System

Abstract

An object of the system according to the embodiment is to efficiently evaluate the performance of a telephone reception operator and to propose an improvement point.SOLUTION: A system according to an embodiment includes an analysis unit, a scoring unit, a proposal unit, a creation unit, and an optimization unit. The analysis unit analyzes the call content. The scoring unit performs scoring based on the evaluation result analyzed by the analysis unit. The proposal unit proposes an improvement point based on the score obtained by the scoring unit. The creation unit creates a training program based on the improvement point proposed by the proposal unit. The optimization unit optimizes the arrangement of the operators based on the training program created by the creation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not adequately evaluate the performance of telephone receptionists efficiently and suggest areas for improvement, so there is room for improvement.

[0005] The system according to the embodiment aims to efficiently evaluate the performance of telephone receptionists and propose areas for improvement. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a scoring unit, a proposal unit, a creation unit, and an optimization unit. The analysis unit analyzes the content of the call. The scoring unit performs scoring based on the evaluation results analyzed by the analysis unit. The proposal unit proposes improvements based on the scores obtained by the scoring unit. The creation unit creates a training program based on the improvements proposed by the proposal unit. The optimization unit optimizes the allocation of agents based on the training program created by the creation unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently evaluate the performance of telephone receptionists and suggest 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) An evaluation system according to an embodiment of the present invention is a system for efficiently evaluating the performance of telephone receptionists. This evaluation system analyzes call content, assigns scores based on the evaluation results, proposes areas for improvement, creates training programs, and optimizes operator deployment. For example, the evaluation system analyzes the content of each operator's call in real time to evaluate the status of complaint handling and reporting. The evaluation system then scores the operator's performance based on the evaluation results and identifies areas for improvement. This allows for efficient evaluation of operator performance, leading to the provision of better service. For example, the evaluation system converts the call content into text and performs sentiment analysis to evaluate the appropriateness of complaint handling and the speed of reporting. The evaluation system then assigns a score based on the evaluation results and quantifies overall performance. Furthermore, the evaluation system identifies areas for improvement based on the scoring results and proposes specific improvement measures. This allows operators to identify their own weaknesses and work to improve their skills. This allows for efficient evaluation of operator performance, leading to the provision of better service. This allows for efficient evaluation of operator performance, proposes areas for improvement, creates training programs, and optimizes operator deployment. For example, a training program for operators can be created based on the evaluation results to improve their skills. It is also possible to optimize operator deployment based on the evaluation results and improve work efficiency.

[0029] The evaluation system according to the embodiment includes an analysis unit, a scoring unit, a suggestion unit, a creation unit, and an optimization unit. The analysis unit analyzes call content. The call content includes, but is not limited to, voice calls, video calls, and text chats. The analysis unit converts the call content into text using, for example, voice recognition technology. The analysis unit can also perform emotion analysis of the call content using an emotion recognition algorithm. For example, the analysis unit converts the call content into text using voice recognition technology and performs emotion analysis using an emotion recognition algorithm. The scoring unit performs scoring based on the evaluation results analyzed by the analysis unit. Scoring is performed based on, for example, the appropriateness of complaint handling and the speed of reporting processing, but is not limited to, such examples. For example, the scoring unit assigns a score based on the appropriateness of complaint handling. The scoring unit can also assign a score based on the speed of reporting processing. The suggestion unit suggests improvements based on the scores obtained by the scoring unit. The suggestions are performed automatically based on, for example, the scoring results, but are not limited to, such examples. For example, the suggestion unit automatically suggests improvements based on the scoring results. The creation unit creates a training program based on the improvements proposed by the suggestion unit. The training program is created based on, for example, the evaluation results, but is not limited to this example. For example, the creation unit creates the training program based on the evaluation results. The optimization unit optimizes the allocation of operators based on the training program created by the creation unit. The optimization of the allocation is performed based on, for example, the evaluation results, but is not limited to this example. For example, the optimization unit optimizes the allocation of operators based on the evaluation results. In this way, the evaluation system according to the embodiment can efficiently evaluate the performance of operators, suggest improvements, create a training program, and optimize the allocation.

[0030] The analysis unit can convert the call content into text or perform sentiment analysis. The analysis unit can convert the call content into text using, for example, voice recognition technology. For example, the analysis unit can automatically analyze the voice using voice recognition software and save it as text. The analysis unit can also perform sentiment analysis of the call content using an emotion recognition algorithm. For example, the analysis unit can convert the call content into text using voice recognition technology and perform sentiment analysis using an emotion recognition algorithm. By converting the call content into text and performing sentiment analysis, the quality of the operator's response can be evaluated. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input voice data to a generation AI to convert the call content into text, and have the generation AI generate text data.

[0031] The scoring unit can assign scores based on the appropriateness of the complaint handling and the speed of the claim processing. The scoring unit assigns scores, for example, based on the appropriateness of the complaint handling. For example, the scoring unit assigns scores based on criteria such as response time, resolution rate, and customer satisfaction. The scoring unit can also assign scores based on the speed of the claim processing. For example, the scoring unit assigns scores based on criteria such as processing time and response speed. This makes it possible to quantify the performance of an operator by assigning scores based on the appropriateness of the complaint handling and the speed of the claim processing. Some or all of the above-described processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can input evaluation data into a generation AI to assign scores based on the appropriateness of the complaint handling and the speed of the claim processing, and have the generation AI generate scores.

