Information processing device, program, and information processing method

Abstract

This invention provides an information processing device, a program, and an information processing method for classifying evaluators. [Solution] In the system 10, the information processing device 100 includes an acquisition unit that acquires evaluation information including score information indicating the score of the company 300 to be evaluated and comment information indicating comments related to the reasons for the score of the company to be evaluated, and a classification unit that classifies evaluators who evaluated the company to be evaluated based on the evaluation information. The classification unit classifies evaluators as recommenders of the company to be evaluated if the score of the company to be evaluated indicated by the score information is higher than a predetermined first score threshold, classifies evaluators as neutrals of the company to be evaluated if the score of the company to be evaluated is lower than the first score threshold and higher than a predetermined second score threshold which is lower than the first score threshold, and classifies evaluators as critics of the company to be evaluated if the score of the company to be evaluated is lower than the second score threshold.

Description

[Technical Field]

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

[0002] Patent Document 1 describes a customer loyalty analysis system that can obtain more accurate analysis results regarding the factors that cause content subscription contracts to be terminated. [Prior art document] [Patent] [Patent Document 1] Japanese Unexamined Patent Publication No. 2024-152190 [Overview of the project] [Means for solving the problem]

[0003] According to one embodiment of the present invention, an information processing device is provided. The information processing device may include an acquisition unit that acquires evaluation information including score information indicating the score of the item to be evaluated and comment information indicating comments related to the reasons for the score of the item to be evaluated. The information processing device may also include a classification unit that classifies the evaluators who evaluated the item to be evaluated based on the evaluation information.

[0004] In the information processing device, the classification unit may classify the evaluator as a recommender of the evaluation target if the score of the evaluation target indicated by the score information is higher than a predetermined first score threshold; classify the evaluator as a neutral party of the evaluation target if the score of the evaluation target is lower than the first score threshold and higher than a predetermined second score threshold which is lower than the first score threshold; and classify the evaluator as a critic of the evaluation target if the score of the evaluation target is lower than the second score threshold.

[0005] In any of the above-mentioned information processing devices, the classification unit may, based on the classification result obtained by classifying the comments indicated by the comment information into positive comments towards the subject of evaluation, neutral comments towards the subject of evaluation, negative comments towards the subject of evaluation, and comments expressing indifference towards the subject of evaluation, reclassify the evaluators, who have been classified into recommenders of the subject of evaluation, neutrals towards the subject of evaluation, and critics of the subject of evaluation, into recommenders of the subject of evaluation, neutrals towards the subject of evaluation, critics of the subject of evaluation, and indifferent persons who are indifferent to the subject of evaluation.

[0006] Any of the above-mentioned information processing devices may further include a calculation unit that calculates the difference between a recommender ratio, which is the ratio of the number of evaluators who have been reclassified by the classification unit as recommenders of the evaluation target to the total number of evaluators who have evaluated the evaluation target, and a critic ratio, which is the ratio of the number of evaluators who have been reclassified by the classification unit as critics of the evaluation target to the total number of evaluators who have evaluated the evaluation target.

[0007] Any of the above-mentioned information processing devices may further include an identification unit that identifies the reason for the score of the subject to evaluation based on the comment information, and the calculation unit may calculate the difference between the proportion of recommenders and the proportion of critics for each reason for the score of the subject to evaluation.

[0008] In any of the above-mentioned information processing devices, the acquisition unit may further acquire prompts for classifying the comments, and the classification unit may classify the comments by inputting the prompts to a generating AI and acquiring the classification results obtained from the generating AI based on the prompts.

[0009] Any of the above-mentioned information processing devices may further include an information storage unit that stores cancellation rate information indicating the cancellation rate at which an evaluator cancels a contract with a company within a predetermined period from the time the evaluator evaluates the company being evaluated, for each combination of the evaluator's category and the comment category, and the classification unit may further reclassify the evaluators based on the cancellation rate information stored in the information storage unit.

[0010] In any of the above-mentioned information processing devices, the acquisition unit may acquire the evaluation information which further includes choice information indicating the choice of option that corresponds to the reason for the score of the evaluation target, and the classification unit may, when the evaluator is reclassified as an indifferent person who is indifferent to the evaluation target, further classify the evaluator who has been reclassified as an indifferent person who is indifferent to the evaluation target based on the choice information.

[0011] Any of the above-mentioned information processing devices may further include an information storage unit that stores the reasons for the score of the evaluation target identified from the comment information and cancellation rate information for each category of the choices, indicating the cancellation rate at which the evaluator cancels a contract with the company within a predetermined period from the time the evaluator evaluated the company that is the evaluation target; and an identification unit that identifies the reasons for the score of the evaluation target based on the comment information. The classification unit may further classify the evaluators who have been reclassified as indifferent persons who are indifferent to the evaluation target, based on the cancellation rate information stored in the information storage unit.

[0012] Any of the above-mentioned information processing devices may further include a learning data storage unit that stores learning data including comment data indicating comments related to the reasons for the scores to be evaluated and comment category data indicating the categories of the comments, and a model generation unit that uses a plurality of the learning data stored in the learning data storage unit as training data to generate a decision model by machine learning that determines the category of the comments related to the reasons for the scores to be evaluated indicated by the comment data from the comment data, and the classification unit may classify the comments by using the decision model to determine the category of the comments indicated by the comment information from the comment information.

[0013] In any of the above-mentioned information processing devices, the classification unit may reclassify the evaluators, who have been classified by the scores of the evaluation targets indicated by the score information, based on the classification result obtained by classifying the comments indicated by the comment information according to predetermined classification criteria.

[0014] Any of the above-mentioned information processing devices may further include a determination unit that determines, based on the comment information, whether the reason for the score of the store of the company being evaluated, as indicated by the score information, is attributable to at least one of the store and the store's crew, and the classification unit may classify the evaluator based on the evaluation information if the determination unit determines that the reason for the score is attributable to at least one of the store and the crew.

[0015] According to one embodiment of the present invention, a program is provided for a computer to perform an acquisition procedure for acquiring evaluation information, which includes score information indicating the score of the subject to evaluation and comment information indicating comments related to the reasons for the score of the subject to evaluation, and a classification procedure for classifying the evaluators who evaluated the subject to evaluation based on the evaluation information.

[0016] According to one embodiment of the present invention, an information processing method performed by a computer is provided. The information processing method may include an acquisition step of acquiring evaluation information, which includes score information indicating the score of the subject to evaluation and comment information indicating comments related to the reasons for the score of the subject to evaluation. The information processing method may include a classification step of classifying the evaluators who evaluated the subject to evaluation based on the evaluation information.

[0017] Furthermore, the above summary of the invention does not enumerate all the necessary features of the present invention. Subcombinations of these features may also constitute an invention. [Brief explanation of the drawing]

[0018] [Figure 1] An example of System 10 is shown in general terms. [Figure 2] This is an explanatory diagram illustrating an example of an evaluation indicator. [Figure 3] This is an explanatory diagram illustrating the general method for calculating evaluation indicators. [Figure 4] This is an explanatory diagram illustrating an example of comparing evaluation targets based on evaluation indicators. [Figure 5] An example of a questionnaire is shown below. [Figure 6] A schematic example of a prompt is shown below. [Figure 7] Here is a schematic example of labels that can be assigned to comments. [Figure 8] A general example of the churn rate for 250 evaluators is shown below. [Figure 9] This is an explanatory diagram illustrating an example of a method for calculating evaluation indicators. [Figure 10] Here is another example of the churn rate for 250 evaluators. [Figure 11] This is an explanatory diagram illustrating another example of how evaluation indicators can be calculated. [Figure 12] Another example of System 10 is outlined below. [Figure 13] This is an explanatory diagram illustrating another example of how evaluation indicators can be calculated. [Figure 14] An example of the functional configuration of the information processing device 100 is shown schematically. [Figure 15] This is an explanatory diagram illustrating an example of the processing flow of System 10. [Figure 16] A schematic example of the hardware configuration of a computer 1200 that functions as an information processing device 100 is shown. [Modes for carrying out the invention]

[0019] In recent years, there has been increasing attention on so-called customer loyalty, which represents customers' attachment to and trust in a company, its products, and services. One reason for this increased attention is that, compared to customer satisfaction, which represents the level of satisfaction of customers who have received products and services from a company, customer loyalty has a stronger correlation with a company's revenue. For this reason, many companies now use NPS (Net Promoter Score), a key performance indicator (KPI) that quantifies customer loyalty. NPS is a performance indicator that quantifies customer loyalty based on the classification results obtained by classifying respondents based on their answers to questions about customer loyalty. Advantages of NPS include its status as a unified global performance indicator and its simplicity. On the other hand, challenges of NPS include the fact that it is a performance indicator calculated based on classification results that may not appropriately classify respondents, and that it is difficult to intuitively grasp the effectiveness of improvement measures based on NPS, or to compare competitors based on NPS. The need for resolving the challenges of NPS is high because it enables the reliable quantification of customer loyalty and provides an evaluation metric that makes it easy to intuitively grasp the effectiveness of improvement measures and compare them with competitors. In the system according to this embodiment, for example, a mechanism is adopted to classify evaluators who evaluated an evaluation target based on the score they gave the target and the comments related to the reason for the score. By classifying evaluators not only based on the score but also on the comments related to the reason for the score, evaluators can be classified more appropriately. In particular, in the system according to this embodiment, for example, C-NPS (Comment-based NPS) is an evaluation metric that quantifies customer loyalty from the classification results obtained by classifying customers based on the customer's response to a question asking about customer loyalty, which is one of a multi-level score scales, and the comments related to the reason for the score.To calculate C-NPS, customers who answer questions about customer loyalty can be classified into one of the following categories: Promoter, Passive, Detractor, or Indifferent. By calculating C-NPS from classification results that appropriately categorize customers not only based on their scores but also on comments related to the reasons for their scores, it is possible to create an evaluation metric that can quantify customer loyalty with high reliability. Furthermore, by calculating C-NPS for each reason for a score based on comments related to the reasons for the score, it is possible to create an evaluation metric that makes it easier to understand the effectiveness of improvement measures and compare with competitors.

[0020] The present invention will be described below through embodiments, but these embodiments are not intended to limit the invention as defined in the claims. Furthermore, not all combinations of features described in the embodiments are necessarily essential to the solution of the invention. In addition, in the drawings, identical or similar parts may be given the same reference numeral to omit redundant descriptions.

[0021] Figure 1 schematically shows an example of system 10. System 10 may include an information processing device 100. System 10 may further include a data collection device 400.

[0022] System 10 may, for example, provide an evaluation service for evaluating the object to be evaluated. System 10 may, for example, provide an evaluation support service to assist in the evaluation of the object to be evaluated. System 10 may also provide any other services related to the evaluation of the object to be evaluated.

[0023] The subject of evaluation may be, for example, Company 300. The subject of evaluation may be, for example, Company 300's stores. The subject of evaluation may be, for example, the services provided by Company 300. The subject of evaluation may be, for example, Company 300's products. Note that services and products may be collectively referred to as goods. The subject of evaluation may be, for example, Company 300's applications. The subject of evaluation may be, for example, Company 300's web pages. Applications and web pages may be included in goods. The subject of evaluation may be anything else related to Company 300.

[0024] Figure 1 shows an example where the evaluation targets 300 companies. Note that the 300 companies may be private companies or public enterprises.

[0025] The 250 evaluators being evaluated are, for example, customers of company 300. The 250 evaluators being evaluated may also be employees of company 300. This explanation will primarily focus on the case where the 250 evaluators being evaluated are customers of company 300.

[0026] The customers of Company 300 are, for example, users who purchase services provided by Company 300. Examples of services include communication services, electronic payment services, customer service, insurance services, medical services, nursing care services, training services, transportation services, and pick-up / drop-off services. The customers of Company 300 may also be users who purchase products from Company 300. Furthermore, the customers of Company 300 may be general consumers or corporations.

[0027] The information processing device 100 performs various information processing tasks. For example, the information processing device 100 performs various information processing tasks in order to evaluate the object to be evaluated.

[0028] The information processing device 100 evaluates the evaluation target, for example, by conducting a questionnaire survey. A questionnaire survey is a research method in which questions are asked to multiple respondents over a predetermined survey period, and the respondents' answers to the questions are used as data. Examples of survey periods include one day, one week, one month, etc. In the example shown in Figure 1, the respondents to the questions may be 250 evaluators.

[0029] The information processing device 100 evaluates one evaluation target by, for example, conducting a questionnaire survey on that single evaluation target. The information processing device 100 evaluates multiple evaluation targets by, for example, conducting a questionnaire survey on multiple evaluation targets. These multiple evaluation targets may be, for example, multiple companies. In this case, these multiple companies may be competing companies. These multiple evaluation targets may be, for example, multiple stores of a single company. These multiple evaluation targets may also be multiple products of one or more companies. In this case, these multiple products may be similar products.

[0030] The information processing device 100 conducts a survey, for example, by sending questions to a communication terminal 200 owned by an evaluator 250. The information processing device 100 sends questions to the communication terminal 200, for example, via the network 20.

[0031] Network 20 may include a core network provided by a telecommunications carrier. The core network may, for example, conform to a 5G (5th Generation) communication system. The core network may conform to a 6G (6th Generation) or later mobile communication system. The core network may conform to a 3G (3rd Generation) communication system. The core network may conform to an LTE (Long Term Evolution) communication system. Network 20 may include the Internet.

[0032] The information processing device 100 may, for example, send a question to the communication terminal 200 using Short Message Service (SMS). The information processing device 100 may also send a question to the communication terminal 200 using email.

