system

Abstract

The system according to this embodiment aims to appropriately feed accurate opinions from the field back to management. [Solution] The system according to the embodiment comprises a reception unit, a filtering unit, an aggregation unit, and a feedback unit. The reception unit anonymously receives opinions from employees. The filtering unit filters the opinions received by the reception unit, removing extreme or low-level opinions. The aggregation unit aggregates the opinions filtered by the filtering unit. The feedback unit provides feedback to management based on the opinions aggregated by the aggregation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there was a problem that the correct opinions on-site in a large organization did not reach the management level.

[0005] The system according to the embodiment aims to appropriately feedback the correct opinions on-site to the management level.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a filtering unit, an aggregation unit, and a feedback unit. The reception unit anonymously receives opinions from employees. The filtering unit filters the opinions received by the reception unit, removing extreme or low-quality opinions. The aggregation unit aggregates the opinions filtered by the filtering unit. The feedback unit provides feedback to management based on the opinions aggregated by the aggregation unit. [Effects of the Invention]

[0007] The system according to this embodiment can appropriately feed accurate opinions from the field to management. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The opinion aggregation system according to an embodiment of the present invention is a system that utilizes generative AI to aggregate correct opinions within a large organization and provide appropriate feedback to management. In the opinion aggregation system, employees post opinions anonymously, and the generative AI filters the posted opinions, removing extreme or low-quality opinions. Furthermore, the generative AI aggregates the filtered opinions and provides appropriate and unbiased feedback to management. This mechanism promotes organizational health and improves employee engagement. For example, employees post opinions anonymously. In this case, employees can post their opinions freely. For example, suggestions for improving work processes or opinions on the workplace environment may be posted. This information is input into the generative AI. Next, the generative AI filters the posted opinions. The generative AI removes extreme or low-quality opinions. For example, abusive language, complaints about salary, and harassment of specific individuals are removed. As a result, only appropriate opinions are fed back to management. Furthermore, the generative AI aggregates the filtered opinions. The generating AI categorizes and classifies opinions, aggregating them while preserving the essence of the qualitative opinions. For example, opinions on business process improvement and opinions on the work environment are aggregated. The aggregated opinions are then quantified in order of frequency (impact). Finally, the generating AI provides feedback on the aggregated opinions to management. To ensure that management responds positively and emotionally, the generating AI transforms the feedback wording into "gentle and polite" language, preserving the essence of the opinions from the field while avoiding hurting the feelings of management. For example, suggestions for business process improvement are fed back to management in a positive way. This system promotes organizational health. Not only complaints from the field, but also appropriate opinions reach management. Furthermore, improved engagement can be expected. By allowing all employees to see the aggregated results, trust in the company increases. For example, employees feel that their opinions are reaching management, which increases their trust in the company. In this way, the opinion aggregation system can automatically aggregate employee opinions and provide appropriate feedback to management.

[0029] The opinion aggregation system according to this embodiment comprises a reception unit, a filtering unit, an aggregation unit, and a feedback unit. The reception unit anonymously receives opinions from employees. Opinions from employees include, but are not limited to, suggestions for business improvement or opinions on the work environment. The reception unit provides, for example, an interface that allows employees to post opinions anonymously. The reception unit may also use anonymization technology to hide employees' personal information. For example, the reception unit hides the employee's name and department and accepts only the opinion. The filtering unit filters the opinions received by the reception unit, removing extreme or low-quality opinions. The filtering unit uses, for example, a generation AI to remove opinions such as abusive language, complaints about salary, or harassment of specific individuals. For example, the filtering unit uses a generation AI to analyze the content of the opinions and remove opinions containing extreme expressions or offensive language. The filtering unit can also use a generation AI to evaluate the content of the opinions and remove unconstructive or unclear opinions. For example, the filtering unit uses a generating AI to evaluate the importance and specificity of opinions and remove low-level opinions. The aggregation unit aggregates the opinions filtered by the filtering unit. The aggregation unit categorizes, classifies, and quantifies the opinions, for example, using a generating AI. For example, the aggregation unit uses a generating AI to analyze the content of the opinions and classify them into opinions related to business improvement, opinions related to the workplace environment, etc. The aggregation unit can also use a generating AI to quantify opinions in order of frequency (impact). For example, the aggregation unit uses a generating AI to evaluate and quantify the number and importance of opinions. The feedback unit provides feedback to management based on the opinions aggregated by the aggregation unit. The feedback unit uses a generating AI to convert the feedback wording into "gentle and polite" language. For example, the feedback unit uses a generating AI to analyze the content of the opinions and convert the feedback wording so as not to hurt the feelings of management. The feedback unit can also use a generating AI to convert the feedback wording so that management can respond emotionally in a positive way. For example, the feedback unit uses a generating AI to provide feedback in a positive way while retaining the essence of the opinion.This enables the opinion aggregation system according to the embodiment to efficiently filter, aggregate, and provide feedback on opinions from employees.

[0030] The reception desk accepts employee feedback anonymously. This feedback may include, but is not limited to, suggestions for business improvements or opinions on the work environment. The reception desk provides an interface that allows employees to submit feedback anonymously. Specifically, it may enable employees to easily submit feedback through web-based forms or mobile applications. This allows employees to express their opinions freely, knowing their privacy is protected. The reception desk can also employ anonymization technologies to conceal employee personal information. For example, it may hide employee names and departments, accepting only feedback. Specifically, it may use algorithms that automatically remove or mask employee personal information when feedback is submitted. This protects employee privacy and allows for focus on the content of the feedback. Furthermore, the reception desk simplifies the feedback submission process, enabling employees to submit feedback quickly. For example, it may provide a dropdown menu for selecting a feedback category or a text box for entering feedback content, allowing employees to submit feedback quickly. This enables the reception desk to efficiently collect employee feedback and enhance the overall system's effectiveness.

[0031] The filtering unit filters the opinions received by the reception unit, removing extreme or low-quality opinions. For example, the filtering unit uses generative AI to remove opinions such as abusive language, complaints about salary, and harassment of specific individuals. Specifically, the generative AI uses natural language processing technology to analyze the content of opinions and detect aggressive expressions and inappropriate words. For example, the generative AI tokenizes the text of an opinion and calculates a sentiment score for each token to identify aggressive opinions. The filtering unit can also have the generative AI evaluate the content of opinions and remove unconstructive or unclear opinions. For example, the generative AI uses algorithms to evaluate the specificity and importance of opinions to remove vague expressions or opinions that do not contain concrete suggestions. Furthermore, the filtering unit can classify the content of opinions by category and prioritize processing opinions belonging to specific categories. For example, it can prioritize processing opinions related to business improvement or the work environment, and postpone other opinions. In this way, the filtering unit can efficiently filter employee opinions and improve the overall quality of the system.

[0032] The aggregation unit consolidates the opinions filtered by the filtering unit. The aggregation unit categorizes, classifies, and quantifies the opinions, for example, using a generative AI. Specifically, the generative AI uses a clustering algorithm to group similar opinions and assigns labels to each group. For example, the generative AI analyzes the content of the opinions and classifies them into categories such as opinions on business improvement or opinions on the workplace environment. The aggregation unit can also use the generative AI to quantify the opinions in order of frequency (impact). For example, the generative AI evaluates and quantifies the number and importance of each opinion. Specifically, it calculates the frequency and importance score of each opinion, quantifying the impact of each opinion. Furthermore, the aggregation unit visualizes the content of the opinions to make them easily understandable to management. For example, it generates pie charts showing the proportion of each opinion category or bar graphs sorted by importance. This allows the aggregation unit to efficiently consolidate the filtered opinions and present them clearly to management.

[0033] The Feedback Department provides feedback to management based on the opinions aggregated by the Aggregation Department. The Feedback Department uses, for example, generative AI to transform feedback into "gentle and polite" language. Specifically, the generative AI uses natural language generation technology to analyze the content of the opinions and transform the feedback into language that does not offend management. For example, the generative AI transforms the opinions into language that includes positive expressions and constructive suggestions while retaining the essence of the opinions. The Feedback Department can also transform feedback into language that allows the generative AI to respond to management in an emotionally positive manner. For example, the generative AI expresses the content of the opinions in a positive tone, making them more readily accepted by management. Furthermore, the Feedback Department visually highlights the feedback to ensure that management does not overlook important opinions. For example, important opinions and suggestions are displayed in bold or colored text. This allows the Feedback Department to effectively provide feedback to management based on the aggregated opinions, ensuring that employee opinions are appropriately reflected.

[0034] The aggregation unit can categorize, classify, and quantify opinions. For example, the aggregation unit uses generative AI to analyze the content of opinions and classify them into opinions related to business improvement, opinions related to the workplace environment, etc. For example, the aggregation unit uses generative AI to analyze the content of opinions and extract relevant keywords and phrases. The aggregation unit can also use generative AI to quantify opinions in order of frequency (impact). For example, the aggregation unit uses generative AI to evaluate and quantify the number and importance of opinions. This makes it easier to organize opinions by categorizing, classifying, and quantifying them. Categorization and classification are performed, for example, by methods such as classification or tagging based on the content of the opinions. Quantification is performed, for example, based on numerical criteria or scoring methods. Some or all of the above processing in the aggregation unit may be performed using generative AI, or it may be performed without generative AI. For example, the aggregation unit can analyze the content of opinions and have generative AI perform categorization, classification, and quantification.

[0035] The feedback unit can convert feedback into "gentle and polite" language. For example, the feedback unit uses a generative AI to convert feedback into "gentle and polite" language. For instance, the generative AI analyzes the content of the opinion and converts the feedback into language that does not offend management. The feedback unit can also convert feedback into language that allows the generative AI to respond to management in a positive and emotionally positive manner. For example, the generative AI preserves the essence of the opinion while providing feedback in a positive way. This ensures that management is not offended by converting feedback into "gentle and polite" language. Gentle and polite language is based on criteria such as the use of honorifics and positive expressions. Some or all of the above-described processes in the feedback unit may be performed using a generative AI, or they may not. For example, the feedback unit can analyze the content of the opinion and have the generative AI perform the conversion of the feedback into language.

