system

Abstract

The system according to the embodiment aims to efficiently evaluate the accuracy of customer service and identify areas for improvement. [Solution] The system according to the embodiment includes a collection unit, a text conversion unit, a matching unit, a digitization unit, and an extraction unit. The collection unit collects communication logs. The text conversion unit converts the logs collected by the collection unit into text. The matching unit matches the logs converted into text by the text conversion unit with a standard response manual. The digitization unit digitizes the accuracy of the response based on the matching results obtained by the matching unit. The extraction unit extracts cases whose numerical values ​​are below a certain standard using the digitization unit.

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 technologies have had the problem of making it difficult to efficiently evaluate the accuracy of customer service and identify areas for improvement.

[0005] The system according to the embodiment aims to efficiently evaluate the accuracy of customer service and identify areas for improvement. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a text conversion unit, a matching unit, a digitization unit, and an extraction unit. The collection unit collects communication logs. The text conversion unit converts the logs collected by the collection unit into text. The matching unit matches the logs converted into text by the text conversion unit with a standard response manual. The digitization unit digitizes the accuracy of the response based on the matching results obtained by the matching unit. The extraction unit extracts cases whose numerical values ​​are below a certain standard using the digitization unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently evaluate the accuracy of customer service and identify areas for improvement. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A customer service evaluation system according to an embodiment of the present invention is a system that visualizes customer communication logs by tracing them all and quantifying them. This customer service evaluation system collects customer communication logs, converts them into text, and compares them with a standard response manual to quantify the accuracy of the response. Cases with low numerical values ​​are extracted and used to provide crew training. This system can improve the quality of customer service. For example, if a crew member provides an inappropriate response to a customer question, appropriate training can be provided to the crew member, resulting in improved response from the next time onwards. Furthermore, visualization through full tracing makes it possible to grasp the crew's response status in real time, enabling faster response. As a result, the customer service evaluation system can improve the quality of customer service.

[0029] A customer interaction evaluation system according to an embodiment includes a collection unit, a text conversion unit, a matching unit, a digitization unit, and an extraction unit. The collection unit collects communication logs with customers. The collected logs include, but are not limited to, text messages, voice recordings, and video calls. For example, the collection unit can collect voice recordings and convert them into text using voice recognition technology. The collection unit can also analyze the content of video calls and extract important parts to convert them into text. The text conversion unit converts the logs collected by the collection unit into text. For example, voice recognition technology or OCR technology can be used for the text conversion, but are not limited to these examples. For example, the text conversion unit can convert voice recordings into text data using voice recognition technology. The text conversion unit can also convert handwritten notes into text data using OCR technology. The matching unit matches the logs converted into text by the text conversion unit with a reference response manual. For example, keyword matching or context analysis can be used for the matching, but are not limited to these examples. For example, the matching unit can calculate the degree of agreement between the logs and the reference response manual using keyword matching. The matching unit can also use context analysis to gain a deeper understanding of the content of the log and perform more accurate matching. The quantification unit quantifies the accuracy of the response based on the matching results obtained by the matching unit. For example, a scoring algorithm or evaluation criteria can be used for the quantification, but this is not a limitation. For example, the quantification unit quantifies the accuracy of the log using a scoring algorithm. The quantification unit can also evaluate and quantify the quality of the log based on the evaluation criteria. The extraction unit extracts cases whose numerical values ​​are below a certain standard using the quantification unit. For example, a score threshold or evaluation criteria can be used for the extraction, but this is not a limitation. For example, the extraction unit extracts cases whose scores are below a certain threshold. The extraction unit can also extract important cases based on the evaluation criteria. This allows the customer service evaluation system according to the embodiment to improve the quality of customer service.

[0030] The customer service evaluation system includes a training unit that provides crew training based on the extracted cases. The training unit provides crew training based on the extracted cases. For example, a training program or a feedback session may be used for the training, but is not limited to such examples. For example, the training unit uses a training program to provide the crew with training on appropriate response methods. The training unit can also point out specific areas for improvement to the crew through feedback sessions. In this way, by providing crew training based on the extracted cases, the quality of customer service can be improved.

[0031] The customer service evaluation system includes a visualization unit that visualizes quantified data. The visualization unit visualizes the quantified data. For example, a graph display or a dashboard display is used for visualization, but is not limited to these examples. For example, the visualization unit displays the quantified data as a graph, allowing the status of customer service to be visually grasped. The visualization unit can also display data in real time using a dashboard, enabling a quick response. In this way, by visualizing the quantified data, the status of customer service can be grasped in real time.

[0032] The customer interaction evaluation system includes an efficiency improvement unit that improves the efficiency of the log collection method. The efficiency improvement unit improves the efficiency of the log collection method. Examples of the improvement in efficiency include, but are not limited to, automating data collection and optimizing processes. For example, the efficiency improvement unit automates data collection to reduce manual collection work. The efficiency improvement unit can also optimize processes to improve the efficiency of collection work. As a result, efficient log collection becomes possible by improving the efficiency of the log collection method.

[0033] The customer service evaluation system includes a suggestion unit that suggests improvements based on the matching results. The suggestion unit suggests improvements based on the matching results. For example, a specific action plan and indicators for improvement are used for the suggestion, but the suggestions are not limited to these examples. For example, the suggestion unit proposes a specific action plan and shows the crew specific steps for improvement. The suggestion unit can also provide indicators for improvement and indicate criteria for the crew to use for self-evaluation. In this way, the quality of customer service can be further improved by suggesting improvements based on the matching results.

[0034] In the customer interaction evaluation system, a collection unit analyzes past communication history and selects the optimal collection method. The collection unit analyzes past communication history and selects the optimal collection method. For example, past data analysis results and collection efficiency may be used for the analysis, but are not limited to such examples. For example, the collection unit identifies the most effective collection method from the past communication history and applies that method. The collection unit can also improve the quality of the logs by analyzing the past history and collecting data at specific time periods. Furthermore, the collection unit can select the optimal collection method for a specific user group based on the past history. In this way, the optimal collection method can be selected by analyzing the past communication history, and the quality of the logs can be improved.

[0035] In the customer interaction evaluation system, when a collection unit collects logs, the collection unit filters the logs based on the user's current situation and areas of interest. When collecting logs, the collection unit filters the logs based on the user's current situation and areas of interest. For example, the user's areas of interest and current situation are used for filtering, but this example is not limiting. For example, the collection unit preferentially collects logs related to topics in which the user is currently interested. The collection unit can also collect appropriate logs based on the user's current situation (e.g., at work, on break). Furthermore, the collection unit can filter logs related to areas of interest by referring to the user's past behavior history. In this way, by filtering the logs based on the user's current situation and areas of interest, highly relevant logs can be collected.

[0036] In the customer interaction evaluation system, when a collection unit collects logs, the collection unit prioritizes collecting highly relevant logs by taking into consideration the user's geographical location information. When collecting logs, the collection unit prioritizes collecting highly relevant logs by taking into consideration the user's geographical location information. For example, GPS data or location information services can be used to acquire the geographical location information, but the present invention is not limited to such examples. For example, when a user is in a specific area, the collection unit prioritizes collecting logs related to that area. The collection unit can also collect the most relevant logs based on the user's current location. Furthermore, the collection unit can select highly relevant logs by referring to the user's movement history. This allows highly relevant logs to be collected efficiently by taking into consideration the user's geographical location information.

[0037] In the customer service evaluation system, the collection unit analyzes the user's social media activities and collects related logs when collecting logs. The collection unit analyzes the user's social media activities and collects related logs when collecting logs. For example, the content of posts, the number of likes, and the number of comments are used to analyze social media activities, but are not limited to these examples. For example, the collection unit analyzes the user's social media activities and collects related logs. The collection unit can also prioritize collecting logs related to topics in which the user has shown interest on social media. Furthermore, the collection unit can collect related logs by referring to the activities of the user's followers and friends on social media. In this way, highly relevant logs can be collected by analyzing the user's social media activities.

[0038] In the customer interaction evaluation system, the text conversion unit adjusts the level of detail of the text based on the importance of the log when converting the log to text. The text conversion unit adjusts the level of detail of the text based on the importance of the log when converting the log to text. For example, the adjustment of the level of detail can be performed by omitting or adding information according to the importance, but is not limited to such an example. For example, the text conversion unit converts logs with high importance into text in detail and logs with low importance into text in a concise manner. The text conversion unit can also determine the priority of the text conversion based on the importance. Furthermore, the text conversion unit can convert logs with high importance into text that includes detailed explanations and annotations. This enables efficient text conversion by adjusting the level of detail of the text based on the importance of the log.

[0039] In the customer interaction evaluation system, the text conversion unit applies different text conversion algorithms depending on the log category when converting the log into text. The text conversion unit applies different text conversion algorithms depending on the log category when converting the log into text. For example, a natural language processing algorithm or a machine learning algorithm is used to apply the text conversion algorithm, but the application is not limited to these examples. For example, the text conversion unit selects and applies an optimal text conversion algorithm for each category. The text conversion unit can also adjust the level of detail and expression method of the text conversion depending on the log category. Furthermore, the text conversion unit can improve accuracy by using different text conversion algorithms for each category. In this way, the accuracy of the text conversion is improved by applying the optimal text conversion algorithm depending on the log category.