[0032] The suggestion unit can automatically suggest improvements based on the scoring results. The suggestion unit, for example, automatically suggests improvements based on the scoring results. For example, the suggestion unit analyzes the scoring results using a suggestion algorithm and identifies improvements. The suggestion unit can also suggest improvements based on the form of feedback. For example, the suggestion unit automatically suggests improvements based on the scoring results and provides feedback. This makes it possible to improve the skills of operators by automatically suggesting improvements based on the scoring results. Some or all of the above-mentioned processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input the scoring results to a generation AI and have the generation AI suggest improvements.

[0033] The creation unit can create a training program based on the evaluation results. The creation unit, for example, creates a training program based on the evaluation results. For example, the creation unit creates a training program based on the scoring results and the feedback content. The creation unit can also create a training program based on the type of training and the implementation method. For example, the creation unit creates a training program based on the evaluation results to improve the operator's skills. In this way, by creating a training program based on the evaluation results, it is possible to improve the operator's skills. Some or all of the above-mentioned processing in the creation unit may be performed using AI, for example, or may be performed without using AI. For example, the creation unit inputs the evaluation results into a generation AI and causes the generation AI to create a training program.

[0034] The optimization unit can optimize the allocation of operators based on the evaluation results. The optimization unit, for example, optimizes the allocation of operators based on the evaluation results. For example, the optimization unit optimizes the allocation based on the skills of the operators and the type of work. The optimization unit can also optimize the allocation based on the shift time period and the priority of the work. For example, the optimization unit optimizes the allocation of operators based on the evaluation results to improve the efficiency of work. In this way, by optimizing the allocation of operators based on the evaluation results, it is possible to improve the efficiency of work. Some or all of the above-mentioned processing in the optimization unit may be performed using AI, for example, or may be performed without using AI. For example, the optimization unit can input the evaluation results to a generation AI and have the generation AI optimize the allocation.

[0035] When analyzing the content of a call, the analysis unit can improve the accuracy of the analysis by referring to the customer's past complaint history. For example, the analysis unit can refer to the customer's past complaint history to check whether a similar problem has recurred. For example, the analysis unit can refer to the customer's past complaint history to check whether a similar problem has recurred. The analysis unit can also evaluate the appropriateness of a response to a specific problem based on the customer's past complaint history. For example, the analysis unit can evaluate the appropriateness of a response to a specific problem based on the customer's past complaint history. The analysis unit can also analyze the customer's past complaint history, identify complaint patterns, and reflect them in the analysis. For example, the analysis unit can analyze the customer's past complaint history, identify complaint patterns, and reflect them in the analysis. In this way, by referring to the customer's past complaint history, the accuracy of the analysis can be improved. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input the customer's past complaint history into a generation AI, which can improve the accuracy of the analysis.

[0036] When analyzing the content of a call, the analysis unit can perform analysis based on customer attribute information. The analysis unit can evaluate an appropriate response method based on, for example, the customer's age. For example, the analysis unit can evaluate an appropriate response method based on the customer's age. The analysis unit can also evaluate whether a specific response was appropriate based on the customer's gender. For example, the analysis unit can evaluate whether a specific response was appropriate based on the customer's gender. The analysis unit can also consider the customer's regional information to evaluate the appropriateness of a response to a problem specific to the region. For example, the analysis unit considers the customer's regional information to evaluate the appropriateness of a response to a problem specific to the region. This enables more appropriate analysis by considering the customer's attribute information. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input customer attribute information into a generation AI and have the generation AI perform the analysis.

[0037] When analyzing the content of a call, the analysis unit can weight the analysis based on the time of day and day of the week of the call. For example, if a call is made during a peak time period, the analysis unit weights the call because a prompt response is required. For example, if a call is made during a peak time period, the analysis unit weights the call because a prompt response is required. The analysis unit can also evaluate whether a specific response was appropriate if the call was made on a weekend. For example, the analysis unit can evaluate whether a specific response was appropriate if the call was made on a weekend. The analysis unit can also analyze the call late at night, placing emphasis on the promptness of the response. For example, the analysis unit analyzes the call late at night, placing emphasis on the promptness of the response. Thus, weighting the analysis based on the time of day and day of the week of the call enables more appropriate analysis. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input data on the time of day and day of the week of the call into a generation AI, and have the generation AI weight the analysis.

[0038] The analysis unit can take into account the customer's geographical location information when analyzing the content of the call. For example, the analysis unit evaluates the appropriateness of a response to a region-specific problem based on the customer's geographical location information. For example, the analysis unit evaluates the appropriateness of a response to a region-specific problem based on the customer's geographical location information. The analysis unit can also refer to the customer's geographical location information and reflect complaint patterns in a specific region in the analysis. For example, the analysis unit refers to the customer's geographical location information and reflects complaint patterns in a specific region in the analysis. The analysis unit can also evaluate differences in response methods for each region by taking into account the customer's geographical location information. For example, the analysis unit evaluates differences in response methods for each region by taking into account the customer's geographical location information. This enables more appropriate analysis by taking into account the customer's geographical location information. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the customer's geographical location information into a generation AI and have the generation AI perform the analysis.

[0039] When analyzing the content of a call, the analysis unit can analyze the customer's social media activity and reflect related information in the analysis. For example, the analysis unit can analyze the customer's social media posts to understand the background of the complaint. For example, the analysis unit can analyze the customer's social media posts to understand the background of the complaint. The analysis unit can also refer to the customer's social media activity to evaluate the appropriateness of a response to a specific problem. For example, the analysis unit can refer to the customer's social media activity to evaluate the appropriateness of a response to a specific problem. The analysis unit can also refer to the activity of the customer's friends on social media to reflect related information in the analysis. For example, the analysis unit refers to the activity of the customer's friends on social media to reflect related information in the analysis. This enables more appropriate analysis by analyzing the customer's social media activity. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the customer's social media activity into a generation AI and have the generation AI perform the analysis.