[0036] The filtering unit can remove opinions such as abusive language, complaints about wages, and harassment of specific individuals. For example, the filtering unit uses a generation AI to remove such opinions. For instance, the generation AI analyzes the content of opinions and removes those containing extreme or offensive language. The filtering unit can also use the generation AI to evaluate the content of opinions and remove unconstructive or unclear opinions. For example, the generation AI evaluates the importance and specificity of opinions and removes low-level opinions. This ensures that only appropriate opinions are fed back by removing abusive language, complaints about wages, and harassment of specific individuals. Abusive language is removed based on criteria such as insulting words and offensive expressions. Complaints about wages are removed based on criteria such as dissatisfaction with low wages or demands for raises. Harassment of specific individuals is removed based on criteria such as personal attacks and accusations by name. Some or all of the above processing in the filtering unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the filtering unit can analyze the content of the opinions and have the generating AI remove opinions such as abusive language, complaints about salary, and harassment of specific individuals.

[0037] The aggregation unit can aggregate opinions to the extent that the essence of the qualitative opinions is not lost. For example, the aggregation unit uses a generative AI to analyze the content of the opinions and aggregate them to the extent that the essence of the qualitative opinions is not lost. For example, the aggregation unit uses a generative AI to extract the core parts and important points of the opinions and aggregates the opinions based on them. In this way, the aggregation can be performed while preserving the essence of the opinions by aggregating them to the extent that the essence of the qualitative opinions is not lost. The essence of the qualitative opinions refers to, for example, the core parts and important points of the opinions. Some or all of the above processing in the aggregation unit may be performed using a generative AI or not. For example, the aggregation unit can have a generative AI perform the processing of analyzing the content of the opinions and aggregating them to the extent that the essence of the qualitative opinions is not lost.

[0038] The feedback unit can transform feedback wording to ensure a positive emotional response to management. For example, the feedback unit uses generative AI to transform feedback wording to ensure a positive emotional response to management. For instance, the feedback unit uses generative AI to analyze the content of the opinion and transform the feedback wording so as not to offend management. The feedback unit can also use generative AI to preserve the essence of the opinion while providing positive feedback. For example, the feedback unit uses generative AI to transform the content of the opinion into positive language and communicate it to management. This transforms the feedback wording to ensure a positive emotional response to management, thus preventing them from being hurt. A positive emotional response is based on criteria such as positive feedback and words of encouragement. Some or all of the above processing in the feedback unit may be performed using generative AI, or without it. For example, the feedback unit can analyze the content of the opinion and have the generative AI perform the transformation of the feedback wording.

[0039] The reception department can analyze an employee's past feedback submission history and select the most suitable method of receiving feedback. For example, the reception department might use AI to analyze an employee's past feedback submission history. For instance, the AI ​​might analyze the employee's feedback submission history and provide a simple interface to employees who frequently submit feedback. The reception department could also provide detailed guidance to employees who have never submitted feedback before. For example, the AI ​​might use the employee's feedback submission history to adjust the reception process for employees who tend to submit feedback during specific time slots. This allows the reception department to select the most suitable method of receiving feedback by analyzing an employee's past feedback submission history. The optimal method might be selected based on criteria such as online forms or direct interaction. Some or all of the above processes in the reception department may be performed using AI or not. For example, the reception department could have AI analyze an employee's feedback submission history and select the most suitable method of receiving feedback.

[0040] The reception department can filter opinions based on the employee's current projects and areas of interest when receiving them. For example, the reception department can use AI to identify an employee's current projects and areas of interest. For instance, the reception department can use AI to analyze project management tools and survey results to identify an employee's current projects and areas of interest. The reception department can also use AI to prioritize receiving opinions that are highly relevant based on the employee's current projects and areas of interest. For example, the reception department can use AI to prioritize receiving opinions related to the current project. The reception department can also use AI to prioritize receiving opinions related to the employee's areas of interest. For example, the reception department can use AI to filter out less relevant opinions based on the employee's current projects and areas of interest. This allows for the priority of receiving highly relevant opinions by filtering based on the employee's current projects and areas of interest. Current projects and areas of interest are identified, for example, using project management tools or survey results. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can identify an employee's current projects and areas of interest and have AI perform the filtering.

[0041] The reception desk can prioritize receiving opinions that are highly relevant, taking into account the geographical location of the employees. For example, the reception desk can use AI to obtain employees' geographical location information. For instance, the reception desk can use AI to analyze GPS data or IP addresses to identify employees' geographical locations. Furthermore, the reception desk can use AI to prioritize receiving opinions that are highly relevant based on the employees' geographical location information. For example, the reception desk can use AI to prioritize opinions from employees in the same office. Alternatively, the reception desk can use AI to prioritize opinions from project teams that are geographically close. For example, the reception desk can use AI to postpone opinions from employees who are geographically far away. This allows for the prioritization of highly relevant opinions, taking into account the employees' geographical location information. Geographical location information is obtained, for example, using GPS data or IP addresses. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can obtain employees' geographical location information and have AI perform the task of receiving highly relevant opinions.

[0042] The reception department can analyze employees' social media activity when receiving feedback and accept relevant feedback. For example, the reception department can use AI to analyze employees' social media activity. For instance, the AI ​​can analyze the content of employees' social media posts and the number of likes to identify relevant social media activity. The reception department can also use AI to prioritize receiving relevant feedback based on employees' social media activity. For example, the AI ​​can prioritize feedback from employees with active social media activity. The reception department can also use AI to prioritize receiving relevant feedback based on the content of social media activity. For example, the AI ​​can postpone feedback from employees with low social media activity. This allows for prioritizing the receipt of relevant feedback by analyzing employees' social media activity. Social media activity is analyzed using, for example, the content of posts and the number of likes. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can have AI analyze employees' social media activity and receive relevant feedback.

[0043] The filtering unit can improve the accuracy of filtering by considering the interrelationships between opinions. For example, the filtering unit may use a generative AI to consider the interrelationships between opinions. For example, the filtering unit may have the generative AI analyze the content of opinions and evaluate contradictions and agreements with other opinions. The filtering unit may also have the generative AI evaluate complementary relationships between opinions. For example, if the content of an opinion contradicts other opinions, the filtering unit will filter that opinion. The filtering unit may also have the generative AI prioritize retaining opinions whose content is consistent with other opinions. For example, if the generative AI finds an opinion to be complementary to other opinions, the filtering unit will retain that opinion. This improves the accuracy of filtering by considering the interrelationships between opinions. The interrelationships between opinions may be considered using, for example, a co-occurrence network or relevance score. Some or all of the above processing in the filtering unit may be performed using a generative AI or without a generative AI. For example, the filtering unit may have the generative AI consider the interrelationships between opinions and improve the accuracy of filtering.

[0044] The filtering unit can perform filtering while considering the attribute information of the opinion submitter. For example, the filtering unit uses a generative AI to identify the attribute information of the opinion submitter. For example, the filtering unit uses a generative AI to analyze attribute information such as the submitter's job title, department, and years of service. The filtering unit can also use a generative AI to evaluate the importance, relevance, and reliability of opinions based on the submitter's attribute information. For example, the filtering unit can use a generative AI to determine the importance of an opinion based on the submitter's job title. The filtering unit can also use a generative AI to determine the relevance of an opinion based on the submitter's department. For example, the filtering unit can use a generative AI to determine the reliability of an opinion based on the submitter's years of service. This allows for appropriate filtering by considering the attribute information of the opinion submitter. The submitter's attribute information is identified based on content such as age, job title, and department. Some or all of the above processing in the filtering unit may be performed using a generative AI or not. For example, the filtering unit can identify the attribute information of the opinion submitter and have the generative AI perform the filtering.

[0045] The filtering unit can perform filtering while considering the geographical distribution of opinions. For example, the filtering unit can use a generative AI to identify the geographical distribution of opinions. For example, the filtering unit can use a generative AI to analyze the location and region where opinions are submitted and identify the geographical distribution. The filtering unit can also have the generative AI prioritize retaining opinions that are highly relevant based on the geographical distribution of opinions. For example, the filtering unit can have the generative AI prioritize retaining opinions that are geographically close. The filtering unit can also have the generative AI postpone opinions that are geographically distant. For example, the filtering unit can have the generative AI determine the relevance of opinions based on their geographical distribution. This allows for prioritizing the retention of highly relevant opinions by considering the geographical distribution of opinions. Geographical distribution may be considered using, for example, the number of opinions by region or geographical bias. Some or all of the above processing in the filtering unit may be performed using a generative AI or not. For example, the filtering unit can identify the geographical distribution of opinions and have the generative AI perform the filtering.

[0046] The filtering unit can improve the accuracy of filtering by referring to relevant literature for opinions during the filtering process. For example, the filtering unit may use a generative AI to refer to relevant literature for opinions. For instance, the generative AI may analyze relevant literature such as academic papers and industry reports to evaluate the reliability and importance of opinions. The filtering unit can also have the generative AI determine the relevance of opinions based on the relevant literature. For example, the filtering unit may have the generative AI determine the reliability of opinions based on the relevant literature. The filtering unit can also have the generative AI determine the importance of opinions based on the relevant literature. For example, the filtering unit may have the generative AI determine the relevance of opinions based on the relevant literature. This improves the accuracy of filtering by referring to relevant literature for opinions. Relevant literature may be referenced using, for example, academic papers and industry reports. Some or all of the above processing in the filtering unit may be performed using a generative AI, or not. For example, the filtering unit can refer to relevant literature for opinions and have the generative AI perform the filtering accuracy improvement.