[0040] In the customer interaction evaluation system, the text conversion unit determines the priority of text conversion based on the time of submission of the logs when converting the logs to text. The text conversion unit determines the priority of text conversion based on the time of submission of the logs when converting the logs to text. For example, the time of submission or importance is used to determine the priority, but is not limited to such examples. For example, the text conversion unit gives priority to converting logs that have been submitted more recently to text. The text conversion unit can also determine the priority of text conversion based on the time of submission. Furthermore, the text conversion unit can also convert logs that have been submitted earlier to text later. In this way, by determining the priority of text conversion based on the time of submission of the logs, efficient text conversion is possible.

[0041] In the customer interaction evaluation system, the text conversion unit adjusts the order of text conversion based on the relevance of the logs when converting the logs to text. The text conversion unit adjusts the order of text conversion based on the relevance of the logs when converting the logs to text. For example, an order based on relevance or an order based on importance is used to adjust the order, but is not limited to these examples. For example, the text conversion unit prioritizes converting highly relevant logs to text. The text conversion unit can also determine the order of text conversion based on relevance. Furthermore, the text conversion unit can also postpone converting less relevant logs to text. In this way, adjusting the order of text conversion based on the relevance of the logs enables efficient text conversion.

[0042] In the customer interaction evaluation system, the matching unit improves the accuracy of matching by taking into account the interrelationships between logs when matching. The matching unit improves the accuracy of matching by taking into account the interrelationships between logs when matching. The interrelationships can be considered, for example, by taking into account the relevance or strength of interaction between the logs, but is not limited to such examples. For example, the matching unit analyzes the interrelationships between the logs and prioritizes matching of highly related logs. The matching unit can also improve the accuracy of matching based on the interrelationships between the logs. Furthermore, the matching unit can perform optimal matching by taking into account the interrelationships between the logs. In this way, the accuracy of matching is improved by taking into account the interrelationships between the logs.

[0043] In the customer interaction evaluation system, the matching unit performs matching by taking into consideration attribute information of the log submitter. The matching unit performs matching by taking into consideration attribute information of the log submitter, for example, but not limited to, age, gender, and occupation. For example, the matching unit performs optimal matching by taking into consideration attribute information of the submitter (e.g., age, gender). The matching unit can also improve the accuracy of matching based on the attribute information of the submitter. Furthermore, the matching unit can match highly relevant logs by referring to the attribute information of the submitter. In this way, optimal matching is possible by taking into consideration the attribute information of the submitter.

[0044] In the customer interaction evaluation system, the matching unit performs matching taking into account the geographical distribution of logs. The matching unit performs matching taking into account the geographical distribution of logs. Consideration of the geographical distribution can be, for example, the distribution of logs by region or geographical relevance, but is not limited to such examples. For example, the matching unit analyzes the geographical distribution of logs and prioritizes matching of highly relevant logs. The matching unit can also improve the accuracy of matching based on the geographical distribution. Furthermore, the matching unit can perform optimal matching taking into account the geographical distribution. This makes it possible to perform optimal matching by considering the geographical distribution of logs.

[0045] In the customer interaction evaluation system, the matching unit improves the accuracy of matching by referring to related literature in the log during matching. The matching unit improves the accuracy of matching by referring to related literature in the log during matching. For example, literature selection criteria and reference methods are used to refer to related literature, but are not limited to such examples. For example, the matching unit improves the accuracy of matching by referring to related literature. The matching unit can also perform optimal matching based on the related literature. Furthermore, the matching unit can match highly related logs by referring to the related literature. In this way, the accuracy of matching is improved by referring to the related literature.

[0046] In the customer interaction evaluation system, the quantifying unit adjusts the level of detail of the quantification based on the importance of the log when quantifying the log. The quantifying unit adjusts the level of detail of the quantification based on the importance of the log when quantifying the log. Adjustments to the level of detail can be made, for example, by adjusting the level of detail of the quantification or omitting or adding information according to the importance, but are not limited to such examples. For example, the quantifying unit quantifies logs of high importance in detail and quantifies logs of low importance in a concise manner. The quantifying unit can also determine the priority of the quantification based on the importance. Furthermore, the quantifying unit can quantify logs of high importance including detailed explanations and annotations. This enables efficient quantification by adjusting the level of detail of the quantification based on the importance of the log.

[0047] In the customer support evaluation system, the quantification unit applies different quantification algorithms depending on the log category when digitizing. The quantification unit applies different quantification algorithms depending on the log category when digitizing. For example, a scoring algorithm or an evaluation algorithm is used to apply the quantification algorithm, but the application is not limited to these examples. For example, the quantification unit selects and applies an optimal quantification algorithm for each category. The quantification unit can also adjust the level of detail and expression method of the quantification depending on the log category. Furthermore, the quantification unit can improve accuracy by using different quantification algorithms for each category. In this way, the accuracy of the quantification is improved by applying the optimal quantification algorithm depending on the log category.

[0048] In the customer response evaluation system, the quantification unit determines the priority of quantification based on the time of log submission when quantifying. The quantification unit determines the priority of quantification based on the time of log submission when quantifying. For example, the time of submission or importance is used to determine the priority, but is not limited to such examples. For example, the quantification unit prioritizes quantification of logs submitted more recently. The quantification unit can also determine the priority of quantification based on the time of submission. Furthermore, the quantification unit can also quantify logs submitted earlier at a later date. In this way, efficient quantification is possible by determining the priority of quantification based on the time of log submission.

[0049] In the customer interaction evaluation system, the quantification unit adjusts the order of quantification based on the relevance of the logs when quantifying. The quantification unit adjusts the order of quantification based on the relevance of the logs when quantifying. For example, an order based on relevance or an order based on importance is used to adjust the order, but is not limited to these examples. For example, the quantification unit prioritizes quantification of highly relevant logs. The quantification unit can also determine the order of quantification based on relevance. Furthermore, the quantification unit can quantify less relevant logs later. In this way, by adjusting the order of quantification based on the relevance of the logs, efficient quantification is possible.

[0050] In the customer interaction evaluation system, the extraction unit improves the accuracy of extraction by taking into account the interrelationships between logs during extraction. The extraction unit improves the accuracy of extraction by taking into account the interrelationships between logs during extraction. The interrelationships can be considered, for example, by taking into account the relevance or strength of interaction between the logs, but is not limited to such examples. For example, the extraction unit analyzes the interrelationships between the logs and preferentially extracts highly related cases. The extraction unit can also improve the accuracy of extraction based on the interrelationships between the logs. Furthermore, the extraction unit can extract the most appropriate cases by taking into account the interrelationships between the logs. In this way, the accuracy of extraction is improved by taking into account the interrelationships between the logs.

[0051] In the customer interaction evaluation system, the extraction unit performs extraction while taking into consideration the attribute information of the log submitter. The extraction unit performs extraction while taking into consideration the attribute information of the log submitter. Examples of attribute information that can be taken into consideration include, but are not limited to, age, gender, and occupation. For example, the extraction unit extracts the most suitable job by taking into consideration the attribute information of the submitter (e.g., age, gender). The extraction unit can also improve the accuracy of extraction based on the attribute information of the submitter. Furthermore, the extraction unit can also extract highly relevant jobs by referring to the attribute information of the submitter. This makes it possible to extract the most suitable job by taking into consideration the attribute information of the submitter.

[0052] In the customer interaction evaluation system, the extraction unit performs extraction taking into account the geographical distribution of logs. The extraction unit performs extraction taking into account the geographical distribution of logs. Consideration of the geographical distribution can be, for example, the distribution of logs by region or geographical relevance, but is not limited to such examples. For example, the extraction unit analyzes the geographical distribution of logs and preferentially extracts highly relevant cases. The extraction unit can also improve the accuracy of extraction based on the geographical distribution. Furthermore, the extraction unit can extract optimal cases taking into account the geographical distribution. This makes it possible to extract optimal cases by considering the geographical distribution of logs.

[0053] In the customer response evaluation system, the extraction unit improves the accuracy of extraction by referring to related literature in the log during extraction. The extraction unit improves the accuracy of extraction by referring to related literature in the log during extraction. For example, literature selection criteria and reference methods are used to refer to related literature, but are not limited to these examples. For example, the extraction unit improves the accuracy of extraction by referring to related literature. The extraction unit can also extract optimal cases based on the related literature. Furthermore, the extraction unit can extract highly relevant cases by referring to the related literature. In this way, the accuracy of extraction is improved by referring to the related literature.

[0054] In the customer response evaluation system, the instruction department refers to past instruction history when providing instruction to select the optimal instruction method. When providing instruction, the instruction department refers to past instruction history to select the optimal instruction method. When providing instruction, the instruction history can be referenced, for example, by using past instruction content and instruction results, but is not limited to such examples. For example, the instruction department analyzes past instruction history to select the most effective instruction method. The instruction department can also select the optimal instruction method for a specific user based on the past instruction history. Furthermore, the instruction department can also improve the accuracy of instruction by referring to the past instruction history. In this way, by referring to the past instruction history, the optimal instruction method can be selected and the accuracy of instruction can be improved.