[0033] The communication terminal 200 can be any communication terminal capable of communicating with the information processing device 100. For example, the communication terminal 200 may be a mobile phone such as a smartphone, a tablet device, or a wearable device. The communication terminal 200 may also be a PC (Personal Computer).

[0034] For example, a question can be a multiple-choice question. In this case, the respondent answers the question by selecting an option. For example, a question can be a comment-based question. In this case, the respondent answers the question by creating a comment.

[0035] The questions include, for example, questions asking for a score on the item being evaluated. The questions also include, for example, questions asking for the reason behind the score on the item being evaluated.

[0036] The information processing device 100 obtains, for example, the respondent's answer to a question and evaluates the object to be evaluated based on the obtained answer. The information processing device 100 obtains the respondent's answer to a question by, for example, receiving the evaluator's answer to the question from the communication terminal 200. The information processing device 100 receives, for example, the evaluator's answer to the question from the communication terminal 200 via the network 20.

[0037] The information processing device 100 acquires evaluation information, for example, as the respondent's answer to a question. The evaluation information includes, for example, score information indicating the score of the subject being evaluated. The evaluation information includes, for example, comment information indicating comments related to the reason for the score of the subject being evaluated. The evaluation information includes, for example, choice information indicating the choices that correspond to the reason for the score of the subject being evaluated.

[0038] The information processing device 100 classifies the evaluators 250 based on, for example, evaluation information. The information processing device 100 classifies the evaluators 250 based on, for example, the scores of the items to be evaluated, indicated by the score information included in the evaluation information. The information processing device 100 classifies the evaluators 250 based on, for example, comments related to the reasons for the scores of the items to be evaluated, indicated by the comment information included in the evaluation information. The information processing device 100 classifies the evaluators 250 based on, for example, the options that correspond to the reasons for the scores of the items to be evaluated, indicated by the option information included in the evaluation information.

[0039] The information processing device 100 evaluates the subject of evaluation based on the classification results obtained by classifying the 250 evaluators. The information processing device 100 evaluates the subject of evaluation by, for example, calculating an evaluation index that quantifies the evaluation of the subject of evaluation. The information processing device 100 evaluates the subject of evaluation by, for example, calculating an evaluation index that quantifies the customer loyalty of the subject of evaluation.

[0040] The data collection device 400 collects the responses of respondents to questions. The data collection device 400 collects the responses of respondents to questions, for example, by conducting a survey. The data collection device 400 collects the responses of respondents to questions, for example, by conducting a survey on the web.

[0041] The data collection device 400 conducts a survey, for example, by sending questions to the communication terminal 200 via the network 20. The data collection device 400 sends questions to the communication terminal 200, for example, using an application installed on its own machine.

[0042] The collection device 400 collects the respondents' answers to questions, for example, by collecting evaluation information. The collection device 400 also collects evaluation information, for example, by receiving evaluation information from the communication terminal 200 via the network 20.

[0043] The data collection device 400 transmits, for example, the respondents' answers to the collected questions to the information processing device 100 via the network 20. The data collection device 400 also transmits, for example, the collected evaluation information to the information processing device 100 as the respondents' answers to the collected questions via the network 20. The information processing device 100 may obtain the respondents' answers to the questions collected by the data collection device 400 from the data collection device 400 and evaluate the evaluation target based on the obtained answers.

[0044] Figure 2 is an explanatory diagram illustrating an example of an evaluation metric. Here, we mainly explain an example of an evaluation metric that quantifies customer loyalty.

[0045] The upper diagram in Figure 2 is an explanatory diagram illustrating an example of a conventional evaluation indicator. Here, we will mainly explain NPS, which is an example of a conventional evaluation indicator.

[0046] NPS can be an evaluation metric that satisfies the relationship "NPS = (Promoter ratio) - (Detractor ratio)". The promoter ratio is the ratio of promoters who recommend the product to the total number of evaluators who evaluated the product. The detractor ratio is the ratio of detractors who criticize the product to the total number of evaluators who evaluated the product.

[0047] To calculate NPS, respondents are categorized as promoters, passives, or detractors based on their scores on a multi-level scale for answering questions about customer loyalty. For example, if there are 11 scoring levels for customer loyalty from 0 to 10, respondents who score 9-10 are classified as promoters, those who score 7-8 are classified as passives, and those who score 0-6 are classified as detractors.

[0048] Critics may be further classified into either weak critics or strong critics. For example, if there are 11 scoring levels from 0 to 10 for a question about customer loyalty, respondents who answered 5-6 points to the question about customer loyalty would be classified as weak critics, and respondents who answered 0-4 points to the question about customer loyalty would be classified as strong critics.

[0049] Examples of questions that ask about customer loyalty include: "How likely are you to recommend Company X to a close friend or colleague?" or "On a scale of 0 to 10, how likely are you to recommend Product A from Company Y to an acquaintance?" It should be noted that questions that ask about customer loyalty, or any question that asks for a score of the item being evaluated, may be multiple-choice questions.

[0050] Promoters are more likely to engage in positive behavior towards the subject of evaluation and less likely to switch from the subject to evaluation to its competitors. Neutrals are less likely to engage in either positive or negative behavior towards the subject of evaluation and are more likely to switch from the subject to evaluation to its competitors compared to promoters. Critics are more likely to engage in negative behavior towards the subject of evaluation and are more likely to switch from the subject to evaluation to its competitors compared to neutrals.

[0051] In the example shown in the upper part of Figure 2, when asked about customer loyalty, A% of respondents answered as promoters, B% answered as passives, C% answered as weak detractors, and D% answered as strong detractors. Therefore, in the example shown in the upper part of Figure 2, NPS = A - (C + D).

[0052] The lower diagram in Figure 2 is an explanatory diagram to illustrate the differences between the conventional evaluation indicator and the new evaluation indicator. Here, we will mainly explain the differences between NPS, which is an example of a conventional evaluation indicator, and the new evaluation indicator.

[0053] One of the challenges of NPS is that it is an evaluation metric calculated based on classification results that may not properly categorize respondents. One reason why respondents may not be properly categorized is that response scores tend to cluster around the median. For example, if the response score scale is 11 points from 0 to 10, responses to questions about customer loyalty tend to cluster around 5 to 6 points. As a result, many respondents are classified as detractors (especially weak detractors). In addition, so-called loyal customers, who have a strong attachment to or high trust in the product being evaluated, may deliberately give low scores to reflect their expectations of the product being evaluated. Therefore, if respondents are classified solely by their response scores to questions about customer loyalty, there is a risk that respondents such as loyal customers, who should be classified as promoters, may be classified as neutrals or detractors. Furthermore, another reason why respondents may not be properly categorized is that questions about customer loyalty heavily depend on the thoughts and feelings of the respondents. For example, loyal customers who are reluctant to recommend their opinions and values ​​to others (sometimes referred to as introverted loyal customers) tend to give low scores on questions about customer loyalty. Therefore, introverted loyal customers are less likely to be classified as promoters. Indeed, introverted loyal customers are less likely to explicitly recommend the product or service to others compared to loyal customers who are eager to share their opinions and values ​​with others (sometimes referred to as extroverted loyal customers). On the other hand, loyal customers, regardless of whether they are introverted or extroverted, tend to have the product or service deeply integrated into their daily lives. Therefore, introverted loyal customers are more likely to implicitly recommend the product or service to others, for example, if the product or service happens to be included in a photo or video posted on social media without the intention of recommending it to others. For this reason, it is desirable that loyal customers, regardless of whether they are introverted or extroverted, be classified as promoters.

[0054] Another challenge with NPS is the difficulty in intuitively grasping the effectiveness of NPS-based competitive comparisons or improvement measures. This difficulty stems from the fact that the evaluation score alone does not allow for the identification of the reasons behind the score. This is particularly true for diversified companies operating across multiple industries; in such cases, intuitively grasping the effectiveness of NPS-based competitive comparisons or improvement measures becomes especially challenging.

[0055] In contrast, the new evaluation index introduced in the system 10 according to this embodiment is an evaluation index calculated based on the classification results obtained by classifying the evaluators 250 who evaluated the evaluation target based on evaluation information including score information and comment information. For example, the information processing device 100 classifies the evaluation target based on the score of the evaluation target indicated by the score information included in the evaluation information, and reclassifies the evaluation target classified based on the score of the evaluation target based on comments related to the reasons for the score of the evaluation target indicated by the comment information included in the evaluation information. Since the new evaluation index introduced in the system 10 according to this embodiment is an evaluation index calculated from the classification results obtained by classifying the evaluators 250 not only on the score of the evaluation target but also on comments related to the reasons for the score of the evaluation target, it is an evaluation index calculated from classification results that appropriately classify the evaluation target compared to conventional evaluation indexes that classify the evaluators 250 based only on the score of the evaluation target.Therefore, by classifying the evaluation target based on evaluation information including score information and comment information, the system 10 according to this embodiment can contribute to the introduction of an evaluation index calculated from classification results that appropriately classify the evaluation target compared to conventional evaluation indexes. Furthermore, by having the information processing device 100 classify the evaluation targets based on evaluation information including score information and comment information and then calculating an evaluation index from the classification results, the system 10 according to this embodiment can introduce an evaluation index calculated from classification results that appropriately classify the evaluation targets compared to conventional evaluation indexes. Moreover, according to the system 10 according to this embodiment, the information processing device 100 identifies the reasons for the scores of the evaluation targets based on comments related to the reasons for the scores of the evaluation targets indicated by the comment information included in the evaluation information, and calculates an evaluation index for each identified reason for the score of the evaluation target. As a result, the system 10 according to this embodiment can introduce an evaluation index that makes it easier to intuitively grasp competitive comparisons based on evaluation indexes, or the improvement effects of improvement measures based on evaluation indexes, compared to conventional evaluation indexes.

[0056] In particular, when the new evaluation index introduced in the system 10 according to this embodiment is C-NPS, C-NPS is calculated from classification results that appropriately classify the evaluation targets, compared to NPS, and is an evaluation index that makes it easy to intuitively grasp competitive comparisons based on the evaluation index, or the improvement effects of improvement measures based on the evaluation index. Therefore, C-NPS is an evaluation index that solves the problems of NPS. As a result, by realizing the introduction of C-NPS, the system 10 according to this embodiment can quantify customer loyalty with a high degree of reliability and realize the introduction of an evaluation index that makes it easy to intuitively grasp competitive comparisons and the improvement effects of improvement measures. Therefore, by circulating the PDCA cycle of planning (Plan), execution (Do), measurement and evaluation (Check), and countermeasures and improvements (Action), such as verification of improvement effects, based on C-NPS, the system 10 according to this embodiment can contribute to the efficient and continuous improvement of companies. As a result, the system 10 according to this embodiment can contribute to the efficient and continuous development of companies.

[0057] Figure 3 is an explanatory diagram illustrating the overview of the calculation method for evaluation indicators. Here, we will mainly explain the overview of the calculation method for C-NPS. Note that the evaluation target is assumed to be 300 companies.

[0058] The information processing device 100 classifies the evaluators 250 based on the scores of their responses to questions about customer loyalty to company 300, which are indicated by the score information included in the evaluation information. In one example shown in Figure 3, the information processing device 100 classifies A% of the evaluators 250 as "promoters," B% of the evaluators 250 as "neutralists," C% of the evaluators 250 as "weak critics," and D% of the evaluators 250 as "strong critics."

[0059] The information processing device 100 calculates the Net Promoter Score (NPS) from the classification results obtained by classifying 250 evaluators based on their scores in response to a question about customer loyalty to company 300. In the example shown in Figure 3, the information processing device 100 calculates NPS as NPS = A - (C + D).

[0060] The information processing device 100 classifies comments related to the reasons for the scores of companies 300, for example, as indicated by comment information included in the evaluation information. The information processing device 100 classifies the comments by, for example, obtaining a prompt to classify the comments, inputting the obtained prompt into a generating AI, and obtaining a classification result from the generating AI that classifies the comments based on the prompt.

[0061] The information processing device 100, for example, classifies comments related to the reasons for the scores of the evaluation target into one of the following categories: positive comments towards the evaluation target, neutral comments towards the evaluation target, negative comments towards the evaluation target, and comments expressing indifference towards the evaluation target. Note that positive comments towards the evaluation target may be referred to as positive comments, neutral comments towards the evaluation target as neutral comments, negative comments towards the evaluation target as negative comments, and comments expressing indifference towards the evaluation target as indifferent comments.

[0062] Positive comments may contain positive content about the subject being evaluated. Neutral comments may contain neutral content about the subject being evaluated. Negative comments may contain negative content about the subject being evaluated. Indifferent comments may contain content that expresses indifference towards the subject being evaluated, and may not contain any positive, neutral, or negative content about the subject being evaluated.

[0063] If comments related to the reasons for the score of the item being evaluated contain both positive and negative content regarding the item being evaluated, the information processing device 100 may classify the comments as neutral comments. The information processing device 100 may also classify the comments as either positive comments or negative comments.

[0064] For example, the information processing device 100 classifies the evaluators 250, who were initially classified as promoters, passives, or detractors based on the scores of their responses to a question about customer loyalty to company 300, from the classification results obtained by classifying comments related to the reasons for company 300's score, to promoters, passives, detractors, or indifferent. In one example shown in Figure 3, the information processing device 100 reclassifies the evaluators 250 as follows.

[0065] The information processing device 100 reclassifies 250 evaluators who answered "9 to 10 points" to a question asking about customer loyalty to company 300, and whose comments related to the reason for company 300's score include "They were very helpful in discussing pricing plans," as "promoters."