[0047] The aggregation unit can improve the accuracy of aggregation by considering the interrelationships between opinions during aggregation. For example, the aggregation unit may use a generative AI to consider the interrelationships between opinions. For example, the generative AI may analyze the content of opinions and evaluate contradictions and agreements with other opinions. The aggregation unit may also have the generative AI evaluate complementary relationships between opinions. For example, if the generative AI finds that an opinion contradicts another opinion, the aggregation unit will carefully aggregate that opinion. The aggregation unit may also prioritize the aggregation of opinions where the content is consistent with other opinions. For example, if the generative AI finds that an opinion is complementary to another opinion, the aggregation unit will aggregate that opinion. This improves the accuracy of aggregation by considering the interrelationships between opinions. The accuracy of aggregation can be improved using, for example, accuracy evaluation criteria or improvement methods. Some or all of the above-described processes in the aggregation unit may be performed using a generative AI or not. For example, the aggregation unit may consider the interrelationships between opinions and have the generative AI perform the task of improving the accuracy of aggregation.

[0048] The aggregation unit can perform aggregation while considering the attribute information of the opinion submitters. For example, the aggregation unit can use a generative AI to identify the attribute information of opinion submitters. For example, the aggregation unit can use a generative AI to analyze attribute information such as the submitter's job title, department, and years of service. The aggregation unit can also use a generative AI to evaluate the importance, relevance, and reliability of opinions based on the submitter's attribute information. For example, the aggregation unit can use a generative AI to determine the importance of an opinion based on the submitter's job title. The aggregation unit can also use a generative AI to determine the relevance of an opinion based on the submitter's department. For example, the aggregation unit can use a generative AI to determine the reliability of an opinion based on the submitter's years of service. This allows for appropriate aggregation by considering the attribute information of the opinion submitters. The submitter's attribute information is identified based on content such as age, job title, and department. Some or all of the above processing in the aggregation unit may be performed using a generative AI or not. For example, the aggregation unit can identify the attribute information of opinion submitters and have a generative AI perform the aggregation.

[0049] The aggregation unit can perform aggregation while considering the geographical distribution of opinions. For example, the aggregation unit can use a generative AI to identify the geographical distribution of opinions. For example, the aggregation unit can use a generative AI to analyze the location and region where opinions were submitted and identify the geographical distribution. The aggregation unit can also use a generative AI to prioritize the aggregation of highly relevant opinions based on the geographical distribution of opinions. For example, the aggregation unit can use a generative AI to prioritize the aggregation of opinions that are geographically close. The aggregation unit can also use a generative AI to postpone the aggregation of opinions that are geographically distant. For example, the aggregation unit can use a generative AI to determine the relevance of opinions based on their geographical distribution. This allows for the prioritization of the aggregation of highly relevant opinions by considering the geographical distribution of opinions. The geographical distribution may be considered using, for example, the number of opinions by region or geographical bias. Some or all of the above processing in the aggregation unit may be performed using a generative AI or not. For example, the aggregation unit can identify the geographical distribution of opinions and have a generative AI perform the aggregation.

[0050] The aggregation unit can improve the accuracy of aggregation by referring to relevant literature for the opinions during the aggregation process. For example, the aggregation unit may use a generative AI to refer to relevant literature for the opinions. For example, the generative AI may analyze relevant literature such as academic papers and industry reports and evaluate the reliability and importance of the opinions. The aggregation unit may also have the generative AI determine the relevance of the opinions based on the relevant literature. For example, the aggregation unit may have the generative AI determine the reliability of the opinions based on the relevant literature. The aggregation unit may also have the generative AI determine the importance of the opinions based on the relevant literature. For example, the aggregation unit may have the generative AI determine the relevance of the opinions based on the relevant literature. This improves the accuracy of aggregation by referring to relevant literature for the opinions. Relevant literature may be referred to using academic papers and industry reports, for example. Some or all of the above processing in the aggregation unit may be performed using a generative AI or not. For example, the aggregation unit may refer to relevant literature for the opinions and have the generative AI perform the task of improving the accuracy of aggregation.

[0051] The feedback unit can adjust the level of detail in feedback based on the importance of the opinion. For example, the feedback unit may use a generative AI to evaluate the importance of an opinion. For instance, the generative AI analyzes the content of the opinion and calculates an importance score. The feedback unit can also have the generative AI adjust the level of detail in the feedback based on the importance of the opinion. For example, the feedback unit provides detailed feedback for important opinions, and concise feedback for less important opinions. For example, the feedback unit adjusts the content of the feedback according to the importance of the opinion. This allows for appropriate feedback by adjusting the level of detail based on the importance of the opinion. The importance of an opinion may be evaluated based on criteria such as impact score or urgency. Some or all of the above processing in the feedback unit may be performed using a generative AI, or without one. For example, the feedback unit can evaluate the importance of an opinion and have the generative AI adjust the level of detail in the feedback.

[0052] The feedback unit can apply different feedback algorithms depending on the category of the opinion during the feedback process. For example, the feedback unit can use generative AI to identify the category of the opinion. For instance, the generative AI analyzes the content of the opinion and identifies categories such as opinions on business improvement or opinions on the work environment. Furthermore, the feedback unit can have the generative AI apply different feedback algorithms depending on the opinion category. For example, for opinions on business improvement, the feedback unit can provide feedback suggesting specific improvement measures. For opinions on the work environment, the feedback unit can also provide feedback suggesting specific actions for improving the environment. For example, for opinions on interpersonal relationships, the feedback unit can provide feedback offering specific advice for improving communication. This allows for appropriate feedback by applying different feedback algorithms depending on the opinion category. The feedback algorithms are applied based on types such as machine learning algorithms or rule-based algorithms. Some or all of the above-described processes in the feedback unit may be performed using generative AI, or they may not. For example, the feedback unit can identify the category of the opinion and have the generative AI apply the feedback algorithm.

[0053] The feedback unit can prioritize feedback based on when the feedback was submitted. For example, the feedback unit can use a generative AI to identify the submission date. For instance, the generative AI analyzes the submission date and time to determine the submission period. The feedback unit can also use the generative AI to prioritize feedback based on the submission date. For example, the feedback unit prioritizes recently submitted feedback. It can also postpone older feedback. For example, the feedback unit adjusts the feedback priority based on the submission date. This allows for appropriate feedback by prioritizing feedback based on the submission date. The submission date is identified based on criteria such as the submission date and time. Some or all of the above processing in the feedback unit may be performed using a generative AI, or not. For example, the feedback unit can have the generative AI identify the submission date and determine the feedback priority.

[0054] The feedback unit can adjust the order of feedback based on the relevance of the opinions during the feedback process. The feedback unit can, for example, use a generative AI to evaluate the relevance of opinions. For example, the generative AI analyzes the content of the opinions and calculates a relevance score. The feedback unit can also have the generative AI adjust the order of feedback based on the relevance of the opinions. For example, the feedback unit prioritizes feedback on highly relevant opinions. The feedback unit can also postpone feedback on less relevant opinions. For example, the feedback unit adjusts the order of feedback based on the relevance of the opinions. This allows feedback to be given in an appropriate order by adjusting the order of feedback based on the relevance of the opinions. The relevance of opinions is evaluated based on criteria such as similarity of content or common themes. Some or all of the above processing in the feedback unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the feedback unit can evaluate the relevance of opinions and have the generative AI perform the adjustment of the feedback order.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The opinion aggregation system can further filter opinions by considering the attribute information of the opinion submitters. For example, the filtering unit can analyze attribute information such as employee job title, department, and years of service, and evaluate the importance and relevance of opinions based on that information. For instance, opinions from employees with high job titles may be judged as highly important and given priority in feedback. Opinions from specific departments may be treated as issues related to that department and judged as highly relevant. Furthermore, opinions from employees with long years of service may be judged as highly reliable and given more importance. In this way, more appropriate filtering can be performed by considering the attribute information of the opinion submitters.

[0057] The opinion aggregation system can further consider the geographical distribution of opinions during aggregation. For example, the aggregation unit can analyze the location and region where employee opinions are submitted and aggregate them based on that geographical distribution. For instance, opinions from the same office or region are treated as common issues and aggregated preferentially. Opinions from geographically close project teams are deemed highly relevant and aggregated preferentially. Furthermore, opinions from geographically distant employees may be given lower priority. In this way, by considering the geographical distribution of opinions, highly relevant opinions can be aggregated preferentially.

[0058] The opinion aggregation system can further improve the accuracy of filtering by referring to relevant literature for each opinion. For example, the filtering unit can analyze relevant literature such as academic papers and industry reports and evaluate the reliability and importance of opinions based on that information. For instance, it can determine the reliability of an opinion based on relevant literature and remove opinions with low reliability. It can also determine the importance of an opinion based on relevant literature and prioritize feedback for opinions with high importance. Furthermore, it can determine the relevance of an opinion based on relevant literature and remove opinions with low relevance. In this way, the accuracy of filtering is improved by referring to relevant literature for each opinion.

[0059] The opinion aggregation system can further prioritize feedback based on when opinions are submitted. For example, the feedback department can analyze the submission date and time of opinions and prioritize feedback based on that information. For instance, recently submitted opinions will be given priority feedback, while older opinions will be given lower priority. Also, opinions submitted at a specific time can be treated as issues relevant to that time and given priority feedback. Furthermore, the importance of opinions can be evaluated based on the submission date, and opinions with high importance can be given priority feedback. In this way, appropriate feedback can be provided by prioritizing feedback based on when opinions are submitted.