[0055] In the customer interaction evaluation system, the instruction department selects the optimal instruction method by taking into account the user's geographical location information when providing instruction. The instruction department selects the optimal instruction method by taking into account the user's geographical location information when providing instruction. Examples of the geographical location information include, but are not limited to, GPS data and location information services. For example, if the user is in a specific area, the instruction department selects an instruction method related to that area. The instruction department can also select the most relevant instruction method based on the user's current location. Furthermore, the instruction department can select the optimal instruction method by referring to the user's movement history. In this way, by taking into account the user's geographical location information, the optimal instruction method can be selected and the accuracy of the instruction can be improved.

[0056] In the customer interaction evaluation system, the visualization unit selects the optimal display method by referring to past visualization data when performing visualization. The visualization unit selects the optimal display method by referring to past visualization data when performing visualization. For example, past data and a history of display methods are used to refer to the visualization data, but this example is not limiting. For example, the visualization unit analyzes past visualization data and selects the most effective display method. The visualization unit can also select the optimal display method for a specific user based on the past visualization data. Furthermore, the visualization unit can also improve the accuracy of the display by referring to the past visualization data. In this way, by referring to the past visualization data, the optimal display method can be selected and the accuracy of the display can be improved.

[0057] In the customer service evaluation system, the visualization unit selects the optimal display method by taking into consideration the user's device information when visualizing. The visualization unit selects the optimal display method by taking into consideration the user's device information when visualizing. The device information can be taken into consideration, for example, the type of device and the usage status, but is not limited to such examples. For example, if the user is using a smartphone, the visualization unit provides a display method that matches the screen size. Furthermore, if the user is using a tablet, the visualization unit can also provide a display method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the visualization unit can also provide a simple and highly visible display method. In this way, by taking into consideration the user's device information, the optimal display method can be selected and the accuracy of the display can be improved.

[0058] In the customer response evaluation system, the optimization unit selects the optimal optimization method by referring to past optimization data during optimization. The optimization unit selects the optimal optimization method by referring to past optimization data during optimization. For example, past data and optimization history are used to refer to the optimization data, but this is not limiting. For example, the optimization unit analyzes past optimization data to select the most effective optimization method. The optimization unit can also select the optimal optimization method for a specific user based on the past optimization data. Furthermore, the optimization unit can also improve the accuracy of optimization by referring to the past optimization data. In this way, by referring to the past optimization data, the optimal optimization method can be selected and the accuracy of optimization can be improved.

[0059] In the customer service evaluation system, the optimization unit selects the optimal optimization method by taking into account the user's device information during optimization. The optimization unit selects the optimal optimization method by taking into account the user's device information during optimization. Examples of device information that can be taken into account include, but are not limited to, the type of device and usage status. For example, if the user is using a smartphone, the optimization unit provides an optimization method tailored to the device's performance. Furthermore, if the user is using a tablet, the optimization unit can provide a method optimized for a large screen. Furthermore, if the user is using a smartwatch, the optimization unit can provide a simple and efficient optimization method. In this way, by taking into account the user's device information, the optimal optimization method can be selected and the accuracy of optimization can be improved.

[0060] In the customer interaction evaluation system, when making a proposal, the proposal unit refers to past proposal history to select the optimal proposal method. When making a proposal, the proposal unit refers to past proposal history to select the optimal proposal method. For example, past proposal content and proposal results are used to refer to the proposal history, but this example is not limiting. For example, the proposal unit analyzes past proposal history to select the most effective proposal method. The proposal unit can also select the optimal proposal method for a specific user based on the past proposal history. Furthermore, the proposal unit can also improve the accuracy of the proposal by referring to the past proposal history. In this way, by referring to the past proposal history, the optimal proposal method can be selected and the accuracy of the proposal can be improved.

[0061] In the customer interaction evaluation system, when making a proposal, the proposal unit selects the optimal proposal method by taking into consideration the user's geographical location information. When making a proposal, the proposal unit selects the optimal proposal method by taking into consideration the user's geographical location information. Examples of the geographical location information include, but are not limited to, GPS data and location information services. For example, when the user is in a specific area, the proposal unit makes proposals related to that area. The proposal unit can also make the most relevant proposal based on the user's current location. Furthermore, the proposal unit can make the optimal proposal by referring to the user's movement history. In this way, by taking into consideration the user's geographical location information, the optimal proposal method can be selected and the accuracy of the proposal can be improved.

[0062] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0063] In the customer interaction evaluation system, the collection unit can also analyze past communication history and select the optimal collection method. For example, the collection unit identifies the most effective collection method from the past communication history and applies that method. The collection unit can also improve the quality of logs by analyzing the past history and collecting data at specific time periods. Furthermore, the collection unit can select the optimal collection method for a specific user group based on the past history. In this way, by analyzing the past communication history, the optimal collection method can be selected and the quality of logs can be improved.

[0064] In the customer interaction evaluation system, when the collection unit collects logs, the collection unit can also filter the logs based on the user's current situation and areas of interest. For example, the collection unit prioritizes collecting logs related to topics that the user is currently interested in. The collection unit can also collect appropriate logs based on the user's current situation (e.g., at work, on break). Furthermore, the collection unit can filter logs related to areas of interest by referring to the user's past behavior history. In this way, highly relevant logs can be collected by filtering the logs based on the user's current situation and areas of interest.

[0065] In the customer interaction evaluation system, when the collection unit collects logs, the collection unit can prioritize collecting highly relevant logs by taking into account the user's geographical location information. For example, if the user is in a specific area, the collection unit can prioritize collecting logs related to that area. The collection unit can also collect the most relevant logs based on the user's current location. Furthermore, the collection unit can select highly relevant logs by referring to the user's movement history. In this way, highly relevant logs can be efficiently collected by taking into account the user's geographical location information.

[0066] In the customer interaction evaluation system, the text conversion unit can also adjust the level of detail of the text based on the importance of the log when converting the log into text. For example, the text conversion unit converts logs with high importance into text in detail and logs with low importance into text in a concise manner. The text conversion unit can also determine the priority of the text conversion based on the importance. Furthermore, the text conversion unit can convert logs with high importance into text that includes detailed explanations and annotations. This allows for efficient text conversion by adjusting the level of detail of the text based on the importance of the log.

[0067] In the customer interaction evaluation system, the text conversion unit can apply different text conversion algorithms depending on the log category when converting the log into text. For example, the text conversion unit selects and applies the optimal text conversion algorithm for each category. The text conversion unit can also adjust the level of detail and expression of the text depending on the log category. Furthermore, the text conversion unit can improve accuracy by using different text conversion algorithms for each category. In this way, the accuracy of the text conversion can be improved by applying the optimal text conversion algorithm depending on the log category.

[0068] In the customer interaction evaluation system, the text conversion unit can also determine the priority of text conversion based on the time of submission of the logs when converting the logs to text. For example, the text conversion unit can give priority to converting logs that were submitted more recently. The text conversion unit can also determine the priority of text conversion based on the time of submission. Furthermore, the text conversion unit can also convert logs that were submitted earlier at a later date. In this way, by determining the priority of text conversion based on the time of submission of the logs, efficient text conversion is possible.

[0069] The processing flow of the first embodiment will be briefly explained below.

[0070] Step 1: The collection department collects communication logs with customers. Collected logs include text messages, voice recordings, video calls, etc. For example, the collection department can collect voice recordings and convert them into text using voice recognition technology. It can also analyze the content of video calls, extract important parts, and convert them into text. Step 2: The text conversion unit converts the logs collected by the collection unit into text. This conversion can be done using voice recognition or OCR technology. For example, voice recordings can be converted into text data using voice recognition technology, and handwritten notes can be converted into text data using OCR technology. Step 3: The matching unit matches the log converted to text by the text conversion unit with the reference response manual. Keyword matching and context analysis are used for matching. For example, keyword matching can be used to calculate the degree of agreement between the log and the reference response manual, and context analysis can be used to gain a deeper understanding of the log content, allowing for more accurate matching. Step 4: The quantification unit quantifies the accuracy of the correspondence based on the matching results obtained by the matching unit. A scoring algorithm or evaluation criteria is used for the quantification. For example, the accuracy of the log can be quantified using a scoring algorithm, and the quality of the log can be evaluated and quantified based on the evaluation criteria. Step 5: The extraction unit extracts cases whose numerical values ​​are below a certain standard using the quantification unit. Score thresholds and evaluation criteria are used for extraction. For example, cases whose scores are below a certain threshold can be extracted, and important cases can be extracted based on the evaluation criteria.

