System

Abstract

An object of a system according to an embodiment is to automatically generate a total score by combining a score evaluation of a customer questionnaire and a reason.SOLUTION: A system includes a collection unit, a classification unit, an exclusion unit, and a score generation unit. The collection unit collects a score and a reason of a customer questionnaire. The classifying unit classifies the free replies collected by the collecting unit in AI of generation. The exclusion unit excludes an answer irrelevant to the employee evaluation from the free answers classified by the classification unit. The score generation unit automatically generates a total score by combining the scores of the free answers not excluded by the exclusion unit and the positive, neutral, and negative scores of the reasons.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, there was a problem of inconsistency between the scores in customer surveys and the actual customer experience, which meant that employees were not satisfied with the evaluations.

[0005] The system according to the embodiment aims to automatically generate a total score by combining the points and reasons from a customer survey. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a classification unit, an exclusion unit, and a score generation unit. The collection unit collects customer survey scores and reasons. The classification unit classifies the free-form responses collected by the collection unit using a generation AI. The exclusion unit excludes any free-form responses classified by the classification unit that are not related to employee evaluation. The score generation unit automatically generates an overall score by combining the scores of the free-form responses not excluded by the exclusion unit and the positive, neutral, and negative scores of the reasons. [Effects of the Invention]

[0007] The system according to the embodiment can automatically generate a total score by combining the points and reasons from the customer survey. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A system according to an embodiment of the present invention resolves discrepancies between customer survey scores and actual customer experiences, enabling employees to feel satisfied with their evaluations. This system collects both the "score" and "reason for the score (free-form response)" in the customer survey. It then uses a generation AI to categorize the free-form responses into positive, neutral, and negative opinions. Responses unrelated to the employee evaluation are excluded, and a score is automatically generated by multiplying the score and the positive, neutral, and negative reasons. This allows the system to more accurately reflect customer evaluations and improve employee satisfaction. For example, a customer survey collects the "score" and "reason for the score (free-form response)." Customers rate their scores on a 10-point scale and write their reasons in free-form responses. Next, the generation AI categorizes the free-form responses. The generation AI analyzes the free-form responses and categorizes them into positive, neutral, and negative opinions. Responses unrelated to the employee evaluation are excluded. Finally, a score is automatically generated by multiplying the score and the positive, neutral, and negative reasons. This will more accurately reflect customer evaluations and increase employee satisfaction.

[0029] The evaluation system according to the embodiment includes a collection unit, a classification unit, an exclusion unit, and a score generation unit. The collection unit collects scores and reasons from customer surveys. For example, the collection unit can collect scores and reasons using online or paper-based surveys. The collection unit can also collect free-form responses using voice input or text input. The classification unit uses a generation AI to classify the free-form responses as positive, neutral, or negative. For example, the generation AI analyzes the free-form responses using natural language processing technology and classifies them as positive, neutral, or negative using a sentiment analysis algorithm. For example, the generation AI classifies a response such as "8 points because the customer service was good" as positive and a response such as "5 points because the store location is poor" as negative. The exclusion unit excludes responses unrelated to employee evaluations. For example, the exclusion unit excludes responses unrelated to employee evaluations based on the presence or absence of specific keywords or the relevance of the content. For example, a response such as "5 points because the store location is poor" is excluded because it is unrelated to employee customer service. The score generation unit automatically generates a total score by combining the points and the positive, neutral, and negative scores of the reasons. For example, the score generation unit calculates each score using a sentiment analysis algorithm to generate the total score. This allows the evaluation system according to the embodiment to resolve inconsistencies between the score evaluation in the customer survey and the actual customer experience, allowing employees to feel satisfied with the evaluation.

[0030] The collection unit can collect scores and reasons from customer surveys. The collection unit can collect scores and reasons using, for example, an online survey or a paper-based survey. For example, the collection unit collects a survey in which customers rate their scores on a 10-point scale and write their reasons in free-form. The collection unit can also collect free-form responses using voice input or text input. For example, when a customer states their reasons by voice, the collection unit converts the voice into text and collects it. This makes it possible to accurately collect scores and reasons from customer surveys.

[0031] The classification unit can classify free responses into positive, neutral, and negative using a generation AI. The classification unit, for example, uses a generation AI to classify free responses into positive, neutral, and negative. The generation AI analyzes free responses using natural language processing technology and classifies them into positive, neutral, and negative using a sentiment analysis algorithm. For example, the generation AI classifies a response such as "The customer service was good, so I gave it an 8" as positive, and a response such as "The store's location is bad, so I gave it a 5" as negative. The generation AI can also analyze free responses using a text generation AI (e.g., LLM) and calculate a sentiment score. This allows for accurate classification of free responses.

[0032] The exclusion unit can exclude responses that are not related to employee evaluations. The exclusion unit excludes responses that are not related to employee evaluations, for example, based on the presence or absence of specific keywords or the relevance of the content. For example, a response such as "The store's location is bad, so it gets a score of 5" is excluded because it is unrelated to employee customer service. The exclusion unit can also use a generation AI to exclude responses that are not related to employee evaluations. For example, the generation AI analyzes free responses and automatically excludes responses that are not related to employee evaluations. This can improve the accuracy of the evaluations by excluding responses that are not related to employee evaluations.

[0033] The score generation unit can automatically generate an overall score by combining the score and each score of the positive, neutral, and negative reasons. The score generation unit, for example, calculates each score using a sentiment analysis algorithm and generates an overall score. For example, the score generation unit sets a high score if the score is 8 for positive reasons, and sets a low score if the score is 8 for negative reasons. The score generation unit can also automatically generate an overall score using a generation AI. For example, the generation AI calculates a score by multiplying the score by the positive, neutral, and negative reasons, and generates an overall score. In this way, the accuracy of the evaluation can be improved by automatically generating a score by multiplying the score by the reason.

[0034] The collection unit can analyze the customer's past survey response history and select an appropriate collection method. The collection unit, for example, analyzes the customer's past survey response history and selects the optimal collection method. For example, if the customer has previously shown a high response rate to text-format surveys, the collection unit can send the survey in a similar format. Also, if the customer has previously preferred voice input, the collection unit can provide a survey that supports voice input. Furthermore, if the customer has previously shown a high response rate to short surveys, the collection unit can also send a short-format survey. In this way, the response rate can be improved by selecting the optimal collection method based on the customer's past response history.

[0035] When collecting surveys, the collection unit can filter the surveys based on the customer's current purchase history and areas of interest. The collection unit performs filtering based on, for example, the customer's current purchase history and areas of interest. For example, the collection unit sends a survey including questions related to products recently purchased by the customer. The collection unit can also preferentially send surveys related to products in categories in which the customer has shown interest in the past. Furthermore, the collection unit can analyze the customer's purchase history and create a survey including highly relevant questions. As a result, highly relevant surveys can be collected by filtering based on the customer's purchase history and areas of interest.