[0060] The opinion aggregation system can further analyze the social media activity of those submitting opinions and accept relevant opinions. For example, the reception department can analyze the content of employees' social media posts and the number of likes they receive, and evaluate the relevance of opinions based on that information. For instance, opinions from employees who are active on social media will be deemed highly relevant and will be accepted preferentially. Opinions with high relevance can also be accepted preferentially based on the content of social media activity. Furthermore, opinions from employees with low social media activity may be given lower priority. In this way, by analyzing employees' social media activity, relevant opinions can be accepted preferentially.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The reception desk receives anonymous feedback from employees. This feedback may include suggestions for improving operations and opinions on the work environment. The reception desk provides an interface that allows employees to submit feedback anonymously and can use anonymization technology to hide employees' personal information. For example, it can hide the employee's name and department, and only accept the feedback. Step 2: The filtering unit filters the opinions received by the reception unit, removing extreme or low-quality opinions. The filtering unit uses a generation AI to remove opinions containing abusive language, complaints about salary, or harassment of specific individuals. The generation AI analyzes the content of the opinions and removes those containing extreme or aggressive language. The generation AI can also evaluate the content of the opinions and remove unconstructive or unclear opinions. The generation AI evaluates the importance and specificity of the opinions and removes low-quality opinions. Step 3: The aggregation unit aggregates the opinions filtered by the filtering unit. The aggregation unit uses a generation AI to categorize, classify, and quantify the opinions. The generation AI analyzes the content of the opinions and classifies them into opinions related to business improvement, opinions related to the workplace environment, etc. The generation AI can also quantify the opinions in order of frequency (impact). The generation AI evaluates and quantifies the number and importance of the opinions. Step 4: The Feedback Department provides feedback to management based on the opinions compiled by the Aggregation Department. The Feedback Department uses a Generative AI to transform the feedback into "gentle and polite" language. The Generative AI analyzes the content of the opinions and transforms the feedback into language that does not hurt the feelings of management. The Generative AI can also transform the feedback into language that allows management to respond emotionally in a positive way. The Generative AI provides feedback in a positive way while retaining the essence of the opinions.

[0063] (Example of form 2) The opinion aggregation system according to an embodiment of the present invention is a system that utilizes generative AI to aggregate correct opinions within a large organization and provide appropriate feedback to management. In the opinion aggregation system, employees post opinions anonymously, and the generative AI filters the posted opinions, removing extreme or low-quality opinions. Furthermore, the generative AI aggregates the filtered opinions and provides appropriate and unbiased feedback to management. This mechanism promotes organizational health and improves employee engagement. For example, employees post opinions anonymously. In this case, employees can post their opinions freely. For example, suggestions for improving work processes or opinions on the workplace environment may be posted. This information is input into the generative AI. Next, the generative AI filters the posted opinions. The generative AI removes extreme or low-quality opinions. For example, abusive language, complaints about salary, and harassment of specific individuals are removed. As a result, only appropriate opinions are fed back to management. Furthermore, the generative AI aggregates the filtered opinions. The generating AI categorizes and classifies opinions, aggregating them while preserving the essence of the qualitative opinions. For example, opinions on business process improvement and opinions on the work environment are aggregated. The aggregated opinions are then quantified in order of frequency (impact). Finally, the generating AI provides feedback on the aggregated opinions to management. To ensure that management responds positively and emotionally, the generating AI transforms the feedback wording into "gentle and polite" language, preserving the essence of the opinions from the field while avoiding hurting the feelings of management. For example, suggestions for business process improvement are fed back to management in a positive way. This system promotes organizational health. Not only complaints from the field, but also appropriate opinions reach management. Furthermore, improved engagement can be expected. By allowing all employees to see the aggregated results, trust in the company increases. For example, employees feel that their opinions are reaching management, which increases their trust in the company. In this way, the opinion aggregation system can automatically aggregate employee opinions and provide appropriate feedback to management.

[0064] The opinion aggregation system according to this embodiment comprises a reception unit, a filtering unit, an aggregation unit, and a feedback unit. The reception unit anonymously receives opinions from employees. Opinions from employees include, but are not limited to, suggestions for business improvement or opinions on the work environment. The reception unit provides, for example, an interface that allows employees to post opinions anonymously. The reception unit may also use anonymization technology to hide employees' personal information. For example, the reception unit hides the employee's name and department and accepts only the opinion. The filtering unit filters the opinions received by the reception unit, removing extreme or low-quality opinions. The filtering unit uses, for example, a generation AI to remove opinions such as abusive language, complaints about salary, or harassment of specific individuals. For example, the filtering unit uses a generation AI to analyze the content of the opinions and remove opinions containing extreme expressions or offensive language. The filtering unit can also use a generation AI to evaluate the content of the opinions and remove unconstructive or unclear opinions. For example, the filtering unit uses a generating AI to evaluate the importance and specificity of opinions and remove low-level opinions. The aggregation unit aggregates the opinions filtered by the filtering unit. The aggregation unit categorizes, classifies, and quantifies the opinions, for example, using a generating AI. For example, the aggregation unit uses a generating AI to analyze the content of the opinions and classify them into opinions related to business improvement, opinions related to the workplace environment, etc. The aggregation unit can also use a generating AI to quantify opinions in order of frequency (impact). For example, the aggregation unit uses a generating AI to evaluate and quantify the number and importance of opinions. The feedback unit provides feedback to management based on the opinions aggregated by the aggregation unit. The feedback unit uses a generating AI to convert the feedback wording into "gentle and polite" language. For example, the feedback unit uses a generating AI to analyze the content of the opinions and convert the feedback wording so as not to hurt the feelings of management. The feedback unit can also use a generating AI to convert the feedback wording so that management can respond emotionally in a positive way. For example, the feedback unit uses a generating AI to provide feedback in a positive way while retaining the essence of the opinion.This enables the opinion aggregation system according to the embodiment to efficiently filter, aggregate, and provide feedback on opinions from employees.

[0065] The reception desk accepts employee feedback anonymously. This feedback may include, but is not limited to, suggestions for business improvements or opinions on the work environment. The reception desk provides an interface that allows employees to submit feedback anonymously. Specifically, it may enable employees to easily submit feedback through web-based forms or mobile applications. This allows employees to express their opinions freely, knowing their privacy is protected. The reception desk can also employ anonymization technologies to conceal employee personal information. For example, it may hide employee names and departments, accepting only feedback. Specifically, it may use algorithms that automatically remove or mask employee personal information when feedback is submitted. This protects employee privacy and allows for focus on the content of the feedback. Furthermore, the reception desk simplifies the feedback submission process, enabling employees to submit feedback quickly. For example, it may provide a dropdown menu for selecting a feedback category or a text box for entering feedback content, allowing employees to submit feedback quickly. This enables the reception desk to efficiently collect employee feedback and enhance the overall system's effectiveness.

[0066] The filtering unit filters the opinions received by the reception unit, removing extreme or low-quality opinions. For example, the filtering unit uses generative AI to remove opinions such as abusive language, complaints about salary, and harassment of specific individuals. Specifically, the generative AI uses natural language processing technology to analyze the content of opinions and detect aggressive expressions and inappropriate words. For example, the generative AI tokenizes the text of an opinion and calculates a sentiment score for each token to identify aggressive opinions. The filtering unit can also have the generative AI evaluate the content of opinions and remove unconstructive or unclear opinions. For example, the generative AI uses algorithms to evaluate the specificity and importance of opinions to remove vague expressions or opinions that do not contain concrete suggestions. Furthermore, the filtering unit can classify the content of opinions by category and prioritize processing opinions belonging to specific categories. For example, it can prioritize processing opinions related to business improvement or the work environment, and postpone other opinions. In this way, the filtering unit can efficiently filter employee opinions and improve the overall quality of the system.

[0067] The aggregation unit consolidates the opinions filtered by the filtering unit. The aggregation unit categorizes, classifies, and quantifies the opinions, for example, using a generative AI. Specifically, the generative AI uses a clustering algorithm to group similar opinions and assigns labels to each group. For example, the generative AI analyzes the content of the opinions and classifies them into categories such as opinions on business improvement or opinions on the workplace environment. The aggregation unit can also use the generative AI to quantify the opinions in order of frequency (impact). For example, the generative AI evaluates and quantifies the number and importance of each opinion. Specifically, it calculates the frequency and importance score of each opinion, quantifying the impact of each opinion. Furthermore, the aggregation unit visualizes the content of the opinions to make them easily understandable to management. For example, it generates pie charts showing the proportion of each opinion category or bar graphs sorted by importance. This allows the aggregation unit to efficiently consolidate the filtered opinions and present them clearly to management.

[0068] The Feedback Department provides feedback to management based on the opinions aggregated by the Aggregation Department. The Feedback Department uses, for example, generative AI to transform feedback into "gentle and polite" language. Specifically, the generative AI uses natural language generation technology to analyze the content of the opinions and transform the feedback into language that does not offend management. For example, the generative AI transforms the opinions into language that includes positive expressions and constructive suggestions while retaining the essence of the opinions. The Feedback Department can also transform feedback into language that allows the generative AI to respond to management in an emotionally positive manner. For example, the generative AI expresses the content of the opinions in a positive tone, making them more readily accepted by management. Furthermore, the Feedback Department visually highlights the feedback to ensure that management does not overlook important opinions. For example, important opinions and suggestions are displayed in bold or colored text. This allows the Feedback Department to effectively provide feedback to management based on the aggregated opinions, ensuring that employee opinions are appropriately reflected.

[0069] The aggregation unit can categorize, classify, and quantify opinions. For example, the aggregation unit uses generative AI to analyze the content of opinions and classify them into opinions related to business improvement, opinions related to the workplace environment, etc. For example, the aggregation unit uses generative AI to analyze the content of opinions and extract relevant keywords and phrases. The aggregation unit can also use generative AI to quantify opinions in order of frequency (impact). For example, the aggregation unit uses generative AI to evaluate and quantify the number and importance of opinions. This makes it easier to organize opinions by categorizing, classifying, and quantifying them. Categorization and classification are performed, for example, by methods such as classification or tagging based on the content of the opinions. Quantification is performed, for example, based on numerical criteria or scoring methods. Some or all of the above processing in the aggregation unit may be performed using generative AI, or it may be performed without generative AI. For example, the aggregation unit can analyze the content of opinions and have generative AI perform categorization, classification, and quantification.

