System

Abstract

An object of a system according to an embodiment is to efficiently analyze complaint data from a customer and to propose a specific improvement measure.SOLUTION: A system includes a complaint data collection part, a preprocessing part, a text analysis part, an insight generation part, a cause analysis part, and an action plan recommendation part. The complaint data collection unit collects complaint data. The pre-processing section pre-processes the complaint data collected by the complaint data collecting section. The text analysis part performs text analysis of the claim data preprocessed by the preprocessing part. The insight generator generates insights based on the frequency, trend, and relevance of the issues extracted by the text analyzer. A cause analysis part analyzes the cause of the claim based on the insight generated by the insight generation part. The action plan recommendation unit recommends an action plan based on the problem identified by the cause analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult to efficiently analyze customer complaint data and derive specific improvement measures.

[0005] The system according to the embodiment aims to efficiently analyze complaint data from customers and propose specific improvement measures. [Means for solving the problem]

[0006] The system according to the embodiment includes a claim data collection unit, a preprocessing unit, a text analysis unit, an insight generation unit, a cause analysis unit, and an action plan recommendation unit. The claim data collection unit collects claim data. The preprocessing unit preprocesses the claim data collected by the claim data collection unit. The text analysis unit performs text analysis on the claim data preprocessed by the preprocessing unit. The insight generation unit generates insights based on the frequency, trends, and relevance of the problems extracted by the text analysis unit. The cause analysis unit analyzes the causes of the claims based on the insights generated by the insight generation unit. The action plan recommendation unit recommends an action plan based on the problems identified by the cause analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently analyze customer complaint data and propose specific improvement measures. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) An AI system according to an embodiment of the present invention analyzes customer complaint data and identifies the underlying issues. The system performs text analysis of complaints, extracts the frequency, trends, and relevance of the issues, and generates insights to help companies develop service and product improvement measures. Furthermore, the system identifies specific points and process flaws that cause complaints and proposes action plans to prevent future complaints. This allows the AI ​​system to efficiently analyze customer complaint data and respond quickly and accurately.

[0029] The AI ​​system according to the present embodiment includes a complaint data collection unit, a preprocessing unit, a text analysis unit, an insight generation unit, a cause analysis unit, and an action plan recommendation unit. The complaint data collection unit collects complaint data from customers. For example, the data is collected in various formats, such as emails, chats, and phone records. The complaint data collection unit can also collect data from social media and review sites. The preprocessing unit preprocesses the collected complaint data. For example, the preprocessing unit normalizes the text, removes unnecessary information, and standardizes language. The preprocessing unit can also convert voice data into text and include voice tone and speed in the analysis. The preprocessing unit can also support different languages ​​and cultural spheres, enabling analysis from a global perspective. The text analysis unit performs text analysis on the preprocessed complaint data. For example, the text analysis unit uses natural language processing technology to analyze the content of complaints and extract the frequency, trends, and relevance of problems. The text analysis unit can also estimate customer sentiment and track sentiment changes over time. The text analysis unit also implements a deep learning model to extract potential issues underlying the content of the complaints. The insight generation unit generates insights based on the frequency, trends, and relevance of the problems extracted by the text analysis unit. For example, it performs frequency analysis, trend analysis, correlation analysis, etc. The insight generation unit can also perform more detailed analysis by taking into account metadata such as the location and time of complaint occurrence. Furthermore, the insight generation unit visualizes and displays the text analysis results for intuitive understanding. The cause analysis unit analyzes the causes of complaints based on the insights generated by the insight generation unit. For example, it performs causal relationship identification, regression analysis, factor analysis, etc. The cause analysis unit can also integrate the company's internal data with complaint data to more accurately identify causes. Furthermore, after identifying problems, the cause analysis unit refers to past solutions to similar complaints and their effectiveness to propose optimal solutions. The action plan recommendation unit recommends action plans based on the problems identified by the cause analysis unit. For example, it proposes improvement measures, develops implementation plans, and measures effectiveness.As a result, the AI ​​system according to the embodiment can efficiently analyze customer complaint data and respond promptly and appropriately. For example, by quickly identifying the cause of a complaint and taking appropriate measures to improve it, customer satisfaction can be improved. In addition, by proposing an action plan to prevent future complaints, the reliability of the company can be improved.