[0036] When collecting a questionnaire, the collection unit can select an appropriate collection means depending on the customer's input method. For example, the collection unit selects the optimal collection means depending on the customer's input method (voice, text, image, etc.). For example, if the customer prefers voice input, the collection unit can provide a questionnaire that supports voice input. Also, if the customer prefers text input, the collection unit can provide a text-format questionnaire. Furthermore, if the customer prefers to provide feedback using images, the collection unit can provide a questionnaire that includes an image upload function. This makes it possible to improve the response rate by selecting the optimal collection means depending on the customer's input method.

[0037] When collecting questionnaires, the collection unit can prioritize collecting highly relevant questionnaires by taking into account the geographical location information of the customer. The collection unit, for example, prioritizes collecting highly relevant questionnaires by taking into account the geographical location information of the customer. For example, if the customer is in a specific area, the collection unit can send a questionnaire about services and products related to that area. Also, if the customer is traveling, the collection unit can send a questionnaire requesting feedback related to the travel destination. Furthermore, if the customer visits a specific store, the collection unit can prioritize sending a questionnaire about that store. In this way, by collecting highly relevant questionnaires by taking into account the geographical location information of the customer, the accuracy of responses can be improved.

[0038] When collecting surveys, the collection unit can analyze the social media activities of customers and collect relevant surveys. The collection unit, for example, analyzes the social media activities of customers and collects relevant surveys. For example, if a customer mentions a particular product on social media, the collection unit can send a survey about the product. Also, if a customer participates in a particular event on social media, the collection unit can send a survey asking for feedback about the event. Furthermore, the collection unit can analyze the social media activities of customers and create relevant surveys. In this way, highly relevant surveys can be collected by analyzing the social media activities of customers.

[0039] The collection unit can customize the collection method by reflecting the customer's past feedback when collecting the questionnaire. The collection unit customizes the collection method by reflecting the customer's past feedback, for example. For example, the collection unit creates a questionnaire including related questions based on feedback provided by the customer in the past. The collection unit can also create a new questionnaire using a questionnaire format that the customer preferred in the past. Furthermore, the collection unit can analyze the customer's past feedback and suggest the optimal collection method. In this way, the optimal collection method can be provided by reflecting the customer's past feedback.

[0040] The classification unit can adjust the level of detail of the classification based on the importance of the response when classifying free responses. For example, the classification unit adjusts the level of detail of the classification based on the importance of the response when classifying free responses. For example, the classification unit performs detailed classification for responses with high importance to extract specific opinions. The classification unit can also perform simplified classification for responses with low importance to grasp overall trends. Furthermore, the classification unit can dynamically adjust the level of detail of the classification according to the importance of the response, thereby achieving efficient classification. In this way, efficient classification can be achieved by adjusting the level of detail of the classification according to the importance of the response.

[0041] The classification unit can apply different classification algorithms depending on the category of the answer when classifying free responses. For example, the classification unit applies different classification algorithms depending on the category of the answer when classifying free responses. For example, the classification unit applies a service-specific classification algorithm to answers about services. The classification unit can also apply a product-specific classification algorithm to answers about products. Furthermore, the classification unit can apply a support-specific classification algorithm to answers about customer support. In this way, by applying an appropriate classification algorithm depending on the category of the answer, the accuracy of classification can be improved.

[0042] When classifying free responses, the classification unit can improve the accuracy of classification by referring to the customer's past response results. The classification unit improves the accuracy of classification by referring to, for example, the customer's past response results. For example, the classification unit accurately classifies similar responses based on responses provided by the customer in the past. The classification unit can also analyze the customer's past response results to improve the accuracy of the classification algorithm. Furthermore, the classification unit can maintain consistency of classification by referring to the customer's past response patterns. In this way, by referring to the customer's past response results, the consistency and accuracy of classification can be improved.

[0043] The classifier can determine the priority of classification based on the time of submission of the answer when classifying free answers. For example, the classifier can determine the priority of classification based on the time of submission of the answer when classifying free answers. For example, the classifier can prioritize classifying recently submitted answers to reflect the latest feedback. The classifier can also prioritize classifying answers submitted in a concentrated manner during a specific period to grasp trends. Furthermore, the classifier can dynamically adjust the priority of classification based on the time of submission of the answer. In this way, by determining the priority of classification based on the time of submission of the answer, the latest feedback can be quickly reflected.

[0044] The classification unit can adjust the order of classification based on the relevance of the answers when classifying free replies. For example, the classification unit adjusts the order of classification based on the relevance of the answers when classifying free replies. For example, the classification unit prioritizes classifying answers with high relevance to extract important opinions. The classification unit can also postpone answers with low relevance to achieve efficient classification. Furthermore, the classification unit can dynamically adjust the order of classification based on the relevance of the answers. In this way, by adjusting the order of classification based on the relevance of the answers, important opinions can be preferentially extracted.

[0045] The classifier can adjust the use of specialized terminology for classification according to the customer's level of expertise when classifying free responses. For example, the classifier adjusts the use of specialized terminology for classification according to the customer's level of expertise when classifying free responses. For example, the classifier uses specialized terminology to perform detailed classification for responses from customers with high levels of expertise. The classifier can also perform simplified classification using general terms for responses from customers with low levels of expertise. Furthermore, the classifier can dynamically adjust the use of specialized terminology for classification according to the customer's level of expertise. This allows for appropriate classification by adjusting the use of specialized terminology for classification according to the customer's level of expertise.

[0046] The exclusion unit can improve the accuracy of exclusion by taking into account the interrelationships between answers at the time of exclusion. For example, the exclusion unit improves the accuracy of exclusion by taking into account the interrelationships between answers at the time of exclusion. For example, the exclusion unit analyzes the interrelationships between answers and excludes answers with low relevance. The exclusion unit can also avoid excluding important opinions by taking into account the interrelationships between answers. Furthermore, the exclusion unit can improve the accuracy of exclusion based on the interrelationships between answers. In this way, it is possible to appropriately exclude answers with low relevance by taking into account the interrelationships between answers.

[0047] When excluding answers, the exclusion unit can perform the exclusion taking into consideration attribute information of the answer submitter. The exclusion unit performs the exclusion taking into consideration, for example, attribute information of the answer submitter. For example, the exclusion unit considers attribute information such as the submitter's age and gender to exclude answers that are biased toward a particular attribute. The exclusion unit can also exclude answers with low reliability based on the submitter's purchasing history and usage frequency. Furthermore, the exclusion unit can analyze the submitter's attribute information and appropriately exclude answers that are not related to employee evaluation. In this way, by considering the submitter's attribute information, answers that are biased toward a particular attribute can be appropriately excluded.