[0070] The feedback unit can convert feedback into "gentle and polite" language. For example, the feedback unit uses a generative AI to convert feedback into "gentle and polite" language. For instance, the generative AI analyzes the content of the opinion and converts the feedback into language that does not offend management. The feedback unit can also convert feedback into language that allows the generative AI to respond to management in a positive and emotionally positive manner. For example, the generative AI preserves the essence of the opinion while providing feedback in a positive way. This ensures that management is not offended by converting feedback into "gentle and polite" language. Gentle and polite language is based on criteria such as the use of honorifics and positive expressions. Some or all of the above-described processes in the feedback unit may be performed using a generative AI, or they may not. For example, the feedback unit can analyze the content of the opinion and have the generative AI perform the conversion of the feedback into language.

[0071] The filtering unit can remove opinions such as abusive language, complaints about wages, and harassment of specific individuals. For example, the filtering unit uses a generation AI to remove such opinions. For instance, the generation AI analyzes the content of opinions and removes those containing extreme or offensive language. The filtering unit can also use the generation AI to evaluate the content of opinions and remove unconstructive or unclear opinions. For example, the generation AI evaluates the importance and specificity of opinions and removes low-level opinions. This ensures that only appropriate opinions are fed back by removing abusive language, complaints about wages, and harassment of specific individuals. Abusive language is removed based on criteria such as insulting words and offensive expressions. Complaints about wages are removed based on criteria such as dissatisfaction with low wages or demands for raises. Harassment of specific individuals is removed based on criteria such as personal attacks and accusations by name. Some or all of the above processing in the filtering unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the filtering unit can analyze the content of the opinions and have the generating AI remove opinions such as abusive language, complaints about salary, and harassment of specific individuals.

[0072] The aggregation unit can aggregate opinions to the extent that the essence of the qualitative opinions is not lost. For example, the aggregation unit uses a generative AI to analyze the content of the opinions and aggregate them to the extent that the essence of the qualitative opinions is not lost. For example, the aggregation unit uses a generative AI to extract the core parts and important points of the opinions and aggregates the opinions based on them. In this way, the aggregation can be performed while preserving the essence of the opinions by aggregating them to the extent that the essence of the qualitative opinions is not lost. The essence of the qualitative opinions refers to, for example, the core parts and important points of the opinions. Some or all of the above processing in the aggregation unit may be performed using a generative AI or not. For example, the aggregation unit can have a generative AI perform the processing of analyzing the content of the opinions and aggregating them to the extent that the essence of the qualitative opinions is not lost.

[0073] The feedback unit can transform feedback wording to ensure a positive emotional response to management. For example, the feedback unit uses generative AI to transform feedback wording to ensure a positive emotional response to management. For instance, the feedback unit uses generative AI to analyze the content of the opinion and transform the feedback wording so as not to offend management. The feedback unit can also use generative AI to preserve the essence of the opinion while providing positive feedback. For example, the feedback unit uses generative AI to transform the content of the opinion into positive language and communicate it to management. This transforms the feedback wording to ensure a positive emotional response to management, thus preventing them from being hurt. A positive emotional response is based on criteria such as positive feedback and words of encouragement. Some or all of the above processing in the feedback unit may be performed using generative AI, or without it. For example, the feedback unit can analyze the content of the opinion and have the generative AI perform the transformation of the feedback wording.

[0074] The reception desk can estimate the user's emotions and adjust the timing of receiving feedback based on those emotions. The reception desk estimates the user's emotions using, for example, an emotion engine or generative AI. For instance, the emotion engine analyzes the user's facial expressions and voice to estimate their emotions. Alternatively, the generative AI can analyze the user's text input to estimate their emotions. For example, the generative AI extracts emotions from the user's text input and calculates an emotion score. Next, the reception desk adjusts the timing of receiving feedback based on the estimated user emotions. For example, if the user is stressed, the reception desk adjusts the timing to receive feedback during a time when they can relax. Similarly, if the user is busy, the reception desk adjusts the timing to receive feedback during a calmer period. For example, if the user is emotional, the reception desk adjusts the timing to receive feedback after they have calmed down. By adjusting the timing of feedback based on the user's emotions, feedback can be received at the appropriate time. The user's emotions are estimated using, for example, emotion analysis algorithms or facial recognition technology. Some or all of the above-described processes in the reception area may be performed using an emotion engine or generative AI, or they may be performed without using an emotion engine or generative AI. For example, the reception area can estimate the user's emotions and have the emotion engine or generative AI adjust the timing of receiving opinions.

[0075] The reception department can analyze an employee's past feedback submission history and select the most suitable method of receiving feedback. For example, the reception department might use AI to analyze an employee's past feedback submission history. For instance, the AI ​​might analyze the employee's feedback submission history and provide a simple interface to employees who frequently submit feedback. The reception department could also provide detailed guidance to employees who have never submitted feedback before. For example, the AI ​​might use the employee's feedback submission history to adjust the reception process for employees who tend to submit feedback during specific time slots. This allows the reception department to select the most suitable method of receiving feedback by analyzing an employee's past feedback submission history. The optimal method might be selected based on criteria such as online forms or direct interaction. Some or all of the above processes in the reception department may be performed using AI or not. For example, the reception department could have AI analyze an employee's feedback submission history and select the most suitable method of receiving feedback.

[0076] The reception department can filter opinions based on the employee's current projects and areas of interest when receiving them. For example, the reception department can use AI to identify an employee's current projects and areas of interest. For instance, the reception department can use AI to analyze project management tools and survey results to identify an employee's current projects and areas of interest. The reception department can also use AI to prioritize receiving opinions that are highly relevant based on the employee's current projects and areas of interest. For example, the reception department can use AI to prioritize receiving opinions related to the current project. The reception department can also use AI to prioritize receiving opinions related to the employee's areas of interest. For example, the reception department can use AI to filter out less relevant opinions based on the employee's current projects and areas of interest. This allows for the priority of receiving highly relevant opinions by filtering based on the employee's current projects and areas of interest. Current projects and areas of interest are identified, for example, using project management tools or survey results. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can identify an employee's current projects and areas of interest and have AI perform the filtering.

[0077] The reception desk can estimate the user's emotions and determine the priority of opinions to receive based on those estimated emotions. The reception desk can estimate the user's emotions using, for example, an emotion engine or generative AI. For example, the emotion engine can analyze the user's facial expressions and voice to estimate emotions. Alternatively, the generative AI can analyze the user's text input to estimate emotions. For example, the generative AI can extract emotions from the user's text input and calculate an emotion score. Next, the reception desk determines the priority of opinions to receive based on the estimated user emotions. For example, if the user is feeling strong dissatisfaction, the reception desk will prioritize that opinion. Conversely, if the user has positive emotions, the reception desk may postpone that opinion. For example, if the user has neutral emotions, the reception desk will treat that opinion equally with others. This allows important opinions to be received preferentially by prioritizing them based on the user's emotions. The priority of opinions is determined based on criteria such as importance score or urgency. Some or all of the above-described processes in the reception area may be performed using an emotion engine or generative AI, or they may be performed without using an emotion engine or generative AI. For example, the reception area can estimate the user's emotions and have the emotion engine or generative AI determine the priority of opinions.

[0078] The reception desk can prioritize receiving opinions that are highly relevant, taking into account the geographical location of the employees. For example, the reception desk can use AI to obtain employees' geographical location information. For instance, the reception desk can use AI to analyze GPS data or IP addresses to identify employees' geographical locations. Furthermore, the reception desk can use AI to prioritize receiving opinions that are highly relevant based on the employees' geographical location information. For example, the reception desk can use AI to prioritize opinions from employees in the same office. Alternatively, the reception desk can use AI to prioritize opinions from project teams that are geographically close. For example, the reception desk can use AI to postpone opinions from employees who are geographically far away. This allows for the prioritization of highly relevant opinions, taking into account the employees' geographical location information. Geographical location information is obtained, for example, using GPS data or IP addresses. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can obtain employees' geographical location information and have AI perform the task of receiving highly relevant opinions.

[0079] The reception department can analyze employees' social media activity when receiving feedback and accept relevant feedback. For example, the reception department can use AI to analyze employees' social media activity. For instance, the AI ​​can analyze the content of employees' social media posts and the number of likes to identify relevant social media activity. The reception department can also use AI to prioritize receiving relevant feedback based on employees' social media activity. For example, the AI ​​can prioritize feedback from employees with active social media activity. The reception department can also use AI to prioritize receiving relevant feedback based on the content of social media activity. For example, the AI ​​can postpone feedback from employees with low social media activity. This allows for prioritizing the receipt of relevant feedback by analyzing employees' social media activity. Social media activity is analyzed using, for example, the content of posts and the number of likes. Some or all of the above processing in the reception department may be performed using AI or not. For example, the reception department can have AI analyze employees' social media activity and receive relevant feedback.

[0080] The filtering unit can estimate the user's emotions and adjust the filtering criteria based on the estimated emotions. The filtering unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, the emotion engine analyzes the user's facial expressions and voice to estimate emotions. Alternatively, the generative AI can analyze the user's text input to estimate emotions. For example, the generative AI extracts emotions from the user's text input and calculates an emotion score. Next, the filtering unit adjusts the filtering criteria based on the estimated emotions. For example, if the user is angry, the filtering unit will strictly filter out opinions containing extreme language. Conversely, if the user is relaxed, the filtering unit may tolerate slightly extreme language. For example, if the user is sad, the filtering unit will carefully filter out opinions containing emotional language. This allows for appropriate filtering by adjusting the filtering criteria based on the user's emotions. The filtering criteria are adjusted based on, for example, keyword filtering or scoring criteria. Some or all of the above-described processing in the filtering unit may be performed using an emotion engine or generative AI, or it may be performed without using an emotion engine or generative AI. For example, the filtering unit can estimate the user's emotions and have the emotion engine or generative AI adjust the filtering criteria.