[0030] The complaint data collection unit can also collect data from social media and review sites. For example, the complaint data collection unit diversifies the sources of complaint data collection and builds a system that collects data from social media and review sites. For example, it automatically collects posts from Twitter and Facebook. The complaint data collection unit also collects data from review sites. For example, it collects data from Amazon reviews and Google reviews. This allows the collection of data from social media and review sites to obtain a wider range of complaint data.

[0031] The pre-processing unit can understand the context of the claim content and automatically link it to related past claim data. For example, in the pre-processing stage, the pre-processing unit introduces natural language processing technology to understand the context of the claim content. For example, it extracts the subject matter and keywords of the claim. The pre-processing unit also automatically links it to related past claim data. For example, it searches a database for similar past claims and links them. This enables quick problem resolution by understanding the context of the claim content and linking it to related past claim data.

[0032] The pre-processing section converts voice data into text, and can also include voice tone and speed in the analysis. For example, when collecting complaint data, the pre-processing section introduces a system that converts voice data into text. For example, it uses voice recognition technology to convert customer comments into text. The pre-processing section also includes voice tone and speed in the analysis. For example, it analyzes the pitch and strength of the voice to infer emotions. In this way, by converting voice data into text and including voice tone and speed in the analysis, more detailed complaint analysis becomes possible.

[0033] The preprocessing unit can accommodate different languages ​​and cultural spheres, enabling analysis from a global perspective. For example, the preprocessing unit builds a system that makes the collection and preprocessing of claim data compatible with different languages ​​and cultural spheres. For example, it introduces natural language processing technology that supports multiple languages. The preprocessing unit also takes into account cultural backgrounds to accommodate different cultural spheres. For example, it analyzes claim data taking cultural differences into account. This makes it possible to accommodate different languages ​​and cultural spheres, and to perform analysis from a global perspective.

[0034] The text analysis unit can introduce a deep learning model to extract potential problems behind the content of a claim. For example, the text analysis unit introduces a deep learning model to extract potential problems behind the content of a claim in text analysis. For example, an LSTM or Transformer model is used. The text analysis unit also uses a deep learning model to identify potential problems in the content of a claim. For example, it extracts patterns and commonalities between claims. By introducing a deep learning model to extract potential problems behind the content of a claim, more accurate problem extraction is possible.

[0035] The insight generation unit can also take into account metadata such as the location and time of day when a claim occurred, and perform a detailed analysis. For example, the insight generation unit builds a system that takes into account metadata such as the location and time of day when a claim occurred when generating insights. For example, the area and time of day when a claim occurred are registered in a database. The insight generation unit also performs a detailed analysis based on the metadata. For example, it analyzes trends and patterns in the occurrence of claims. This enables a more detailed analysis by taking into account metadata such as the location and time of day when a claim occurred.

[0036] The insight generation unit can visualize and display the text analysis results to enable intuitive understanding. The insight generation unit, for example, builds a system that visualizes the text analysis results. For example, it displays trends in claims using graphs and charts. The insight generation unit also makes the visualized results intuitively understandable. For example, it designs a user interface and visually highlights the results. In this way, visualizing and displaying the text analysis results enables intuitive understanding.

[0037] The insight generation unit can compare claims data from different industries and fields to identify common problems and trends. The insight generation unit, for example, builds a system that collects claims data from different industries and fields and performs comparative analysis. For example, it compares claims data from the manufacturing industry and the service industry. The insight generation unit also identifies common problems and trends. For example, it extracts frequently occurring problems and analyzes common trends. This makes it possible to identify common problems and trends by comparing claims data from different industries and fields.

