, and when generating group name information for groups grouped in SB8 in Figure 6, the "negative" emotional information identified in SA2 will be used.

[0134] Here, for example, regarding the group in the upper part of Figure 8, opinion information such as "The image quality is good" and "The new design is very easy to use" is obtained as opinion information belonging to that group, and "Positive," which was identified in SA2 in Figure 4, is obtained as sentiment information corresponding to that group. Then, the query information, which includes the aforementioned obtained "The image quality is good" and "The new design is very easy to use," as well as the instruction information that includes the aforementioned obtained "Positive," is input into the generative model.

[0135] The generation model then outputs, for example, "The image quality is good and desirable" as group name information corresponding to the input "The image quality is good," "The new design is very easy to use," etc., and "Positive," for the response information corresponding to the inquiry information. In this case, the control unit 23 acquires "The image quality is good and desirable" and uses the acquired "The image quality is good and desirable" as the group name information generated for the aforementioned group. That is, it generates "The image quality is good and desirable" as the group name information for the aforementioned group.

[0136] Furthermore, by performing a similar process for the other groups in Figure 8, group name information for each group is generated.

[0137] In the explanatory diagram of Figure 5, the processing here generates group name information 61, etc.

[0138] ===SA5=== Figure 9 illustrates the selection of setting category information. In SA5 of Figure 4, the control unit 23 of the server device 2 selects the setting category information.

[0139] Specifically, although optional, let's assume that the recording unit 22 has recorded multiple candidate category information (not shown in Figure 1). "Multiple candidate category information" refers to information indicating multiple candidate categories that are candidates to be set as categories representing each of multiple groups, and is information that is recorded in advance by a user of the information system 100 who determines it in accordance with their own analysis policy regarding the subject and inputs it into the server device 2.

[0140] In this embodiment, we will explain using an example where multiple candidate category information such as "cost," "UI" (user interface), and "performance" shown in Figure 9 is stored in the recording unit 22.

[0141] Specifically, for example, the control unit 23 processes the data using a generation model stored outside the server device 2 (such as a model that outputs response information indicating the answer corresponding to the query information when query information is input), similar to the case of SA4 in Figure 3.

[0142] ==Processing== In detail, the control unit 23 acquires group name information generated in SA4 for each group grouped in SA3 (specifically SB3 and SB8 in Figure 6), and also acquires opinion information that identifies "TRUE" as representative opinion flag information in SB5 or SB10 in Figure 6 (i.e., opinion information indicating a representative opinion among the opinion information belonging to the group), and multiple candidate category information from the recording unit 22. Then, by communicating with an external source, the control unit 23 inputs query information that includes the acquired multiple candidate category information, the aforementioned acquired group name information, the aforementioned acquired opinion information (opinion information indicating a representative opinion), and instruction information (information indicating an instruction to select and output one or more appropriate candidate category information corresponding to the input group name information and opinion information indicating a representative opinion from the input multiple candidate category information).

[0143] The generation model then selects and outputs one or more appropriate candidate category information from among the multiple candidate category information inputs as response information corresponding to the inquiry information, corresponding to the input group name information and opinion information indicating representative opinions. The control unit 23 then communicates with an external source to acquire this one or more candidate category information and selects the acquired candidate category information as the set category information.

[0144] Furthermore, the aforementioned instruction information includes information that has been pre-adjusted and created to obtain appropriate setting category information. By configuring it in this way, it becomes possible to select appropriate candidate category information as setting category information.

[0145] Here, for example, regarding the group in the upper part of Figure 9, the group name information is obtained as "The image quality is good and desirable," and opinion information indicating a representative opinion such as "The image quality is good" is obtained, as well as information on multiple candidate categories such as "Cost," "UI," and "Performance." Then, query information including this information and instruction information is input into the generation model.

[0146] The generation model then outputs "UI," one of the candidate category information, as the answer information corresponding to the query information. In this case, the control unit 23 selects "UI" as the set category information, as shown in Figure 9.

[0147] Furthermore, by performing a similar process for the other groups in Figure 9, the setting category information for each group is selected.