[0066] The information processing device 100 reclassifies 250 evaluators who answered "7-8 points" to a question about customer loyalty to company 300 and whose comments related to the reason for company 300's score include "positive comments" such as "the pricing plan is a good deal" as "promoters." The information processing device 100 also reclassifies 250 evaluators who answered "7-8 points" to a question about customer loyalty to company 300 and whose comments related to the reason for company 300's score include "neutral comments" such as "there are few line problems, but the price is higher than other companies" as "passives."

[0067] The information processing device 100 reclassifies 250 evaluators who answered "5-6 points" to the question about customer loyalty to company 300 and whose comments related to the reason for company 300's score include "I don't really understand it myself, so I can't recommend it to others" as "indifferent". The information processing device 100 reclassifies 250 evaluators who answered "5-6 points" to the question about customer loyalty to company 300 and whose comments related to the reason for company 300's score include "positive comments" such as "The connection is easy to make, and it feels relatively safe" as "neutral". The information processing device 100 reclassifies 250 evaluators who answered "5-6 points" to the question about customer loyalty to company 300 and whose comments related to the reason for company 300's score include "There are no particular problems" as "neutral". The information processing device 100 reclassifies 250 evaluators who answered "5 to 6 points" to a question asking about customer loyalty to company 300, and whose comments related to the reason for company 300's score include "negative" comments such as "there are no benefits for long-term users," as "detractors."

[0068] The information processing device 100 reclassifies evaluators 250 who answered a question about customer loyalty to company 300 with a score of "0 to 4" and whose comments related to the reason for company 300's score include "communication quality is average" as "neutral" comments, and also reclassifies evaluators 250 who answered a question about customer loyalty to company 300 with a score of "0 to 4" and whose comments related to the reason for company 300's score include "store staff are unfriendly" as "negative" comments, and also reclassifies them as "detractors."

[0069] In the example shown in Figure 3, the classification results obtained by the information processing device 100, which reclassifies the 250 evaluators based on the comment classification results, are as follows: The information processing device 100 reclassifies E'% of the 250 evaluators as "indifferent", A'% of the 250 evaluators as "promoters", B'% of the 250 evaluators as "neutral", and C'% of the 250 evaluators as "critics".

[0070] The information processing device 100 calculates C-NPS from the classification results obtained by reclassifying the 250 evaluators based on the classification results of the comments. C-NPS may be an evaluation index that satisfies the relationship "C-NPS = (percentage of promoters after reclassification) - (percentage of detractors after reclassification)". In the example shown in Figure 3, the information processing device 100 calculates C-NPS = A' - C'.

[0071] Here, we examine the differences between the classification results obtained by classifying 250 evaluators based on their scores in a question asking about customer loyalty to company 300 in an example shown in Figure 3, and the classification results obtained by reclassifying the 250 evaluators based on comments related to the reasons for company 300's scores. Here, we will mainly examine three aspects: the proportion of promoters, the proportion of detractors, and the inclusion of indifferent evaluators. Note that classifying 250 evaluators based on their scores in a question asking about customer loyalty to the evaluation target may be referred to as NPS classification, and the results of NPS classification may be referred to as NPS classification results. Furthermore, reclassifying 250 evaluators based on comments related to the reasons for the evaluation target's scores may be referred to as C-NPS classification, and the results of C-NPS classification may be referred to as C-NPS classification results.

[0072] The promoter rate in the NPS classification is A%. On the other hand, the promoter rate in the C-NPS classification is A'%. Therefore, the promoter rate in the C-NPS classification differs from the promoter rate in the NPS classification. This means that the C-NPS classification can appropriately reclassify 250 evaluators who could not be classified as promoters in the NPS classification, such as loyal customers who deliberately gave low scores to reflect their expectations of company 300, or introverted loyal customers, into promoters.

[0073] The percentage of detractors in the NPS classification is C+D%. On the other hand, the percentage of detractors in the C-NPS classification is C'%. Therefore, the percentage of detractors in the C-NPS classification differs from the percentage of detractors in the NPS classification. This means that the C-NPS classification can appropriately reclassify the 250 evaluators who answered a score of 5-6 to the question about customer loyalty to company 300, who were uniformly classified as detractors in the NPS classification, based on comments related to the reasons for company 300's score.

[0074] The inventors discovered that indifferent individuals are less likely to engage in either positive or negative behavior towards the product being evaluated, while also being less likely to switch from the product being evaluated to its competitors. The tendencies of indifferent individuals do not correspond to those of promoters, passives, or critics. Therefore, the C-NPS classification can reclassify the 250 evaluators into indifferent individuals, a category not present in the 250 evaluator categories of the NPS classification. By introducing a new category of indifferent individuals, which was not present in the 250 evaluator categories of the NPS classification, the C-NPS classification results can generate useful data for determining the cyclical policies of the PDCA cycle, in addition to calculating C-NPS, which can quantify customer loyalty with high reliability. As a result, the system 10 according to the embodiment shown in Figure 3 can contribute even more to the efficient and continuous development of companies.

[0075] Figure 4 is an explanatory diagram illustrating an example of comparing evaluation targets based on evaluation indicators. Here, we will mainly explain an example of competitive comparison of evaluation targets based on C-NPS. The comparison targets for the competitive comparison will be telecommunications carriers A, B, and C.

[0076] The information processing device 100 calculates the C-NPS for each of companies A, B, and C by performing NPS classification and C-NPS classification for each of these companies. For example, in order to calculate the C-NPS for each of companies A, B, and C, the information processing device 100 identifies the reasons for the scores based on comments related to the reasons for the scores given by 250 evaluators in response to a question asking about customer loyalty to telecommunications carriers.

[0077] The reasons for the score include, for example, "pricing," "customer touchpoints," "network," "economic sphere," "brand," and "other." "Price" refers to matters related to the price of the telecommunications carrier's products. "Customer touchpoints" refers to matters related to the touchpoints or interactions between the customer and the telecommunications carrier. Examples of touchpoints or interactions between the customer and the telecommunications carrier include customer service by the telecommunications carrier's store crew and applications used by customers when confirming contract details. "Network" refers to matters related to the telecommunications carrier's communication network. "Economic sphere" refers to matters related to electronic payment services, etc., associated with the telecommunications carrier's communication services. "Brand" refers to matters related to the telecommunications carrier's brand image. "Other" refers to matters that do not fall under any of "pricing," "customer touchpoints," "network," "economic sphere," or "brand."

[0078] For example, the information processing device 100 calculates the C-NPS for each reason for a score by performing a C-NPS classification for each of the identified reasons for the score for each company A, B, and C, and then calculates the C-NPS for each of the companies A, B, and C by summing the C-NPS for each reason for the score. In the example shown in Figure 4, the information processing device 100 calculates the C-NPS for each of the companies A, B, and C as follows.

[0079] The information processing device 100 calculates the C-NPS for Company A's "Pricing" as "-a1", the C-NPS for Company A's "Customer Touchpoints" as "+a2", the C-NPS for Company A's "Network" as "+a3", the C-NPS for Company A's "Economic Zone" as "+a4", the C-NPS for Company A's "Brand" as "+a5", and the C-NPS for Company A's "Other" as "+a6". Then, the information processing device 100 calculates the C-NPS for "Company A" as "-a1+a2+a3+a4+a5+a6=AA".

[0080] The information processing device 100 calculates the C-NPS for Company B's "Pricing" as "+b1", the C-NPS for Company B's "Customer Touchpoints" as "+b2", the C-NPS for Company B's "Network" as "-b3", the C-NPS for Company B's "Economic Zone" as "+b4", the C-NPS for Company B's "Brand" as "+b5", and the C-NPS for Company B's "Other" as "0". Then, the information processing device 100 calculates the C-NPS for "Company B" as "+b1+b2-b3+b4+b5+0=BB".

[0081] The information processing device 100 calculates the C-NPS for Company C's "Pricing" as "+c1", the C-NPS for Company C's "Customer Touchpoints" as "-c2", the C-NPS for Company C's "Network" as "-c3", the C-NPS for Company C's "Economic Zone" as "0", the C-NPS for Company C's "Brand" as "+c5", and the C-NPS for Company C's "Other" as "+c6". Then, the information processing device 100 calculates the C-NPS for "Company C" as "+c1-c2-c3+0+c5+c6=CC".

[0082] Here, we will explain an example of a competitive comparison using the C-NPS of companies A, B, and C shown in Figure 4, with company A as the comparison standard. Among the C-NPS for each reason for the score, company A's "pricing," calculated as "-a1," is particularly low compared to company B's "pricing" C-NPS, calculated as "+b1," and company C's "pricing" C-NPS, calculated as "+c1." On the other hand, among the C-NPS for each reason for the score, company A's "network" C-NPS, calculated as "+a3," is particularly high compared to company B's "network" C-NPS, calculated as "-b3," and company C's "network" C-NPS, calculated as "-c3." Therefore, as a result of the competitive comparison, it can be intuitively understood that "pricing" is company A's weak point and "network" is company A's strong point when competing in the market with companies B and C. Therefore, Company A can gain an advantage over Companies B and C in market competition by developing a new business strategy that leverages its strengths while overcoming its weaknesses, such as reviewing its pricing plans while maintaining the communication quality of its communication network. Furthermore, after developing the new business strategy, Company A can intuitively grasp the improvement effect of the new business strategy by conducting a competitive comparison again using the C-NPS for each company's score, based on the reasons for the scores of Companies A, B, and C. Thus, by calculating the C-NPS of the target of evaluation by classifying the scores of 250 evaluators' responses to a question asking about customer loyalty to the target of evaluation, the system 10 according to the embodiment shown in Figure 4 can introduce C-NPS, which, compared to NPS, makes it easier to intuitively grasp the improvement effect of improvement measures based on evaluation indicators, or the improvement effect of improvement measures based on evaluation indicators.

[0083] Figure 5 provides a schematic overview of an example questionnaire. Figure 5 shows an example questionnaire used to calculate the C-NPS of telecommunications carriers.

[0084] The questionnaire includes questions that require respondents to rate the company. In the example questionnaire shown in Figure 5, question (Q1) "Imagine you have been asked for advice about a mobile phone company by a family member or friend. How likely are you to recommend Company A? Please answer on a scale of 0 to 10. 10 is the highest recommendation, and 0 is the lowest recommendation." is a question that requires respondents to rate the company.

[0085] The questionnaire may include questions that require respondents to provide comments explaining the reasons for their assigned scores. In the example questionnaire shown in Figure 5, question (Q2), "Please provide details on the reasons for your score in Q1. If you have a specific anecdote, please also include it," is a question that requires respondents to provide comments explaining the reasons for their assigned scores.

[0086] The questionnaire may include questions that ask respondents to provide reasons for their chosen score, for example, by selecting from a list of options. In the example questionnaire shown in Figure 5, question (Q3) "Please select from the following options the reason you gave for your score in Q1 (multiple selections allowed)" is a question that asks respondents to provide reasons for their chosen score. In this case, the 250 evaluators may select from the following options the reason for their chosen score: "Price / Benefits and drawbacks for long-term users / Points and payment services / Discount campaigns / Campaigns for visitors (distribution of goods, etc.) / Gift campaigns / Waiting time in stores / Explanations and suggestions from staff / General customer service / Malfunctions and repair services / In-store experience / Call center / Types and assortment of devices / Price of devices / Initial setup and usage of devices / Network (radio waves, communication speed, etc.) / Wi-Fi (registered trademark) spots / Content services / Advertising / Official website / Comparison with other companies / Differences / Company image / Other / Something like that"

[0087] Figure 6 schematically illustrates an example of a prompt. Figure 6 shows an example of a prompt for classifying comments by labeling comments related to the reasons for the scores given by 250 evaluators in response to a question about customer loyalty to telecommunications carriers.

[0088] A prompt includes, for example, an "instruction sheet" for giving commands to a generative AI. In the example prompt shown in Figure 6, "You are a comment analysis expert. Please label the comments in the input text according to the following conditions." is the instruction sheet for giving commands to the generative AI.

[0089] The prompts include, for example, "labeling conditions" generated by the AI ​​for comments related to the reasons for the scores of the 250 evaluators' responses. In the example prompts shown in Figure 6, the options include: 'Pr1: Negative comments regarding the company's "price (service fees and device prices)" and "price services (plans, courses, and optional services)" (expensive / overpriced / not cheap / small discounts / few plan options / no suitable plan / complex plans / no family discount / no internet bundle discount, etc.),', 'Pr3: Positive comments regarding the company's "price (service fees and device prices)" and "price services (plans, courses, and optional services)" (cheap / inexpensive / large discounts / many plan options / suitable plan / easy-to-understand plan / family discount available / internet bundle discount available / good deal for switching carriers / device price is 1 yen, etc.),', 'Pr2: Comments that include both positive and negative or are neutral regarding the company's "price (service fees and device prices)" and "price services (plans, courses, and optional services)," and 'Cs1: Negative comments regarding the company's "customer service (shops / stores or call centers / telephone support)" (poor service / time-consuming / cannot be reached by phone, etc.),' "Cs3: Positive comments regarding the company's 'customer service (shops / stores or call centers / telephone support)'", "Cs2: Comments regarding the company's 'customer service (shops / stores or call centers / telephone support)' that include both positive and negative comments or are neutral", "Nw1: Negative comments regarding the company's 'communication environment (communication quality and coverage area)' (communication doesn't connect / disconnects / unusable / limited / out of range, etc.)", "Nw3: Positive comments regarding the company's 'communication environment (communication quality and coverage area)'", "Nw2: "Positive and negative comments or neutral comments regarding the company's 'communication environment (communication quality and coverage area)', 'Ec1: Negative comments regarding the company's 'economic sphere (point rewards, QR code payment and internet shopping, credit card benefits, benefits for long-term use)', 'Ec3: Positive comments regarding the company's 'economic sphere (point rewards, QR code payment and internet shopping, credit card benefits, benefits for long-term use)', 'Ec2: Positive comments regarding the company's 'economic sphere (point rewards,'Positive and negative comments or neutral comments regarding QR code payments, internet shopping, credit card benefits, and long-term usage benefits,', 'Br1: Negative comments regarding the company's "brand image" (bad company image / not trustworthy / dishonest / arrogant business practices, etc.), 'Br3: Positive comments regarding the company's "brand image" (trustworthy / because it's a large company / because it's a major player / because we have an attachment to it / good image / safe), 'Br2: Positive and negative comments or neutral comments regarding the company's "brand image," 'Ot1: Negative comments regarding aspects other than the company's pricing, pricing services, customer service, communication environment, economic sphere, and brand image (not specific comments but negative, etc.), 'Ot3: Positive comments regarding aspects other than the company's pricing, pricing services, customer service, communication environment, economic sphere, and brand image (good / good, OK, etc., not specific comments but positive, etc.)' The following are the conditions for label assignment by the generating AI: ',

[0090] A prompt includes, for example, an "input sentence" to which a label is assigned by a generative AI. In the example prompt shown in Figure 6, the comments related to the reasons for the scores given by 250 evaluators to a question about customer loyalty to telecommunications carriers are the input sentences to which a label is assigned by a generative AI.