[0038] The cause analysis department can integrate a company's internal data with complaint data to identify causes with high accuracy. For example, in cause analysis, the cause analysis department builds a system that integrates a company's internal data with complaint data. For example, it compares product production data and logistics data with complaint data. The cause analysis department also identifies causes with high accuracy based on the integrated data. For example, it analyzes correlations in the data to identify the root cause of the problem. In this way, by integrating a company's internal data with complaint data, it becomes possible to identify causes with high accuracy.

[0039] After identifying a problem, the cause analysis unit can refer to past solutions to similar complaints and their effects to propose the optimal solution. For example, after identifying a problem, the cause analysis unit builds a system that refers to past solutions to similar complaints and their effects. For example, it searches a past database for similar complaints. The cause analysis unit also proposes the optimal solution based on the referenced solutions and their effects. For example, it proposes improvement measures based on past success stories. In this way, the optimal solution can be proposed by referring to past solutions to similar complaints and their effects.

[0040] The cause analysis unit can identify problems and compare their cause analysis with data from different industries and fields to find common causes and solutions. For example, the cause analysis unit builds a system that compares problem identification and cause analysis with data from different industries and fields. For example, it compares data from the manufacturing industry and the service industry. The cause analysis unit also finds common causes and solutions. For example, it analyzes causal relationships and extracts common patterns. This makes it possible to find common causes and solutions by comparing data from different industries and fields.

[0041] The cause analysis unit can visualize and display the cause analysis results to enable intuitive understanding. The cause analysis unit, for example, builds a system that visualizes the cause analysis results. For example, it displays the causes using graphs and charts. The cause analysis unit also makes the visualized results intuitively understandable. For example, it designs a user interface and visually highlights the results. In this way, the visualized and displayed cause analysis results enable intuitive understanding.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The complaint data collection department can also collect data from social media and review sites. For example, it automatically collects posts from Twitter and Facebook, as well as data from Amazon and Google reviews. This allows for the collection of data from social media and review sites, enabling a wider range of complaint data to be obtained. Furthermore, analyzing this data allows for early detection of potential customer dissatisfaction and trends.

[0044] The preprocessing unit can understand the context of a claim and automatically link it to related past claim data. For example, it can extract the subject matter and keywords of a claim and search a database for similar past claims and link them. This enables faster problem resolution and more effective responses by referring to past solutions. Contextual understanding can also identify the underlying issues behind the claim.

[0045] The preprocessing section can accommodate different languages ​​and cultural spheres, enabling analysis from a global perspective. For example, multilingual natural language processing technology can be introduced to analyze complaint data while taking cultural differences into account. This makes it possible to accommodate different languages ​​and cultural spheres and perform analysis from a global perspective. Furthermore, by comparing complaint trends across different cultures, it is possible to propose international service improvement measures.

[0046] The text analysis unit can incorporate deep learning models to extract potential problems behind the content of complaints. For example, LSTM or Transformer models can be used to extract patterns and commonalities between complaints. By incorporating deep learning models to extract potential problems behind the content of complaints, more accurate problem extraction becomes possible. Specific improvement measures can also be proposed based on the extracted problems.