[0048] The exclusion unit can weight the exclusion based on the frequency of answer submission at the time of exclusion. The exclusion unit, for example, weights the exclusion based on the frequency of answer submission. For example, the exclusion unit preferentially considers and weights answers that are submitted more frequently. The exclusion unit can also appropriately exclude answers that are submitted less frequently to maintain overall balance. Furthermore, the exclusion unit can dynamically adjust the weighting of the exclusion based on the frequency of answer submission. In this way, by weighting the exclusion based on the frequency of answer submission, it is possible to maintain overall balance.

[0049] The exclusion unit can perform exclusion taking into consideration the geographic distribution of answers. The exclusion unit performs exclusion taking into consideration, for example, the geographic distribution of answers. For example, the exclusion unit excludes answers that are biased toward a specific region, thereby maintaining overall balance. The exclusion unit can also appropriately exclude answers that are geographically less relevant. Furthermore, the exclusion unit can analyze the geographic distribution of answers and improve the accuracy of exclusion. In this way, by taking into consideration the geographic distribution of answers, it is possible to maintain overall balance.

[0050] The exclusion unit can improve the accuracy of exclusion by referring to literature related to the answer at the time of exclusion. The exclusion unit can improve the accuracy of exclusion by, for example, referring to literature related to the answer. For example, the exclusion unit compares the content of the answer with related literature and excludes answers with low reliability. The exclusion unit can also refer to related literature to appropriately exclude answers that are not relevant to employee evaluation. Furthermore, the exclusion unit can improve the accuracy of exclusion based on literature related to the answer. In this way, by referring to related literature, it is possible to appropriately exclude answers with low reliability.

[0051] The exclusion unit can perform exclusion taking into consideration the market value of the answer when performing exclusion. The exclusion unit performs exclusion taking into consideration, for example, the market value of the answer. For example, the exclusion unit preferentially considers and weights answers with high market value. The exclusion unit can also appropriately exclude answers with low market value to maintain overall balance. Furthermore, the exclusion unit can dynamically adjust the weighting of exclusion based on the market value of the answer. This makes it possible to maintain overall balance by preferentially considering answers with high market value.

[0052] The score generation unit can improve the accuracy of the score by taking into account the interrelationships between answers when generating the score. For example, the score generation unit improves the accuracy of the score by taking into account the interrelationships between answers when generating the score. For example, the score generation unit analyzes the interrelationships between answers and generates a score by emphasizing highly relevant answers. The score generation unit can also generate a score by taking into account the interrelationships between answers and appropriately reflecting important opinions. Furthermore, the score generation unit can improve the accuracy of the score based on the interrelationships between answers. In this way, by taking into account the interrelationships between answers, it is possible to generate a score by emphasizing highly relevant answers.

[0053] When generating a score, the score generation unit can generate the score by taking into account the attribute information of the person who submitted the answer. The score generation unit generates the score by taking into account, for example, the attribute information of the person who submitted the answer. For example, the score generation unit takes into account attribute information such as the submitter's age and gender to avoid generating a score that is biased toward a particular attribute. The score generation unit can also generate a highly reliable score based on the submitter's purchasing history and usage frequency. Furthermore, the score generation unit can analyze the submitter's attribute information and generate a score by excluding elements that are not related to employee evaluation. In this way, by taking into account the submitter's attribute information, it is possible to avoid generating a score that is biased toward a particular attribute.

[0054] The score generation unit can weight the scores based on the frequency of answer submissions when generating the scores. For example, the score generation unit weights the scores based on the frequency of answer submissions when generating the scores. For example, the score generation unit preferentially considers and weights answers that are submitted more frequently. The score generation unit can also appropriately exclude answers that are submitted less frequently to maintain overall balance. Furthermore, the score generation unit can dynamically adjust the weighting of the scores based on the frequency of answer submissions. In this way, by weighting the scores based on the frequency of answer submissions, overall balance can be maintained.

[0055] The score generation unit can generate scores taking into account the geographical distribution of answers when generating scores. For example, the score generation unit generates scores taking into account the geographical distribution of answers when generating scores. For example, the score generation unit generates a score that maintains overall balance by taking into account answers that are biased toward a specific region. The score generation unit can also generate a score by emphasizing answers that are highly geographically relevant. Furthermore, the score generation unit can analyze the geographical distribution of answers and improve the accuracy of the score. In this way, by taking into account the geographical distribution of answers, it is possible to generate a score that maintains overall balance.

[0056] The score generation unit can improve the accuracy of the score by referring to literature related to the answer when generating the score. For example, the score generation unit can improve the accuracy of the score by referring to literature related to the answer when generating the score. For example, the score generation unit can compare the content of the answer with the related literature to generate a highly reliable score. The score generation unit can also generate a score by referring to the related literature and excluding elements that are not relevant to employee evaluation. Furthermore, the score generation unit can improve the accuracy of the score based on literature related to the answer. In this way, by referring to the related literature, a highly reliable score can be generated.

[0057] The score generation unit can generate a score taking into account the market value of the answer when generating the score. For example, the score generation unit generates a score taking into account the market value of the answer when generating the score. For example, the score generation unit preferentially considers and weights answers with high market value. The score generation unit can also appropriately exclude answers with low market value to generate a score that maintains overall balance. Furthermore, the score generation unit can dynamically adjust the weighting of the score based on the market value of the answer. This makes it possible to generate a score that maintains overall balance by preferentially considering answers with high market value.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The rating system may further include a reliability evaluation unit that evaluates the reliability of the feedback. The reliability evaluation unit, for example, analyzes the customer's past response history and behavioral patterns to evaluate the reliability of the feedback. For example, if the customer has provided consistent ratings in the past, the reliability evaluation unit may rate the feedback highly. Also, if the customer has provided inconsistent ratings in the past, the reliability evaluation unit may rate the feedback low. Furthermore, the reliability evaluation unit may analyze the customer's behavioral patterns and prioritize highly reliable feedback. This allows for a more accurate evaluation by evaluating the reliability of the feedback.

[0060] The collection unit may further include a real-time collection function for collecting customer feedback in real time. For example, the collection unit may collect feedback in real time when a customer visits a store. The collection unit may also collect feedback in real time when a customer is shopping online. The collection unit may also collect feedback in real time when a customer participates in a specific event. This allows for faster response by collecting feedback in real time.

[0061] The excluding unit may further include a context analysis function that takes into account the context of the answer to improve the accuracy of the excluding. For example, the excluding unit may analyze the context before and after the answer to exclude parts that are not relevant to the employee evaluation. The excluding unit may also evaluate the relevance of the answer based on the context analysis to appropriately extract important opinions. Furthermore, the excluding unit may use the context analysis to evaluate the consistency of the answer to exclude answers with low reliability. In this way, the accuracy of the excluding can be improved by taking the context into account.