[0040] When analyzing the content of a call, the analysis unit can customize the analysis method by reflecting the customer's past feedback. For example, the analysis unit refers to the customer's past feedback and evaluates whether a specific response was appropriate. For example, the analysis unit refers to the customer's past feedback and evaluates whether a specific response was appropriate. The analysis unit can also customize the analysis method based on the customer's past feedback to improve accuracy. For example, the analysis unit customizes the analysis method based on the customer's past feedback to improve accuracy. The analysis unit can also analyze the customer's past feedback and reflect feedback patterns in the analysis. For example, the analysis unit analyzes the customer's past feedback and reflects feedback patterns in the analysis. In this way, by reflecting the customer's past feedback, the analysis method can be customized and accuracy can be improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the customer's past feedback into a generation AI and have the generation AI customize the analysis method.

[0041] The scoring unit can adjust the level of detail of the score based on the importance of the call content when scoring. For example, in the case of an important complaint response, the scoring unit performs detailed scoring to evaluate the quality of the response. For example, in the case of an important complaint response, the scoring unit performs detailed scoring to evaluate the quality of the response. Furthermore, in the case of a general complaint processing, the scoring unit can perform simplified scoring to emphasize speed. For example, in the case of a general complaint processing, the scoring unit can perform simplified scoring to emphasize speed. Furthermore, in the case of a response to a specific issue, the scoring unit can adjust the level of detail of the scoring according to the importance. For example, in the case of a response to a specific issue, the scoring unit adjusts the level of detail of the scoring according to the importance. In this way, adjusting the level of detail of the score based on the importance of the call content enables more appropriate scoring. Some or all of the above-described processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can input importance data of the call content to a generation AI and have the generation AI adjust the level of detail of the score.

[0042] The scoring unit can apply different scoring algorithms depending on the call category when scoring. For example, in the case of handling a complaint, the scoring unit applies a scoring algorithm that emphasizes the quality of the response. For example, in the case of handling a complaint, the scoring unit applies a scoring algorithm that emphasizes the quality of the response. Furthermore, the scoring unit can also apply a scoring algorithm that emphasizes speed in the case of reporting processing. For example, in the case of reporting processing, the scoring unit applies a scoring algorithm that emphasizes speed. Furthermore, the scoring unit can also apply a scoring algorithm according to the category in the case of handling a specific problem. For example, in the case of handling a specific problem, the scoring unit applies a scoring algorithm according to the category. In this way, by applying different scoring algorithms depending on the call category, more appropriate scoring is possible. Some or all of the above-mentioned processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can input call category data into a generation AI and have the generation AI apply a scoring algorithm.

[0043] The scoring unit can improve the accuracy of the score by referring to the operator's past scoring results when scoring. For example, the scoring unit can refer to the operator's past scoring results to evaluate whether a specific response has improved. For example, the scoring unit can refer to the operator's past scoring results to evaluate whether a specific response has improved. The scoring unit can also adjust the scoring criteria based on the operator's past scoring results. For example, the scoring unit can adjust the scoring criteria based on the operator's past scoring results. The scoring unit can also analyze the operator's past scoring results to improve the accuracy of the score. For example, the scoring unit can analyze the operator's past scoring results to improve the accuracy of the score. In this way, the accuracy of the score can be improved by referring to the operator's past scoring results. Some or all of the above-described processing in the scoring unit can be performed using, for example, AI, or can be performed without using AI. For example, the scoring unit can input the operator's past scoring results into a generation AI, which can improve the accuracy of the score.

[0044] When scoring, the scoring unit can weight the score based on the time of day and day of the week of the call. For example, the scoring unit weights the call when it is made during a peak time period because a prompt response is required. For example, the scoring unit weights the call when it is made during a peak time period because a prompt response is required. The scoring unit can also evaluate whether a specific response was appropriate when the call was made on a weekend. For example, the scoring unit evaluates whether a specific response was appropriate when the call was made on a weekend. The scoring unit can also score the call late at night by emphasizing the promptness of the response. For example, the scoring unit scores the call late at night by emphasizing the promptness of the response. Thus, weighting the score based on the time of day and day of the week of the call enables more appropriate scoring. Some or all of the above-described processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can input data on the time of day and day of the week of the call into the generation AI, and have the generation AI weight the score.

[0045] The scoring unit can assign a score taking into account customer attribute information when scoring. The scoring unit evaluates an appropriate response method based on, for example, the customer's age. For example, the scoring unit evaluates an appropriate response method based on the customer's age. The scoring unit can also evaluate whether a specific response was appropriate based on the customer's gender. For example, the scoring unit evaluates whether a specific response was appropriate based on the customer's gender. The scoring unit can also evaluate the appropriateness of a response to a problem specific to the region by taking into account the customer's regional information. For example, the scoring unit evaluates the appropriateness of a response to a problem specific to the region by taking into account the customer's regional information. This enables more appropriate scoring by taking into account the customer's attribute information. Some or all of the above-described processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can input customer attribute information into a generation AI and have the generation AI assign a score.