[0047] The insight generation unit can compare claims data from different industries and fields to identify common problems and trends. For example, it can compare claims data from the manufacturing and service industries to extract frequently occurring issues and analyze common trends. This makes it possible to identify common problems and trends by comparing claims data from different industries and fields. It can also share best practices between different industries and propose improvement measures.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The complaint data collection department collects complaint data from customers. For example, data that exists in various formats such as emails, chats, and phone records can be collected. The complaint data collection department can also collect data from social media and review sites. Step 2: The preprocessing section preprocesses the collected claim data. For example, it normalizes the text, removes unnecessary information, and standardizes the language. The preprocessing section also converts audio data into text, allowing the tone and speed of the speech to be included in the analysis. Furthermore, the preprocessing section supports different languages ​​and cultural backgrounds, enabling analysis from a global perspective. Step 3: The text analysis unit performs text analysis on the preprocessed complaint data. For example, natural language processing technology is used to analyze the content of complaints and extract the frequency, trends, and relevance of problems. The text analysis unit can also estimate customer sentiment and track sentiment changes over time. Furthermore, the text analysis unit introduces a deep learning model to extract potential problems behind the content of complaints. Step 4: The insight generation unit generates insights based on the frequency, trends, and relevance of the issues extracted by the text analysis unit. For example, it performs frequency analysis, trend analysis, correlation analysis, etc. The insight generation unit can also take into account metadata such as the location and time of the complaint to perform a more detailed analysis. Furthermore, the insight generation unit visualizes and displays the results of the text analysis to enable intuitive understanding. Step 5: The Cause Analysis Department analyzes the causes of the complaint based on the insights generated by the Insight Generation Department. For example, it performs causal relationship identification, regression analysis, factor analysis, etc. The Cause Analysis Department also integrates the company's internal data with complaint data to more accurately identify the cause. After identifying the problem, the Cause Analysis Department also refers to past solutions to similar complaints and their effectiveness to propose the optimal solution. Step 6: The action plan recommendation unit recommends an action plan based on the problems identified by the cause analysis unit. For example, it proposes improvement measures, formulates an implementation plan, and measures the effectiveness. This enables the AI ​​system according to the embodiment to efficiently analyze customer complaint data and respond quickly and appropriately. For example, by quickly identifying the cause of a complaint and taking appropriate improvement measures, customer satisfaction can be improved. In addition, by recommending an action plan to prevent future complaints, the company's credibility can be enhanced.

[0050] (Example 2) An AI system according to an embodiment of the present invention analyzes customer complaint data and identifies the underlying issues. The system performs text analysis of complaints, extracts the frequency, trends, and relevance of the issues, and generates insights to help companies develop service and product improvement measures. Furthermore, the system identifies specific points and process flaws that cause complaints and proposes action plans to prevent future complaints. This allows the AI ​​system to efficiently analyze customer complaint data and respond quickly and accurately.

[0051] The AI ​​system according to the present embodiment includes a complaint data collection unit, a preprocessing unit, a text analysis unit, an insight generation unit, a cause analysis unit, and an action plan recommendation unit. The complaint data collection unit collects complaint data from customers. For example, the data is collected in various formats, such as emails, chats, and phone records. The complaint data collection unit can also collect data from social media and review sites. The preprocessing unit preprocesses the collected complaint data. For example, the preprocessing unit normalizes the text, removes unnecessary information, and standardizes language. The preprocessing unit can also convert voice data into text and include voice tone and speed in the analysis. The preprocessing unit can also support different languages ​​and cultural spheres, enabling analysis from a global perspective. The text analysis unit performs text analysis on the preprocessed complaint data. For example, the text analysis unit uses natural language processing technology to analyze the content of complaints and extract the frequency, trends, and relevance of problems. The text analysis unit can also estimate customer sentiment and track sentiment changes over time. The text analysis unit also implements a deep learning model to extract potential issues underlying the content of the complaints. The insight generation unit generates insights based on the frequency, trends, and relevance of the problems extracted by the text analysis unit. For example, it performs frequency analysis, trend analysis, correlation analysis, etc. The insight generation unit can also perform more detailed analysis by taking into account metadata such as the location and time of complaint occurrence. Furthermore, the insight generation unit visualizes and displays the text analysis results for intuitive understanding. The cause analysis unit analyzes the causes of complaints based on the insights generated by the insight generation unit. For example, it performs causal relationship identification, regression analysis, factor analysis, etc. The cause analysis unit can also integrate the company's internal data with complaint data to more accurately identify causes. Furthermore, after identifying problems, the cause analysis unit refers to past solutions to similar complaints and their effectiveness to propose optimal solutions. The action plan recommendation unit recommends action plans based on the problems identified by the cause analysis unit. For example, it proposes improvement measures, develops implementation plans, and measures effectiveness.As a result, the AI ​​system according to the embodiment can efficiently analyze customer complaint data and respond promptly and appropriately. For example, by quickly identifying the cause of a complaint and taking appropriate measures to improve it, customer satisfaction can be improved. In addition, by proposing an action plan to prevent future complaints, the reliability of the company can be improved.