[0071] (Example 2) A customer service evaluation system according to an embodiment of the present invention is a system that visualizes customer communication logs by tracing them all and quantifying them. This customer service evaluation system collects customer communication logs, converts them into text, and compares them with a standard response manual to quantify the accuracy of the response. Cases with low numerical values ​​are extracted and used to provide crew training. This system can improve the quality of customer service. For example, if a crew member provides an inappropriate response to a customer question, appropriate training can be provided to the crew member, resulting in improved response from the next time onwards. Furthermore, visualization through full tracing makes it possible to grasp the crew's response status in real time, enabling faster response. As a result, the customer service evaluation system can improve the quality of customer service.

[0072] A customer interaction evaluation system according to an embodiment includes a collection unit, a text conversion unit, a matching unit, a digitization unit, and an extraction unit. The collection unit collects communication logs with customers. The collected logs include, but are not limited to, text messages, voice recordings, and video calls. For example, the collection unit can collect voice recordings and convert them into text using voice recognition technology. The collection unit can also analyze the content of video calls and extract important parts to convert them into text. The text conversion unit converts the logs collected by the collection unit into text. For example, voice recognition technology or OCR technology can be used for the text conversion, but are not limited to these examples. For example, the text conversion unit can convert voice recordings into text data using voice recognition technology. The text conversion unit can also convert handwritten notes into text data using OCR technology. The matching unit matches the logs converted into text by the text conversion unit with a reference response manual. For example, keyword matching or context analysis can be used for the matching, but are not limited to these examples. For example, the matching unit can calculate the degree of agreement between the logs and the reference response manual using keyword matching. The matching unit can also use context analysis to gain a deeper understanding of the content of the log and perform more accurate matching. The quantification unit quantifies the accuracy of the response based on the matching results obtained by the matching unit. For example, a scoring algorithm or evaluation criteria can be used for the quantification, but this is not a limitation. For example, the quantification unit quantifies the accuracy of the log using a scoring algorithm. The quantification unit can also evaluate and quantify the quality of the log based on the evaluation criteria. The extraction unit extracts cases whose numerical values ​​are below a certain standard using the quantification unit. For example, a score threshold or evaluation criteria can be used for the extraction, but this is not a limitation. For example, the extraction unit extracts cases whose scores are below a certain threshold. The extraction unit can also extract important cases based on the evaluation criteria. This allows the customer service evaluation system according to the embodiment to improve the quality of customer service.

[0073] The customer service evaluation system includes a training unit that provides crew training based on the extracted cases. The training unit provides crew training based on the extracted cases. For example, a training program or a feedback session may be used for the training, but is not limited to such examples. For example, the training unit uses a training program to provide the crew with training on appropriate response methods. The training unit can also point out specific areas for improvement to the crew through feedback sessions. In this way, by providing crew training based on the extracted cases, the quality of customer service can be improved.

[0074] The customer service evaluation system includes a visualization unit that visualizes quantified data. The visualization unit visualizes the quantified data. For example, a graph display or a dashboard display is used for visualization, but is not limited to these examples. For example, the visualization unit displays the quantified data as a graph, allowing the status of customer service to be visually grasped. The visualization unit can also display data in real time using a dashboard, enabling a quick response. In this way, by visualizing the quantified data, the status of customer service can be grasped in real time.

[0075] The customer interaction evaluation system includes an efficiency improvement unit that improves the efficiency of the log collection method. The efficiency improvement unit improves the efficiency of the log collection method. Examples of the improvement in efficiency include, but are not limited to, automating data collection and optimizing processes. For example, the efficiency improvement unit automates data collection to reduce manual collection work. The efficiency improvement unit can also optimize processes to improve the efficiency of collection work. As a result, efficient log collection becomes possible by improving the efficiency of the log collection method.

[0076] The customer service evaluation system includes a suggestion unit that suggests improvements based on the matching results. The suggestion unit suggests improvements based on the matching results. For example, a specific action plan and indicators for improvement are used for the suggestion, but the suggestions are not limited to these examples. For example, the suggestion unit proposes a specific action plan and shows the crew specific steps for improvement. The suggestion unit can also provide indicators for improvement and indicate criteria for the crew to use for self-evaluation. In this way, the quality of customer service can be further improved by suggesting improvements based on the matching results.

[0077] In a customer interaction evaluation system, a collection unit estimates a user's emotions and adjusts the timing of log collection based on the estimated user emotions. The collection unit estimates a user's emotions and adjusts the timing of log collection based on the estimated user emotions. The emotion estimation may be performed using, for example, emotion recognition technology or survey results, but is not limited to these examples. For example, if the user is feeling stressed, the collection unit delays the collection timing to reduce the burden on the user. Furthermore, if the user is relaxed, the collection unit can also advance the collection timing to collect more logs. Furthermore, if the user is in a hurry, the collection unit can optimize the collection timing to quickly collect the minimum necessary logs. This reduces the burden on the user by adjusting the timing of log collection according to the user's emotions, enabling efficient log collection.

[0078] In the customer interaction evaluation system, a collection unit analyzes past communication history and selects the optimal collection method. The collection unit analyzes past communication history and selects the optimal collection method. For example, past data analysis results and collection efficiency may be used for the analysis, but are not limited to such examples. For example, the collection unit identifies the most effective collection method from the past communication history and applies that method. The collection unit can also improve the quality of the logs by analyzing the past history and collecting data at specific time periods. Furthermore, the collection unit can select the optimal collection method for a specific user group based on the past history. In this way, the optimal collection method can be selected by analyzing the past communication history, and the quality of the logs can be improved.

[0079] In the customer interaction evaluation system, when a collection unit collects logs, the collection unit filters the logs based on the user's current situation and areas of interest. When collecting logs, the collection unit filters the logs based on the user's current situation and areas of interest. For example, the user's areas of interest and current situation are used for filtering, but this example is not limiting. For example, the collection unit preferentially collects logs related to topics in which the user is currently interested. The collection unit can also collect appropriate logs based on the user's current situation (e.g., at work, on break). Furthermore, the collection unit can filter logs related to areas of interest by referring to the user's past behavior history. In this way, by filtering the logs based on the user's current situation and areas of interest, highly relevant logs can be collected.

[0080] In the customer interaction evaluation system, a collection unit estimates a user's emotions and determines the priority of logs to be collected based on the estimated user emotions. The collection unit estimates a user's emotions and determines the priority of logs to be collected based on the estimated user emotions. For example, emotion recognition technology or survey results may be used to estimate emotions, but the present invention is not limited to these examples. For example, if the user is feeling stressed, the collection unit postpones logs of low importance. Furthermore, if the user is relaxed, the collection unit can also prioritize collecting logs of high importance. Furthermore, if the user is in a hurry, the collection unit can prioritize logs that can be collected quickly. In this way, efficient log collection is possible by determining the priority of logs to be collected according to the user's emotions.

[0081] In the customer interaction evaluation system, when a collection unit collects logs, the collection unit prioritizes collecting highly relevant logs by taking into consideration the user's geographical location information. When collecting logs, the collection unit prioritizes collecting highly relevant logs by taking into consideration the user's geographical location information. For example, GPS data or location information services can be used to acquire the geographical location information, but the present invention is not limited to such examples. For example, when a user is in a specific area, the collection unit prioritizes collecting logs related to that area. The collection unit can also collect the most relevant logs based on the user's current location. Furthermore, the collection unit can select highly relevant logs by referring to the user's movement history. This allows highly relevant logs to be collected efficiently by taking into consideration the user's geographical location information.

[0082] In the customer service evaluation system, the collection unit analyzes the user's social media activities and collects related logs when collecting logs. The collection unit analyzes the user's social media activities and collects related logs when collecting logs. For example, the content of posts, the number of likes, and the number of comments are used to analyze social media activities, but are not limited to these examples. For example, the collection unit analyzes the user's social media activities and collects related logs. The collection unit can also prioritize collecting logs related to topics in which the user has shown interest on social media. Furthermore, the collection unit can collect related logs by referring to the activities of the user's followers and friends on social media. In this way, highly relevant logs can be collected by analyzing the user's social media activities.

[0083] In a customer service evaluation system, a text conversion unit estimates a user's emotions and adjusts the text expression method based on the estimated user emotions. The text conversion unit estimates a user's emotions and adjusts the text expression method based on the estimated user emotions. Emotion estimation can be performed using, for example, emotion recognition technology or survey results, but is not limited to these examples. For example, if the user is feeling stressed, the text conversion unit uses concise and easy-to-understand expressions. Furthermore, if the user is relaxed, the text conversion unit can also use expressions including detailed explanations. Furthermore, if the user is in a hurry, the text conversion unit can use short expressions that get to the point. In this way, by adjusting the text expression method according to the user's emotions, it is possible to create text that is easy for the user to understand.

[0084] In the customer interaction evaluation system, the text conversion unit adjusts the level of detail of the text based on the importance of the log when converting the log to text. The text conversion unit adjusts the level of detail of the text based on the importance of the log when converting the log to text. For example, the adjustment of the level of detail can be performed by omitting or adding information according to the importance, but is not limited to such an example. For example, the text conversion unit converts logs with high importance into text in detail and logs with low importance into text in a concise manner. The text conversion unit can also determine the priority of the text conversion based on the importance. Furthermore, the text conversion unit can convert logs with high importance into text that includes detailed explanations and annotations. This enables efficient text conversion by adjusting the level of detail of the text based on the importance of the log.