[0046] The scoring unit can improve the accuracy of the score by referring to the customer's past complaint history when scoring. For example, the scoring unit can refer to the customer's past complaint history to check whether a similar problem has recurred. For example, the scoring unit can refer to the customer's past complaint history to check whether a similar problem has recurred. The scoring unit can also evaluate the appropriateness of a response to a specific problem based on the customer's past complaint history. For example, the scoring unit can evaluate the appropriateness of a response to a specific problem based on the customer's past complaint history. The scoring unit can also analyze the customer's past complaint history, identify complaint patterns, and reflect them in the scoring. For example, the scoring unit can analyze the customer's past complaint history, identify complaint patterns, and reflect them in the scoring. In this way, by referring to the customer's past complaint history, the accuracy of the score can be improved. Some or all of the above-mentioned processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can input the customer's past complaint history into a generation AI, which can improve the accuracy of the score.

[0047] When making a proposal, the suggestion unit can adjust the level of detail of the proposal based on the importance of the scoring result. For example, in the case of an important complaint response, the suggestion unit can suggest detailed improvements to improve the quality of the response. For example, in the case of an important complaint response, the suggestion unit can suggest detailed improvements to improve the quality of the response. The suggestion unit can also suggest simplified improvements to emphasize speed in the case of general complaint processing. For example, in the case of general complaint processing, the suggestion unit can suggest simplified improvements to emphasize speed. The suggestion unit can also adjust the level of detail of the proposal based on the importance in the case of a response to a specific problem. For example, in the case of a response to a specific problem, the suggestion unit adjusts the level of detail of the proposal based on the importance. This enables more appropriate proposals to be made by adjusting the level of detail of the proposal based on the importance of the scoring result. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input importance data of the scoring result to a generation AI, causing the generation AI to adjust the level of detail of the proposal.

[0048] When making a proposal, the suggestion unit can improve the accuracy of the proposal by referring to the operator's past improvement history. For example, the suggestion unit can refer to the operator's past improvement history to evaluate whether a specific response has improved. For example, the suggestion unit can refer to the operator's past improvement history to evaluate whether a specific response has improved. The suggestion unit can also adjust the criteria for the proposal based on the operator's past improvement history. For example, the suggestion unit can adjust the criteria for the proposal based on the operator's past improvement history. The suggestion unit can also analyze the operator's past improvement history to improve the accuracy of the proposal. For example, the suggestion unit can analyze the operator's past improvement history to improve the accuracy of the proposal. In this way, the accuracy of the proposal can be improved by referring to the operator's past improvement history. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input the operator's past improvement history into a generation AI, which can improve the accuracy of the proposal.

[0049] When making a proposal, the proposal unit can apply different proposal algorithms depending on the category of the call content. For example, in the case of handling a complaint, the proposal unit applies a proposal algorithm that emphasizes the quality of the response. For example, in the case of handling a complaint, the proposal unit applies a proposal algorithm that emphasizes the quality of the response. The proposal unit can also apply a proposal algorithm that emphasizes speed in the case of reporting processing. For example, in the case of reporting processing, the proposal unit applies a proposal algorithm that emphasizes speed. The proposal unit can also apply a proposal algorithm according to the category in the case of responding to a specific problem. For example, in the case of responding to a specific problem, the proposal unit applies a proposal algorithm according to the category. This enables more appropriate proposals by applying different proposal algorithms depending on the category of the call content. Some or all of the above-mentioned processing in the proposal unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal unit can input category data of the call content to a generation AI, and have the generation AI apply the proposal algorithm.

[0050] When making a proposal, the suggestion unit can determine the priority of the proposal based on the time of day and day of the week of the call. For example, if a call is made during a peak time period, the suggestion unit sets a high priority because a prompt response is required. For example, if a call is made during a peak time period, the suggestion unit sets a high priority because a prompt response is required. The suggestion unit can also evaluate whether a specific response was appropriate and set a priority when a call is made on a weekend. For example, the suggestion unit evaluates whether a specific response was appropriate and set a priority when a call is made on a weekend. The suggestion unit can also determine the priority of the proposal by emphasizing the speed of the response when a call is made late at night. For example, the suggestion unit determines the priority of the proposal by emphasizing the speed of the response when a call is made late at night. In this way, by determining the priority of the proposal based on the time of day and day of the week of the call, more appropriate proposals can be made. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input data on the time of day and day of the week of the call into the generation AI, and have the generation AI determine the priority of the suggestions.

[0051] When making a proposal, the suggestion unit can take into account the attribute information of the operator. The suggestion unit can make a proposal by taking into account the attribute information of the operator. For example, the suggestion unit can suggest appropriate improvements based on the years of experience of the operator. The suggestion unit can also suggest detailed improvements based on the skill level of the operator. For example, the suggestion unit can suggest detailed improvements based on the skill level of the operator. The suggestion unit can also make individually customized proposals by taking into account the attribute information of the operator. For example, the suggestion unit can make individually customized proposals by taking into account the attribute information of the operator. This enables more appropriate proposals by taking into account the attribute information of the operator. Some or all of the above-mentioned processing in the suggestion unit can be performed using AI, for example, or without using AI. For example, the suggestion unit can input the attribute information of the operator to a generation AI and have the generation AI make a proposal.

[0052] When making a proposal, the suggestion unit can improve the accuracy of the proposal by referring to the customer's past complaint history. For example, the suggestion unit can refer to the customer's past complaint history and propose improvements for a specific problem. For example, the suggestion unit can refer to the customer's past complaint history and propose improvements for a specific problem. The suggestion unit can also adjust the criteria for the proposal based on the customer's past complaint history. For example, the suggestion unit can adjust the criteria for the proposal based on the customer's past complaint history. The suggestion unit can also analyze the customer's past complaint history and improve the accuracy of the proposal. For example, the suggestion unit can analyze the customer's past complaint history and improve the accuracy of the proposal. In this way, the accuracy of the proposal can be improved by referring to the customer's past complaint history. Some or all of the above-mentioned processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input the customer's past complaint history into a generation AI, which can improve the accuracy of the proposal.