[0052] The complaint data collection unit can estimate customer emotions in real time and set the priority of complaints according to the intensity of the emotions. For example, the complaint data collection unit introduces a system that estimates customer emotions in real time when collecting complaint data. For example, it analyzes facial expressions and tone of voice when customers enter complaints and calculates an emotion score. The complaint data collection unit also sets the priority of complaints according to the intensity of the emotions. For example, it handles complaints with a high emotion score first. This allows for a quick response by setting the priority of complaints based on customer emotions.

[0053] The complaint data collection unit can also collect data from social media and review sites. For example, the complaint data collection unit diversifies the sources of complaint data collection and builds a system that collects data from social media and review sites. For example, it automatically collects posts from Twitter and Facebook. The complaint data collection unit also collects data from review sites. For example, it collects data from Amazon reviews and Google reviews. This allows the collection of data from social media and review sites to obtain a wider range of complaint data.

[0054] The pre-processing unit can understand the context of the claim content and automatically link it to related past claim data. For example, in the pre-processing stage, the pre-processing unit introduces natural language processing technology to understand the context of the claim content. For example, it extracts the subject matter and keywords of the claim. The pre-processing unit also automatically links it to related past claim data. For example, it searches a database for similar past claims and links them. This enables quick problem resolution by understanding the context of the claim content and linking it to related past claim data.

[0055] The pre-processing section converts voice data into text, and can also include voice tone and speed in the analysis. For example, when collecting complaint data, the pre-processing section introduces a system that converts voice data into text. For example, it uses voice recognition technology to convert customer comments into text. The pre-processing section also includes voice tone and speed in the analysis. For example, it analyzes the pitch and strength of the voice to infer emotions. In this way, by converting voice data into text and including voice tone and speed in the analysis, more detailed complaint analysis becomes possible.

[0056] The preprocessing unit can accommodate different languages ​​and cultural spheres, enabling analysis from a global perspective. For example, the preprocessing unit builds a system that makes the collection and preprocessing of claim data compatible with different languages ​​and cultural spheres. For example, it introduces natural language processing technology that supports multiple languages. The preprocessing unit also takes into account cultural backgrounds to accommodate different cultural spheres. For example, it analyzes claim data taking cultural differences into account. This makes it possible to accommodate different languages ​​and cultural spheres, and to perform analysis from a global perspective.

[0057] The preprocessing unit can use the emotion estimation function to provide feedback on customer emotions in real time when collecting complaint data, thereby encouraging improvements in customer service. The preprocessing unit, for example, uses the emotion estimation function to build a system that provides feedback on customer emotions in real time when collecting complaint data. For example, it analyzes the customer's facial expressions and voice and displays an emotion score. The preprocessing unit also provides feedback to encourage improvements in customer service. For example, it notifies the customer of areas for improvement in customer service in real time. This makes it possible to provide feedback on customer emotions in real time and encourage improvements in customer service.

[0058] The text analysis unit can estimate customer emotions and track changes in emotions over time. For example, the text analysis unit introduces a system that estimates customer emotions during text analysis. For example, it calculates an emotion score from text using natural language processing technology. The text analysis unit also tracks changes in emotions over time. For example, it analyzes the timing of complaints and changes in emotions. In this way, by tracking changes in customer emotions over time, it is possible to analyze the timing of complaints and changes in emotions.

[0059] The text analysis unit can introduce a deep learning model to extract potential problems behind the content of a claim. For example, the text analysis unit introduces a deep learning model to extract potential problems behind the content of a claim in text analysis. For example, an LSTM or Transformer model is used. The text analysis unit also uses a deep learning model to identify potential problems in the content of a claim. For example, it extracts patterns and commonalities between claims. By introducing a deep learning model to extract potential problems behind the content of a claim, more accurate problem extraction is possible.

[0060] The insight generation unit can also take into account metadata such as the location and time of day when a claim occurred, and perform a detailed analysis. For example, the insight generation unit builds a system that takes into account metadata such as the location and time of day when a claim occurred when generating insights. For example, the area and time of day when a claim occurred are registered in a database. The insight generation unit also performs a detailed analysis based on the metadata. For example, it analyzes trends and patterns in the occurrence of claims. This enables a more detailed analysis by taking into account metadata such as the location and time of day when a claim occurred.