[0062] The score generation unit may further include a trend analysis function that analyzes trends in customer feedback. For example, the score generation unit may analyze past feedback data to identify trends in customer ratings. The score generation unit may also adjust the score based on the trends to reflect the latest customer opinions. Furthermore, the score generation unit may use trend analysis to predict future ratings, which may be useful in improving employee performance. This allows for the generation of more accurate scores by analyzing trends.

[0063] The collection unit may further include an anonymization function for anonymizing customer feedback. For example, the collection unit may anonymize customer personal information to protect privacy. The collection unit may also use the anonymized feedback to perform evaluations and eliminate bias. The collection unit may also analyze the anonymized feedback to identify overall trends. This allows for accurate evaluations while protecting customer privacy.

[0064] The collection unit may further include a translation function that automatically translates customer feedback. For example, the collection unit may automatically translate feedback provided in different languages ​​and provide a rating in a unified format. The collection unit may also use the translated feedback to provide a multilingual rating. Furthermore, the collection unit may use the translation function to collect feedback from international customers and provide a rating from a global perspective. This allows for a unified rating of feedback provided in different languages.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The collection unit collects customer survey scores and reasons. For example, the collection unit can collect scores and reasons using an online survey or a paper-based survey. The collection unit can also collect free responses using voice input or text input. Step 2: The classification unit uses the generation AI to classify the free responses as positive, neutral, or negative. For example, the generation AI analyzes the free responses using natural language processing technology and classifies them as positive, neutral, or negative using a sentiment analysis algorithm. For example, the generation AI classifies a response such as "The customer service was good, so I'd give it an 8" as positive, and a response such as "The store's location was bad, so I'd give it a 5" as negative. Step 3: The exclusion unit filters out responses that are not relevant to employee evaluations. For example, the exclusion unit filters out responses that are not relevant to employee evaluations based on the presence or absence of specific keywords or the relevance of the content. For example, a response such as "The store's location is bad, so it gets a score of 5" is filtered out because it is unrelated to employee customer service. Step 4: The score generator automatically generates a total score by combining the points and the positive, neutral, and negative scores of the reasons. For example, the score generator may use a sentiment analysis algorithm to calculate each score and generate a total score.

[0067] (Example 2) A system according to an embodiment of the present invention resolves discrepancies between customer survey scores and actual customer experiences, enabling employees to feel satisfied with their evaluations. This system collects both the "score" and "reason for the score (free-form response)" in the customer survey. It then uses a generation AI to categorize the free-form responses into positive, neutral, and negative opinions. Responses unrelated to the employee evaluation are excluded, and a score is automatically generated by multiplying the score and the positive, neutral, and negative reasons. This allows the system to more accurately reflect customer evaluations and improve employee satisfaction. For example, a customer survey collects the "score" and "reason for the score (free-form response)." Customers rate their scores on a 10-point scale and write their reasons in free-form responses. Next, the generation AI categorizes the free-form responses. The generation AI analyzes the free-form responses and categorizes them into positive, neutral, and negative opinions. Responses unrelated to the employee evaluation are excluded. Finally, a score is automatically generated by multiplying the score and the positive, neutral, and negative reasons. This will more accurately reflect customer evaluations and increase employee satisfaction.

[0068] The evaluation system according to the embodiment includes a collection unit, a classification unit, an exclusion unit, and a score generation unit. The collection unit collects scores and reasons from customer surveys. For example, the collection unit can collect scores and reasons using online or paper-based surveys. The collection unit can also collect free-form responses using voice input or text input. The classification unit uses a generation AI to classify the free-form responses as positive, neutral, or negative. For example, the generation AI analyzes the free-form responses using natural language processing technology and classifies them as positive, neutral, or negative using a sentiment analysis algorithm. For example, the generation AI classifies a response such as "8 points because the customer service was good" as positive and a response such as "5 points because the store location is poor" as negative. The exclusion unit excludes responses unrelated to employee evaluations. For example, the exclusion unit excludes responses unrelated to employee evaluations based on the presence or absence of specific keywords or the relevance of the content. For example, a response such as "5 points because the store location is poor" is excluded because it is unrelated to employee customer service. The score generation unit automatically generates a total score by combining the points and the positive, neutral, and negative scores of the reasons. For example, the score generation unit calculates each score using a sentiment analysis algorithm to generate the total score. This allows the evaluation system according to the embodiment to resolve inconsistencies between the score evaluation in the customer survey and the actual customer experience, allowing employees to feel satisfied with the evaluation.

[0069] The collection unit can collect scores and reasons from customer surveys. The collection unit can collect scores and reasons using, for example, an online survey or a paper-based survey. For example, the collection unit collects a survey in which customers rate their scores on a 10-point scale and write their reasons in free-form. The collection unit can also collect free-form responses using voice input or text input. For example, when a customer states their reasons by voice, the collection unit converts the voice into text and collects it. This makes it possible to accurately collect scores and reasons from customer surveys.

[0070] The classification unit can classify free responses into positive, neutral, and negative using a generation AI. The classification unit, for example, uses a generation AI to classify free responses into positive, neutral, and negative. The generation AI analyzes free responses using natural language processing technology and classifies them into positive, neutral, and negative using a sentiment analysis algorithm. For example, the generation AI classifies a response such as "The customer service was good, so I gave it an 8" as positive, and a response such as "The store's location is bad, so I gave it a 5" as negative. The generation AI can also analyze free responses using a text generation AI (e.g., LLM) and calculate a sentiment score. This allows for accurate classification of free responses.

[0071] The exclusion unit can exclude responses that are not related to employee evaluations. The exclusion unit excludes responses that are not related to employee evaluations, for example, based on the presence or absence of specific keywords or the relevance of the content. For example, a response such as "The store's location is bad, so it gets a score of 5" is excluded because it is unrelated to employee customer service. The exclusion unit can also use a generation AI to exclude responses that are not related to employee evaluations. For example, the generation AI analyzes free responses and automatically excludes responses that are not related to employee evaluations. This can improve the accuracy of the evaluations by excluding responses that are not related to employee evaluations.

[0072] The score generation unit can automatically generate an overall score by combining the score and each score of the positive, neutral, and negative reasons. The score generation unit, for example, calculates each score using a sentiment analysis algorithm and generates an overall score. For example, the score generation unit sets a high score if the score is 8 for positive reasons, and sets a low score if the score is 8 for negative reasons. The score generation unit can also automatically generate an overall score using a generation AI. For example, the generation AI calculates a score by multiplying the score by the positive, neutral, and negative reasons, and generates an overall score. In this way, the accuracy of the evaluation can be improved by automatically generating a score by multiplying the score by the reason.