[0081] The filtering unit can improve the accuracy of filtering by considering the interrelationships between opinions. For example, the filtering unit may use a generative AI to consider the interrelationships between opinions. For example, the filtering unit may have the generative AI analyze the content of opinions and evaluate contradictions and agreements with other opinions. The filtering unit may also have the generative AI evaluate complementary relationships between opinions. For example, if the content of an opinion contradicts other opinions, the filtering unit will filter that opinion. The filtering unit may also have the generative AI prioritize retaining opinions whose content is consistent with other opinions. For example, if the generative AI finds an opinion to be complementary to other opinions, the filtering unit will retain that opinion. This improves the accuracy of filtering by considering the interrelationships between opinions. The interrelationships between opinions may be considered using, for example, a co-occurrence network or relevance score. Some or all of the above processing in the filtering unit may be performed using a generative AI or without a generative AI. For example, the filtering unit may have the generative AI consider the interrelationships between opinions and improve the accuracy of filtering.

[0082] The filtering unit can perform filtering while considering the attribute information of the opinion submitter. For example, the filtering unit uses a generative AI to identify the attribute information of the opinion submitter. For example, the filtering unit uses a generative AI to analyze attribute information such as the submitter's job title, department, and years of service. The filtering unit can also use a generative AI to evaluate the importance, relevance, and reliability of opinions based on the submitter's attribute information. For example, the filtering unit can use a generative AI to determine the importance of an opinion based on the submitter's job title. The filtering unit can also use a generative AI to determine the relevance of an opinion based on the submitter's department. For example, the filtering unit can use a generative AI to determine the reliability of an opinion based on the submitter's years of service. This allows for appropriate filtering by considering the attribute information of the opinion submitter. The submitter's attribute information is identified based on content such as age, job title, and department. Some or all of the above processing in the filtering unit may be performed using a generative AI or not. For example, the filtering unit can identify the attribute information of the opinion submitter and have the generative AI perform the filtering.

[0083] The filtering unit can estimate the user's emotions and adjust the order in which filtered results are displayed based on the estimated emotions. The filtering unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, the emotion engine analyzes the user's facial expressions and voice to estimate emotions. Alternatively, the generative AI can analyze the user's text input to estimate emotions. For example, the generative AI extracts emotions from the user's text input and calculates an emotion score. Next, the filtering unit adjusts the order in which filtered results are displayed based on the estimated emotions. For example, if the user is angry, the filtering unit will postpone more extreme opinions. Conversely, if the user is relaxed, the filtering unit may display slightly more extreme opinions first. For example, if the user is sad, the filtering unit will carefully display emotional opinions. This allows the results to be displayed in an appropriate order by adjusting the order in which filtered results are displayed based on the user's emotions. The display order is adjusted based on criteria such as importance or chronological order. Some or all of the above-described processing in the filtering unit may be performed using an emotion engine or generative AI, or it may be performed without using an emotion engine or generative AI. For example, the filtering unit can estimate the user's emotions and have the emotion engine or generative AI adjust the display order of the filtering results.

[0084] The filtering unit can perform filtering while considering the geographical distribution of opinions. For example, the filtering unit can use a generative AI to identify the geographical distribution of opinions. For example, the filtering unit can use a generative AI to analyze the location and region where opinions are submitted and identify the geographical distribution. The filtering unit can also have the generative AI prioritize retaining opinions that are highly relevant based on the geographical distribution of opinions. For example, the filtering unit can have the generative AI prioritize retaining opinions that are geographically close. The filtering unit can also have the generative AI postpone opinions that are geographically distant. For example, the filtering unit can have the generative AI determine the relevance of opinions based on their geographical distribution. This allows for prioritizing the retention of highly relevant opinions by considering the geographical distribution of opinions. Geographical distribution may be considered using, for example, the number of opinions by region or geographical bias. Some or all of the above processing in the filtering unit may be performed using a generative AI or not. For example, the filtering unit can identify the geographical distribution of opinions and have the generative AI perform the filtering.

[0085] The filtering unit can improve the accuracy of filtering by referring to relevant literature for opinions during the filtering process. For example, the filtering unit may use a generative AI to refer to relevant literature for opinions. For instance, the generative AI may analyze relevant literature such as academic papers and industry reports to evaluate the reliability and importance of opinions. The filtering unit can also have the generative AI determine the relevance of opinions based on the relevant literature. For example, the filtering unit may have the generative AI determine the reliability of opinions based on the relevant literature. The filtering unit can also have the generative AI determine the importance of opinions based on the relevant literature. For example, the filtering unit may have the generative AI determine the relevance of opinions based on the relevant literature. This improves the accuracy of filtering by referring to relevant literature for opinions. Relevant literature may be referenced using, for example, academic papers and industry reports. Some or all of the above processing in the filtering unit may be performed using a generative AI, or not. For example, the filtering unit can refer to relevant literature for opinions and have the generative AI perform the filtering accuracy improvement.

[0086] The aggregation unit can estimate the user's emotions and adjust the aggregation method based on the estimated emotions. The aggregation unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, the aggregation unit can use an emotion engine to analyze the user's facial expressions and voice to estimate emotions. Alternatively, the aggregation unit can use generative AI to analyze the user's text input to estimate emotions. For example, the aggregation unit can use generative AI to extract emotions from the user's text input and calculate an emotion score. Next, the aggregation unit adjusts the aggregation method based on the estimated emotions. For example, if the user is angry, the aggregation unit carefully aggregates extreme opinions. Conversely, if the user is relaxed, the aggregation unit can include some extreme opinions in the aggregation. For example, if the user is sad, the aggregation unit carefully aggregates emotional opinions. This allows for the aggregation of opinions in an appropriate manner by adjusting the aggregation method based on the user's emotions. The aggregation method is adjusted based on criteria such as clustering techniques or summarization algorithms. Some or all of the above-described processing in the aggregation unit may be performed using an emotion engine or generative AI, or it may be performed without using an emotion engine or generative AI. For example, the aggregation unit can estimate the user's emotions and have the emotion engine or generative AI adjust the aggregation method.

[0087] The aggregation unit can improve the accuracy of aggregation by considering the interrelationships between opinions during aggregation. For example, the aggregation unit may use a generative AI to consider the interrelationships between opinions. For example, the generative AI may analyze the content of opinions and evaluate contradictions and agreements with other opinions. The aggregation unit may also have the generative AI evaluate complementary relationships between opinions. For example, if the generative AI finds that an opinion contradicts another opinion, the aggregation unit will carefully aggregate that opinion. The aggregation unit may also prioritize the aggregation of opinions where the content is consistent with other opinions. For example, if the generative AI finds that an opinion is complementary to another opinion, the aggregation unit will aggregate that opinion. This improves the accuracy of aggregation by considering the interrelationships between opinions. The accuracy of aggregation can be improved using, for example, accuracy evaluation criteria or improvement methods. Some or all of the above-described processes in the aggregation unit may be performed using a generative AI or not. For example, the aggregation unit may consider the interrelationships between opinions and have the generative AI perform the task of improving the accuracy of aggregation.

[0088] The aggregation unit can perform aggregation while considering the attribute information of the opinion submitters. For example, the aggregation unit can use a generative AI to identify the attribute information of opinion submitters. For example, the aggregation unit can use a generative AI to analyze attribute information such as the submitter's job title, department, and years of service. The aggregation unit can also use a generative AI to evaluate the importance, relevance, and reliability of opinions based on the submitter's attribute information. For example, the aggregation unit can use a generative AI to determine the importance of an opinion based on the submitter's job title. The aggregation unit can also use a generative AI to determine the relevance of an opinion based on the submitter's department. For example, the aggregation unit can use a generative AI to determine the reliability of an opinion based on the submitter's years of service. This allows for appropriate aggregation by considering the attribute information of the opinion submitters. The submitter's attribute information is identified based on content such as age, job title, and department. Some or all of the above processing in the aggregation unit may be performed using a generative AI or not. For example, the aggregation unit can identify the attribute information of opinion submitters and have a generative AI perform the aggregation.

[0089] The aggregation unit can estimate the user's emotions and adjust how the aggregation results are displayed based on the estimated emotions. The aggregation unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, the emotion engine analyzes the user's facial expressions and voice to estimate emotions. Alternatively, the generative AI can analyze the user's text input to estimate emotions. For example, the generative AI extracts emotions from the user's text input and calculates an emotion score. Next, the aggregation unit adjusts how the aggregation results are displayed based on the estimated emotions. For example, if the user is angry, the aggregation unit will postpone more extreme opinions. Conversely, if the user is relaxed, the aggregation unit may display some more extreme opinions first. For example, if the user is sad, the aggregation unit will carefully display emotional opinions. This allows the results to be displayed in an appropriate manner by adjusting how the aggregation results are displayed based on the user's emotions. The display method is adjusted based on criteria such as graph display or list display. Some or all of the above-described processing in the aggregation unit may be performed using an emotion engine or a generative AI, or it may be performed without using an emotion engine or a generative AI. For example, the aggregation unit can estimate the user's emotions and have the emotion engine or a generative AI adjust how the aggregation results are displayed.

[0090] The aggregation unit can perform aggregation while considering the geographical distribution of opinions. For example, the aggregation unit can use a generative AI to identify the geographical distribution of opinions. For example, the aggregation unit can use a generative AI to analyze the location and region where opinions were submitted and identify the geographical distribution. The aggregation unit can also use a generative AI to prioritize the aggregation of highly relevant opinions based on the geographical distribution of opinions. For example, the aggregation unit can use a generative AI to prioritize the aggregation of opinions that are geographically close. The aggregation unit can also use a generative AI to postpone the aggregation of opinions that are geographically distant. For example, the aggregation unit can use a generative AI to determine the relevance of opinions based on their geographical distribution. This allows for the prioritization of the aggregation of highly relevant opinions by considering the geographical distribution of opinions. The geographical distribution may be considered using, for example, the number of opinions by region or geographical bias. Some or all of the above processing in the aggregation unit may be performed using a generative AI or not. For example, the aggregation unit can identify the geographical distribution of opinions and have a generative AI perform the aggregation.