[0061] The insight generation unit can visualize and display the text analysis results to enable intuitive understanding. The insight generation unit, for example, builds a system that visualizes the text analysis results. For example, it displays trends in claims using graphs and charts. The insight generation unit also makes the visualized results intuitively understandable. For example, it designs a user interface and visually highlights the results. In this way, visualizing and displaying the text analysis results enables intuitive understanding.

[0062] The insight generation unit can compare claims data from different industries and fields to identify common problems and trends. The insight generation unit, for example, builds a system that collects claims data from different industries and fields and performs comparative analysis. For example, it compares claims data from the manufacturing industry and the service industry. The insight generation unit also identifies common problems and trends. For example, it extracts frequently occurring problems and analyzes common trends. This makes it possible to identify common problems and trends by comparing claims data from different industries and fields.

[0063] The insight generation unit uses the emotion estimation function to consider customer emotions when generating insights, and can propose improvement measures that are likely to resonate emotionally. The insight generation unit, for example, uses the emotion estimation function to build a system that considers customer emotions when generating insights. For example, it calculates a customer emotion score from the content of a complaint. The insight generation unit also proposes improvement measures that are likely to resonate emotionally. For example, it uses an expression method that elicits empathy based on the emotion analysis results. This makes it possible to consider customer emotions and propose improvement measures that are likely to resonate emotionally.

[0064] The cause analysis unit can estimate the customer's emotions and set the priority of the problem based on the intensity of the emotions. For example, the cause analysis unit introduces a system that estimates the customer's emotions when identifying a problem. For example, it calculates an emotion score from the content of the complaint and sets the priority of the problem. The cause analysis unit also sets the priority of the problem based on the intensity of the emotions. For example, it handles problems with a high emotion score first. This allows for a quick response by setting the priority of the problem based on the intensity of the customer's emotions.

[0065] The cause analysis department can integrate a company's internal data with complaint data to identify causes with high accuracy. For example, in cause analysis, the cause analysis department builds a system that integrates a company's internal data with complaint data. For example, it compares product production data and logistics data with complaint data. The cause analysis department also identifies causes with high accuracy based on the integrated data. For example, it analyzes correlations in the data to identify the root cause of the problem. In this way, by integrating a company's internal data with complaint data, it becomes possible to identify causes with high accuracy.

[0066] After identifying a problem, the cause analysis unit can refer to past solutions to similar complaints and their effects to propose the optimal solution. For example, after identifying a problem, the cause analysis unit builds a system that refers to past solutions to similar complaints and their effects. For example, it searches a past database for similar complaints. The cause analysis unit also proposes the optimal solution based on the referenced solutions and their effects. For example, it proposes improvement measures based on past success stories. In this way, the optimal solution can be proposed by referring to past solutions to similar complaints and their effects.

[0067] The cause analysis unit can identify problems and compare their cause analysis with data from different industries and fields to find common causes and solutions. For example, the cause analysis unit builds a system that compares problem identification and cause analysis with data from different industries and fields. For example, it compares data from the manufacturing industry and the service industry. The cause analysis unit also finds common causes and solutions. For example, it analyzes causal relationships and extracts common patterns. This makes it possible to find common causes and solutions by comparing data from different industries and fields.

[0068] The cause analysis unit can visualize and display the cause analysis results to enable intuitive understanding. The cause analysis unit, for example, builds a system that visualizes the cause analysis results. For example, it displays the causes using graphs and charts. The cause analysis unit also makes the visualized results intuitively understandable. For example, it designs a user interface and visually highlights the results. In this way, the visualized and displayed cause analysis results enable intuitive understanding.