[0091] Figure 7 schematically shows an example of labels assigned to comments. Figure 7 shows an example of labels when the generating AI, following the prompts shown in Figure 6, assigns labels to comments related to the reasons for the scores given by 250 evaluators to a question asking about customer loyalty to telecommunications carriers. The categories of comments to be labeled are "positive" comments, "neutral" comments, "negative" comments, and "indifferent" comments.

[0092] The label "Pr1" is assigned to comments whose reason is "price / plan" and whose comment category is "negative comment". Examples of comments assigned the label "Pr1" include content that is "negative" regarding "price amount (service fee or device price)" or "price service (plan, course, optional service)". The label "Pr2" is assigned to comments whose reason is "price / plan" and whose comment category is "neutral comment". Examples of comments assigned the label "Pr2" include content that is "mixed positive / negative or neutral" regarding "price amount (service fee or device price)" or "price service (plan, course, optional service)". Mixed positive / negative can mean including both positive and negative content. The label "Pr3" is assigned to comments whose reason is "price / plan" and whose comment category is "positive comment". Comments that receive the label "Pr3" include comments that are positive regarding "price (service fees and device costs)" or "price services (plans, courses, and optional services)."

[0093] The label "Cs1" is assigned to comments where the reason is "customer touchpoint (store / CS / Web)" and the comment category is "negative." An example of a comment assigned the label "Cs1" is one that includes "negative content regarding customer service (shop / store or call center / telephone service)." The label "Cs2" is assigned to comments where the reason is "customer touchpoint (store / CS / Web)" and the comment category is "neutral." An example of a comment assigned the label "Cs2" is one that includes "mixed positive / negative or neutral content regarding customer service (shop / store or call center / telephone service)." The label "Cs3" is assigned to comments where the reason is "customer touchpoint (store / CS / Web)" and the comment category is "positive." An example of a comment assigned the label "Cs3" is one that includes "positive content regarding customer service (shop / store or call center / telephone service)."

[0094] The label "Nw1" is assigned to comments whose reason is "Network" and whose comment category is "Negative." An example of a comment assigned the label "Nw1" would be one that contains negative content regarding "communication environment (communication quality and coverage area)." The label "Nw2" is assigned to comments whose reason is "Network" and whose comment category is "Neutral." An example of a comment assigned the label "Nw2" would be one that contains mixed positive / negative or neutral content regarding "communication environment (communication quality and coverage area)." The label "Nw3" is assigned to comments whose reason is "Network" and whose comment category is "Positive." An example of a comment assigned the label "Nw3" would be one that contains positive content regarding "communication environment (communication quality and coverage area)."

[0095] The label "Ec1" is assigned to comments whose reason is "economic sphere" and whose comment category is "negative comment". An example of a comment assigned the label "Ec1" is one that contains negative content regarding the "economic sphere (point rewards, QR code payments and online shopping, credit card benefits, benefits for long-term use)". The label "Ec2" is assigned to comments whose reason is "economic sphere" and whose comment category is "neutral comment". An example of a comment assigned the label "Ec2" is one that contains mixed positive / negative or neutral content regarding the "economic sphere (point rewards, QR code payments and online shopping, credit card benefits, benefits for long-term use)". The label "Ec3" is assigned to comments whose reason is "economic sphere" and whose comment category is "positive comment". Comments that receive the label "Ec3" include content that is "positive towards the 'economic ecosystem' (point rewards, QR code payments and online shopping, credit card benefits, and benefits for long-term use)."

[0096] The label "Br1" is assigned to comments whose reason is "brand" and whose comment category is "negative." Examples of comments assigned the label "Br1" include content that is "negative towards the brand image." The label "Br2" is assigned to comments whose reason is "brand" and whose comment category is "neutral." Examples of comments assigned the label "Br2" include content that is "mixed positive / negative or neutral towards the brand image." The label "Br3" is assigned to comments whose reason is "brand" and whose comment category is "positive." Examples of comments assigned the label "Br3" include content that is "positive towards the brand image."

[0097] The label "Ot1" is assigned to comments where the reason is "Other" and the comment category is "Negative Comment". An example of a comment assigned the label "Ot1" is one that includes content that is "Negative towards anything other than the above ("Pricing / Plans", "Customer Touchpoints (Stores / CS / Web)", "Network", "Economy", and "Brand"). The label "Ot2" is assigned to comments where the reason is "Other" and the comment category is "Neutral Comment". An example of a comment assigned the label "Ot2" is one that includes content that is "Positive / Negative or Neutral towards anything other than the above ("Pricing / Plans", "Customer Touchpoints (Stores / CS / Web)", "Network", "Economy", and "Brand"). The label "Ot3" is assigned to comments where the reason is "Other" and the comment category is "Positive Comment". Comments that receive the label "Ot3" include comments that are positive about anything other than the above ("Pricing / Plans", "Customer Touchpoints (Stores / CS / Web)", "Network", "Ecosystem", and "Brand").

[0098] The label "Ot4" is assigned to comments where the reason is "none" and the comment category is "indifferent". Examples of comments assigned the label "Ot4" include comments similar to "nothing in particular" (e.g., no episode / no particular reason). The label "Ot5" is assigned to comments where the reason is "none" and the comment category is "indifferent". Examples of comments assigned the label "Ot5" include comments similar to "I don't know" (e.g., I don't really understand / can't judge / just a feeling / can't think of anything / just started using it). The label "Ot6" is assigned to comments where the reason is "none" and the comment category is "indifferent". Examples of comments assigned the label "Ot6" include comments similar to "I've been using it for a long time" (e.g., I've only ever contracted with our company / I don't know about other companies / I've never used other companies). The label "Ot7" is assigned to comments with no stated reason and categorized as "Indifferent" comments. Examples of comments assigned the label "Ot7" include comments similar to "Not Recommended / Cannot Recommend" (e.g., I don't recommend it to others / To each their own / Personal freedom / Not knowledgeable enough to recommend it / Others use other companies / No one to recommend it to). The label "Ot8" is assigned to comments with no stated reason and categorized as "Indifferent" comments. Examples of comments assigned the label "Ot8" include comments similar to "Not Giving a Good Score" (e.g., I don't give perfect scores / Looking forward to future improvements / Being critical).

[0099] Figure 8 schematically shows an example of the churn rate for 250 evaluators. Figure 8 shows an example of the churn rate for each combination of evaluator category and category of comments related to the reasons for the evaluators' scores in response to a question about customer loyalty to company 300, for the number of evaluators who terminated their contract with company 300 within one year of evaluating company 300.

[0100] The cancellation rate after one year for 250 evaluators whose evaluator category is "recommender" and whose comment category is "positive" comment is "CR r3 %". The cancellation rate after one year for 250 evaluators whose evaluator category is "recommender" and whose comment category is "neutral" comment is "CR r2 %". The cancellation rate after one year for 250 evaluators whose evaluator category is "recommender" and whose comment category is "negative" comment is "CR r1 %". The cancellation rate after one year for 250 evaluators whose evaluator category is "recommender" and whose comment category is "indifferent" comment is "CR r4 %". Here, CR r1 %, CR r2 %, CR r3 % and CR r4 % shall satisfy the relationship of CR r4 % ≒ CR r3 % < CR r2 % < CR r1 %.

[0101] The cancellation rate after one year for 250 evaluators whose evaluator category is "neutral" and whose comment category is "positive" comment is "CR n3 %". The cancellation rate after one year for 250 evaluators whose evaluator category is "neutral" and whose comment category is "neutral" comment is "CR n2 %". The cancellation rate after one year for 250 evaluators whose evaluator category is "neutral" and whose comment category is "negative" comment is "CR n1 %". The cancellation rate after one year for 250 evaluators whose evaluator category is "neutral" and whose comment category is "indifferent" comment is "CR n4 %". Here, CR n1 %, CR n2 %, CR n3 % and CR n4 % shall satisfy the relationship of CR n4 % ≒ CR n3 % < CR n2 % < CR n1 %.

[0102] The churn rate after one year for 250 evaluators whose evaluator category is "weak critic" and whose comment category is "positive" was "CR wc3 The churn rate after one year for 250 evaluators whose evaluator category is "weak critic" and whose comment category is "neutral" is "CR wc2 The churn rate after one year for 250 evaluators whose evaluator category is "weak critic" and whose comment category is "negative" is "CR wc1 The churn rate after one year for 250 evaluators whose evaluator category is "weak critic" and whose comment category is "indifferent" is "CR wc4 % is the case here. wc1 %, CR wc2 %, CR wc3 % and CR wc4 % is CR wc4 %≒CR wc3 % <CR wc2 % <CR wc1 Assume that the % relationship is satisfied.

[0103] The churn rate after one year for 250 evaluators whose evaluator category is "strong critic" and whose comment category is "positive" was "CR sc3 The churn rate after one year for 250 evaluators whose evaluator category is "strong critic" and whose comment category is "neutral" is "CR sc2 The churn rate after one year for 250 evaluators whose evaluator category is "strong critic" and whose comment category is "negative" is "CR sc1 The churn rate after one year for 250 evaluators whose evaluator category is "strong critic" and whose comment category is "indifferent" is "CR sc4 % is the case here. sc1 %, CR sc2 %, CR sc3 % and CR sc4 % is CR sc4 %≒CR sc3 % <CR sc2% <CR sc1 Assume that the % relationship is satisfied.

[0104] Figure 9 is an explanatory diagram illustrating an example of how evaluation indicators are calculated. Here, we primarily explain an example where the information processing device 100 performs C-NPS classification using an example of the churn rate of 250 evaluators shown in Figure 8. Note that the evaluation target is assumed to be 300 companies.

[0105] The information processing device 100 classifies the 250 evaluators, for example, by performing NPS classification. In the example shown in Figure 9, the information processing device 100 classifies A% of the 250 evaluators as "promoters," B% of the 250 evaluators as "passives," C% of the 250 evaluators as "weak critics," and D% of the 250 evaluators as "strong critics." In this case, the information processing device 100 calculates NPS = A - (C + D).

[0106] The information processing device 100 further classifies the evaluators 250, who have been classified by NPS classification, based on comments related to the reasons for the scores of companies 300, as indicated by comment information included in the evaluation information. In one example shown in Figure 9, the information processing device 100 further classifies the evaluators 250, who have been classified by NPS classification, as follows.

[0107] The information processing device 100 classifies 250 A4% evaluators into "promoters" and "indifferent" comments, 250 A3% evaluators into "promoters" and "positive" comments, and 250 A2% evaluators into "promoters" and "neutral" comments. The relationship A2% + A3% + A4% = A% is satisfied. The information processing device 100 also classifies 250 B4% evaluators into "neutral" and "indifferent" comments, 250 B3% evaluators into "neutral" and "positive" comments, 250 B2% evaluators into "neutral" and "neutral" comments, and 250 B1% evaluators into "neutral" and "negative" comments. The relationship B1% + B2% + B3% + B4% = B% is satisfied. The information processing device 100 classifies 250 evaluators with a C4% rating as "weak critics" and "indifferent" comments, 250 evaluators with a C3% rating as "weak critics" and "positive" comments, 250 evaluators with a C2% rating as "weak critics" and "neutral" comments, and 250 evaluators with a C1% rating as "weak critics" and "negative" comments. The relationship C1% + C2% + C3% + C4% = C% is satisfied. The information processing device 100 also classifies 250 evaluators with a D4% rating as "strong critics" and "indifferent" comments, 250 evaluators with a D2% rating as "strong critics" and "neutral" comments, and 250 evaluators with a D1% rating as "strong critics" and "negative" comments. The relationship D1% + D2% + D4% = D% is satisfied.

[0108] The information processing device 100 reclassifies the evaluators 250, who have been classified by NPS classification, into one of the following categories: promoters, passives, detractors, and indifferent, based on the one-year churn rate of each evaluator 250 for each combination of evaluator 250 category and comment category. Here, the explanation continues by assuming that the information processing device 100 reclassifies the evaluators 250 based on churn rate information, shown in Figure 8, which indicates the churn rate at which evaluators 250 terminate their contracts with the company 300 within a predetermined period from the time they evaluated the company 300 being evaluated. Examples of predetermined periods include one month, three months, six months, and one year. Note that this churn rate information may be referred to as the first churn rate information.