[0148] In the explanatory diagram of Figure 5, the processing here sets the setting category information 51, etc.

[0149] ===SA6=== In SA6 in Figure 4, the control unit 23 of the server device 2 performs management processing on the opinion information acquired in SA1 based on the processing results of each of the aforementioned processes (SA1 to SA5).

[0150] "Management processing" refers to the process of managing opinion information, and is a concept that includes, for example, the process of storing information related to the opinion information, and the process of outputting (display output or audio output) information related to said opinion information.

[0151] In this embodiment, the process for storing information related to opinion information, as shown in Figure 3, will be described, and the process for displaying and outputting information related to opinion information based on said opinion-related information will also be described.

[0152] ==Storage of Opinion-Related Information== =Product name information, date information, and post content information= The control unit 23 stores information with the same name as the post-related information in Figure 2 as product name information, date information, and post content information in the opinion-related information in Figure 3.

[0153] =Opinion information, emotion information, emotion likelihood information= The control unit 23 stores the opinion information, emotion information, and emotion likelihood information as shown in Figure 3, specifically the opinion information acquired by SA1 in Figure 4, the emotion information identified by SA2, and the emotion likelihood information.

[0154] =Group name information, group likelihood information= The control unit 23 stores the group name information generated in SA4 in Figure 4 and the group likelihood information identified in SB4 or SB9 in Figure 6 as group name information and group likelihood information in Figure 3.

[0155] In addition, in SA4-SA5 of Figure 4, sentiment information is processed only for "positive" and "negative" opinion information (see SB1 and SB6 in Figure 6), and opinion information with "neutral" sentiment information is not processed. Therefore, for opinion information with "neutral" sentiment information, group name information and group likelihood information are not stored, as shown in the third row of Figure 3 (the same applies to representative opinion flag information and set category information).

[0156] =Representative Opinion Flag Information, Setting Category Information= The control unit 23 stores the representative opinion flag information and setting category information as shown in Figure 3, specifically the representative opinion flag information identified in SB5 and SB10 in Figure 6, and the setting category information selected in SA5 in Figure 4.

[0157] In this way, the opinion-related information in Figure 3 is stored.

[0158] ==Display and output information related to opinion information== The control unit 23 generates screen information for displaying information related to the opinion information based on the opinion-related information in Figure 3 and transmits it to the terminal device 1, thereby enabling the display of the information related to the opinion information on the display 13 of the terminal device 1 in a predetermined display manner.

[0159] =Part 1= Specifically, although optional, the system may be configured to display information indicating the number of opinion pieces belonging to each group indicated by the group name information on the date (date information) when a particular product was posted, based on the product name information, date information, opinion information, and group name information in Figure 3. In other words, it may be configured to display the change in the number of opinion pieces belonging to a group over time.

[0160] For example, information showing the change over time in the number of opinion pieces associated with "Product Name Information" = "AAA" and "Group Name Information" = "Good image quality" in Figure 3 may be displayed. In this case, it may be displayed as a line graph with the date on the horizontal axis and the number of opinion pieces on the vertical axis, or it may be displayed in other display formats (the same applies to "Part 2" below).

[0161] In this case, if the user selects and inputs specific information (for example, "positive" or "UI") as the emotion information or setting category information in Figure 3, the system may be configured to display the number of opinion pieces associated with that specific information, taking the emotion information or setting category information into consideration.

[0162] =Part 2= Furthermore, for example, based on the product name information, date information, opinion information, and sentiment information in Figure 3, the system may be configured to display information showing the number of opinion pieces associated with each sentiment indicated by the sentiment information on the date (date information) when the product was posted for a specific product. In other words, the system may be configured to display the change in the number of opinion pieces associated with each sentiment over time.

[0163] For example, information such as the change over time in the number of opinion pieces associated with "Product Name Information" = "AAA" and "Sentiment Information" = "Positive" in Figure 3 may be displayed.

[0164] In this case, date information may be disregarded, and the number and percentage of opinion information associated with each product name and sentiment information may be displayed in a predetermined format (e.g., bar graph, pie chart, radar chart, etc.).