[0085] In the customer interaction evaluation system, the text conversion unit applies different text conversion algorithms depending on the log category when converting the log into text. The text conversion unit applies different text conversion algorithms depending on the log category when converting the log into text. For example, a natural language processing algorithm or a machine learning algorithm is used to apply the text conversion algorithm, but the application is not limited to these examples. For example, the text conversion unit selects and applies an optimal text conversion algorithm for each category. The text conversion unit can also adjust the level of detail and expression method of the text conversion depending on the log category. Furthermore, the text conversion unit can improve accuracy by using different text conversion algorithms for each category. In this way, the accuracy of the text conversion is improved by applying the optimal text conversion algorithm depending on the log category.

[0086] In a customer service evaluation system, a text conversion unit estimates a user's emotion and adjusts the length of the text based on the estimated user emotion. The text conversion unit estimates a user's emotion and adjusts the length of the text based on the estimated user emotion. The emotion estimation can be performed using, for example, emotion recognition technology or survey results, but is not limited to these examples. For example, if the user is feeling stressed, the text conversion unit generates a short, concise text. Furthermore, if the user is relaxed, the text conversion unit can generate a longer text that includes detailed explanations. Furthermore, if the user is in a hurry, the text conversion unit can generate a short text that focuses on the main points. This allows the length of the text to be adjusted according to the user's emotion, making it possible to generate a text of an appropriate length for the user.

[0087] In the customer interaction evaluation system, the text conversion unit determines the priority of text conversion based on the time of submission of the logs when converting the logs to text. The text conversion unit determines the priority of text conversion based on the time of submission of the logs when converting the logs to text. For example, the time of submission or importance is used to determine the priority, but is not limited to such examples. For example, the text conversion unit gives priority to converting logs that have been submitted more recently to text. The text conversion unit can also determine the priority of text conversion based on the time of submission. Furthermore, the text conversion unit can also convert logs that have been submitted earlier to text later. In this way, by determining the priority of text conversion based on the time of submission of the logs, efficient text conversion is possible.

[0088] In the customer interaction evaluation system, the text conversion unit adjusts the order of text conversion based on the relevance of the logs when converting the logs to text. The text conversion unit adjusts the order of text conversion based on the relevance of the logs when converting the logs to text. For example, an order based on relevance or an order based on importance is used to adjust the order, but is not limited to these examples. For example, the text conversion unit prioritizes converting highly relevant logs to text. The text conversion unit can also determine the order of text conversion based on relevance. Furthermore, the text conversion unit can also postpone converting less relevant logs to text. In this way, adjusting the order of text conversion based on the relevance of the logs enables efficient text conversion.

[0089] In the customer service evaluation system, a matching unit estimates a user's emotions and adjusts matching criteria based on the estimated user emotions. The matching unit estimates a user's emotions and adjusts matching criteria based on the estimated user emotions. Emotion estimation can be performed using, for example, emotion recognition technology or survey results, but is not limited to these examples. For example, if the user is feeling stressed, the matching unit uses simple and easy-to-understand criteria. Alternatively, if the user is relaxed, the matching unit can use detailed criteria. Furthermore, if the user is in a hurry, the matching unit can use criteria that focus on the main points. In this way, by adjusting the matching criteria according to the user's emotions, appropriate matching for the user is possible.

[0090] In the customer interaction evaluation system, the matching unit improves the accuracy of matching by taking into account the interrelationships between logs when matching. The matching unit improves the accuracy of matching by taking into account the interrelationships between logs when matching. The interrelationships can be considered, for example, by taking into account the relevance or strength of interaction between the logs, but is not limited to such examples. For example, the matching unit analyzes the interrelationships between the logs and prioritizes matching of highly related logs. The matching unit can also improve the accuracy of matching based on the interrelationships between the logs. Furthermore, the matching unit can perform optimal matching by taking into account the interrelationships between the logs. In this way, the accuracy of matching is improved by taking into account the interrelationships between the logs.

[0091] In the customer interaction evaluation system, the matching unit performs matching by taking into consideration attribute information of the log submitter. The matching unit performs matching by taking into consideration attribute information of the log submitter, for example, but not limited to, age, gender, and occupation. For example, the matching unit performs optimal matching by taking into consideration attribute information of the submitter (e.g., age, gender). The matching unit can also improve the accuracy of matching based on the attribute information of the submitter. Furthermore, the matching unit can match highly relevant logs by referring to the attribute information of the submitter. In this way, optimal matching is possible by taking into consideration the attribute information of the submitter.

[0092] In a customer service evaluation system, a matching unit estimates a user's emotions and adjusts the order in which matching results are displayed based on the estimated user emotions. The matching unit estimates a user's emotions and adjusts the order in which matching results are displayed based on the estimated user emotions. Emotion estimation can be performed using, for example, emotion recognition technology or survey results, but is not limited to these examples. For example, if a user is feeling stressed, the matching unit can prioritize displaying results with high importance. Furthermore, if a user is relaxed, the matching unit can also display detailed results. Furthermore, if a user is in a hurry, the matching unit can prioritize displaying results that highlight the main points. In this way, by adjusting the order in which matching results are displayed based on the user's emotions, it is possible to display results that are appropriate for the user.

[0093] In the customer interaction evaluation system, the matching unit performs matching taking into account the geographical distribution of logs. The matching unit performs matching taking into account the geographical distribution of logs. Consideration of the geographical distribution can be, for example, the distribution of logs by region or geographical relevance, but is not limited to such examples. For example, the matching unit analyzes the geographical distribution of logs and prioritizes matching of highly relevant logs. The matching unit can also improve the accuracy of matching based on the geographical distribution. Furthermore, the matching unit can perform optimal matching taking into account the geographical distribution. This makes it possible to perform optimal matching by considering the geographical distribution of logs.

[0094] In the customer interaction evaluation system, the matching unit improves the accuracy of matching by referring to related literature in the log during matching. The matching unit improves the accuracy of matching by referring to related literature in the log during matching. For example, literature selection criteria and reference methods are used to refer to related literature, but are not limited to such examples. For example, the matching unit improves the accuracy of matching by referring to related literature. The matching unit can also perform optimal matching based on the related literature. Furthermore, the matching unit can match highly related logs by referring to the related literature. In this way, the accuracy of matching is improved by referring to the related literature.

[0095] In the customer service evaluation system, a quantification unit estimates a user's emotions and adjusts the quantification method based on the estimated user emotions. The quantification unit estimates a user's emotions and adjusts the quantification method based on the estimated user emotions. Emotion recognition technology and survey results are used, for example, to estimate emotions, but are not limited to these examples. For example, if the user is feeling stressed, the quantification unit uses a simple and easy-to-understand quantification method. Furthermore, if the user is relaxed, the quantification unit can also use a detailed quantification method. Furthermore, if the user is in a hurry, the quantification unit can use a quantification method that focuses on the main points. In this way, by adjusting the quantification method according to the user's emotions, quantification that is easy for the user to understand can be achieved.

[0096] In the customer interaction evaluation system, the quantifying unit adjusts the level of detail of the quantification based on the importance of the log when quantifying the log. The quantifying unit adjusts the level of detail of the quantification based on the importance of the log when quantifying the log. Adjustments to the level of detail can be made, for example, by adjusting the level of detail of the quantification or omitting or adding information according to the importance, but are not limited to such examples. For example, the quantifying unit quantifies logs of high importance in detail and quantifies logs of low importance in a concise manner. The quantifying unit can also determine the priority of the quantification based on the importance. Furthermore, the quantifying unit can quantify logs of high importance including detailed explanations and annotations. This enables efficient quantification by adjusting the level of detail of the quantification based on the importance of the log.

[0097] In the customer support evaluation system, the quantification unit applies different quantification algorithms depending on the log category when digitizing. The quantification unit applies different quantification algorithms depending on the log category when digitizing. For example, a scoring algorithm or an evaluation algorithm is used to apply the quantification algorithm, but the application is not limited to these examples. For example, the quantification unit selects and applies an optimal quantification algorithm for each category. The quantification unit can also adjust the level of detail and expression method of the quantification depending on the log category. Furthermore, the quantification unit can improve accuracy by using different quantification algorithms for each category. In this way, the accuracy of the quantification is improved by applying the optimal quantification algorithm depending on the log category.

[0098] In the customer service evaluation system, a quantification unit estimates a user's emotions and determines the priority of quantification based on the estimated user emotions. The quantification unit estimates a user's emotions and determines the priority of quantification based on the estimated user emotions. For example, emotion recognition technology or survey results are used to estimate emotions, but the present invention is not limited to these examples. For example, if the user is feeling stressed, the quantification unit postpones quantification of less important items. Furthermore, if the user is relaxed, the quantification unit can also prioritize quantification of more important items. Furthermore, if the user is in a hurry, the quantification unit can prioritize items that can be quantified quickly. In this way, efficient quantification is possible by determining the priority of quantification according to the user's emotions.