[0109] For example, if the churn rate of the evaluator 250 to be reclassified after one year for a combination of the category and comment category of the evaluator 250 to be reclassified, as indicated by the first churn rate information, is less than or equal to the churn rate of the evaluator 250 for a combination of "promoter" and "positive" comments, as indicated by the first churn rate information, the information processing device 100 reclassifies the evaluator 250 to be reclassified as a "promoter". In an example shown in Figure 9, the information processing device 100 performs CR n3 250 evaluators who were reclassified for A3% of the combination of "promoters" and "positive" comments, and CR n3 %≦CR r3 The 250 evaluators who meet the 3% requirement for a combination of "neutral" and "positive" comments will be reclassified as "promoters."

[0110] For example, if the churn rate of the evaluator 250 to be reclassified, based on the first churn rate information, is higher than the churn rate of the evaluator 250 based on the combination of category and comment category of the evaluator 250 to be reclassified, based on the first churn rate information, and is less than or equal to the churn rate of the evaluator 250 based on the combination of "promoter" and "positive" comments, and is less than or equal to the churn rate of the evaluator 250 based on the combination of "passive" and "neutral" categories, the information processing device 100 reclassifies the evaluator 250 to be reclassified as "passive". In an example shown in Figure 9, the information processing device 100 performs CR r3 % <CR r2 %≦CR n2 250 evaluators, CR, who were reclassified for A2% of the combination of "promoters" and "neutral" comments that met the % criteria. n2 250 evaluators who were reclassified for B2% of the combination of "neutral" and "passive" comments, and CR r3 % <CR wc3 %≦CR n2 The 250 evaluators who meet the C3% reclassification criteria for the combination of "weak critics" and "positive" comments will be reclassified as "neutral."

[0111] For example, if the churn rate of the evaluators 250 to be reclassified, based on the first churn rate information, after one year is higher than the churn rate of the evaluators 250 based on the first churn rate information, based on the combination of categories and comment categories of the evaluators 250 to be reclassified, then the information processing device 100 reclassifies the evaluators 250 to be reclassified as "critics". In one example shown in Figure 9, the information processing device 100 performs CR n2 % <CR n1 250 evaluators, CR, who were reclassified as B1% for combinations of "neutral" and "negative" comments that met the % criteria. n2 % <CR wc2 250 evaluators, CR, who were reclassified as C2% for combinations of "weak critics" and "neutral" comments that met the % criteria. n2 % <CR wc1250 evaluators, CR, who were reclassified as C1% for combinations of "weak critics" and "negative" comments that met the % criteria. n2 % <CR sc2 250 evaluators who were reclassified by D2% for combinations of "strong critic" and "neutral" comments that met the % criteria, and CR n2 % <CR wc1 The 250 evaluators who meet the D1% reclassification criteria for combinations of "strong critics" and "negative" comments that satisfy the % requirement will be reclassified as "critics".

[0112] Regardless of the category of the evaluators 250 to be reclassified, the information processing device 100 may classify evaluators 250 whose comments fall under the category of "indifferent" as "indifferent." In one example shown in Figure 9, the information processing device 100 reclassifies 4% of evaluators 250 to be reclassified as "indifferent" if they fall under the category of "promoter" and "indifferent" comments (A), 4% of evaluators 250 to be reclassified as "neutral" and "indifferent" comments (B), 4% of evaluators 250 to be reclassified as "weak critic" and "indifferent" comments (C), and 4% of evaluators 250 to be reclassified as "indifferent" if they fall under the category of "strong critic" and "indifferent" comments (D).

[0113] In the example shown in Figure 9, the reclassification results obtained by the information processing device 100 based on the first churn rate information for the 250 evaluators are as follows: The information processing device 100 reclassifies the 250 evaluators with A4+B4+C4+D4=E'% as "indifferent", the 250 evaluators with A3+B3=A'% as "promoters", the 250 evaluators with A2+B2+C3=B'% as "neutral", and the 250 evaluators with B1+C2+C1+D2+D1=C'% as "critics".

[0114] The information processing device 100 calculates C-NPS from the classification results obtained by reclassifying the evaluators 250 based on the first churn rate information. In the example shown in Figure 9, the information processing device 100 calculates C-NPS = A' - C', for example.

[0115] As shown in the example of the churn rate for 250 evaluators in Figure 8, the churn rate for indifferent evaluators tends to be low regardless of the category of the 250 evaluators. Therefore, C-NPS may be an evaluation index that satisfies the relationship "C-NPS = (Percentage of promoters after reclassification + Percentage of indifferent evaluators after reclassification) - (Percentage of detractors after reclassification)". Note that the percentage of indifferent evaluators is the ratio of the number of indifferent evaluators who are indifferent to the evaluation target to the total number of evaluators who evaluated the evaluation target. Therefore, in the example shown in Figure 9, the information processing device 100 may calculate C-NPS = (A' + E') - C'.

[0116] To gain a competitive advantage in the market, it is crucial for companies to not only acquire new customers but also to retain existing customers who generate a certain level of revenue. This is especially true in industries with numerous competitors or those experiencing overall market contraction, where acquiring new customers is extremely difficult; therefore, retaining existing customers is paramount. Furthermore, the cost of retaining existing customers tends to be lower than the cost of acquiring new ones. Consequently, it is desirable to develop business strategies that take into account the retention of existing customers.

[0117] In contrast, according to the system 10 of the embodiment shown in Figure 9, the information processing device 100 reclassifies the NPS-classified evaluators 250 based on the first churn rate information. The churn rate is a parameter directly related to retaining existing customers. Therefore, by reclassifying the NPS-classified evaluators 250 based not only on comments but also on the churn rate, the system 10 of the embodiment shown in Figure 9 can contribute to the introduction of C-NPS, which can generate useful data when developing business strategies considering the perspective of retaining existing customers. Furthermore, by calculating C-NPS from the classification results obtained when the information processing device 100 reclassifies the NPS-classified evaluators 250 based on comments and the churn rate, the system 10 of the embodiment shown in Figure 9 can introduce C-NPS, which can generate useful data when developing business strategies considering the perspective of retaining existing customers. As a result, the system 10 of the embodiment shown in Figure 9 can contribute even more to realizing the efficient and continuous development of companies.

[0118] Figure 10 schematically illustrates another example of the churn rate for 250 evaluators. Here, 250 evaluators are assumed to be indifferent. Figure 10 shows an example of the churn rate for evaluators 250 who terminated their contract with company 300 within one year of their evaluation of company 300, broken down by the labels assigned to comments related to the reasons for the scores given by 250 evaluators in response to a question about customer loyalty to company 300, and by the category of choices corresponding to the reasons for the scores given by 250 evaluators.

[0119] The churn rate after one year for indifferent individuals who have the label "Ot4" or "Ot5" shown in Figure 7 attached to their comments and whose category of choice is "Reasonable" is "CR ot4,5w / The churn rate after one year for indifferent customers who have the label "Ot4" or "Ot5" attached to their comment and whose option category is "No reason" is "CR ot4,5w / o The value is "%". Note that if the category of an option is "Reason Given", it means that in response to a question asking for the reason behind Company 300's score, 250 evaluators selected an option that corresponds to the reason for Company 300's score. If the category of an option is "No Reason Given", it means that 250 evaluators did not select an option that corresponds to the reason for Company 300's score.

[0120] The label "Ot6" shown in Figure 7 is attached to the comment, and the churn rate after one year for indifferent individuals whose category is "Reasonable" is "CR ot6w / The churn rate after one year for indifferent customers who have the label "Ot6" attached to their comment and whose option category is "No reason" is "CR ot6w / o It is %.

[0121] The label "Ot7" shown in Figure 7 is attached to the comment, and the churn rate after one year for indifferent individuals whose category is "Reasonable" is "CR ot7w / The churn rate after one year for indifferent customers who have the label "Ot7" attached to their comment and whose category of choice is "No reason" is "CR ot7w / o It is %.

[0122] The label "Ot8" shown in Figure 7 is attached to the comment, and the churn rate after one year for indifferent individuals whose category is "Reasonable" is "CR ot8w / The churn rate after one year for indifferent individuals who have the label "Ot8" attached to their comments and whose category of choice is "No reason" is "CR ot8w / o It is %.

[0123] Figure 11 is an explanatory diagram illustrating another example of how evaluation indicators are calculated. Here, we mainly explain an example in which the information processing device 100 performs C-NPS classification using an example of the churn rate of 250 evaluators shown in Figure 11. It is assumed that the evaluation target is 300 companies.

[0124] The information processing device 100 classifies the 250 evaluators by, for example, performing NPS classification and C-NPS classification. In one example shown in Figure 11, the information processing device 100 reclassifies E'% of the 250 evaluators as "indifferent", A'% of the 250 evaluators as "promoters", B'% of the 250 evaluators as "passives", and C'% of the 250 evaluators as "detractors".

[0125] The information processing device 100 identifies the reasons for company 300's score by, for example, assigning labels to comments related to the reasons for company 300's score, which are indicated by comment information included in the evaluation information. In one example shown in Figure 11, the information processing device 100 identifies E' x For the comments of 250 evaluators who were reclassified as % indifferent, the label "Ot4" or "Ot5" was assigned, and E' y The label "Ot6" was assigned to the comments of 250 evaluators who were reclassified as % indifferent, and E' z The label "Ot8" will be assigned to the comments of the 250 evaluators who were reclassified as % indifferent. x %+E' y %+E' z The relationship %=E'% is satisfied.

[0126] The information processing apparatus 100 further classifies the evaluators 250 reclassified as indifferent persons based on the cancellation rate of the evaluators 250 one year later for each combination of options corresponding to the reasons for the scores of the company 300 specified by, for example, attaching labels to comments and the option information included in the reason and evaluation information for the scores of the company 300. Here, the information processing apparatus 100 will continue the explanation on the assumption that it further classifies the evaluators 250 reclassified as indifferent persons based on the cancellation rate information indicating the cancellation rate at which the evaluators 250 cancel the contract with the company 300 within a predetermined period from when the evaluators 250 evaluate the company 300 which is the evaluation target, for each category of the reasons for the scores of the evaluation target specified from the comments and the options shown in FIG. 10. Note that the cancellation rate information may be referred to as second cancellation rate information.

[0127] For example, when the cancellation rate one year later of the evaluators 250 reclassified as indifferent persons for the combination of the reasons for the scores of the company 300 specified from the comments indicated by the second cancellation rate information and the options corresponding to the reasons for the scores of the company 300 is less than or equal to the cancellation rate one year later of the evaluators 250 for the combination of "recommenders" and "positive" comments indicated by the first cancellation rate information, the information processing apparatus 100 classifies the evaluators 250 reclassified as indifferent persons as "indifferent persons". In an example shown in FIG. 11, when the first cancellation rate information is the first cancellation rate information shown in FIG. 8, the cancellation rate one year later of the evaluators 250 for the combination of "recommenders" and "positive" comments is "CR r3 %", so the information processing apparatus 100 determines that CR ot4,5w / o % ≦ CR r3 % for the combination of the label "Ot4" or "Ot5" and "no reason", and E' w / o % of the evaluators 250 reclassified as indifferent persons, and CR ot6w / % ≦ CR r3 % and CR ot6w / o % ≦ CR r3 % for the label "Ot6", and E' y % of the evaluators 250 reclassified as indifferent persons are classified as "indifferent persons".

[0128] For example, when the one-year cancellation rate of the evaluator 250 reclassified as an indifferent person to the combination of options corresponding to the reason for the score of the company 300 specified from the comment indicated by the second cancellation rate information and the reason for the score of the company 300 is higher than the one-year cancellation rate of the evaluator 250 for the combination of "recommenders" and "positive" comments indicated by the first cancellation rate information, the evaluator 250 reclassified as an indifferent person is classified as a "neutral person". In an example shown in FIG. 11, the information processing apparatus 100 is CR r3 %<CR ot4,5w / % for the combination of the label "Ot4" or "Ot5" and "with reason" of E' w / % of the evaluators 250 reclassified as indifferent persons, and CR r3 %<CR ot8w / % and CR r3 %<CR ot8w / o % for the E' of the label "Ot8" that satisfies the combination of z % of the evaluators 250 reclassified as indifferent persons are classified as "neutral persons".

[0129] In an example shown in FIG. 11, the reclassification result of further classifying the evaluator 250 reclassified as an indifferent person by the information processing apparatus 100 based on the second cancellation rate information is as follows. The information processing apparatus 100 classifies the evaluator 250 of E' w / o % + E' y % = E''% as "indifferent persons", reclassifies the evaluator 250 of A'% as "recommenders", reclassifies the evaluator 250 of B'% + (E' w / % + E' z %) = B''% as "neutral persons", and reclassifies the evaluator 250 of C'% as "critics".

[0130] The information processing apparatus 100 calculates the C-NPS from the classification result of reclassifying the evaluator 250 based on the second cancellation rate information, for example. In an example shown in FIG. 11, the information processing apparatus 100 calculates, for example, C-NPS = A' - C'.

[0131] Comment-style questions, which allow respondents to answer freely, can elicit more detailed responses compared to multiple-choice questions. On the other hand, comment-style questions place a greater burden on respondents. Therefore, when 300 companies were asked about the reasons for their scores using comment-style questions, some 250 evaluators found answering these questions cumbersome and submitted the questionnaire with no response or only a vague answer. As a result, these 250 evaluators tended to be reclassified as indifferent according to the C-NPS classification. However, as mentioned above, the tendency of indifferent evaluators does not coincide with the tendency of promoters, passives, or critics. Therefore, it is desirable to be able to determine whether the 250 evaluators reclassified as indifferent are truly indifferent, or simply found answering the questionnaire cumbersome and are actually promoters, passives, or critics.