[0073] The collection unit can estimate the user's emotions and adjust the timing of collecting the questionnaire based on the estimated user's emotions. The collection unit estimates the user's emotions using, for example, an emotion analysis algorithm. For example, if the collection unit estimates that the user is relaxed, it selects the timing to send the questionnaire, thereby improving the response rate. Furthermore, if the collection unit estimates that the user is feeling stressed, it can temporarily delay sending the questionnaire and resend it at an appropriate time. Furthermore, if the collection unit estimates that the user is excited, it can immediately send the questionnaire and collect feedback in real time. In this way, by adjusting the timing of collecting the questionnaire according to the user's emotions, it is possible to improve the response rate.

[0074] The collection unit can analyze the customer's past survey response history and select an appropriate collection method. The collection unit, for example, analyzes the customer's past survey response history and selects the optimal collection method. For example, if the customer has previously shown a high response rate to text-format surveys, the collection unit can send the survey in a similar format. Also, if the customer has previously preferred voice input, the collection unit can provide a survey that supports voice input. Furthermore, if the customer has previously shown a high response rate to short surveys, the collection unit can also send a short-format survey. In this way, the response rate can be improved by selecting the optimal collection method based on the customer's past response history.

[0075] When collecting surveys, the collection unit can filter the surveys based on the customer's current purchase history and areas of interest. The collection unit performs filtering based on, for example, the customer's current purchase history and areas of interest. For example, the collection unit sends a survey including questions related to products recently purchased by the customer. The collection unit can also preferentially send surveys related to products in categories in which the customer has shown interest in the past. Furthermore, the collection unit can analyze the customer's purchase history and create a survey including highly relevant questions. As a result, highly relevant surveys can be collected by filtering based on the customer's purchase history and areas of interest.

[0076] When collecting a questionnaire, the collection unit can select an appropriate collection means depending on the customer's input method. For example, the collection unit selects the optimal collection means depending on the customer's input method (voice, text, image, etc.). For example, if the customer prefers voice input, the collection unit can provide a questionnaire that supports voice input. Also, if the customer prefers text input, the collection unit can provide a text-format questionnaire. Furthermore, if the customer prefers to provide feedback using images, the collection unit can provide a questionnaire that includes an image upload function. This makes it possible to improve the response rate by selecting the optimal collection means depending on the customer's input method.

[0077] The collection unit can estimate the user's emotions and determine the priority of surveys to be collected based on the estimated user's emotions. The collection unit estimates the user's emotions using, for example, an emotion analysis algorithm. For example, if the collection unit estimates that the user has positive emotions, it can prioritize sending surveys requesting important feedback. Also, if the collection unit estimates that the user has neutral emotions, it can send surveys requesting general feedback. Furthermore, if the collection unit estimates that the user has negative emotions, it can prioritize sending surveys requesting improvements. In this way, by prioritizing surveys according to the user's emotions, it is possible to prioritize collecting important feedback.

[0078] When collecting questionnaires, the collection unit can prioritize collecting highly relevant questionnaires by taking into account the geographical location information of the customer. The collection unit, for example, prioritizes collecting highly relevant questionnaires by taking into account the geographical location information of the customer. For example, if the customer is in a specific area, the collection unit can send a questionnaire about services and products related to that area. Also, if the customer is traveling, the collection unit can send a questionnaire requesting feedback related to the travel destination. Furthermore, if the customer visits a specific store, the collection unit can prioritize sending a questionnaire about that store. In this way, by collecting highly relevant questionnaires by taking into account the geographical location information of the customer, the accuracy of responses can be improved.

[0079] When collecting surveys, the collection unit can analyze the social media activities of customers and collect relevant surveys. The collection unit, for example, analyzes the social media activities of customers and collects relevant surveys. For example, if a customer mentions a particular product on social media, the collection unit can send a survey about the product. Also, if a customer participates in a particular event on social media, the collection unit can send a survey asking for feedback about the event. Furthermore, the collection unit can analyze the social media activities of customers and create relevant surveys. In this way, highly relevant surveys can be collected by analyzing the social media activities of customers.

[0080] The collection unit can customize the collection method by reflecting the customer's past feedback when collecting the questionnaire. The collection unit customizes the collection method by reflecting the customer's past feedback, for example. For example, the collection unit creates a questionnaire including related questions based on feedback provided by the customer in the past. The collection unit can also create a new questionnaire using a questionnaire format that the customer preferred in the past. Furthermore, the collection unit can analyze the customer's past feedback and suggest the optimal collection method. In this way, the optimal collection method can be provided by reflecting the customer's past feedback.

[0081] The classification unit can estimate the user's emotions and adjust the classification criteria for free responses based on the estimated user's emotions. The classification unit estimates the user's emotions using, for example, an emotion analysis algorithm. For example, if the classification unit estimates that the user has positive emotions, it can apply classification criteria that emphasize positive opinions. Furthermore, if the classification unit estimates that the user has neutral emotions, it can also apply classification criteria that emphasize neutral opinions. Furthermore, if the classification unit estimates that the user has negative emotions, it can also apply criteria that classify negative opinions in more detail. In this way, by adjusting the classification criteria according to the user's emotions, it is possible to improve the accuracy of classification.

[0082] The classification unit can adjust the level of detail of the classification based on the importance of the response when classifying free responses. For example, the classification unit adjusts the level of detail of the classification based on the importance of the response when classifying free responses. For example, the classification unit performs detailed classification for responses with high importance to extract specific opinions. The classification unit can also perform simplified classification for responses with low importance to grasp overall trends. Furthermore, the classification unit can dynamically adjust the level of detail of the classification according to the importance of the response, thereby achieving efficient classification. In this way, efficient classification can be achieved by adjusting the level of detail of the classification according to the importance of the response.

[0083] The classification unit can apply different classification algorithms depending on the category of the answer when classifying free responses. For example, the classification unit applies different classification algorithms depending on the category of the answer when classifying free responses. For example, the classification unit applies a service-specific classification algorithm to answers about services. The classification unit can also apply a product-specific classification algorithm to answers about products. Furthermore, the classification unit can apply a support-specific classification algorithm to answers about customer support. In this way, by applying an appropriate classification algorithm depending on the category of the answer, the accuracy of classification can be improved.

[0084] When classifying free responses, the classification unit can improve the accuracy of classification by referring to the customer's past response results. The classification unit improves the accuracy of classification by referring to, for example, the customer's past response results. For example, the classification unit accurately classifies similar responses based on responses provided by the customer in the past. The classification unit can also analyze the customer's past response results to improve the accuracy of the classification algorithm. Furthermore, the classification unit can maintain consistency of classification by referring to the customer's past response patterns. In this way, by referring to the customer's past response results, the consistency and accuracy of classification can be improved.