[0165] Furthermore, in this case, if a user selects and inputs specific information (for example, "good image quality" or "UI") as the group name information or setting category information in Figure 3, the system may be configured to display the number of opinion pieces associated with that specific information, taking into account the group name information or setting category information.

[0166] =Part 3= Furthermore, for example, based on the product name information, opinion information, and setting category information in Figure 3, the system may be configured to display information indicating the number or percentage of opinion information associated with each product name information and each setting category information in a predetermined format (e.g., bar graph, pie chart, radar chart, etc.).

[0167] In this case, if the user selects and inputs specific information (for example, "The image quality is good and pleasing" or "Positive") as the group name information or sentiment information in Figure 3, the system may be configured to display the number of opinion pieces associated with that specific information.

[0168] =Part 4= Although the above description explains that the number of opinion pieces is displayed, the system may also be configured to display the opinion pieces themselves (i.e., "The image quality is good"), the number of posted content pieces, or the posted content pieces themselves when a user performs a specified operation, or automatically.

[0169] Furthermore, all or part of the opinion-related information in Figure 3 may be configured to be displayed in a predetermined format (such as a graph or chart based on an arbitrary item, or a table showing all of the information).

[0170] Furthermore, the system may be configured to allow filtering and sorting of each piece of information based on criteria such as group name information, sentiment information, setting category information, or other information.

[0171] =Part 5= The above explanation regarding the display of each piece of information included in the opinion-related information in Figure 3 is illustrative, and this opinion-related information may be configured to be displayed using any other method, as long as it is possible to provide useful information regarding the target (a predetermined application program).

[0172] (Effects of this embodiment) According to this embodiment, by dividing multiple opinion pieces into multiple groups based on predetermined criteria and managing the multiple opinion pieces based on these groups, for example, opinion pieces can be managed on a group basis, making it possible to provide useful information regarding the target (a predetermined application program).

[0173] Furthermore, since each piece of opinion information is a combination of a first-word piece of information corresponding to the subject and a second-word piece of information corresponding to the predicate (the predicate corresponding to the subject), it becomes possible to use appropriate information as opinion information, for example, thereby providing useful information regarding the subject.

[0174] Furthermore, by dividing multiple opinion pieces into multiple groups based on predetermined criteria and emotional information, it becomes possible to appropriately group them while considering emotions, for example, thereby providing useful information regarding the subject.

[0175] Furthermore, by managing multiple opinion pieces based on multiple groups and their group name information (name information), it becomes possible to manage opinion pieces on a group-by-group basis, for example, by considering the group name information, thereby providing useful information regarding the subject.

[0176] Furthermore, by managing multiple opinion pieces based on multiple groups, their group name information, and selected candidate category information, it becomes possible to manage opinion pieces on a group-by-group basis, for example, by considering group name information and candidate category information, thereby providing useful information regarding the subject.

[0177] [III] Modifications of the Embodiment While embodiments of the present invention have been described above, the specific configurations and means of the present invention can be arbitrarily modified and improved within the scope of the technical idea of ​​each invention described in the claims. Such modifications will be described below.

[0178] (Regarding the problems to be solved and the effects of the invention) First, the problems that the invention aims to solve and the effects of the invention are not limited to those described above, and may vary depending on the implementation environment and details of the invention's configuration. In some cases, only a portion of the problems described above may be solved, or only a portion of the effects described above may be achieved.

[0179] (Regarding decentralization and integration) Furthermore, the aforementioned electrical components are functional concepts and do not necessarily need to be physically configured as shown in the diagram. In other words, the specific forms of distribution and integration of each part are not limited to those shown in the diagram, and all or part of them can be functionally or physically distributed or integrated in any unit according to various loads and usage conditions.

[0180] (Regarding shape, numerical values, structure, and time series) With regard to the components illustrated in the embodiments and drawings, the shapes, numerical values, paragraphs, or the interrelationships of the structure or time series of multiple components can be arbitrarily modified and improved within the scope of the technical idea of ​​the present invention. For example, the information items included in the post-related information in Figure 2 and the information items included in the opinion-related information in Figure 3 are illustrative examples, and the present invention is not limited to these items; some items may be omitted or other items may be added.