[0132] In contrast, according to the system 10 of the embodiment shown in Figure 11, the information processing device 100 acquires evaluation information including choice information indicating the options corresponding to the reasons for the company 300's score, and further classifies the evaluators 250 who have been reclassified as indifferent based on the second churn rate information. By asking evaluators 250 for the reasons for the company 300's score using a choice format question, which places less burden on respondents compared to a comment format question, and further classifying the evaluators 250 who have been reclassified as indifferent based on the choice information and the second churn rate information, the system 10 of the embodiment shown in Figure 11 can more appropriately determine whether the evaluators 250 are truly indifferent or not. As a result, the system 10 of the embodiment shown in Figure 11 can introduce C-NPS that can generate more useful data when developing business strategies, and can contribute even more to the efficient and continuous development of companies.

[0133] Figure 12 schematically shows another example of system 10. Here, we will mainly explain the differences from system 10 shown in Figure 1.

[0134] In Figure 12, the evaluation targets are multiple stores 350 belonging to company 300. The stores 350 may be branches or offices of company 300.

[0135] For example, if a store 350 is visited by an evaluator 250, the information processing device 100 evaluates the store 350 visited by the evaluator 250 by conducting a questionnaire survey of the store 350 after the evaluator 250's visit. For example, if a contract between the evaluator 250 and a company 300 is concluded at the store 350, the information processing device 100 evaluates the store 350 where the contract between the evaluator 250 and the company 300 has been concluded by conducting a questionnaire survey of the store 350 periodically or irregularly for the evaluator 250.

[0136] Figure 13 is an explanatory diagram illustrating another example of how to calculate the evaluation indicators. Here, we will mainly explain the differences from the calculation method of the evaluation indicators described above. Note that the evaluation targets are assumed to be 300 companies and 350 stores.

[0137] The information processing device 100 classifies the 250 evaluators, for example, by performing NPS classification. In the example shown in Figure 13, the information processing device 100 classifies A% of the 250 evaluators as "promoters," B% of the 250 evaluators as "passives," and C% of the 250 evaluators as "detractors." In this case, the information processing device 100 calculates NPS = AC.

[0138] The information processing device 100 determines, for example, whether the reason for the score of store 350 is attributable to store 350 or at least one of its crew members, based on the comments in the responses to the comment-format questions asking for the reason for the score of store 350, which are indicated by the comment information included in the evaluation information. For example, "The explanation was polite and easy to understand," "The store was thoroughly cleaned," and "The telephone service was unpleasant" are examples of reasons that the reason for the score is attributable to at least one of store 350 or its crew members. On the other hand, for example, "There are no stores nearby," "I am satisfied with the quality of the products," "The prices are too high," "I don't know anyone who would recommend it," and no response are examples of reasons that the reason for the score is not attributable to either store 350 or its crew members.

[0139] For example, the information processing device 100 extracts data from evaluators 250 who determined that the reason for the score was attributable to either store 350 or at least one of the crew members of store 350, and uses this data to calculate C-NPS. On the other hand, the information processing device 100 does not extract data from evaluators 250 who determined that the reason for the score was not attributable to either store 350 or the crew members of store 350, and uses this data to calculate C-NPS. In this case, the information processing device 100 may remove the data of those evaluators 250.

[0140] In one example shown in Figure 13, the information processing device 100 is A w / Data on the percentage of "recommenders", B w / % of the data for "neutral" and C w / The data of % "critics" is extracted and used as data for calculating C-NPS. On the other hand, in the example shown in Figure 13, the information processing device 100, A w / o Data on the percentage of "recommenders", B w / o % of the data for "neutral" and C w / o Remove data from the % "critics".

[0141] In the example shown in Figure 13, after the information processing device 100 performs data extraction, A'% of 250 evaluators are "promoters," B'% of 250 evaluators are "passives," and C'% of 250 evaluators are "detractors." In this case, "(promoter percentage) - (detractor percentage)" after the information processing device 100 performs data extraction is A' - C'. "(promoter percentage) - (detractor percentage)" after the data extraction is performed may be an example of C-NPS.

[0142] For example, after performing data extraction processing, the information processing device 100 performs C-NPS classification to reclassify the 250 evaluators who have been classified as either promoters, passives, or detractors into either promoters, passives, or detractors. For example, after removing data to be removed, the information processing device 100 performs C-NPS classification for each reason for the score of the 350 stores to reclassify the 250 evaluators who have been classified as either promoters, passives, or detractors into either promoters, passives, or detractors.

[0143] In the example shown in Figure 13, the information processing device 100 reclassifies 250 evaluators at A''% as "promoters," 250 evaluators at B''% as "neutralists," and 250 evaluators at C''% as "detractors." In this case, the information processing device 100 calculates C-NPS = A''-C''.

[0144] When the evaluation target is a part of a company, such as a company's stores, the reason for the evaluation score is not necessarily attributable to the evaluation target. For example, when calculating evaluation indicators for multiple stores in order to compare them within a single company, if the data of evaluators whose scores are not directly attributable to the store is used in calculating the evaluation indicators, it becomes impossible to achieve an appropriate comparison between the multiple stores using the evaluation indicators for each store. Therefore, when the evaluation target is a part of a company, it is desirable to prevent the use of data of evaluators whose scores are not directly attributable to the evaluation target in calculating evaluation indicators.

[0145] In contrast, according to the system 10 of the embodiment shown in Figure 13, the information processing device 100 determines whether the reason for the score of store 350 is attributable to store 350 or at least one of the store's crew, based on comments related to the reason for the score of store 350, which are indicated by comment information included in the evaluation information. The information processing device 100 then extracts data from evaluators 250 who determined that the reason for the score is attributable to at least one of store 350 or the store's crew, and uses the extracted data to calculate the evaluation index. As a result, the system 10 of the embodiment shown in Figure 13 can prevent the use of data from evaluators whose reasons for the score are not directly attributable to the evaluation target when the evaluation target is a part of a company. Consequently, the system 10 of the embodiment shown in Figure 13 can achieve appropriate comparisons between multiple stores using the evaluation index of each store.

[0146] Figure 14 schematically shows an example of the functional configuration of the information processing device 100. The information processing device 100 comprises an information storage unit 102, an acquisition unit 104, a classification unit 106, a calculation unit 108, a specific unit 110, a determination unit 112, a learning data storage unit 114, a model generation unit 116, a model storage unit 118, and an output unit 120. However, it is not necessarily required that the information processing device 100 comprises all of these components.

[0147] The information storage unit 102 stores various types of information. For example, the information storage unit 102 stores first churn rate information. For example, the information storage unit 102 stores second churn rate information.

[0148] The churn rates included in the first and second churn rate information may be determined based on the results of past surveys. The churn rates included in the first and second churn rate information may be updated each time churn rate data is accumulated through surveys.

[0149] The acquisition unit 104 acquires various types of information. The acquisition unit 104 acquires various types of information, for example, by receiving various types of information via the network 20. The acquisition unit 104 may also acquire various types of information when the input unit of the information processing device 100 accepts input of various types of information. The acquisition unit 104 may store the acquired various types of information in the information storage unit 102.

[0150] The acquisition unit 104 may acquire various information from, for example, a communication terminal 200. The acquisition unit 104 may acquire various information from, for example, a data collection device 400. The acquisition unit 104 may also acquire various information from any other device.

[0151] The acquisition unit 104 acquires, for example, evaluation information. The acquisition unit 104 also acquires, for example, prompts for classifying comments related to the reasons for the scores of the evaluated items, as indicated by the comment information included in the evaluation information.

[0152] The classification unit 106 classifies the evaluators 250 who evaluated the evaluation target. The classification unit 106 classifies the evaluators 250 based, for example, on various information stored in the information storage unit 102.

[0153] The classification unit 106 classifies the evaluators 250 based on, for example, evaluation information. The classification unit 106 classifies the evaluators 250 based on, for example, score information included in the evaluation information. The classification unit 106 classifies the evaluators 250 by, for example, performing NPS classification.

[0154] For example, the classification unit 106 classifies the evaluator 250 as a recommender of the evaluation target if the score of the evaluation target indicated by the score information is higher than a predetermined first score threshold. The classification unit 106 classifies the evaluator 250 as a neutral party of the evaluation target if the score of the evaluation target is lower than the first score threshold and higher than a predetermined second score threshold that is lower than the first score threshold. The classification unit 106 classifies the evaluator 250 as a critic of the evaluation target if the score of the evaluation target is lower than the second score threshold.

[0155] The classification unit 106 may further classify the evaluators 250 who have been classified as critics of the subject being evaluated. For example, the classification unit 106 classifies evaluators 250 as weak critics of the subject being evaluated if their score is lower than the second score threshold and higher than a predetermined third score threshold that is lower than the second score threshold. On the other hand, the classification unit 106 classifies evaluators 250 as strong critics of the subject being evaluated if their score is lower than the third score threshold.

[0156] The classification unit 106 reclassifies the evaluators 250, who were previously classified based on score information, based on, for example, comment information included in the evaluation information. The classification unit 106 reclassifies the evaluators 250, who were previously classified by the scores of the evaluation targets indicated by score information, based on the classification results obtained by classifying the comments indicated by the comment information according to predetermined classification criteria. The classification unit 106 reclassifies the evaluators 250, who were previously classified by NPS classification, by, for example, performing C-NPS classification.

[0157] The classification unit 106 classifies the comments indicated by the comment information into one of the following categories: positive comments, neutral comments, negative comments, and indifferent comments. The classification unit 106 classifies the comments by, for example, performing analysis processing on the comments. The classification criteria used to classify a comment into one of the following categories is just one example of the classification criteria for that comment. The comments may also be classified using classification criteria different from those used to classify them into one of the following categories.

[0158] For example, the classification unit 106 classifies a comment as a positive comment if it contains positive content regarding the subject being evaluated. For example, the classification unit 106 classifies a comment as a neutral comment if it contains neutral content regarding the subject being evaluated. For example, the classification unit 106 classifies a comment as a negative comment if it contains negative content regarding the subject being evaluated. For example, the classification unit 106 classifies a comment as an indifferent comment if it contains content that is indifferent to the subject being evaluated, or if it does not contain any positive, neutral, or negative content regarding the subject being evaluated.

[0159] For example, if the classification unit 106 contains both positive and negative content regarding the subject being evaluated, it classifies the comment as a neutral comment. The classification unit 106 may also classify the comment as either a positive comment or a negative comment if it contains both positive and negative content regarding the subject being evaluated.

[0160] For example, the classification unit 106 classifies a comment as a positive comment if the amount of positive content in the comment is greater than the amount of negative content in the comment. On the other hand, the classification unit 106 classifies a comment as a negative comment if the amount of negative content in the comment is greater than the amount of positive content in the comment.

[0161] For example, the classification unit 106 classifies a comment as a positive comment if the positive content contained in the comment is stronger than the negative content contained in the comment. On the other hand, the classification unit 106 classifies a comment as a negative comment if the negative content contained in the comment is stronger than the positive content contained in the comment.

[0162] The classification unit 106, for example, inputs a prompt acquired by the acquisition unit 104 to the generation AI, and acquires a classification result from the generation AI that classifies the comment based on the prompt, thereby classifying the comment into one of the following: positive comment, neutral comment, negative comment, or indifferent comment. The generation AI classifies the comment by, for example, assigning a label to the comment that indicates it is a positive comment, a neutral comment, a negative comment, or an indifferent comment.

[0163] "Pr3", "Cs3", "Nw3", "Ec3", "Br3", and "Ot3" shown in Figure 7 are examples of positive labels. "Pr2", "Cs2", "Nw2", "Ec2", "Br2", and "Ot2" shown in Figure 7 are examples of neutral labels. "Pr1", "Cs1", "Nw1", "Ec1", "Br1", and "Ot1" shown in Figure 7 are examples of negative labels. "Ot4", "Ot5", "Ot6", "Ot7", and "Ot8" shown in Figure 7 are examples of indifferent labels.

[0164] The classification unit 106 obtains the classification result of the comment by, for example, inputting a prompt to the generation AI installed in the information processing device 100. The classification unit 106 also obtains the classification result of the comment by sending a prompt to an external device via the network 20 and inputting the prompt to the generation AI installed in the external device.

[0165] The classification unit 106, for example, classifies the comment into one of the following categories: positive comment, neutral comment, negative comment, or indifferent comment. Based on this classification result, it reclassifies the evaluators 250, who were previously classified as either promoters of the evaluation, neutrals of the evaluation, or critics of the evaluation, into either promoters of the evaluation, neutrals of the evaluation, critics of the evaluation, or indifferent individuals who are indifferent to the evaluation. The classification unit 106 reclassifies the evaluators 250 for each combination of the category of the evaluators 250 classified based on score information and the category of the comments classified based on comment information.

[0166] For example, the classification unit 106 reclassifies 250 evaluators of the combination of promoters and positive comments of the product being evaluated, 250 evaluators of the combination of promoters and neutral comments of the product being evaluated, and 250 evaluators of the combination of neutrals and positive comments of the product being evaluated into promoters of the product being evaluated. For example, the classification unit 106 reclassifies 250 evaluators of the combination of promoters and negative comments of the product being evaluated, 250 evaluators of the combination of neutrals and neutral comments of the product being evaluated, and 250 evaluators of the combination of weak critics and positive comments of the product being evaluated into neutrals of the product being evaluated.