[0085] The classification unit can estimate the user's emotions and adjust the length of the classification of free responses based on the estimated user emotions. The classification unit estimates the user's emotions using, for example, an emotion analysis algorithm. For example, if the classification unit estimates that the user has positive emotions, it performs detailed classification and emphasizes positive opinions. Furthermore, if the classification unit estimates that the user has neutral emotions, it can perform simplified classification and grasp neutral opinions. Furthermore, if the classification unit estimates that the user has negative emotions, it can perform detailed classification and extract negative opinions. In this way, the accuracy of classification can be improved by adjusting the length of classification according to the user's emotions.

[0086] The classifier can determine the priority of classification based on the time of submission of the answer when classifying free answers. For example, the classifier can determine the priority of classification based on the time of submission of the answer when classifying free answers. For example, the classifier can prioritize classifying recently submitted answers to reflect the latest feedback. The classifier can also prioritize classifying answers submitted in a concentrated manner during a specific period to grasp trends. Furthermore, the classifier can dynamically adjust the priority of classification based on the time of submission of the answer. In this way, by determining the priority of classification based on the time of submission of the answer, the latest feedback can be quickly reflected.

[0087] The classification unit can adjust the order of classification based on the relevance of the answers when classifying free replies. For example, the classification unit adjusts the order of classification based on the relevance of the answers when classifying free replies. For example, the classification unit prioritizes classifying answers with high relevance to extract important opinions. The classification unit can also postpone answers with low relevance to achieve efficient classification. Furthermore, the classification unit can dynamically adjust the order of classification based on the relevance of the answers. In this way, by adjusting the order of classification based on the relevance of the answers, important opinions can be preferentially extracted.

[0088] The classifier can adjust the use of specialized terminology for classification according to the customer's level of expertise when classifying free responses. For example, the classifier adjusts the use of specialized terminology for classification according to the customer's level of expertise when classifying free responses. For example, the classifier uses specialized terminology to perform detailed classification for responses from customers with high levels of expertise. The classifier can also perform simplified classification using general terms for responses from customers with low levels of expertise. Furthermore, the classifier can dynamically adjust the use of specialized terminology for classification according to the customer's level of expertise. This allows for appropriate classification by adjusting the use of specialized terminology for classification according to the customer's level of expertise.

[0089] The exclusion unit can estimate the user's emotions and adjust the exclusion criteria based on the estimated user's emotions. The exclusion unit estimates the user's emotions using, for example, an emotion analysis algorithm. For example, if the exclusion unit estimates that the user has positive emotions, it does not exclude positive opinions. Furthermore, if the exclusion unit estimates that the user has neutral emotions, it can also appropriately exclude neutral opinions. Furthermore, if the exclusion unit estimates that the user has negative emotions, it can also carefully examine negative opinions and appropriately exclude them. In this way, the accuracy of exclusion can be improved by adjusting the exclusion criteria according to the user's emotions.

[0090] The exclusion unit can improve the accuracy of exclusion by taking into account the interrelationships between answers at the time of exclusion. For example, the exclusion unit improves the accuracy of exclusion by taking into account the interrelationships between answers at the time of exclusion. For example, the exclusion unit analyzes the interrelationships between answers and excludes answers with low relevance. The exclusion unit can also avoid excluding important opinions by taking into account the interrelationships between answers. Furthermore, the exclusion unit can improve the accuracy of exclusion based on the interrelationships between answers. In this way, it is possible to appropriately exclude answers with low relevance by taking into account the interrelationships between answers.

[0091] When excluding answers, the exclusion unit can perform the exclusion taking into consideration attribute information of the answer submitter. The exclusion unit performs the exclusion taking into consideration, for example, attribute information of the answer submitter. For example, the exclusion unit considers attribute information such as the submitter's age and gender to exclude answers that are biased toward a particular attribute. The exclusion unit can also exclude answers with low reliability based on the submitter's purchasing history and usage frequency. Furthermore, the exclusion unit can analyze the submitter's attribute information and appropriately exclude answers that are not related to employee evaluation. In this way, by considering the submitter's attribute information, answers that are biased toward a particular attribute can be appropriately excluded.

[0092] The exclusion unit can weight the exclusion based on the frequency of answer submission at the time of exclusion. The exclusion unit, for example, weights the exclusion based on the frequency of answer submission. For example, the exclusion unit preferentially considers and weights answers that are submitted more frequently. The exclusion unit can also appropriately exclude answers that are submitted less frequently to maintain overall balance. Furthermore, the exclusion unit can dynamically adjust the weighting of the exclusion based on the frequency of answer submission. In this way, by weighting the exclusion based on the frequency of answer submission, it is possible to maintain overall balance.

[0093] The excluding unit can estimate the user's emotions and adjust the display method of answers to be excluded based on the estimated user's emotions. The excluding unit estimates the user's emotions using, for example, an emotion analysis algorithm. For example, if the excluding unit estimates that the user has positive emotions, it can highlight and display positive opinions. Furthermore, if the excluding unit estimates that the user has neutral emotions, it can also appropriately display neutral opinions. Furthermore, if the excluding unit estimates that the user has negative emotions, it can also display negative opinions in detail. In this way, it is possible to provide appropriate feedback by adjusting the display method according to the user's emotions.

[0094] The exclusion unit can perform exclusion taking into consideration the geographic distribution of answers. The exclusion unit performs exclusion taking into consideration, for example, the geographic distribution of answers. For example, the exclusion unit excludes answers that are biased toward a specific region, thereby maintaining overall balance. The exclusion unit can also appropriately exclude answers that are geographically less relevant. Furthermore, the exclusion unit can analyze the geographic distribution of answers and improve the accuracy of exclusion. In this way, by taking into consideration the geographic distribution of answers, it is possible to maintain overall balance.

[0095] The exclusion unit can improve the accuracy of exclusion by referring to literature related to the answer at the time of exclusion. The exclusion unit can improve the accuracy of exclusion by, for example, referring to literature related to the answer. For example, the exclusion unit compares the content of the answer with related literature and excludes answers with low reliability. The exclusion unit can also refer to related literature to appropriately exclude answers that are not relevant to employee evaluation. Furthermore, the exclusion unit can improve the accuracy of exclusion based on literature related to the answer. In this way, by referring to related literature, it is possible to appropriately exclude answers with low reliability.

[0096] The exclusion unit can perform exclusion taking into consideration the market value of the answer when performing exclusion. The exclusion unit performs exclusion taking into consideration, for example, the market value of the answer. For example, the exclusion unit preferentially considers and weights answers with high market value. The exclusion unit can also appropriately exclude answers with low market value to maintain overall balance. Furthermore, the exclusion unit can dynamically adjust the weighting of exclusion based on the market value of the answer. This makes it possible to maintain overall balance by preferentially considering answers with high market value.