[0069] The cause analysis unit can use the emotion estimation function to consider the customer's emotions when identifying a problem and propose a solution that is likely to resonate emotionally. The cause analysis unit, for example, uses the emotion estimation function to build a system that considers the customer's emotions when identifying a problem. For example, it calculates a customer's emotion score from the content of the complaint. The cause analysis unit also proposes a solution that is likely to resonate emotionally. For example, it uses an expression method that elicits empathy based on the emotion analysis results. This makes it possible to consider the customer's emotions and propose a solution that is likely to resonate emotionally.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The complaint data collection unit can estimate customer emotions in real time and prioritize complaints according to the intensity of the emotion. For example, it can analyze facial expressions and tone of voice when customers enter their complaints and calculate an emotion score. Furthermore, by prioritizing complaints with high emotion scores, it is possible to respond quickly. Furthermore, it is possible to adjust the way complaints are handled based on the intensity of the emotion, thereby improving customer satisfaction.

[0072] The complaint data collection department can also collect data from social media and review sites. For example, it automatically collects posts from Twitter and Facebook, as well as data from Amazon and Google reviews. This allows for the collection of data from social media and review sites, enabling a wider range of complaint data to be obtained. Furthermore, analyzing this data allows for early detection of potential customer dissatisfaction and trends.

[0073] The preprocessing unit can understand the context of a claim and automatically link it to related past claim data. For example, it can extract the subject matter and keywords of a claim and search a database for similar past claims and link them. This enables faster problem resolution and more effective responses by referring to past solutions. Contextual understanding can also identify the underlying issues behind the claim.

[0074] The preprocessing section can accommodate different languages ​​and cultural spheres, enabling analysis from a global perspective. For example, multilingual natural language processing technology can be introduced to analyze complaint data while taking cultural differences into account. This makes it possible to accommodate different languages ​​and cultural spheres and perform analysis from a global perspective. Furthermore, by comparing complaint trends across different cultures, it is possible to propose international service improvement measures.

[0075] The preprocessing unit uses the emotion estimation function to provide real-time feedback on customer emotions when collecting complaint data, encouraging improvements in customer service. For example, it can analyze the customer's facial expressions and voice and display an emotion score. It can also notify areas for improvement in customer service in real time, enabling responses based on the customer's emotions. This allows for real-time feedback on customer emotions and encouraging improvements in customer service.

[0076] The text analysis unit can estimate customer emotions and track changes in emotions over time. For example, it uses natural language processing technology to calculate an emotion score from text and analyze the timing of complaints and changes in emotions. By tracking changes in customer emotions over time, it is possible to analyze the timing of complaints and changes in emotions. It is also possible to propose countermeasures at the appropriate time based on changes in emotions.

[0077] The text analysis unit can incorporate deep learning models to extract potential problems behind the content of complaints. For example, LSTM or Transformer models can be used to extract patterns and commonalities between complaints. By incorporating deep learning models to extract potential problems behind the content of complaints, more accurate problem extraction becomes possible. Specific improvement measures can also be proposed based on the extracted problems.

[0078] The insight generation unit can compare claims data from different industries and fields to identify common problems and trends. For example, it can compare claims data from the manufacturing and service industries to extract frequently occurring issues and analyze common trends. This makes it possible to identify common problems and trends by comparing claims data from different industries and fields. It can also share best practices between different industries and propose improvement measures.

[0079] The insight generation unit uses the emotion estimation function to consider customer emotions when generating insights and propose improvement measures that are likely to resonate with the customer emotionally. For example, it calculates a customer emotion score from the content of the complaint and uses an expression method that elicits empathy based on the emotion analysis results. This makes it possible to consider customer emotions and propose improvement measures that are likely to resonate with the customer emotionally. It is also possible to formulate a communication strategy based on emotions.

[0080] The cause analysis unit can estimate the customer's emotions and set the priority of the problem based on the intensity of the emotion. For example, it can calculate an emotion score from the content of the complaint and prioritize the problem with a high emotion score. This allows for a prompt response by setting the priority of the problem based on the intensity of the customer's emotion. It can also suggest countermeasures according to the intensity of the emotion, improving customer satisfaction.

[0081] The processing flow of the second embodiment will be briefly explained below.