[0167] For example, the classification unit 106 reclassifies 250 evaluators of the evaluation target, including those with a combination of neutral and negative comments, those with a combination of weak critics and neutral comments, those with a combination of weak critics and negative comments, those with a combination of strong critics and positive comments, those with a combination of strong critics and neutral comments, and those with a combination of strong critics and negative comments, into critics of the evaluation target. For example, the classification unit 106 reclassifies 250 evaluators of the evaluation target, including those with a combination of recommenders and indifferent comments, those with a combination of neutral and indifferent comments, those with a combination of weak critics and indifferent comments, and those with a combination of strong critics and indifferent comments, into indifferent individuals.

[0168] The classification unit 106 further reclassifies the evaluators 250 based on the first churn rate information stored in the information storage unit 102. For example, the classification unit 106 further reclassifies the evaluators 250 based on the first churn rate information for each combination of the category of evaluators 250 classified based on score information and the category of comments classified based on comment information.

[0169] For example, the classification unit 106 reclassifies evaluator 250 as a recommender if the churn rate of evaluator 250 within a predetermined period for a combination of evaluator category and comment category indicated by the first churn rate information is less than or equal to the churn rate of evaluator 250 within the same period for a combination of recommender and positive comment indicated by the first churn rate information. For example, the classification unit 106 reclassifies evaluator 250 as a neutral if the churn rate of evaluator 250 within a given period for a combination of evaluator category and comment category is higher than the churn rate of evaluator 250 within the same period for a combination of recommender and positive comment, and is less than or equal to the churn rate of evaluator 250 within the same period for a combination of neutral and neutral categories indicated by the first churn rate information. For example, the classification unit 106 reclassifies evaluator 250 as a critic if the churn rate of evaluator 250 during the period for a combination of evaluator 250's category and comment category is higher than the churn rate of evaluator 250 during the period for a combination of neutral and neutral comments. For example, regardless of the evaluator 250's category, the classification unit 106 reclassifies evaluator 250 whose comment category is indifferent as indifferent.

[0170] For example, the classification unit 106 reclassifies evaluator 250 as a recommender if the churn rate of evaluator 250 within the given period for a given combination of evaluator 250's category and comment category is lower than a predetermined first churn rate threshold. For example, the classification unit 106 reclassifies evaluator 250 as a neutral if the churn rate of evaluator 250 within the given period for a given combination of evaluator 250's category and comment category is higher than the first churn rate threshold and lower than a predetermined second churn rate threshold that is higher than the first churn rate threshold. For example, the classification unit 106 reclassifies evaluator 250 as a critic if the churn rate of evaluator 250 within the given period for a given combination of evaluator 250's category and comment category is higher than the second churn rate threshold.

[0171] The calculation unit 108 calculates evaluation indicators. The calculation unit 108 calculates evaluation indicators based on the classification results obtained by the classification unit 106, which has classified the 250 evaluators. The calculation unit 108 calculates evaluation indicators based on the classification results obtained by the classification unit 106, which has classified the comments of the 250 evaluators.

[0172] The calculation unit 108 calculates evaluation indicators based on, for example, the NPS classification results obtained by the classification unit 106. The calculation unit 108 also calculates evaluation indicators based on, for example, the C-NPS classification results obtained by the classification unit 106.

[0173] The calculation unit 108 calculates, for example, the difference between the promoter ratio, which is the ratio of the 250 evaluators classified as promoters of the evaluation target by the classification unit 106 to the total number of evaluators who evaluated the evaluation target, and the detractor ratio, which is the ratio of the 250 evaluators classified as detractors of the evaluation target by the classification unit 106 to the total number of evaluators who evaluated the evaluation target. The calculation unit 108 also calculates, for example, the NPS as an evaluation indicator.

[0174] The calculation unit 108 calculates, for example, the difference between the promoter ratio, which is the ratio of the 250 evaluators who were reclassified by the classification unit 106 into promoters of the evaluation target to the total number of evaluators who evaluated the evaluation target, and the detractor ratio, which is the ratio of the 250 evaluators who were reclassified by the classification unit 106 into detractors of the evaluation target to the total number of evaluators who evaluated the evaluation target. The calculation unit 108 calculates, for example, C-NPS as an evaluation indicator.

[0175] The identification unit 110 identifies the reason for the score of the evaluation target, which is indicated by the score information included in the evaluation information. The identification unit 110 identifies the reason for the score, for example, based on various information stored in the information storage unit 102.

[0176] The identification unit 110 identifies the reason for the score based on comments related to the reason for the score, indicated by comment information included in the evaluation information. The identification unit 110 identifies the reason for the score by, for example, performing analysis processing on the comment. The identification unit 110 identifies the reason for the score by, for example, assigning a label to the comment using a generation AI. The identification unit 110 may identify the reason for the score by inputting a prompt acquired by the acquisition unit 104 to the generation AI, and acquiring the comment with a label assigned based on the prompt from the generation AI, in the same manner as the classification unit 106. The identification unit 110 may identify the reason for the score based on the option that corresponds to the reason for the score, indicated by the option information included in the evaluation information.

[0177] The calculation unit 108 calculates, for example, the difference between the promoter ratio and the detractor ratio for each reason for the score of the evaluation target identified by the identification unit 110. The calculation unit 108 calculates the difference between the promoter ratio and the detractor ratio of the evaluation target by summing the differences between the promoter ratio and the detractor ratio for each reason for the score of the evaluation target.

[0178] The classification unit 106, for example, if it reclassifies the evaluators 250 as indifferent individuals who are indifferent to the evaluation subject, further classifies the reclassified evaluators 250 based on the choice information included in the evaluation information. The categories of choices indicated by the choice information include, for example, categories with reasons and categories without reasons. The categories with reasons include, for example, categories of choices that are positive towards the evaluation subject, categories of choices that are neutral towards the evaluation subject, categories of choices that are negative towards the evaluation subject, and categories of choices that are indifferent towards the evaluation subject.

[0179] For example, the classification unit 106 classifies, among the 250 evaluators who have been reclassified as indifferent to the evaluation subject, those who were classified as promoters of the evaluation subject before reclassification and selected positive options toward the evaluation subject, those who were classified as promoters of the evaluation subject before reclassification and selected neutral options toward the evaluation subject, and those who were classified as neutrals of the evaluation subject before reclassification and selected positive options toward the evaluation subject, into promoters of the evaluation subject. For example, the classification unit 106 classifies, among the 250 evaluators who have been reclassified as indifferent to the evaluation subject, those who were classified as promoters of the evaluation subject before reclassification and selected negative options toward the evaluation subject, those who were classified as neutrals of the evaluation subject before reclassification and selected neutral options toward the evaluation subject, and those who were classified as weak critics of the evaluation subject before reclassification and selected positive options toward the evaluation subject, into neutrals of the evaluation subject.

[0180] For example, the classification unit 106 classifies the following evaluators 250 who have been reclassified as indifferent to the evaluation subject as critics of the evaluation subject: evaluators 250 who were previously classified as neutral to the evaluation subject and selected negative options regarding the evaluation subject; evaluators 250 who were previously classified as weak critics to the evaluation subject and selected neutral options regarding the evaluation subject; evaluators 250 who were previously classified as weak critics to the evaluation subject and selected negative options regarding the evaluation subject; evaluators 250 who were previously classified as strong critics to the evaluation subject and selected positive options regarding the evaluation subject; evaluators 250 who were previously classified as strong critics to the evaluation subject and selected neutral options regarding the evaluation subject; and evaluators 250 who were previously classified as strong critics to the evaluation subject and selected negative options regarding the evaluation subject. For example, the classification unit 106 reclassifies the following evaluators 250 who have been reclassified as indifferent to the evaluation subject: evaluators 250 who were classified as advocates of the evaluation subject before reclassification and selected an option indicating indifference to the evaluation subject; evaluators 250 who were classified as neutrals of the evaluation subject before reclassification and selected an option indicating indifference to the evaluation subject; evaluators 250 who were classified as weak critics of the evaluation subject before reclassification and selected an option indicating indifference to the evaluation subject; and evaluators 250 who were classified as strong critics of the evaluation subject before reclassification and selected an option indicating indifference to the evaluation subject, into indifferent to the evaluation subject.

[0181] The classification unit 106 further classifies the evaluators 250 who have been reclassified as indifferent to the evaluation target, for example, based on the second churn rate information stored in the information storage unit 102. The classification unit 106 further classifies the evaluators 250 who have been reclassified as indifferent to the evaluation target, for example, based on the second churn rate information, based on the reasons for the evaluation target scores identified from the comments indicated by the comment information of the evaluators 250 who have been reclassified as indifferent to the evaluation target, and for each combination of categories of choices indicated by the choice information of the evaluators 250 who have been reclassified as indifferent to the evaluation target.

[0182] For example, if the churn rate of evaluators 250 within a predetermined period for a combination of reasons for the score and category of choices identified from the comment, as indicated by the second churn rate information, is less than or equal to the churn rate of evaluators 250 within the same period for a combination of recommenders and positive comments, as indicated by the first churn rate information, the classification unit 106 reclassifies the evaluators 250 who have been reclassified as indifferent to the evaluation target into indifferent individuals. The classification unit 106 may also reclassify the evaluators 250 who have been reclassified as indifferent to the evaluation target into recommenders if the churn rate of evaluators 250 within the same period for a combination of reasons for the score and category of choices identified from the comment, as less than or equal to the churn rate of evaluators 250 within the same period for a combination of recommenders and positive comments.

[0183] For example, if the churn rate of the evaluators 250 during the period for the combination of reasons for the score and the category of the options identified from the comment is higher than the churn rate of the evaluators 250 during the period for the combination of recommenders and positive comments, and is less than or equal to the churn rate of the evaluators 250 during the period for the combination of neutral and neutral categories indicated by the first churn rate information, the classification unit 106 reclassifies the evaluators 250 who were reclassified as indifferent to the evaluation subject into neutral. If the churn rate of the evaluators 250 during the period for the combination of reasons for the score and the category of the options identified from the comment is higher than the churn rate of the evaluators 250 during the period for the combination of neutral and neutral comments, the classification unit 106 may reclassify the evaluators 250 who were reclassified as indifferent to the evaluation subject into detractors.

[0184] For example, if the churn rate of the evaluators 250 during the period for the combination of reasons for the score and category of the choices identified from the comment is lower than a predetermined third churn rate threshold, the classification unit 106 reclassifies the evaluators 250 who were reclassified as indifferent to the evaluation subject as indifferent. The classification unit 106 may also reclassify the evaluators 250 who were reclassified as indifferent to the evaluation subject as recommenders if the churn rate of the evaluators 250 during the period for the combination of reasons for the score and category of the choices identified from the comment is lower than a predetermined third churn rate threshold.

[0185] For example, if the churn rate of the evaluators 250 during the period for the combination of reasons for the score and category of the choices identified from the comment is higher than the third churn rate threshold and lower than a predetermined fourth churn rate threshold that is higher than the third churn rate threshold, the classification unit 106 reclassifies the evaluators 250 who were reclassified as indifferent to the evaluation subject as neutral. If the churn rate of the evaluators 250 during the period for the combination of reasons for the score and category of the choices identified from the comment is higher than the fourth churn rate threshold, the classification unit 106 may reclassify the evaluators 250 who were reclassified as indifferent to the evaluation subject as critics.

[0186] The determination unit 112 determines whether the reason for the score of the evaluated subject, as indicated by the score information included in the evaluation information, is attributable to the evaluated subject. The determination unit 112 determines, for example, whether the reason for the score is attributable to the evaluated subject based on various information stored in the information storage unit 102.

[0187] The determination unit 112 determines, for example, whether the reason for the score is attributable to the subject of evaluation, based on the comment information included in the evaluation information. The determination unit 112 also determines, for example, whether the reason for the score is attributable to the subject of evaluation, based on the choice information included in the evaluation information.

[0188] The determination unit 112 determines, for example, if the subject of evaluation is a store 350 of company 300, whether the reason for the score is attributable to at least one of the store 350 and the crew of store 350, thereby determining whether the reason for the score is attributable to the subject of evaluation. The determination unit 112 determines, for example, if the subject of evaluation is a product of company 300, whether the reason for the score is attributable to the product, thereby determining whether the reason for the score is attributable to the subject of evaluation.

[0189] For example, if the determination unit 112 determines that the reason for the score is attributable to the subject of evaluation, the classification unit 106 classifies the evaluators 250 based on evaluation information that includes the score information. In this case, the classification unit 106 classifies the evaluators 250 based on the evaluation information, for example, by extracting the evaluation information. On the other hand, if the determination unit 112 determines that the reason for the score is not attributable to the subject of evaluation, the classification unit 106 does not classify the evaluators 250 based on the evaluation information. In this case, the classification unit 106 removes the evaluation information, for example.

[0190] The acquisition unit 104 acquires, for example, training data that includes comment data indicating comments related to the reasons for the scores being evaluated, and comment category data indicating the category of the comments. The acquisition unit 104 may store the acquired training data in the training data storage unit 114.

[0191] The model generation unit 116 generates a decision model from the comment data to determine the category of comments related to the reasons for the scores of the evaluation target indicated by the comment data. The model generation unit 116 generates the decision model by machine learning, for example, using multiple training data stored in the training data storage unit 114 as training data. The model generation unit 116 may store the generated decision model in the model storage unit 118.

[0192] The acquisition unit 104 may acquire a decision model. For example, the acquisition unit 104 may acquire a decision model similar to the decision model generated by the model generation unit 116. The acquisition unit 104 may store the acquired decision model in the model storage unit 118.

[0193] The classification unit 106 may classify the comment information included in the evaluation information using the decision model stored in the model storage unit 118. The classification unit 106 classifies the comments by, for example, using the decision model to determine the category of comments related to the reasons for the scores of the evaluation subject indicated by the comment information.