[0053] When creating a training program, the creation unit can adjust the level of detail of the program based on the importance of the scoring results. For example, when handling an important complaint, the creation unit creates a detailed training program to improve the quality of the response. For example, when handling an important complaint, the creation unit creates a detailed training program to improve the quality of the response. The creation unit can also create a simplified training program for general reporting processes to emphasize speed. For example, the creation unit can create a simplified training program for general reporting processes to emphasize speed. The creation unit can also adjust the level of detail of the training program depending on the importance when responding to a specific problem. For example, when responding to a specific problem, the creation unit adjusts the level of detail of the training program depending on the importance. This enables the creation of a more appropriate training program by adjusting the level of detail of the program based on the importance of the scoring results. Some or all of the above-described processing in the creation unit may be performed using, or without, AI. For example, the creation unit may input importance data of the scoring results into a generation AI, causing the generation AI to adjust the level of detail of the program.

[0054] When creating a training program, the creation unit can improve the accuracy of the program by referring to the operator's past training history. For example, the creation unit can refer to the operator's past training history to evaluate whether a specific skill has improved. For example, the creation unit can refer to the operator's past training history to evaluate whether a specific skill has improved. The creation unit can also adjust the content of the training program based on the operator's past training history. For example, the creation unit can adjust the content of the training program based on the operator's past training history. The creation unit can also analyze the operator's past training history to improve the accuracy of the program. For example, the creation unit can analyze the operator's past training history to improve the accuracy of the program. In this way, the accuracy of the program can be improved by referring to the operator's past training history. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the operator's past training history into a generation AI, and the generation AI can improve the accuracy of the program.

[0055] When creating a training program, the creation unit can apply different training algorithms depending on the category of the call content. For example, in the case of handling a complaint, the creation unit applies a training algorithm that emphasizes the quality of the response. For example, in the case of handling a complaint, the creation unit applies a training algorithm that emphasizes the quality of the response. The creation unit can also apply a training algorithm that emphasizes speed in the case of reporting processing. For example, in the case of reporting processing, the creation unit applies a training algorithm that emphasizes speed. The creation unit can also apply a training algorithm according to the category in the case of responding to a specific problem. For example, in the case of responding to a specific problem, the creation unit applies a training algorithm according to the category. This makes it possible to create a more appropriate training program by applying different training algorithms depending on the category of the call content. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input category data of the call content to a generation AI and cause the generation AI to apply a training algorithm.

[0056] When creating a training program, the creation unit can determine the priority of the program based on the time of day and day of the week of the call. For example, if a call is made during a peak time period, the creation unit sets a high priority because a prompt response is required. For example, if a call is made during a peak time period, the creation unit sets a high priority because a prompt response is required. The creation unit can also evaluate whether a specific response was appropriate and set a priority when a call is made on a weekend. For example, the creation unit evaluates whether a specific response was appropriate and set a priority when a call is made on a weekend. The creation unit can also determine the priority of a training program by emphasizing the speed of the response when a call is made late at night. For example, the creation unit determines the priority of a training program by emphasizing the speed of the response when a call is made late at night. In this way, by determining the priority of the program based on the time of day and day of the week of the call, a more appropriate training program can be created. Some or all of the above-described processing in the creation unit may be performed, for example, using AI or without AI. For example, the creation unit can input data on the time of day and day of the week of the call into the generation AI, and have the generation AI determine the priority of the program.

[0057] When creating a training program, the creation unit can create the program taking into account the attribute information of the operator. The creation unit creates an appropriate training program, for example, based on the operator's years of experience. For example, the creation unit creates an appropriate training program based on the operator's years of experience. The creation unit can also create a detailed training program according to the operator's skill level. For example, the creation unit creates a detailed training program according to the operator's skill level. The creation unit can also create an individually customized training program taking into account the operator's attribute information. For example, the creation unit creates an individually customized training program taking into account the operator's attribute information. This makes it possible to create a more appropriate training program by taking into account the operator's attribute information. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the operator's attribute information into a generation AI and cause the generation AI to create a program.

[0058] When creating a training program, the creation unit can refer to the customer's past complaint history to improve the accuracy of the program. For example, the creation unit references the customer's past complaint history to create a training program for a specific problem. For example, the creation unit references the customer's past complaint history to create a training program for a specific problem. The creation unit can also adjust the content of the training program based on the customer's past complaint history. For example, the creation unit adjusts the content of the training program based on the customer's past complaint history. The creation unit can also analyze the customer's past complaint history to improve the accuracy of the program. For example, the creation unit analyzes the customer's past complaint history to improve the accuracy of the program. In this way, the accuracy of the program can be improved by referring to the customer's past complaint history. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the customer's past complaint history into a generation AI, which can improve the accuracy of the program.

[0059] During placement optimization, the optimization unit can adjust the level of detail of placement based on the importance of the scoring results. For example, the optimization unit assigns an experienced operator when handling an important complaint. For example, the optimization unit assigns an experienced operator when handling an important complaint. The optimization unit can also assign an operator who can respond quickly when processing a general complaint. For example, the optimization unit assigns an operator who can respond quickly when processing a general complaint. The optimization unit can also assign the optimal operator based on the scoring results when responding to a specific problem. For example, the optimization unit assigns the optimal operator based on the scoring results when responding to a specific problem. This enables more appropriate placement by adjusting the level of detail of placement based on the importance of the scoring results. Some or all of the above-mentioned processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input importance data of the scoring results to the generation AI, causing the generation AI to adjust the level of detail of placement.