[0181] (Regarding emotional information (Part 1)) Furthermore, while the above embodiment describes the case where processing from SA3 (SB1 to SB10 in Figure 6) onwards is performed for emotional information that is "positive" or "negative," the system is not limited to this. For example, the system may also be configured to perform processing from SA3 onwards in Figure 4 for emotional information that is "neutral."

[0182] Alternatively, the system may be configured to process information without considering emotional information. In this case, for example, SA2 in Figure 4 may be omitted, and the opinion information obtained in SA1 may be processed using SB2 to SB5 in Figure 6, while SA4 to SA6 in Figure 4 may be processed in the same way as each other without using emotional information.

[0183] (Regarding emotional information (Part 2)) Furthermore, while the above embodiment describes the use of three types of emotional information—"positive," "negative," and "neutral"—the system is not limited to these. For example, any two of the above types of information may be used, or the system may be configured to use four or more types of information, including other types of information. In addition, any information related to emotions other than "positive," "negative," or "neutral" (for example, information indicating the intensity of an emotion, the event to which the emotion is directed, its type, or its direction) may be used as emotional information.

[0184] Furthermore, hierarchical information may be structured to be used as emotional information. For example, information such as "direction of opinion," "self-expression," "instructions," and "advice" may be set as information belonging to a subcategory of "neutral," and these subcategory pieces of information may also be structured to be used as emotional information. "Positive" and "negative" may be structured similarly.

[0185] (Regarding related information) Furthermore, while the above embodiment describes the case where the opinion information in Figure 3 is the target-related information, it is not limited to this. For example, the system may be configured to perform each process assuming that the posted content information in Figure 2 is the target-related information. In this case, the system may be configured to acquire the posted content information in SA1 of Figure 4, and then in SA2 and subsequent steps, the system may be configured to perform a process in which the opinion information is replaced with the posted content information in the process of the embodiment. In this case, the processing content may be modified as appropriate to achieve the purpose of each process.

[0186] Furthermore, although the above embodiment describes a case in SA1 of Figure 4 where opinion information is acquired based on the posted content information in Figure 3, it is not limited to this. For example, an administrator or user may input opinion information into the server device 2, and the opinion information may be pre-stored in the recording unit 22. In Figure 4, SA1 may be configured to acquire this opinion information and execute each process from SA2 onward.

[0187] Furthermore, while the above embodiment described a case where "target-related information" is text information that shows the subjective opinion of the subject, the invention is not limited to this, and information that shows facts about the subject may also be used as target-related information.

[0188] For example, the post content information in Figure 2 may include information that indicates facts about the subject, such as information corresponding to an error message output by the computer regarding the product "AAA" (e.g., "Function A does not work"). The system may be configured to perform the processing described in the above embodiment, including this information. In this case, the information corresponding to this error message will also be acquired and processed as opinion information.

[0189] In this case, the names of the information such as "post content information" and "opinion information" may be replaced with more appropriate names such as "post content information, etc." and "opinion information, etc." Also, as mentioned above, the system may be configured to process "neutral" information or to process information without considering sentiment.

[0190] Furthermore, although the above embodiment described the case where the target-related information is text information, the system is not limited to this, and any type of information (for example, image information, etc.) may be used as the target-related information.

[0191] (About the model) Furthermore, the processing performed using the trained model (the model recorded in the information system 100) described in the above embodiment may be implemented using an externally recorded generative model, and the processing performed using the generative model may be implemented using the trained model.

[0192] (Regarding setting category information) Furthermore, although the above embodiment described a case in which one or more candidate category information is selected from the entire set of candidate category information, it is not limited to this.

[0193] For example, a first group containing multiple candidate category information and a second group containing other multiple candidate category information may be predetermined, and by performing the same processing as SA5 in Figure 4, one or more candidate category information in the first group may be selected as the set category information, and one or more candidate category information in the second group may be selected as the other set category information.