[0091] The aggregation unit can improve the accuracy of aggregation by referring to relevant literature for the opinions during the aggregation process. For example, the aggregation unit may use a generative AI to refer to relevant literature for the opinions. For example, the generative AI may analyze relevant literature such as academic papers and industry reports and evaluate the reliability and importance of the opinions. The aggregation unit may also have the generative AI determine the relevance of the opinions based on the relevant literature. For example, the aggregation unit may have the generative AI determine the reliability of the opinions based on the relevant literature. The aggregation unit may also have the generative AI determine the importance of the opinions based on the relevant literature. For example, the aggregation unit may have the generative AI determine the relevance of the opinions based on the relevant literature. This improves the accuracy of aggregation by referring to relevant literature for the opinions. Relevant literature may be referred to using academic papers and industry reports, for example. Some or all of the above processing in the aggregation unit may be performed using a generative AI or not. For example, the aggregation unit may refer to relevant literature for the opinions and have the generative AI perform the task of improving the accuracy of aggregation.

[0092] The feedback unit can estimate the user's emotions and adjust the feedback text based on those emotions. The feedback unit estimates the user's emotions using, for example, an emotion engine or generative AI. For instance, the emotion engine analyzes the user's facial expressions and voice to estimate their emotions. Alternatively, the generative AI can analyze the user's text input to estimate their emotions. For example, the generative AI extracts emotions from the user's text input and calculates an emotion score. Next, the feedback unit adjusts the feedback text based on the estimated user emotions. For example, if the user is angry, the feedback unit provides calm feedback. Similarly, if the user is relaxed, the feedback unit provides positive feedback. For example, if the user is sad, the feedback unit provides gentle feedback. This allows for appropriate feedback by adjusting the feedback text based on the user's emotions. The feedback text is adjusted based on criteria such as changes in wording or revisions to the content. Some or all of the processing described above in the feedback unit may be performed using an emotion engine or generative AI, or it may be performed without using an emotion engine or generative AI. For example, the feedback unit can estimate the user's emotions and have the emotion engine or generative AI adjust the feedback wording.

[0093] The feedback unit can adjust the level of detail in feedback based on the importance of the opinion. For example, the feedback unit may use a generative AI to evaluate the importance of an opinion. For instance, the generative AI analyzes the content of the opinion and calculates an importance score. The feedback unit can also have the generative AI adjust the level of detail in the feedback based on the importance of the opinion. For example, the feedback unit provides detailed feedback for important opinions, and concise feedback for less important opinions. For example, the feedback unit adjusts the content of the feedback according to the importance of the opinion. This allows for appropriate feedback by adjusting the level of detail based on the importance of the opinion. The importance of an opinion may be evaluated based on criteria such as impact score or urgency. Some or all of the above processing in the feedback unit may be performed using a generative AI, or without one. For example, the feedback unit can evaluate the importance of an opinion and have the generative AI adjust the level of detail in the feedback.

[0094] The feedback unit can apply different feedback algorithms depending on the category of the opinion during the feedback process. For example, the feedback unit can use generative AI to identify the category of the opinion. For instance, the generative AI analyzes the content of the opinion and identifies categories such as opinions on business improvement or opinions on the work environment. Furthermore, the feedback unit can have the generative AI apply different feedback algorithms depending on the opinion category. For example, for opinions on business improvement, the feedback unit can provide feedback suggesting specific improvement measures. For opinions on the work environment, the feedback unit can also provide feedback suggesting specific actions for improving the environment. For example, for opinions on interpersonal relationships, the feedback unit can provide feedback offering specific advice for improving communication. This allows for appropriate feedback by applying different feedback algorithms depending on the opinion category. The feedback algorithms are applied based on types such as machine learning algorithms or rule-based algorithms. Some or all of the above-described processes in the feedback unit may be performed using generative AI, or they may not. For example, the feedback unit can identify the category of the opinion and have the generative AI apply the feedback algorithm.

[0095] The feedback unit can estimate the user's emotions and adjust the length of the feedback based on the estimated emotions. The feedback unit estimates the user's emotions using, for example, an emotion engine or generative AI. For example, the emotion engine analyzes the user's facial expressions and voice to estimate emotions. Alternatively, the generative AI can analyze the user's text input to estimate emotions. For example, the generative AI extracts emotions from the user's text input and calculates an emotion score. Next, the feedback unit adjusts the length of the feedback based on the estimated emotions. For example, if the user is angry, the feedback unit provides short, to-the-point feedback. Conversely, if the user is relaxed, the feedback unit can provide detailed feedback. For example, if the user is sad, the feedback unit provides detailed feedback in gentle language. This allows for appropriate feedback by adjusting the length of the feedback based on the user's emotions. The length of the feedback is adjusted based on criteria such as character limits or the degree of summarization. Some or all of the processing described above in the feedback unit may be performed using an emotion engine or generative AI, or it may be performed without using an emotion engine or generative AI. For example, the feedback unit can estimate the user's emotions and have the emotion engine or generative AI adjust the length of the feedback.

[0096] The feedback unit can prioritize feedback based on when the feedback was submitted. For example, the feedback unit can use a generative AI to identify the submission date. For instance, the generative AI analyzes the submission date and time to determine the submission period. The feedback unit can also use the generative AI to prioritize feedback based on the submission date. For example, the feedback unit prioritizes recently submitted feedback. It can also postpone older feedback. For example, the feedback unit adjusts the feedback priority based on the submission date. This allows for appropriate feedback by prioritizing feedback based on the submission date. The submission date is identified based on criteria such as the submission date and time. Some or all of the above processing in the feedback unit may be performed using a generative AI, or not. For example, the feedback unit can have the generative AI identify the submission date and determine the feedback priority.

[0097] The feedback unit can adjust the order of feedback based on the relevance of the opinions during the feedback process. The feedback unit can, for example, use a generative AI to evaluate the relevance of opinions. For example, the generative AI analyzes the content of the opinions and calculates a relevance score. The feedback unit can also have the generative AI adjust the order of feedback based on the relevance of the opinions. For example, the feedback unit prioritizes feedback on highly relevant opinions. The feedback unit can also postpone feedback on less relevant opinions. For example, the feedback unit adjusts the order of feedback based on the relevance of the opinions. This allows feedback to be given in an appropriate order by adjusting the order of feedback based on the relevance of the opinions. The relevance of opinions is evaluated based on criteria such as similarity of content or common themes. Some or all of the above processing in the feedback unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the feedback unit can evaluate the relevance of opinions and have the generative AI perform the adjustment of the feedback order.

[0098] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0099] The opinion aggregation system can also include an emotion estimation unit. This unit estimates the emotions an employee feels when submitting an opinion and adjusts the filtering and aggregation methods based on those emotions. For example, if an employee is feeling anger or frustration, the emotion estimation unit will handle their opinion carefully and remove any parts containing extreme language. Conversely, if an employee has positive emotions, their opinion will be prioritized for aggregation and provided to management. Furthermore, if an employee is feeling stressed, the emotion estimation unit can adjust the system to accept their opinion during a time when they are more relaxed. This allows for more appropriate opinion aggregation by adjusting the processing method based on the employee's emotions.

[0100] The opinion aggregation system can further filter opinions by considering the attribute information of the opinion submitters. For example, the filtering unit can analyze attribute information such as employee job title, department, and years of service, and evaluate the importance and relevance of opinions based on that information. For instance, opinions from employees with high job titles may be judged as highly important and given priority in feedback. Opinions from specific departments may be treated as issues related to that department and judged as highly relevant. Furthermore, opinions from employees with long years of service may be judged as highly reliable and given more importance. In this way, more appropriate filtering can be performed by considering the attribute information of the opinion submitters.

[0101] The opinion aggregation system can further consider the geographical distribution of opinions during aggregation. For example, the aggregation unit can analyze the location and region where employee opinions are submitted and aggregate them based on that geographical distribution. For instance, opinions from the same office or region are treated as common issues and aggregated preferentially. Opinions from geographically close project teams are deemed highly relevant and aggregated preferentially. Furthermore, opinions from geographically distant employees may be given lower priority. In this way, by considering the geographical distribution of opinions, highly relevant opinions can be aggregated preferentially.

[0102] The opinion aggregation system can further improve the accuracy of filtering by referring to relevant literature for each opinion. For example, the filtering unit can analyze relevant literature such as academic papers and industry reports and evaluate the reliability and importance of opinions based on that information. For instance, it can determine the reliability of an opinion based on relevant literature and remove opinions with low reliability. It can also determine the importance of an opinion based on relevant literature and prioritize feedback for opinions with high importance. Furthermore, it can determine the relevance of an opinion based on relevant literature and remove opinions with low relevance. In this way, the accuracy of filtering is improved by referring to relevant literature for each opinion.

[0103] The opinion aggregation system can further prioritize feedback based on when opinions are submitted. For example, the feedback department can analyze the submission date and time of opinions and prioritize feedback based on that information. For instance, recently submitted opinions will be given priority feedback, while older opinions will be given lower priority. Also, opinions submitted at a specific time can be treated as issues relevant to that time and given priority feedback. Furthermore, the importance of opinions can be evaluated based on the submission date, and opinions with high importance can be given priority feedback. In this way, appropriate feedback can be provided by prioritizing feedback based on when opinions are submitted.