[0060] During placement optimization, the optimization unit can improve placement accuracy by referring to the operator's past placement history. The optimization unit, for example, refers to the operator's past placement history and evaluates whether a specific response has improved. For example, the optimization unit refers to the operator's past placement history and evaluates whether a specific response has improved. The optimization unit can also adjust placement criteria based on the operator's past placement history. For example, the optimization unit adjusts placement criteria based on the operator's past placement history. The optimization unit can also analyze the operator's past placement history and improve placement accuracy. For example, the optimization unit analyzes the operator's past placement history and improves placement accuracy. In this way, the placement accuracy can be improved by referring to the operator's past placement history. Some or all of the above-described processing in the optimization unit may be performed using AI, for example, or may be performed without using AI. For example, the optimization unit can input the operator's past placement history into a generation AI, which can improve the placement accuracy.

[0061] The optimization unit can apply different allocation algorithms depending on the category of call content during allocation optimization. For example, in the case of complaint handling, the optimization unit applies an allocation algorithm that emphasizes the quality of the response. For example, in the case of complaint handling, the optimization unit applies an allocation algorithm that emphasizes the quality of the response. The optimization unit can also apply an allocation algorithm that emphasizes speed in the case of reporting processing. For example, in the case of reporting processing, the optimization unit applies an allocation algorithm that emphasizes speed. The optimization unit can also apply an allocation algorithm according to the category in the case of handling a specific problem. For example, in the case of handling a specific problem, the optimization unit applies an allocation algorithm according to the category. In this way, applying different allocation algorithms depending on the category of call content enables more appropriate allocation. Some or all of the above-mentioned processing in the optimization unit may be performed using, for example, AI, or may be performed without using AI. For example, the optimization unit can input call content category data into a generation AI and cause the generation AI to apply the allocation algorithm.

[0062] During allocation optimization, the optimization unit can determine allocation priorities based on the time period and day of the week of the call. For example, if a call is made during a peak time period, the optimization unit sets a high priority because a prompt response is required. For example, if a call is made during a peak time period, the optimization unit sets a high priority because a prompt response is required. The optimization unit can also evaluate whether a specific response was appropriate and set a priority when a call is made on a weekend. For example, the optimization unit evaluates whether a specific response was appropriate and set a priority when a call is made on a weekend. The optimization unit can also determine allocation priorities by emphasizing speed of response when a call is made late at night. For example, the optimization unit determines allocation priorities by emphasizing speed of response when a call is made late at night. This enables more appropriate allocation by determining allocation priorities based on the time period and day of the week of the call. Some or all of the above-described processing in the optimization unit may be performed using, for example, AI, or may be performed without using AI. For example, the optimization unit can input data on the time of day and day of the week when calls are made into the generation AI, allowing the generation AI to determine placement priorities.

[0063] The optimization unit can perform the placement optimization by taking into account the attribute information of the operators. The optimization unit performs appropriate placement based on, for example, the years of experience of the operators. For example, the optimization unit performs appropriate placement based on the years of experience of the operators. The optimization unit can also perform detailed placement according to the skill level of the operators. For example, the optimization unit performs detailed placement according to the skill level of the operators. The optimization unit can also perform individually customized placement by taking into account the attribute information of the operators. For example, the optimization unit performs individually customized placement by taking into account the attribute information of the operators. This enables more appropriate placement by taking into account the attribute information of the operators. Some or all of the above-described processing in the optimization unit may be performed using AI, or may be performed without using AI. For example, the optimization unit can input the attribute information of the operators into the generation AI and have the generation AI perform the placement.

[0064] During allocation optimization, the optimization unit can improve the accuracy of allocation by referring to the customer's past complaint history. For example, the optimization unit refers to the customer's past complaint history and performs allocation for a specific problem. For example, the optimization unit refers to the customer's past complaint history and performs allocation for a specific problem. The optimization unit can also adjust the allocation criteria based on the customer's past complaint history. For example, the optimization unit adjusts the allocation criteria based on the customer's past complaint history. The optimization unit can also analyze the customer's past complaint history and improve the accuracy of allocation. For example, the optimization unit analyzes the customer's past complaint history and improves the accuracy of allocation. In this way, the accuracy of allocation can be improved by referring to the customer's past complaint history. Some or all of the above-mentioned processing in the optimization unit may be performed using, for example, AI, or may be performed without using AI. For example, the optimization unit can input the customer's past complaint history into a generation AI, which can improve the accuracy of allocation.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] When analyzing the content of a call, the analysis unit can improve the accuracy of the analysis by referring to the customer's past purchase history. For example, the analysis unit can refer to the customer's past purchase history to check the frequency of complaints about a specific product. The analysis unit can also evaluate the appropriateness of the response to a specific product based on the customer's purchase history. Furthermore, the analysis unit can analyze the customer's purchase history, identify purchasing patterns, and reflect these in the analysis. In this way, by referring to the customer's past purchase history, the accuracy of the analysis can be improved.

[0067] When analyzing the content of a call, the scoring unit can refer to the results of a customer satisfaction survey to improve the accuracy of the score. For example, the scoring unit can refer to the results of a customer satisfaction survey to evaluate how a specific response affected customer satisfaction. The scoring unit can also adjust the scoring criteria based on the results of the satisfaction survey. Furthermore, the scoring unit can analyze the results of the satisfaction survey to improve the accuracy of the score. In this way, the accuracy of the score can be improved by referring to the results of the customer satisfaction survey.