[0194] Furthermore, for example, instead of limiting ourselves to the first and second groups, we may pre-define three or more groups containing multiple candidate category information, and perform processing similar to SA5 in Figure 4 to select one or more candidate category information as the set category information from among the multiple candidate category information in each group.

[0195] (Regarding opinion information) Furthermore, while Figure 4's SA1 describes a case where information combining the first word information corresponding to the subject and the second word information corresponding to the predicate is acquired as opinion information, it is not limited to this. For example, as long as the information indicates the subject's subjective view of the subject, or indicates facts about the subject, the system may be configured to acquire information that has any components, not limited to sentence components such as subjects and predicates, as opinion information.

[0196] (Regarding the selection of setting category information) Furthermore, while Figure 4's SA5 describes the case where opinion information identified as "TRUE" as representative opinion flag information in Figure 6's SB5 or SB10 (i.e., opinion information indicating a representative opinion among the opinion information belonging to the group) is acquired and processed, the system is not limited to this. For example, the system may focus on the group likelihood information identified in Figure 6's SB4 or SB9, acquire a predetermined number of opinion pieces from the group with the largest group likelihood information value, and process the data using that opinion information. In other words, instead of opinion information indicating a representative opinion, the system may be configured to process the data using a predetermined number of opinion pieces from the group with the largest group likelihood information value.

[0197] (Regarding the omission of processing) Furthermore, in the above embodiment, some processing may be omitted. For example, SA4 or SA5 in Figure 4 may be omitted. If SA4 is omitted, group name information will not be generated, but since the opinion information is grouped in SA3, it will be possible to manage the opinion information by displaying and outputting it on a group basis in SA6.

[0198] (Regarding changes to the process) Furthermore, in the above embodiments, any other method may be applied insofar as it achieves the objective of each process.

[0199] (Regarding combinations) Furthermore, the technologies of the embodiments and modified examples may be combined in any way.

[0200] (Note) The management system described in Appendix 1 comprises: acquisition means for acquiring multiple pieces of subject-related information that indicate the subject's subjective opinion or facts about the subject; grouping means for dividing the multiple pieces of subject-related information acquired by the acquisition means into multiple groups based on predetermined criteria; and management means for managing the multiple pieces of subject-related information acquired by the acquisition means based on the multiple groups divided by the grouping means.

[0201] The management system in Appendix 2 is a management system described in Appendix 1, in which each of the multiple pieces of object-related information acquired by the acquisition means is information that combines a first word information corresponding to the subject and a second word information corresponding to the predicate.

[0202] The management system in Appendix 3, in the management system described in Appendix 1, wherein the plurality of object-related information acquired by the acquisition means at least indicates the subjective opinion of the subject regarding the object, the management system further comprises identification means for identifying emotional information indicating the subject's feelings regarding each of the plurality of object-related information acquired by the acquisition means, and the grouping means divides the plurality of object-related information acquired by the acquisition means into a plurality of groups based on predetermined criteria and the emotional information identified by the identification means.

[0203] The management system of Appendix 4 further comprises a generation means that generates name information indicating the name of each of the multiple groups divided into the grouping means, based on the target-related information belonging to each of the multiple groups divided into the grouping means, and the management means manages the multiple target-related information acquired by the acquisition means based on the multiple groups divided into the grouping means and the name information generated by the generation means.

[0204] The management system described in Appendix 5 further comprises a selection means that selects one or more candidate category information from a plurality of candidate category information based on the plurality of groups divided by the grouping means and the name information generated by the generation means, wherein the plurality of candidate category information is information indicating a plurality of candidate categories that are candidates to be set as categories representing each of the plurality of groups divided by the grouping means, and the management means manages the plurality of target-related information acquired by the acquisition means based on the plurality of groups divided by the grouping means, the name information generated by the generation means and the one or more candidate category information selected by the selection means.

[0205] The management program described in Appendix 6 causes the computer to function as an acquisition means for acquiring multiple pieces of subject-related information that indicate the subject's subjective opinion or facts about the subject; a grouping means for dividing the multiple pieces of subject-related information acquired by the acquisition means into multiple groups based on predetermined criteria; and a management means for managing the multiple pieces of subject-related information acquired by the acquisition means based on the multiple groups divided by the grouping means.