[0082] Step 1: The complaint data collection department collects complaint data from customers. For example, data that exists in various formats such as emails, chats, and phone records can be collected. The complaint data collection department can also collect data from social media and review sites. Step 2: The preprocessing section preprocesses the collected claim data. For example, it normalizes the text, removes unnecessary information, and standardizes the language. The preprocessing section also converts audio data into text, allowing the tone and speed of the speech to be included in the analysis. Furthermore, the preprocessing section supports different languages ​​and cultural backgrounds, enabling analysis from a global perspective. Step 3: The text analysis unit performs text analysis on the preprocessed complaint data. For example, natural language processing technology is used to analyze the content of complaints and extract the frequency, trends, and relevance of problems. The text analysis unit can also estimate customer sentiment and track sentiment changes over time. Furthermore, the text analysis unit introduces a deep learning model to extract potential problems behind the content of complaints. Step 4: The insight generation unit generates insights based on the frequency, trends, and relevance of the issues extracted by the text analysis unit. For example, it performs frequency analysis, trend analysis, correlation analysis, etc. The insight generation unit can also take into account metadata such as the location and time of the complaint to perform a more detailed analysis. Furthermore, the insight generation unit visualizes and displays the results of the text analysis to enable intuitive understanding. Step 5: The Cause Analysis Department analyzes the causes of the complaint based on the insights generated by the Insight Generation Department. For example, it performs causal relationship identification, regression analysis, factor analysis, etc. The Cause Analysis Department also integrates the company's internal data with complaint data to more accurately identify the cause. After identifying the problem, the Cause Analysis Department also refers to past solutions to similar complaints and their effectiveness to propose the optimal solution. Step 6: The action plan recommendation unit recommends an action plan based on the problems identified by the cause analysis unit. For example, it proposes improvement measures, formulates an implementation plan, and measures the effectiveness. This enables the AI ​​system according to the embodiment to efficiently analyze customer complaint data and respond quickly and appropriately. For example, by quickly identifying the cause of a complaint and taking appropriate improvement measures, customer satisfaction can be improved. In addition, by recommending an action plan to prevent future complaints, the company's credibility can be enhanced.

[0083] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0084] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0085] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0086] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0087] 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.

[0088] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0089] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0090] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0091] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0092] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0093] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0094] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0095] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0096] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0097] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0099] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0100] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0101] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0102] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0103] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0104] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0105] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0107] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0108] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0111] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0112] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0113] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0116] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0117] 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.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0124] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0127] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0133] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0134] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0135] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0136] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0137] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0138] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0139] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0140] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0141] 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.

[0142] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0143] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0144] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0145] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0146] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0147] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0148] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0149] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0150] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a claim data collection unit that collects claim data; a preprocessing unit that preprocesses the complaint data collected by the complaint data collection unit; a text analysis unit that performs text analysis on the claim data preprocessed by the preprocessing unit; an insight generation unit that generates insights based on the frequency, tendency, and relevance of the problems extracted by the text analysis unit; a cause analysis unit that analyzes the cause of a complaint based on the insight generated by the insight generation unit; an action plan recommendation unit that recommends an action plan based on the problem identified by the cause analysis unit. A system characterized by:

2. The complaint data collection unit Collect data from the aforementioned social media and review sites 2. The system of claim 1.

3. The pre-treatment unit Converts voice data to text and includes voice tone and speed in the analysis 2. The system of claim 1.

4. The text analysis unit Estimate customer sentiment and track changes in sentiment over time 2. The system of claim 1.

5. The insight generation unit Visualize and display text analysis results for intuitive understanding 2. The system of claim 1.

6. The cause analysis unit Estimating customer sentiment and prioritizing the issue based on the intensity of the sentiment 2. The system of claim 1.

7. The complaint data collection unit Estimate customer sentiment in real time and prioritize the complaint according to the intensity of the sentiment.

2. The system of claim 1.

8. The cause analysis unit Using emotion estimation, consider customer emotions when identifying problems and propose solutions that resonate with them emotionally.

2. The system of claim 1.

Images