[0099] In the customer response evaluation system, the quantification unit determines the priority of quantification based on the time of log submission when quantifying. The quantification unit determines the priority of quantification based on the time of log submission when quantifying. For example, the time of submission or importance is used to determine the priority, but is not limited to such examples. For example, the quantification unit prioritizes quantification of logs submitted more recently. The quantification unit can also determine the priority of quantification based on the time of submission. Furthermore, the quantification unit can also quantify logs submitted earlier at a later date. In this way, efficient quantification is possible by determining the priority of quantification based on the time of log submission.

[0100] In the customer interaction evaluation system, the quantification unit adjusts the order of quantification based on the relevance of the logs when quantifying. The quantification unit adjusts the order of quantification based on the relevance of the logs when quantifying. For example, an order based on relevance or an order based on importance is used to adjust the order, but is not limited to these examples. For example, the quantification unit prioritizes quantification of highly relevant logs. The quantification unit can also determine the order of quantification based on relevance. Furthermore, the quantification unit can quantify less relevant logs later. In this way, by adjusting the order of quantification based on the relevance of the logs, efficient quantification is possible.

[0101] In the customer interaction evaluation system, an extraction unit estimates a user's emotions and determines the priority of the cases to be extracted based on the estimated user emotions. The extraction unit estimates a user's emotions and determines the priority of the cases to be extracted based on the estimated user emotions. For example, emotion recognition technology or survey results are used to estimate emotions, but the invention is not limited to these examples. For example, if the user is feeling stressed, the extraction unit postpones cases with low importance. Furthermore, if the user is relaxed, the extraction unit can also prioritize cases with high importance. Furthermore, if the user is in a hurry, the extraction unit can prioritize cases that can be extracted quickly. In this way, by determining the priority of the cases to be extracted according to the user's emotions, efficient case extraction is possible.

[0102] In the customer interaction evaluation system, the extraction unit improves the accuracy of extraction by taking into account the interrelationships between logs during extraction. The extraction unit improves the accuracy of extraction by taking into account the interrelationships between logs during extraction. The interrelationships can be considered, for example, by taking into account the relevance or strength of interaction between the logs, but is not limited to such examples. For example, the extraction unit analyzes the interrelationships between the logs and preferentially extracts highly related cases. The extraction unit can also improve the accuracy of extraction based on the interrelationships between the logs. Furthermore, the extraction unit can extract the most appropriate cases by taking into account the interrelationships between the logs. In this way, the accuracy of extraction is improved by taking into account the interrelationships between the logs.

[0103] In the customer interaction evaluation system, the extraction unit performs extraction while taking into consideration the attribute information of the log submitter. The extraction unit performs extraction while taking into consideration the attribute information of the log submitter. Examples of attribute information that can be taken into consideration include, but are not limited to, age, gender, and occupation. For example, the extraction unit extracts the most suitable job by taking into consideration the attribute information of the submitter (e.g., age, gender). The extraction unit can also improve the accuracy of extraction based on the attribute information of the submitter. Furthermore, the extraction unit can also extract highly relevant jobs by referring to the attribute information of the submitter. This makes it possible to extract the most suitable job by taking into consideration the attribute information of the submitter.

[0104] In the customer service evaluation system, an extraction unit estimates a user's emotions and adjusts the display method of the extracted cases based on the estimated user emotions. The extraction unit estimates a user's emotions and adjusts the display method of the extracted cases based on the estimated user emotions. Emotion estimation can be performed using, for example, emotion recognition technology or survey results, but is not limited to these examples. For example, if the user is feeling stressed, the extraction unit provides a simple and easy-to-understand display method. Furthermore, if the user is relaxed, the extraction unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the extraction unit can provide a display method that focuses on the main points. In this way, by adjusting the display method of the extracted cases according to the user's emotions, a display that is easy for the user to understand can be achieved.

[0105] In the customer interaction evaluation system, the extraction unit performs extraction taking into account the geographical distribution of logs. The extraction unit performs extraction taking into account the geographical distribution of logs. Consideration of the geographical distribution can be, for example, the distribution of logs by region or geographical relevance, but is not limited to such examples. For example, the extraction unit analyzes the geographical distribution of logs and preferentially extracts highly relevant cases. The extraction unit can also improve the accuracy of extraction based on the geographical distribution. Furthermore, the extraction unit can extract optimal cases taking into account the geographical distribution. This makes it possible to extract optimal cases by considering the geographical distribution of logs.

[0106] In the customer response evaluation system, the extraction unit improves the accuracy of extraction by referring to related literature in the log during extraction. The extraction unit improves the accuracy of extraction by referring to related literature in the log during extraction. For example, literature selection criteria and reference methods are used to refer to related literature, but are not limited to these examples. For example, the extraction unit improves the accuracy of extraction by referring to related literature. The extraction unit can also extract optimal cases based on the related literature. Furthermore, the extraction unit can extract highly relevant cases by referring to the related literature. In this way, the accuracy of extraction is improved by referring to the related literature.

[0107] In the customer interaction evaluation system, a training unit estimates a user's emotions and adjusts the training method based on the estimated user emotions. The training unit estimates a user's emotions and adjusts the training method based on the estimated user emotions. Emotion estimation can be performed using, for example, emotion recognition technology or survey results, but is not limited to these examples. For example, if the user is feeling stressed, the training unit can provide training in a gentle tone. Furthermore, if the user is relaxed, the training unit can provide training that includes detailed explanations. Furthermore, if the user is in a hurry, the training unit can provide short training that focuses on the main points. In this way, by adjusting the training method according to the user's emotions, it is possible to provide appropriate training for the user.

[0108] In the customer response evaluation system, the instruction department refers to past instruction history when providing instruction to select the optimal instruction method. When providing instruction, the instruction department refers to past instruction history to select the optimal instruction method. When providing instruction, the instruction history can be referenced, for example, by using past instruction content and instruction results, but is not limited to such examples. For example, the instruction department analyzes past instruction history to select the most effective instruction method. The instruction department can also select the optimal instruction method for a specific user based on the past instruction history. Furthermore, the instruction department can also improve the accuracy of instruction by referring to the past instruction history. In this way, by referring to the past instruction history, the optimal instruction method can be selected and the accuracy of instruction can be improved.

[0109] In the customer interaction evaluation system, an instruction unit estimates a user's emotions and determines the priority of instruction based on the estimated user emotions. The instruction unit estimates a user's emotions and determines the priority of instruction based on the estimated user emotions. For example, emotion recognition technology or survey results are used to estimate emotions, but the present invention is not limited to these examples. For example, if the user is feeling stressed, the instruction unit postpones less important instruction. Also, if the user is relaxed, the instruction unit can prioritize more important instruction. Furthermore, if the user is in a hurry, the instruction unit can prioritize items that can be quickly instructed. In this way, efficient instruction is possible by determining the priority of instruction according to the user's emotions.

[0110] In the customer interaction evaluation system, the instruction department selects the optimal instruction method by taking into account the user's geographical location information when providing instruction. The instruction department selects the optimal instruction method by taking into account the user's geographical location information when providing instruction. Examples of the geographical location information include, but are not limited to, GPS data and location information services. For example, if the user is in a specific area, the instruction department selects an instruction method related to that area. The instruction department can also select the most relevant instruction method based on the user's current location. Furthermore, the instruction department can select the optimal instruction method by referring to the user's movement history. In this way, by taking into account the user's geographical location information, the optimal instruction method can be selected and the accuracy of the instruction can be improved.

[0111] In a customer service evaluation system, a visualization unit estimates a user's emotions and adjusts the display method of the visualization based on the estimated user emotions. The visualization unit estimates a user's emotions and adjusts the display method of the visualization based on the estimated user emotions. Emotion estimation can be performed using, for example, emotion recognition technology or survey results, but is not limited to these examples. For example, if the user is feeling stressed, the visualization unit provides a simple and easy-to-understand display method. Furthermore, if the user is relaxed, the visualization unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the visualization unit can provide a display method that focuses on the main points. In this way, by adjusting the display method of the visualization according to the user's emotions, a display that is easy for the user to understand can be achieved.

[0112] In the customer interaction evaluation system, the visualization unit selects the optimal display method by referring to past visualization data when performing visualization. The visualization unit selects the optimal display method by referring to past visualization data when performing visualization. For example, past data and a history of display methods are used to refer to the visualization data, but this example is not limiting. For example, the visualization unit analyzes past visualization data and selects the most effective display method. The visualization unit can also select the optimal display method for a specific user based on the past visualization data. Furthermore, the visualization unit can also improve the accuracy of the display by referring to the past visualization data. In this way, by referring to the past visualization data, the optimal display method can be selected and the accuracy of the display can be improved.

[0113] In the customer service evaluation system, a visualization unit estimates a user's emotions and determines a visualization priority based on the estimated user emotions. The visualization unit estimates a user's emotions and determines a visualization priority based on the estimated user emotions. Emotion estimation can be performed using, for example, emotion recognition technology or survey results, but is not limited to these examples. For example, if the user is feeling stressed, the visualization unit postpones visualization of less important items. Furthermore, if the user is relaxed, the visualization unit can also prioritize visualization of more important items. Furthermore, if the user is in a hurry, the visualization unit can prioritize items that can be visualized quickly. In this way, efficient visualization is possible by determining the visualization priority based on the user's emotions.