[0068] When creating a training program, the creation unit can adjust the program content by reflecting the operator's past feedback. For example, the creation unit can refer to the operator's past feedback to evaluate whether a specific skill has improved. The creation unit can also customize the training program content based on the feedback content. Furthermore, the creation unit can analyze feedback patterns and improve the accuracy of the program. This makes it possible to adjust the program content and improve accuracy by reflecting the operator's past feedback.

[0069] When analyzing the content of a call, the analysis unit can improve the accuracy of the analysis by referring to the customer's social media activity. For example, the analysis unit can analyze the customer's social media posts to understand the background of a complaint. It can also evaluate the appropriateness of a response to a specific problem based on social media activity. It can also incorporate related information into the analysis by referring to the activity of friends on social media. In this way, the accuracy of the analysis can be improved by referring to the customer's social media activity.

[0070] When making a proposal, the proposal unit can improve the accuracy of the proposal by referring to the operator's past performance data. For example, the proposal unit can refer to the operator's past performance data to evaluate whether a specific response has improved. The proposal standard can also be adjusted based on the performance data. Furthermore, the performance data can be analyzed to improve the accuracy of the proposal. In this way, the accuracy of the proposal can be improved by referring to the operator's past performance data.

[0071] During placement optimization, the optimization unit can improve placement accuracy by referring to the operator's past training history. For example, the optimization unit can refer to the operator's past training history to evaluate whether a specific skill has improved. It can also adjust placement criteria based on the training history. Furthermore, it can analyze the training history to improve placement accuracy. In this way, it is possible to improve placement accuracy by referring to the operator's past training history.

[0072] The processing flow of the first embodiment will be briefly explained below.

[0073] Step 1: The analysis unit analyzes the call content. The call content includes voice calls, video calls, text chats, etc. The analysis unit converts the call content into text using voice recognition technology and performs emotion analysis using an emotion recognition algorithm. Step 2: The scoring department assigns a score based on the evaluation results analyzed by the analysis department. The score is determined based on the appropriateness of the complaint handling and the speed of the declaration processing. Step 3: The suggestion unit suggests improvements based on the scores obtained by the scoring unit. Suggestions are made automatically based on the scoring results. Step 4: The development department creates a training program based on the improvements proposed by the proposal department. The training program is created based on the evaluation results. Step 5: The optimization unit adjusts the allocation of operators based on the training program created by the creation unit. The adjustment of the allocation is made based on the evaluation results.

[0074] (Example 2) An evaluation system according to an embodiment of the present invention is a system for efficiently evaluating the performance of telephone receptionists. This evaluation system analyzes call content, assigns scores based on the evaluation results, proposes areas for improvement, creates training programs, and optimizes operator deployment. For example, the evaluation system analyzes the content of each operator's call in real time to evaluate the status of complaint handling and reporting. The evaluation system then scores the operator's performance based on the evaluation results and identifies areas for improvement. This allows for efficient evaluation of operator performance, leading to the provision of better service. For example, the evaluation system converts the call content into text and performs sentiment analysis to evaluate the appropriateness of complaint handling and the speed of reporting. The evaluation system then assigns a score based on the evaluation results and quantifies overall performance. Furthermore, the evaluation system identifies areas for improvement based on the scoring results and proposes specific improvement measures. This allows operators to identify their own weaknesses and work to improve their skills. This allows for efficient evaluation of operator performance, leading to the provision of better service. This allows for efficient evaluation of operator performance, proposes areas for improvement, creates training programs, and optimizes operator deployment. For example, a training program for operators can be created based on the evaluation results to improve their skills. It is also possible to optimize operator deployment based on the evaluation results and improve work efficiency.

[0075] The evaluation system according to the embodiment includes an analysis unit, a scoring unit, a suggestion unit, a creation unit, and an optimization unit. The analysis unit analyzes call content. The call content includes, but is not limited to, voice calls, video calls, and text chats. The analysis unit converts the call content into text using, for example, voice recognition technology. The analysis unit can also perform emotion analysis of the call content using an emotion recognition algorithm. For example, the analysis unit converts the call content into text using voice recognition technology and performs emotion analysis using an emotion recognition algorithm. The scoring unit performs scoring based on the evaluation results analyzed by the analysis unit. Scoring is performed based on, for example, the appropriateness of complaint handling and the speed of reporting processing, but is not limited to, such examples. For example, the scoring unit assigns a score based on the appropriateness of complaint handling. The scoring unit can also assign a score based on the speed of reporting processing. The suggestion unit suggests improvements based on the scores obtained by the scoring unit. The suggestions are performed automatically based on, for example, the scoring results, but are not limited to, such examples. For example, the suggestion unit automatically suggests improvements based on the scoring results. The creation unit creates a training program based on the improvements proposed by the suggestion unit. The training program is created based on, for example, the evaluation results, but is not limited to this example. For example, the creation unit creates the training program based on the evaluation results. The optimization unit optimizes the allocation of operators based on the training program created by the creation unit. The optimization of the allocation is performed based on, for example, the evaluation results, but is not limited to this example. For example, the optimization unit optimizes the allocation of operators based on the evaluation results. In this way, the evaluation system according to the embodiment can efficiently evaluate the performance of operators, suggest improvements, create a training program, and optimize the allocation.

[0076] The analysis unit can convert the call content into text or perform sentiment analysis. The analysis unit can convert the call content into text using, for example, voice recognition technology. For example, the analysis unit can automatically analyze the voice using voice recognition software and save it as text. The analysis unit can also perform sentiment analysis of the call content using an emotion recognition algorithm. For example, the analysis unit can convert the call content into text using voice recognition technology and perform sentiment analysis using an emotion recognition algorithm. By converting the call content into text and performing sentiment analysis, the quality of the operator's response can be evaluated. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input voice data to a generation AI to convert the call content into text, and have the generation AI generate text data.