[0097] The score generation unit can estimate the user's emotions and adjust the score generation method based on the estimated user's emotions. The score generation unit estimates the user's emotions using, for example, an emotion analysis algorithm. For example, if the score generation unit estimates that the user has positive emotions, it generates a score that emphasizes positive opinions. Furthermore, if the score generation unit estimates that the user has neutral emotions, it can generate a score that appropriately reflects neutral opinions. Furthermore, if the score generation unit estimates that the user has negative emotions, it can generate a score that reflects negative opinions in detail. In this way, an appropriate score can be generated by adjusting the score generation method according to the user's emotions.

[0098] The score generation unit can improve the accuracy of the score by taking into account the interrelationships between answers when generating the score. For example, the score generation unit improves the accuracy of the score by taking into account the interrelationships between answers when generating the score. For example, the score generation unit analyzes the interrelationships between answers and generates a score by emphasizing highly relevant answers. The score generation unit can also generate a score by taking into account the interrelationships between answers and appropriately reflecting important opinions. Furthermore, the score generation unit can improve the accuracy of the score based on the interrelationships between answers. In this way, by taking into account the interrelationships between answers, it is possible to generate a score by emphasizing highly relevant answers.

[0099] When generating a score, the score generation unit can generate the score by taking into account the attribute information of the person who submitted the answer. The score generation unit generates the score by taking into account, for example, the attribute information of the person who submitted the answer. For example, the score generation unit takes into account attribute information such as the submitter's age and gender to avoid generating a score that is biased toward a particular attribute. The score generation unit can also generate a highly reliable score based on the submitter's purchasing history and usage frequency. Furthermore, the score generation unit can analyze the submitter's attribute information and generate a score by excluding elements that are not related to employee evaluation. In this way, by taking into account the submitter's attribute information, it is possible to avoid generating a score that is biased toward a particular attribute.

[0100] The score generation unit can weight the scores based on the frequency of answer submissions when generating the scores. For example, the score generation unit weights the scores based on the frequency of answer submissions when generating the scores. For example, the score generation unit preferentially considers and weights answers that are submitted more frequently. The score generation unit can also appropriately exclude answers that are submitted less frequently to maintain overall balance. Furthermore, the score generation unit can dynamically adjust the weighting of the scores based on the frequency of answer submissions. In this way, by weighting the scores based on the frequency of answer submissions, overall balance can be maintained.

[0101] The score generation unit can estimate the user's emotions and adjust the score display method based on the estimated user's emotions. The score generation unit estimates the user's emotions using, for example, an emotion analysis algorithm. For example, if the score generation unit estimates that the user has positive emotions, it can highlight and display positive opinions. Furthermore, if the score generation unit estimates that the user has neutral emotions, it can also appropriately display neutral opinions. Furthermore, if the score generation unit estimates that the user has negative emotions, it can also display negative opinions in detail. In this way, by adjusting the score display method according to the user's emotions, it is possible to provide appropriate feedback.

[0102] The score generation unit can generate scores taking into account the geographical distribution of answers when generating scores. For example, the score generation unit generates scores taking into account the geographical distribution of answers when generating scores. For example, the score generation unit generates a score that maintains overall balance by taking into account answers that are biased toward a specific region. The score generation unit can also generate a score by emphasizing answers that are highly geographically relevant. Furthermore, the score generation unit can analyze the geographical distribution of answers and improve the accuracy of the score. In this way, by taking into account the geographical distribution of answers, it is possible to generate a score that maintains overall balance.

[0103] The score generation unit can improve the accuracy of the score by referring to literature related to the answer when generating the score. For example, the score generation unit can improve the accuracy of the score by referring to literature related to the answer when generating the score. For example, the score generation unit can compare the content of the answer with the related literature to generate a highly reliable score. The score generation unit can also generate a score by referring to the related literature and excluding elements that are not relevant to employee evaluation. Furthermore, the score generation unit can improve the accuracy of the score based on literature related to the answer. In this way, by referring to the related literature, a highly reliable score can be generated.

[0104] The score generation unit can generate a score taking into account the market value of the answer when generating the score. For example, the score generation unit generates a score taking into account the market value of the answer when generating the score. For example, the score generation unit preferentially considers and weights answers with high market value. The score generation unit can also appropriately exclude answers with low market value to generate a score that maintains overall balance. Furthermore, the score generation unit can dynamically adjust the weighting of the score based on the market value of the answer. This makes it possible to generate a score that maintains overall balance by preferentially considering answers with high market value. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, classification unit, exclusion unit, and score generation unit, described above, is implemented, for example, in at least one of the smart device 14 and the data processing device 12. For example, the collection unit is implemented in at least one of the smart device 14 and the data processing device 12. For example, the collection unit can collect customer survey scores and reasons using the reception device 38 of the smart device 14. The classification unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and classifies free responses into positive, neutral, and negative using a generation AI. The exclusion unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and excludes responses unrelated to employee evaluation. The score generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates a total score by combining the scores and the positive, neutral, and negative scores of the reasons. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, classification unit, exclusion unit, and score generation unit, described above, is implemented, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit can collect customer survey scores and reasons using the microphone 238 of the smart glasses 214. The classification unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and classifies free responses into positive, neutral, and negative using a generation AI. The exclusion unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and excludes responses unrelated to employee evaluation. The score generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates a total score by combining the scores and the positive, neutral, and negative scores of the reasons. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, classification unit, exclusion unit, and score generation unit, described above, is implemented, for example, in at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit is implemented in at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit can collect customer survey scores and reasons using the microphone 238 of the headset terminal 314. The classification unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and classifies free responses into positive, neutral, and negative using a generation AI. The exclusion unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and excludes responses unrelated to employee evaluation. The score generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates a total score by combining the scores and the positive, neutral, and negative scores of the reasons. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, classification unit, exclusion unit, and score generation unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit is realized by at least one of the robot 414 and the data processing device 12. For example, the collection unit can collect customer survey scores and reasons using the microphone 238 of the robot 414. The classification unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and classifies free responses into positive, neutral, and negative using a generation AI. The exclusion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and excludes responses unrelated to employee evaluation. The score generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and automatically generates a total score by combining the scores and the positive, neutral, and negative scores of the reasons.

[0105] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0106] The rating system may further include a reliability evaluation unit that evaluates the reliability of the feedback. The reliability evaluation unit, for example, analyzes the customer's past response history and behavioral patterns to evaluate the reliability of the feedback. For example, if the customer has provided consistent ratings in the past, the reliability evaluation unit may rate the feedback highly. Also, if the customer has provided inconsistent ratings in the past, the reliability evaluation unit may rate the feedback low. Furthermore, the reliability evaluation unit may analyze the customer's behavioral patterns and prioritize highly reliable feedback. This allows for a more accurate evaluation by evaluating the reliability of the feedback.