[0104] The opinion aggregation system can also include an emotion estimation unit. This unit estimates the emotions of employees when they submit their opinions and can adjust the timing of opinion submission based on those emotions. For example, if an employee is feeling stressed, the emotion estimation unit can adjust the timing of opinion submission to coincide with a time when they can relax. If an employee is busy, it can adjust the timing to coincide with a time when their workload has subsided. Furthermore, if an employee is emotional, it can adjust the timing to coincide with a time when they have calmed down. In this way, by adjusting the timing of opinion submission based on the employee's emotions, opinions can be received at the appropriate time.

[0105] The opinion aggregation system can also be equipped with an emotion estimation unit. This unit can estimate the emotions an employee is feeling when submitting an opinion and adjust the feedback wording based on those emotions. For example, if an employee is angry, the emotion estimation unit can provide feedback in calm language. If the employee is relaxed, it can provide feedback in cheerful language. Furthermore, if the employee is sad, it can provide feedback in gentle language. This allows for appropriate feedback to be provided by adjusting the feedback wording based on the employee's emotions.

[0106] The opinion aggregation system can also include an emotion estimation unit. This unit estimates the emotions of employees when they submit their opinions and adjusts the filtering criteria based on those emotions. For example, if an employee is angry, the emotion estimation unit will strictly filter out opinions containing extreme language. Conversely, if an employee is relaxed, it may tolerate slightly extreme language. Furthermore, if an employee is sad, it may carefully filter out opinions containing emotional language. This allows for appropriate filtering by adjusting the filtering criteria based on the employee's emotions.

[0107] The opinion aggregation system may also include an emotion estimation unit. This unit estimates the emotions of employees when they submit their opinions and adjusts the aggregation method based on those emotions. For example, if an employee is angry, the emotion estimation unit will carefully aggregate extreme opinions. Conversely, if an employee is relaxed, it may include some extreme opinions in the aggregation. Furthermore, if an employee is sad, it may carefully aggregate emotional opinions. This allows for appropriate opinion aggregation by adjusting the aggregation method based on the employee's emotions.

[0108] The opinion aggregation system can further analyze the social media activity of those submitting opinions and accept relevant opinions. For example, the reception department can analyze the content of employees' social media posts and the number of likes they receive, and evaluate the relevance of opinions based on that information. For instance, opinions from employees who are active on social media will be deemed highly relevant and will be accepted preferentially. Opinions with high relevance can also be accepted preferentially based on the content of social media activity. Furthermore, opinions from employees with low social media activity may be given lower priority. In this way, by analyzing employees' social media activity, relevant opinions can be accepted preferentially.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The reception desk receives anonymous feedback from employees. This feedback may include suggestions for improving operations and opinions on the work environment. The reception desk provides an interface that allows employees to submit feedback anonymously and can use anonymization technology to hide employees' personal information. For example, it can hide the employee's name and department, and only accept the feedback. Step 2: The filtering unit filters the opinions received by the reception unit, removing extreme or low-quality opinions. The filtering unit uses a generation AI to remove opinions containing abusive language, complaints about salary, or harassment of specific individuals. The generation AI analyzes the content of the opinions and removes those containing extreme or aggressive language. The generation AI can also evaluate the content of the opinions and remove unconstructive or unclear opinions. The generation AI evaluates the importance and specificity of the opinions and removes low-quality opinions. Step 3: The aggregation unit aggregates the opinions filtered by the filtering unit. The aggregation unit uses a generation AI to categorize, classify, and quantify the opinions. The generation AI analyzes the content of the opinions and classifies them into opinions related to business improvement, opinions related to the workplace environment, etc. The generation AI can also quantify the opinions in order of frequency (impact). The generation AI evaluates and quantifies the number and importance of the opinions. Step 4: The Feedback Department provides feedback to management based on the opinions compiled by the Aggregation Department. The Feedback Department uses a Generative AI to transform the feedback into "gentle and polite" language. The Generative AI analyzes the content of the opinions and transforms the feedback into language that does not hurt the feelings of management. The Generative AI can also transform the feedback into language that allows management to respond emotionally in a positive way. The Generative AI provides feedback in a positive way while retaining the essence of the opinions.

[0111] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0112] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0113] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0114] Each of the multiple elements described above, including the reception unit, filtering unit, aggregation unit, and feedback unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and provides an interface that allows employees to post opinions anonymously. The filtering unit is implemented by the specific processing unit 290 of the data processing unit 12 and uses generating AI to remove extreme or low-level opinions. The aggregation unit is implemented by the specific processing unit 290 of the data processing unit 12 and uses generating AI to categorize, classify, and quantify opinions. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and uses generating AI to convert feedback statements into "gentle and polite" language. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0115] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0116] As shown in Figure 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.

[0117] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0118] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0119] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0121] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0122] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0123] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0124] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0125] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0126] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0127] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0129] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements described above, including the reception unit, filtering unit, aggregation unit, and feedback unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and provides an interface that allows employees to post opinions anonymously. The filtering unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and uses generating AI to remove extreme or low-level opinions. The aggregation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and uses generating AI to categorize, classify, and quantify opinions. The feedback unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and uses generating AI to convert feedback statements into "gentle and polite" language. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0131] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0132] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0135] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0139] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0140] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0141] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements described above, including the reception unit, filtering unit, aggregation unit, and feedback unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and provides an interface that allows employees to post opinions anonymously. The filtering unit is implemented by the specific processing unit 290 of the data processing unit 12 and uses generating AI to remove extreme or low-level opinions. The aggregation unit is implemented by the specific processing unit 290 of the data processing unit 12 and uses generating AI to categorize, classify, and quantify opinions. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and uses generating AI to convert feedback statements into "gentle and polite" language. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0147] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0148] As shown in Figure 7, the 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.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0151] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0153] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0154] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0155] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0156] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] Each of the multiple elements described above, including the reception unit, filtering unit, aggregation unit, and feedback unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and provides an interface that allows employees to post opinions anonymously. The filtering unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and uses generating AI to remove extreme or low-level opinions. The aggregation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and uses generating AI to categorize, classify, and quantify opinions. The feedback unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and uses generating AI to convert feedback statements into "gentle and polite" language. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0164] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0165] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0166] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0167] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0168] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0169] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0172] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0173] 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.

[0174] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0175] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0176] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0177] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0179] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0180] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0181] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0182] (Note 1) A reception desk that accepts anonymous feedback from employees, A filtering unit filters the opinions received by the aforementioned reception unit, removing extreme or low-quality opinions. An aggregation unit that aggregates the opinions filtered by the filtering unit, The system includes a feedback unit that provides feedback to management based on the opinions gathered by the aggregation unit. A system characterized by the following features. (Note 2) The aforementioned aggregation unit is Categorize, classify, and quantify opinions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned feedback unit is Transforming feedback into "gentle and polite" language. The system described in Appendix 1, characterized by the features described herein. (Note 4) The filtering unit is Remove comments containing abusive language, complaints about salary, and harassment of specific individuals. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned aggregation unit is Summarize opinions to the extent that the essence of the qualitative opinions is not lost. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned feedback unit is Transform the feedback wording to allow for a more emotionally positive response from management. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of feedback submissions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is Analyze employees' past feedback submission history to select the most suitable method for receiving feedback. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When receiving feedback, we filter it based on the employee's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is It estimates the user's emotions and determines the priority of the opinions to be accepted based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving feedback, we will prioritize receiving feedback that is highly relevant, taking into account the geographical location of employees. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When receiving feedback, we analyze employees' social media activity and collect relevant opinions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The filtering unit is It estimates the user's sentiment and adjusts the filtering criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The filtering unit is When filtering, consider the interrelationships between opinions to improve the accuracy of the filtering process. The system described in Appendix 1, characterized by the features described herein. (Note 15) The filtering unit is When filtering, the attribute information of the person submitting the opinion is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 16) The filtering unit is It estimates the user's sentiment and adjusts the order in which filtering results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The filtering unit is When filtering, consider the geographical distribution of opinions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The filtering unit is During filtering, refer to relevant literature to improve the accuracy of the filtering. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned aggregation unit is We estimate the user's emotions and adjust the aggregation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned aggregation unit is When aggregating opinions, consider the interrelationships between them to improve the accuracy of the aggregation. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned aggregation unit is When aggregating opinions, the attribute information of the person who submitted the opinion will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned aggregation unit is It estimates the user's emotions and adjusts how the aggregated results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned aggregation unit is When aggregating opinions, the geographical distribution of those opinions should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned aggregation unit is When aggregating opinions, we refer to relevant literature to improve the accuracy of the aggregation. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned feedback unit is It estimates the user's emotions and adjusts the feedback wording based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned feedback unit is When providing feedback, adjust the level of detail based on the importance of the feedback. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned feedback unit is When providing feedback, different feedback algorithms are applied depending on the category of the opinion. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned feedback unit is It estimates the user's emotions and adjusts the length of the feedback based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned feedback unit is When providing feedback, we prioritize feedback based on when the feedback was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned feedback unit is When giving feedback, adjust the order of feedback based on the relevance of the opinions. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that accepts anonymous feedback from employees, A filtering unit filters the opinions received by the aforementioned reception unit, removing extreme or low-quality opinions. An aggregation unit that aggregates the opinions filtered by the filtering unit, The system includes a feedback unit that provides feedback to management based on the opinions gathered by the aggregation unit. A system characterized by the following features.

2. The aforementioned aggregation unit is Categorize, classify, and quantify opinions. The system according to feature 1.

3. The aforementioned feedback unit is Transforming feedback into gentle and polite language The system according to feature 1.

4. The filtering unit is Remove comments containing abusive language, complaints about salary, and harassment of specific individuals. The system according to feature 1.

5. The aforementioned aggregation unit is Summarize opinions to the extent that the essence of the qualitative opinions is not lost. The system according to feature 1.

6. The aforementioned feedback unit is Transform the feedback wording to allow for a more emotionally positive response from management. The system according to feature 1.

7. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of feedback submissions based on those estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is Analyze employees' past feedback submission history to select the most suitable method for receiving feedback. The system according to feature 1.

Images