[0194] The output unit 120 outputs various types of information. For example, the output unit 120 displays and outputs various types of information to a display or the like provided by the information processing device 100. For example, the output unit 120 outputs various types of information as audio to a speaker or the like provided by the information processing device 100. The output unit 120 may also output various types of information by transmitting them to any communication device via the network 20.

[0195] The output unit 120 outputs, for example, the classification results classified by the classification unit 106. The output unit 120 also outputs, for example, the evaluation index calculated by the calculation unit 108.

[0196] Furthermore, the information processing device 100 does not necessarily have to include a learning data storage unit 114, a model generation unit 116, and a model storage unit 118. In this case, the information processing device 100 may classify the comment information included in the evaluation information without using a decision model.

[0197] Figure 15 is an explanatory diagram illustrating an example of the processing flow of system 10. Here, the state in which the information processing device 100 has not yet acquired evaluation information is described as the starting state.

[0198] In step 102 (step may be abbreviated as S), the acquisition unit 104 acquires evaluation information from the communication terminal 200. In S104, the classification unit 106 classifies the evaluators 250 using NPS based on the scores of the evaluation targets indicated by the score information included in the evaluation information acquired by the acquisition unit 104 in S102.

[0199] In S106, the classification unit 106 classifies comments related to the reasons for the scores of the evaluation subject, which are indicated by the comment information included in the evaluation information acquired by the acquisition unit 104 in S102. In S108, the classification unit 106 classifies the evaluators 250 classified in S104 into C-NPS categories based on the classification results obtained in S106.

[0200] In S110, the identification unit 110 identifies the reason for the score of the evaluation target indicated by the score information based on the comment information. In S112, the calculation unit 108 calculates the C-NPS for each reason for the score of the evaluation target identified by the identification unit 110 in S110, based on the C-NPS classification result classified by the classification unit 106 in S108. Subsequently, the calculation unit 108 calculates the C-NPS of the evaluation target by summing the C-NPS for each reason for the score of the evaluation target.

[0201] Figure 16 schematically shows an example of the hardware configuration of a computer 1200 that functions as an information processing device 100. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of the device according to this embodiment, or to cause the computer 1200 to execute operations associated with the device according to this embodiment or such one or more "parts", and / or to cause the computer 1200 to execute a process or a stage of such process according to this embodiment. Such a program may be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0202] The computer 1200 according to this embodiment includes a CPU 1212, RAM 1214, and a graphics controller 1216, which are interconnected by a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a storage device 1224, a DVD drive 1226, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive 1226 may be a DVD-ROM drive and a DVD-RAM drive, etc. The storage device 1224 may be a hard disk drive and a solid-state drive, etc. The computer 1200 also includes legacy input / output units such as a ROM 1230 and a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0203] The CPU 1212 operates according to the programs stored in the ROM 1230 and RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires the image data generated by the CPU 1212 and stores it in the frame buffer provided in RAM 1214 or within itself, so that the image data is displayed on the display device 1218.

[0204] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive 1226 reads programs or data from a DVD-ROM 1227, etc., and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0205] The ROM 1230 stores boot programs and / or hardware-dependent programs of the computer 1200, which are executed by the computer 1200 upon activation. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via USB ports, parallel ports, serial ports, keyboard ports, mouse ports, etc.

[0206] The program is provided on a computer-readable storage medium such as a DVD-ROM 1227 or an IC card. The program is read from the computer-readable storage medium and installed on a storage device 1224, RAM 1214, or ROM 1230, which are examples of computer-readable storage media, and executed by the CPU 1212. The information processing described within these programs is read by the computer 1200, resulting in coordination between the program and the various types of hardware resources described above. The apparatus or method may be configured to realize the operation or processing of information in accordance with the use of the computer 1200.

[0207] For example, when communication is performed between a computer 1200 and an external device, the CPU 1212 may execute a communication program loaded into RAM 1214 and, based on the processing described in the communication program, instruct the communication interface 1222 to perform communication processing. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in a recording medium such as RAM 1214, storage device 1224, DVD-ROM 1227, or IC card, transmits the read transmission data to the network, or writes received data received from the network to a reception buffer area or the like provided on the recording medium.

[0208] Furthermore, the CPU 1212 may read all or necessary parts of files or databases stored on external recording media such as the storage device 1224, DVD drive 1226 (DVD-ROM 1227), or IC card into the RAM 1214, and perform various types of processing on the data in the RAM 1214. The CPU 1212 may then write the processed data back to the external recording media.

[0209] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and subjected to information processing. The CPU 1212 may perform various types of processing on the data read from RAM 1214, including various types of operations, information processing, conditional judgments, conditional branching, unconditional branching, information retrieval / replacement, etc., as described throughout this disclosure and specified by the program instruction sequence, and write the results back to RAM 1214. The CPU 1212 may also retrieve information in files, databases, etc., within the recording medium. For example, if multiple entries are stored in the recording medium, each having an attribute value of a first attribute associated with an attribute value of a second attribute, the CPU 1212 may search among the multiple entries for an entry that matches the specified condition for the attribute value of the first attribute, read the attribute value of the second attribute stored in that entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies the predetermined condition.

[0210] The program or software module described above may be stored on or near the computer 1200 in a computer-readable storage medium. Alternatively, a recording medium such as a hard disk or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the program to the computer 1200 via the network.

[0211] In this embodiment, blocks in the flowchart and block diagram may represent a stage in a process in which an operation is performed or a "part" of a device that has the role of performing an operation. A particular stage and "part" may be implemented by a dedicated circuit, a programmable circuit supplied with computer-readable instructions stored on a computer-readable storage medium, and / or a processor supplied with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuit may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuit may include reconfigurable hardware circuits, such as field-programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), which include logical AND, logical OR, exclusive OR, negated AND, negated OR, and other logical operations, flip-flops, registers, and memory elements.

[0212] Computer-readable media may include any tangible device capable of storing instructions to be executed by a suitable device, and as a result, computer-readable media having instructions stored therein will comprise a product containing instructions that can be executed to create means for performing operations specified in a flowchart or block diagram. Examples of computer-readable media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disk read-only memory (CD-ROM), digital multipurpose disc (DVD), Blu-ray® disc, memory stick, integrated circuit card, etc.

[0213] Computer-readable instructions may include assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, Java®, C++, and traditional procedural programming languages ​​such as the C programming language or similar programming languages.

[0214] Computer-readable instructions are provided locally or via a wide area network (WAN) such as a local area network (LAN) or the internet to the processor or programmable circuit of a programmable data processing device such as a computer, and may be executed to create means for performing operations specified in a flowchart or block diagram. Here, the computer may be a PC (personal computer), tablet computer, smartphone, workstation, server computer, general-purpose computer, or special-purpose computer, and may also be a computer system in which multiple computers are connected. Such a computer system in which multiple computers are connected is also called a distributed computing system and is a computer in a broad sense. In a distributed computing system, multiple computers execute a program collectively by having each computer execute a part of the program and passing data during program execution between computers as needed.

[0215] Examples of processors include computer processors, central processing units (CPUs), processing units, microprocessors, digital signal processors, controllers, and microcontrollers. A computer may have one or more processors. In a multiprocessor system with multiple processors, each processor executes a portion of the program, and the processors collectively execute the program by passing program execution data between them as needed. For example, in the execution of multitasking, each of the multiple processors may execute a portion of each task in small chunks by switching tasks at each time slice. In this case, which part of a program each processor executes changes dynamically. Which part of a program each of the multiple processors executes may also be statically determined by multiprocessor-aware programming.

[0216] This invention can contribute to the introduction of evaluation indicators calculated from classification results that appropriately classify the evaluation targets compared to conventional evaluation indicators, and therefore can contribute to achieving Sustainable Development Goal (SDG) 9, "Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation."

[0217] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications or improvements can be made to the above embodiments. It will be clear from the claims that such modified or improved forms may also be included in the technical scope of the present invention.

[0218] It should be noted that the execution order of operations, procedures, steps, and stages in the apparatus, systems, programs, and methods shown in the claims, specifications, and drawings is not explicitly stated as "before" or "prior to," and that these can be implemented in any order unless the output of a previous process is used in a later process. Even if the operation flow in the claims, specifications, and drawings is described using phrases such as "first," and "next," for convenience, this does not mean that it is essential to perform the operations in that order. [Explanation of symbols]

[0219] 10 System, 20 Network, 100 Information Processing Unit, 102 Information Storage Unit, 104 Acquisition Unit, 106 Classification Unit, 108 Calculation Unit, 110 Identification Unit, 112 Judgment Unit, 114 Learning Data Storage Unit, 116 Model Generation Unit, 118 Model Storage Unit, 120 Output Unit, 200 Communication Terminal, 250 Evaluator, 300 Company, 350 Store, 400 Collection Device, 1200 Computer, 1210 Host Controller, 1212 CPU, 1214 RAM, 1216 Graphics Controller, 1218 Display Device, 1220 Input / Output Controller, 1222 Communication Interface, 1224 Storage Device, 1226 DVD Drive, 1227 DVD-ROM, 1230 ROM, 1240 Input / Output Chip

Claims

1. An acquisition unit that acquires evaluation information including score information indicating the score of the subject to evaluation and comment information indicating comments related to the reason for the score of the subject to evaluation, A classification unit that classifies the evaluators who evaluated the subject of evaluation based on the evaluation information. An information processing device equipped with the following features.

2. The information processing device according to claim 1, wherein the classification unit classifies the evaluator as a recommender of the evaluation target if the score of the evaluation target indicated by the score information is higher than a predetermined first score threshold, classifies the evaluator as a neutral party of the evaluation target if the score of the evaluation target is lower than the first score threshold and higher than a predetermined second score threshold which is lower than the first score threshold, and classifies the evaluator as a critic of the evaluation target if the score of the evaluation target is lower than the second score threshold.

3. The information processing apparatus according to claim 2, wherein the classification unit classifies the comments indicated by the comment information into positive comments towards the subject of evaluation, neutral comments towards the subject of evaluation, negative comments towards the subject of evaluation, and comments expressing indifference towards the subject of evaluation, and based on the classification result, the evaluators who were classified into recommenders of the subject of evaluation, neutrals towards the subject of evaluation, and critics towards the subject of evaluation are reclassified into recommenders of the subject of evaluation, neutrals towards the subject of evaluation, critics towards the subject of evaluation, and indifferent persons who are indifferent towards the subject of evaluation.

4. A calculation unit calculates the difference between the recommender ratio, which is the ratio of the number of evaluators who were reclassified by the classification unit as recommenders of the evaluation target to the total number of evaluators who evaluated the evaluation target, and the critic ratio, which is the ratio of the number of evaluators who were reclassified by the classification unit as critics of the evaluation target to the total number of evaluators who evaluated the evaluation target. The information processing apparatus according to claim 3, further comprising:

5. A specific unit identifies the reason for the score of the subject of evaluation based on the comment information. Furthermore, The calculation unit calculates the difference between the percentage of recommenders and the percentage of critics for each reason for the score of the subject being evaluated. The information processing apparatus according to claim 4.

6. The acquisition unit further acquires prompts for classifying the comments, The classification unit inputs the prompt to the generating AI and classifies the comments by obtaining the classification result obtained from the generating AI based on the prompt. The information processing apparatus according to claim 3.

7. Information storage unit that stores cancellation rate information indicating the cancellation rate for each combination of the evaluator's category and the comment category, which shows the rate at which the evaluator cancels a contract with the company within a predetermined period from the time the evaluator evaluates the company being evaluated. Furthermore, The classification unit further reclassifies the evaluators based on the churn rate information stored in the information storage unit. The information processing apparatus according to claim 3.

8. The acquisition unit acquires the evaluation information, which further includes option information indicating the option corresponding to the reason for the score of the subject to evaluation. When the classification unit reclassifies the evaluators as indifferent persons who are indifferent to the evaluation subject, it further classifies the evaluators who have been reclassified as indifferent persons who are indifferent to the evaluation subject based on the choice information. The information processing apparatus according to claim 3.

9. An information storage unit that stores the reasons for the score of the evaluated subject identified from the comment information and cancellation rate information for each category of the options, which indicates the cancellation rate at which the evaluator cancels a contract with the company within a predetermined period from the time the evaluator evaluated the company being evaluated, Based on the aforementioned comment information, a specific unit identifies the reason for the score of the subject to evaluation. Furthermore, The classification unit further classifies the evaluators who have been reclassified as indifferent to the evaluation target, based on the churn rate information stored in the information storage unit. The information processing apparatus according to claim 8.

10. The information processing device according to any one of claims 1 to 6, wherein the classification unit reclassifies the evaluators, who have been classified by the score of the evaluation target indicated by the score information, based on the classification result obtained by classifying the comments indicated by the comment information according to predetermined classification criteria.

11. A determination unit determines, based on the comment information, whether the reason for the score of the store of the company being evaluated, as indicated by the score information, is attributable to at least one of the store and the store's crew. Furthermore, The classification unit classifies the evaluator based on the evaluation information when the determination unit determines that the reason for the score is attributable to at least one of the store and the crew. The information processing apparatus according to any one of claims 1 to 6.

12. On the computer, A procedure for obtaining evaluation information that includes score information indicating the score of the subject to evaluation, and comment information indicating comments related to the reasons for the score of the subject to evaluation, A classification procedure for classifying the evaluators who evaluated the subject of evaluation based on the aforementioned evaluation information. A program to execute.

13. A method of information processing performed by a computer, An acquisition step is to acquire evaluation information that includes score information indicating the score of the subject to evaluation, and comment information indicating comments related to the reasons for the score of the subject to evaluation, Based on the aforementioned evaluation information, a classification stage is established to classify the evaluators who evaluated the subject of evaluation. An information processing method comprising:

Images