[0114] In the customer service evaluation system, the visualization unit selects the optimal display method by taking into consideration the user's device information when visualizing. The visualization unit selects the optimal display method by taking into consideration the user's device information when visualizing. The device information can be taken into consideration, for example, the type of device and the usage status, but is not limited to such examples. For example, if the user is using a smartphone, the visualization unit provides a display method that matches the screen size. Furthermore, if the user is using a tablet, the visualization unit can also provide a display method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the visualization unit can also provide a simple and highly visible display method. In this way, by taking into consideration the user's device information, the optimal display method can be selected and the accuracy of the display can be improved.

[0115] In a customer interaction evaluation system, an optimization unit estimates a user's emotion and adjusts an optimization method based on the estimated user's emotion. The optimization unit estimates a user's emotion and adjusts an optimization method based on the estimated user's emotion. Emotion estimation can be performed using, for example, emotion recognition technology or survey results, but is not limited to these examples. For example, if the user is feeling stressed, the optimization unit uses a simple and easy-to-understand optimization method. Alternatively, if the user is relaxed, the optimization unit can use a detailed optimization method. Furthermore, if the user is in a hurry, the optimization unit can use an optimization method that focuses on the main points. In this way, by adjusting the optimization method according to the user's emotion, it is possible to achieve optimization that is easy for the user to understand.

[0116] In the customer response evaluation system, the optimization unit selects the optimal optimization method by referring to past optimization data during optimization. The optimization unit selects the optimal optimization method by referring to past optimization data during optimization. For example, past data and optimization history are used to refer to the optimization data, but this is not limiting. For example, the optimization unit analyzes past optimization data to select the most effective optimization method. The optimization unit can also select the optimal optimization method for a specific user based on the past optimization data. Furthermore, the optimization unit can also improve the accuracy of optimization by referring to the past optimization data. In this way, by referring to the past optimization data, the optimal optimization method can be selected and the accuracy of optimization can be improved.

[0117] In the customer service evaluation system, an optimization unit estimates a user's emotions and determines the priority of optimization based on the estimated user emotions. The optimization unit estimates a user's emotions and determines the priority of optimization based on the estimated user emotions. For example, emotion recognition technology or survey results are used to estimate emotions, but the present invention is not limited to these examples. For example, if the user is feeling stressed, the optimization unit postpones optimization of less important items. Furthermore, if the user is relaxed, the optimization unit can also prioritize optimization of more important items. Furthermore, if the user is in a hurry, the optimization unit can prioritize items that can be optimized quickly. In this way, efficient optimization is possible by determining the priority of optimization according to the user's emotions.

[0118] In the customer service evaluation system, the optimization unit selects the optimal optimization method by taking into account the user's device information during optimization. The optimization unit selects the optimal optimization method by taking into account the user's device information during optimization. Examples of device information that can be taken into account include, but are not limited to, the type of device and usage status. For example, if the user is using a smartphone, the optimization unit provides an optimization method tailored to the device's performance. Furthermore, if the user is using a tablet, the optimization unit can provide a method optimized for a large screen. Furthermore, if the user is using a smartwatch, the optimization unit can provide a simple and efficient optimization method. In this way, by taking into account the user's device information, the optimal optimization method can be selected and the accuracy of optimization can be improved.

[0119] In the customer interaction evaluation system, a suggestion unit estimates a user's emotions and adjusts the suggestion method based on the estimated user emotions. The suggestion unit estimates a user's emotions and adjusts the suggestion method based on the estimated user emotions. Emotion estimation can be performed using, for example, emotion recognition technology or survey results, but is not limited to these examples. For example, if the user is feeling stressed, the suggestion unit makes a concise and easy-to-understand suggestion. Furthermore, if the user is relaxed, the suggestion unit can also make a suggestion that includes a detailed explanation. Furthermore, if the user is in a hurry, the suggestion unit can make a short suggestion that hits the main points. In this way, by adjusting the suggestion method according to the user's emotions, it is possible to make a suggestion that is easy for the user to understand.

[0120] In the customer interaction evaluation system, when making a proposal, the proposal unit refers to past proposal history to select the optimal proposal method. When making a proposal, the proposal unit refers to past proposal history to select the optimal proposal method. For example, past proposal content and proposal results are used to refer to the proposal history, but this example is not limiting. For example, the proposal unit analyzes past proposal history to select the most effective proposal method. The proposal unit can also select the optimal proposal method for a specific user based on the past proposal history. Furthermore, the proposal unit can also improve the accuracy of the proposal by referring to the past proposal history. In this way, by referring to the past proposal history, the optimal proposal method can be selected and the accuracy of the proposal can be improved.

[0121] In the customer interaction evaluation system, a suggestion unit estimates a user's emotions and determines the priority of suggestions based on the estimated user emotions. The suggestion unit estimates a user's emotions and determines the priority of suggestions based on the estimated user emotions. For example, emotion recognition technology or survey results are used to estimate emotions, but the present invention is not limited to these examples. For example, if the user is feeling stressed, the suggestion unit postpones suggestions of lower importance. Furthermore, if the user is relaxed, the suggestion unit can also prioritize suggestions of higher importance. Furthermore, if the user is in a hurry, the suggestion unit can prioritize items that can be suggested quickly. This enables efficient suggestions by determining the priority of suggestions according to the user's emotions.

[0122] In the customer interaction evaluation system, when making a proposal, the proposal unit selects the optimal proposal method by taking into consideration the user's geographical location information. When making a proposal, the proposal unit selects the optimal proposal method by taking into consideration the user's geographical location information. Examples of the geographical location information include, but are not limited to, GPS data and location information services. For example, when the user is in a specific area, the proposal unit makes proposals related to that area. The proposal unit can also make the most relevant proposal based on the user's current location. Furthermore, the proposal unit can make the optimal proposal by referring to the user's movement history. In this way, by taking into consideration the user's geographical location information, the optimal proposal method can be selected and the accuracy of the proposal can be improved. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, text conversion unit, matching unit, digitization unit, extraction unit, instruction unit, visualization unit, efficiency improvement unit, and suggestion unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects communication logs with customers using the camera 42 and microphone 38B of the smart device 14 and transmits the logs to the data processing device 12 via the control unit 46A. The text conversion unit converts the logs into text using voice recognition technology or OCR technology via the specific processing unit 290 of the data processing device 12. The matching unit matches the logs with a standard response manual via the specific processing unit 290 of the data processing device 12. The digitization unit digitizes the matching results via the specific processing unit 290 of the data processing device 12. The extraction unit extracts cases with numerical values ​​below the standard via the specific processing unit 290 of the data processing device 12. The instruction unit provides crew instruction based on the cases extracted by the specific processing unit 290 of the data processing device 12. The visualization unit visualizes the data digitized by the specific processing unit 290 of the data processing device 12. The efficiency improvement unit improves the efficiency of the log collection method by the specific processing unit 290 of the data processing device 12. The suggestion unit suggests improvements based on the matching results by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, text conversion unit, matching unit, digitization unit, extraction unit, instruction unit, visualization unit, efficiency improvement unit, and suggestion unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects communication logs with customers using the camera 42 and microphone 238 of the smart glasses 214 and transmits the logs to the data processing device 12 via the control unit 46A. The text conversion unit converts the logs into text using voice recognition technology or OCR technology via the specific processing unit 290 of the data processing device 12. The matching unit matches the logs with a standard response manual via the specific processing unit 290 of the data processing device 12. The digitization unit digitizes the matching results via the specific processing unit 290 of the data processing device 12. The extraction unit extracts cases with numerical values ​​below the standard via the specific processing unit 290 of the data processing device 12. The instruction unit provides crew instruction based on the cases extracted by the specific processing unit 290 of the data processing device 12. The visualization unit visualizes the data digitized by the specific processing unit 290 of the data processing device 12. The efficiency improvement unit improves the efficiency of the log collection method by the specific processing unit 290 of the data processing device 12. The suggestion unit suggests improvements based on the matching results by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, text conversion unit, matching unit, digitization unit, extraction unit, instruction unit, visualization unit, efficiency improvement unit, and suggestion unit, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit collects communication logs with customers using the camera 42 and microphone 238 of the headset terminal 314 and transmits the logs to the data processing device 12 via the control unit 46A. The text conversion unit converts the logs into text using voice recognition technology or OCR technology via the specific processing unit 290 of the data processing device 12. The matching unit matches the logs with a standard response manual via the specific processing unit 290 of the data processing device 12. The digitization unit digitizes the matching results via the specific processing unit 290 of the data processing device 12. The extraction unit extracts cases with numerical values ​​below the standard via the specific processing unit 290 of the data processing device 12. The instruction unit provides crew guidance based on the cases extracted by the specific processing unit 290 of the data processing device 12. The visualization unit visualizes the data digitized by the specific processing unit 290 of the data processing device 12. The efficiency improvement unit improves the efficiency of the log collection method by the specific processing unit 290 of the data processing device 12. The suggestion unit suggests improvements based on the matching results by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, text conversion unit, matching unit, digitization unit, extraction unit, instruction unit, visualization unit, efficiency improvement unit, and suggestion unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects communication logs with customers using the camera 42 and microphone 238 of the robot 414 and transmits the logs to the data processing device 12 via the control unit 46A. The text conversion unit converts the logs into text using voice recognition technology or OCR technology via the specific processing unit 290 of the data processing device 12. The matching unit matches the logs with a standard response manual via the specific processing unit 290 of the data processing device 12. The digitization unit digitizes the matching results via the specific processing unit 290 of the data processing device 12. The extraction unit extracts cases with numerical values ​​below the standard via the specific processing unit 290 of the data processing device 12. The instruction unit provides crew guidance based on the cases extracted by the specific processing unit 290 of the data processing device 12. The visualization unit visualizes the data digitized by the specific processing unit 290 of the data processing device 12. The efficiency improvement unit improves the efficiency of the log collection method by the specific processing unit 290 of the data processing device 12. The suggestion unit suggests improvements based on the matching results by the specific processing unit 290 of the data processing device 12.