[0107] The collection unit may further include a real-time collection function for collecting customer feedback in real time. For example, the collection unit may collect feedback in real time when a customer visits a store. The collection unit may also collect feedback in real time when a customer is shopping online. The collection unit may also collect feedback in real time when a customer participates in a specific event. This allows for faster response by collecting feedback in real time.

[0108] The classification unit may further include an emotional intensity evaluation function that evaluates the emotional intensity of the free responses. For example, the classification unit may extract parts of the free responses that show particularly strong emotions and evaluate their intensity. The classification unit may also further classify the free responses based on the emotional intensity. Furthermore, the classification unit may visually display the emotional intensity so that employees can intuitively understand the importance of the feedback. In this way, the importance of the feedback can be more accurately grasped by evaluating the emotional intensity.

[0109] The excluding unit may further include a context analysis function that takes into account the context of the answer to improve the accuracy of the excluding. For example, the excluding unit may analyze the context before and after the answer to exclude parts that are not relevant to the employee evaluation. The excluding unit may also evaluate the relevance of the answer based on the context analysis to appropriately extract important opinions. Furthermore, the excluding unit may use the context analysis to evaluate the consistency of the answer to exclude answers with low reliability. In this way, the accuracy of the excluding can be improved by taking the context into account.

[0110] The score generation unit may further include a trend analysis function that analyzes trends in customer feedback. For example, the score generation unit may analyze past feedback data to identify trends in customer ratings. The score generation unit may also adjust the score based on the trends to reflect the latest customer opinions. Furthermore, the score generation unit may use trend analysis to predict future ratings, which may be useful in improving employee performance. This allows for the generation of more accurate scores by analyzing trends.

[0111] The collection unit can further estimate the customer's emotions and customize the content of the feedback based on the estimated emotions. For example, if the collection unit estimates that the customer has positive emotions, it can send a questionnaire including questions that emphasize positive feedback. Alternatively, if the collection unit estimates that the customer has negative emotions, it can send a questionnaire including questions that request improvements. Furthermore, the collection unit can dynamically adjust the content of the questionnaire according to the customer's emotions to collect more appropriate feedback. This makes it possible to collect more useful information by customizing the content of the feedback based on the customer's emotions.

[0112] The collection unit may further include an anonymization function for anonymizing customer feedback. For example, the collection unit may anonymize customer personal information to protect privacy. The collection unit may also use the anonymized feedback to perform evaluations and eliminate bias. The collection unit may also analyze the anonymized feedback to identify overall trends. This allows for accurate evaluations while protecting customer privacy.

[0113] The collection unit can further estimate the customer's emotions and evaluate the importance of the feedback based on the estimated emotions. For example, if the collection unit estimates that the customer has strong emotions, it can highly evaluate the feedback. Alternatively, if the collection unit estimates that the customer has neutral emotions, it can appropriately evaluate the feedback. Furthermore, the collection unit can dynamically adjust the importance of the feedback based on the customer's emotions and prioritize important opinions. In this way, by evaluating the importance of feedback based on the customer's emotions, more useful information can be collected.

[0114] The collection unit may further include a translation function that automatically translates customer feedback. For example, the collection unit may automatically translate feedback provided in different languages ​​and provide a rating in a unified format. The collection unit may also use the translated feedback to provide a multilingual rating. Furthermore, the collection unit may use the translation function to collect feedback from international customers and provide a rating from a global perspective. This allows for a unified rating of feedback provided in different languages.

[0115] The collection unit can further estimate the customer's emotions and adjust the display method of the feedback based on the estimated emotions. For example, if the collection unit estimates that the customer has positive emotions, it can highlight and display positive opinions. Also, if the collection unit estimates that the customer has neutral emotions, it can appropriately display neutral opinions. Furthermore, if the collection unit estimates that the customer has negative emotions, it can display negative opinions in detail. In this way, by adjusting the display method of the feedback according to the customer's emotions, it is possible to provide appropriate feedback.

[0116] The processing flow of the second embodiment will be briefly explained below.

[0117] Step 1: The collection unit collects customer survey scores and reasons. For example, the collection unit can collect scores and reasons using an online survey or a paper-based survey. The collection unit can also collect free responses using voice input or text input. Step 2: The classification unit uses the generation AI to classify the free responses as positive, neutral, or negative. For example, the generation AI analyzes the free responses using natural language processing technology and classifies them as positive, neutral, or negative using a sentiment analysis algorithm. For example, the generation AI classifies a response such as "The customer service was good, so I'd give it an 8" as positive, and a response such as "The store's location was bad, so I'd give it a 5" as negative. Step 3: The exclusion unit filters out responses that are not relevant to employee evaluations. For example, the exclusion unit filters out responses that are not relevant to employee evaluations based on the presence or absence of specific keywords or the relevance of the content. For example, a response such as "The store's location is bad, so it gets a score of 5" is filtered out because it is unrelated to employee customer service. Step 4: The score generator automatically generates a total score by combining the points and the positive, neutral, and negative scores of the reasons. For example, the score generator may use a sentiment analysis algorithm to calculate each score and generate a total score.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0121] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0122] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0123] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0138] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0139] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0145] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0146] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0147] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0148] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0149] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0150] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0154] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0155] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0156] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0157] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0158] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0159] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0160] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0161] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0162] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0163] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0164] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0165] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0166] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0167] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0168] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0169] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0170] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0171] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0172] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0173] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0174] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0175] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0176] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0177] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0178] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0179] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0180] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0181] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0182] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0183] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0184] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0185] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0186] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0187] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0188] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0189] [Explanation of symbols]

[0190] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects customer survey scores and reasons; a classification unit that classifies the free responses collected by the collection unit using a generation AI; an exclusion unit that excludes responses that are not related to employee evaluation from the free responses classified by the classification unit; a score generation unit that automatically generates a total score by combining the scores of the free responses that were not excluded by the exclusion unit and the positive, neutral, and negative scores of the reasons. A system characterized by:

2. The collecting unit Collect customer survey scores and reasons 2. The system of claim 1.

3. The classification unit Using generative AI to categorize free responses as positive, neutral, or negative 2. The system of claim 1.

4. The exclusion section is Filter out responses that are not relevant to employee evaluations 2. The system of claim 1.

5. The score generation unit Automatically generate an overall score by combining the points and the positive, neutral, and negative reasons.

2. The system of claim 1.

6. The collecting unit Estimate user emotions and adjust the timing of survey collection based on the estimated user emotions 2. The system of claim 1.

7. The collecting unit Analyze customers' past survey response history and select the appropriate collection method 2. The system of claim 1.

8. The collecting unit When collecting surveys, filter them based on customers' current purchasing history and interests.

2. The system of claim 1.

Images