[0206] (Effect of the note) According to the management system described in Appendix 1 and the management program described in Appendix 6, by dividing multiple subject-related information into multiple groups based on predetermined criteria and managing multiple subject-related information based on these groups, it becomes possible to manage subject-related information on a group basis, for example, thereby providing useful information regarding the subject.

[0207] According to the management system described in Appendix 2, each of the multiple object-related pieces of information is a combination of first-word information corresponding to the subject and second-word information corresponding to the predicate. Therefore, for example, appropriate information can be used as object-related information, making it possible to provide useful information about the object.

[0208] According to the management system described in Appendix 3, by dividing multiple subject-related pieces of information into multiple groups based on predetermined criteria and emotional information, it becomes possible to appropriately group them, for example, by taking emotions into consideration, thereby providing useful information about the subject.

[0209] According to the management system described in Appendix 4, by managing multiple object-related information based on multiple groups and the name information of those groups, it becomes possible to manage object-related information on a group basis, for example, by taking the name information into consideration, thereby making it possible to provide useful information regarding the object.

[0210] According to the management system described in Appendix 5, by managing multiple subject-related information based on multiple groups, the name information of those groups, and the selected candidate category information, it becomes possible to manage subject-related information on a group basis, for example, by considering the name information and candidate category information, thereby making it possible to provide useful information regarding the subject. [Explanation of Symbols]

[0211] 1. Terminal device 2 Server devices 11 Communications Department 12 Touchpads 13 displays 14 Records Section 15 Control Unit 21 Communications Department 22 Records Section 23 Control Unit 51. Settings Category Information 61 Group Name Information 71 Emotional information 72 Emotional information 73 Emotional information 81 Opinion information 81A Representative opinion 82 Opinion information 83 Opinion information 91 Post Content Information 100 Information Systems

Claims

1. A means for acquiring multiple pieces of subject-related information that indicate the subject's subjective opinion or facts about the subject, A grouping means that divides the multiple object-related information acquired by the acquisition means into multiple groups based on predetermined criteria, A management means for managing a plurality of object-related information acquired by the acquisition means based on the plurality of groups divided into the grouping means, A management system equipped with the following features.

2. Each of the multiple pieces of object-related information acquired by the acquisition means is information that combines a first word information corresponding to the subject and a second word information corresponding to the predicate. The management system according to claim 1.

3. The multiple pieces of subject-related information acquired by the acquisition means at least indicate the subject's subjective opinion regarding the subject, The aforementioned management system is The acquisition means further comprises a means for identifying emotional information indicating the emotions of the subject with respect to each of the plurality of subject-related pieces of information acquired by the acquisition means, The grouping means divides the plurality of object-related pieces of information acquired by the acquisition means into a plurality of groups based on the predetermined criteria and the emotion information identified by the identification means. The management system according to claim 1.

4. The grouping means further comprises a generation means that generates name information indicating the name of each of the multiple groups divided into the grouping means, based on the object-related information belonging to each of the multiple groups divided into the grouping means, The management means manages the multiple target-related information acquired by the acquisition means based on the multiple groups divided by the grouping means and the name information generated by the generation means. The management system according to claim 1.

5. The system further comprises a selection means that selects one or more candidate category information from among multiple candidate category information based on the multiple groups divided by the grouping means and the name information generated by the generation means, The aforementioned multiple candidate category information is information indicating multiple candidate categories that are candidates to be set as categories representing each of the multiple groups divided by the grouping means, The management means manages a plurality of target-related pieces of information acquired by the acquisition means based on a plurality of groups divided by the grouping means, name information generated by the generation means, and one or more candidate category pieces of information selected by the selection means. The management system according to claim 4.

6. Computers, A means for acquiring multiple pieces of subject-related information that indicate the subject's subjective opinion or facts about the subject, A grouping means that divides the multiple object-related information acquired by the acquisition means into multiple groups based on predetermined criteria, A management means for managing a plurality of object-related information acquired by the acquisition means based on the plurality of groups divided into the grouping means, A management program that functions as such.

Images