[0123] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0124] In the customer interaction evaluation system, the collection unit can estimate the user's emotions and adjust the timing of log collection based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit can delay the collection timing to reduce the burden on the user. Also, if the user is relaxed, the collection unit can advance the collection timing to collect more logs. Furthermore, if the user is in a hurry, the collection unit can optimize the collection timing to quickly collect the minimum number of logs necessary. In this way, adjusting the log collection timing according to the user's emotions reduces the burden on the user and enables efficient log collection.

[0125] In the customer interaction evaluation system, the collection unit can also analyze past communication history and select the optimal collection method. For example, the collection unit identifies the most effective collection method from the past communication history and applies that method. The collection unit can also improve the quality of logs by analyzing the past history and collecting data at specific time periods. Furthermore, the collection unit can select the optimal collection method for a specific user group based on the past history. In this way, by analyzing the past communication history, the optimal collection method can be selected and the quality of logs can be improved.

[0126] In the customer interaction evaluation system, when the collection unit collects logs, the collection unit can also filter the logs based on the user's current situation and areas of interest. For example, the collection unit prioritizes collecting logs related to topics that the user is currently interested in. The collection unit can also collect appropriate logs based on the user's current situation (e.g., at work, on break). Furthermore, the collection unit can filter logs related to areas of interest by referring to the user's past behavior history. In this way, highly relevant logs can be collected by filtering the logs based on the user's current situation and areas of interest.

[0127] In the customer interaction evaluation system, the collection unit can estimate the user's emotions and determine the priority of logs to be collected based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit can postpone collecting logs of low importance. Also, if the user is relaxed, the collection unit can prioritize collecting logs of high importance. Furthermore, if the user is in a hurry, the collection unit can prioritize logs that can be collected quickly. In this way, efficient log collection is possible by determining the priority of logs to be collected according to the user's emotions.

[0128] In the customer interaction evaluation system, when the collection unit collects logs, the collection unit can prioritize collecting highly relevant logs by taking into account the user's geographical location information. For example, if the user is in a specific area, the collection unit can prioritize collecting logs related to that area. The collection unit can also collect the most relevant logs based on the user's current location. Furthermore, the collection unit can select highly relevant logs by referring to the user's movement history. In this way, highly relevant logs can be efficiently collected by taking into account the user's geographical location information.

[0129] In the customer service evaluation system, the text conversion unit can estimate the user's emotions and adjust the text expression method based on the estimated user emotions. For example, if the user is feeling stressed, the text conversion unit can use concise and easy-to-understand expressions. If the user is relaxed, the text conversion unit can also use expressions that include detailed explanations. Furthermore, if the user is in a hurry, the text conversion unit can use short expressions that get to the point. In this way, by adjusting the text expression method according to the user's emotions, it is possible to create text that is easy for the user to understand.

[0130] In the customer interaction evaluation system, the text conversion unit can also adjust the level of detail of the text based on the importance of the log when converting the log into text. For example, the text conversion unit converts logs with high importance into text in detail and logs with low importance into text in a concise manner. The text conversion unit can also determine the priority of the text conversion based on the importance. Furthermore, the text conversion unit can convert logs with high importance into text that includes detailed explanations and annotations. This allows for efficient text conversion by adjusting the level of detail of the text based on the importance of the log.

[0131] In the customer interaction evaluation system, the text conversion unit can apply different text conversion algorithms depending on the log category when converting the log into text. For example, the text conversion unit selects and applies the optimal text conversion algorithm for each category. The text conversion unit can also adjust the level of detail and expression of the text depending on the log category. Furthermore, the text conversion unit can improve accuracy by using different text conversion algorithms for each category. In this way, the accuracy of the text conversion can be improved by applying the optimal text conversion algorithm depending on the log category.

[0132] In the customer interaction evaluation system, the text conversion unit can estimate the user's emotions and adjust the length of the text based on the estimated user emotions. For example, if the user is feeling stressed, the text conversion unit can generate short, concise text. If the user is relaxed, the text conversion unit can generate longer text that includes detailed explanations. Furthermore, if the user is in a hurry, the text conversion unit can generate short, concise text that focuses on the main points. This allows the length of the text to be adjusted according to the user's emotions, making it possible to generate text of an appropriate length for the user.

[0133] In the customer interaction evaluation system, the text conversion unit can also determine the priority of text conversion based on the time of submission of the logs when converting the logs to text. For example, the text conversion unit can give priority to converting logs that were submitted more recently. The text conversion unit can also determine the priority of text conversion based on the time of submission. Furthermore, the text conversion unit can also convert logs that were submitted earlier at a later date. In this way, by determining the priority of text conversion based on the time of submission of the logs, efficient text conversion is possible.

[0134] The processing flow of the second embodiment will be briefly explained below.

[0135] Step 1: The collection department collects communication logs with customers. Collected logs include text messages, voice recordings, video calls, etc. For example, the collection department can collect voice recordings and convert them into text using voice recognition technology. It can also analyze the content of video calls, extract important parts, and convert them into text. Step 2: The text conversion unit converts the logs collected by the collection unit into text. This conversion can be done using voice recognition or OCR technology. For example, voice recordings can be converted into text data using voice recognition technology, and handwritten notes can be converted into text data using OCR technology. Step 3: The matching unit matches the log converted to text by the text conversion unit with the reference response manual. Keyword matching and context analysis are used for matching. For example, keyword matching can be used to calculate the degree of agreement between the log and the reference response manual, and context analysis can be used to gain a deeper understanding of the log content, allowing for more accurate matching. Step 4: The quantification unit quantifies the accuracy of the correspondence based on the matching results obtained by the matching unit. A scoring algorithm or evaluation criteria is used for the quantification. For example, the accuracy of the log can be quantified using a scoring algorithm, and the quality of the log can be evaluated and quantified based on the evaluation criteria. Step 5: The extraction unit extracts cases whose numerical values ​​are below a certain standard using the quantification unit. Score thresholds and evaluation criteria are used for extraction. For example, cases whose scores are below a certain threshold can be extracted, and important cases can be extracted based on the evaluation criteria.

[0136] 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.

[0137] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0138] 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.

[0139] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0140] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0150] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0151] 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.

[0152] 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.

[0153] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0157] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0166] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0167] 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.

[0168] 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.

[0169] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0170] 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.

[0171] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0172] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0173] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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).

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0183] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0184] 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.

[0185] 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.

[0186] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0187] 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.

[0188] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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).

[0193] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. 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 indicated, and when they approach the ideal, a state of pleasure is indicated. 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.

[0194] 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."

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] [Explanation of symbols]

[0208] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects communication logs; a text conversion unit that converts the logs collected by the collection unit into text; a matching unit that matches the log converted into text by the text conversion unit with a reference response manual; a quantification unit that quantifies the accuracy of correspondence based on the matching result obtained by the matching unit; an extraction unit that extracts cases where the numerical value is equal to or less than a certain standard by the digitization unit; A system characterized by:

2. Equipped with a training department that provides crew training based on the extracted cases 2. The system of claim 1.

3. Equipped with a visualization section that visualizes digitized data 2. The system of claim 1.

4. Equipped with an efficiency improvement section that streamlines log collection methods 2. The system of claim 1.

5. Equipped with a proposal department that proposes improvements based on matching results 2. The system of claim 1.

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

7. The collecting unit Analyze past communication history and select the optimal collection method 2. The system of claim 1.

8. The collecting unit When collecting logs, filter them based on the user's current situation and areas of interest.

2. The system of claim 1.

9. The collecting unit Estimate the user's emotions and prioritize the logs to be collected based on the estimated user emotions.

2. The system of claim 1.

10. The collecting unit When collecting logs, the system takes into account the user's geographic location information to prioritize the collection of highly relevant logs.

2. The system of claim 1.

Images