[0077] The scoring unit can assign scores based on the appropriateness of the complaint handling and the speed of the claim processing. The scoring unit assigns scores, for example, based on the appropriateness of the complaint handling. For example, the scoring unit assigns scores based on criteria such as response time, resolution rate, and customer satisfaction. The scoring unit can also assign scores based on the speed of the claim processing. For example, the scoring unit assigns scores based on criteria such as processing time and response speed. This makes it possible to quantify the performance of an operator by assigning scores based on the appropriateness of the complaint handling and the speed of the claim processing. Some or all of the above-described processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can input evaluation data into a generation AI to assign scores based on the appropriateness of the complaint handling and the speed of the claim processing, and have the generation AI generate scores.

[0078] The suggestion unit can automatically suggest improvements based on the scoring results. The suggestion unit, for example, automatically suggests improvements based on the scoring results. For example, the suggestion unit analyzes the scoring results using a suggestion algorithm and identifies improvements. The suggestion unit can also suggest improvements based on the form of feedback. For example, the suggestion unit automatically suggests improvements based on the scoring results and provides feedback. This makes it possible to improve the skills of operators by automatically suggesting improvements based on the scoring results. Some or all of the above-mentioned processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input the scoring results to a generation AI and have the generation AI suggest improvements.

[0079] The creation unit can create a training program based on the evaluation results. The creation unit, for example, creates a training program based on the evaluation results. For example, the creation unit creates a training program based on the scoring results and the feedback content. The creation unit can also create a training program based on the type of training and the implementation method. For example, the creation unit creates a training program based on the evaluation results to improve the operator's skills. In this way, by creating a training program based on the evaluation results, it is possible to improve the operator's skills. Some or all of the above-mentioned processing in the creation unit may be performed using AI, for example, or may be performed without using AI. For example, the creation unit inputs the evaluation results into a generation AI and causes the generation AI to create a training program.

[0080] The optimization unit can optimize the allocation of operators based on the evaluation results. The optimization unit, for example, optimizes the allocation of operators based on the evaluation results. For example, the optimization unit optimizes the allocation based on the skills of the operators and the type of work. The optimization unit can also optimize the allocation based on the shift time period and the priority of the work. For example, the optimization unit optimizes the allocation of operators based on the evaluation results to improve the efficiency of work. In this way, by optimizing the allocation of operators based on the evaluation results, it is possible to improve the efficiency of work. Some or all of the above-mentioned processing in the optimization unit may be performed using AI, for example, or may be performed without using AI. For example, the optimization unit can input the evaluation results to a generation AI and have the generation AI optimize the allocation.

[0081] The analysis unit can estimate the operator's emotions and adjust the analysis method for the call content based on the estimated operator's emotions. For example, if the operator is stressed, the analysis unit simplifies the analysis method and focuses on important points. For example, if the operator is stressed, the analysis unit simplifies the analysis method and focuses on important points. Furthermore, if the operator is relaxed, the analysis unit can perform a detailed analysis and extract more information. For example, if the operator is relaxed, the analysis unit can perform a detailed analysis and extract more information. Furthermore, if the operator is nervous, the analysis unit can enhance the emotion analysis and evaluate the quality of the conversation with the customer. For example, if the operator is nervous, the analysis unit can enhance the emotion analysis and evaluate the quality of the conversation with the customer. This enables more appropriate analysis by adjusting the analysis method based on the operator's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input the operator's emotion data into the generation AI, which may then adjust the analysis method.

[0082] When analyzing the content of a call, the analysis unit can improve the accuracy of the analysis by referring to the customer's past complaint history. For example, the analysis unit can refer to the customer's past complaint history to check whether a similar problem has recurred. For example, the analysis unit can refer to the customer's past complaint history to check whether a similar problem has recurred. The analysis unit can also evaluate the appropriateness of a response to a specific problem based on the customer's past complaint history. For example, the analysis unit can evaluate the appropriateness of a response to a specific problem based on the customer's past complaint history. The analysis unit can also analyze the customer's past complaint history, identify complaint patterns, and reflect them in the analysis. For example, the analysis unit can analyze the customer's past complaint history, identify complaint patterns, and reflect them in the analysis. In this way, by referring to the customer's past complaint history, the accuracy of the analysis can be improved. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input the customer's past complaint history into a generation AI, which can improve the accuracy of the analysis.

[0083] When analyzing the content of a call, the analysis unit can perform analysis based on customer attribute information. The analysis unit can evaluate an appropriate response method based on, for example, the customer's age. For example, the analysis unit can evaluate an appropriate response method based on the customer's age. The analysis unit can also evaluate whether a specific response was appropriate based on the customer's gender. For example, the analysis unit can evaluate whether a specific response was appropriate based on the customer's gender. The analysis unit can also consider the customer's regional information to evaluate the appropriateness of a response to a problem specific to the region. For example, the analysis unit considers the customer's regional information to evaluate the appropriateness of a response to a problem specific to the region. This enables more appropriate analysis by considering the customer's attribute information. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input customer attribute information into a generation AI and have the generation AI perform the analysis.

[0084] When analyzing the content of a call, the analysis unit can weight the analysis based on the time of day and day of the week of the call. For example, if a call is made during a peak time period, the analysis unit weights the call because a prompt response is required. For example, if a call is made during a peak time period, the analysis unit weights the call because a prompt response is required. The analysis unit can also evaluate whether a specific response was appropriate if the call was made on a weekend. For example, the analysis unit can evaluate whether a specific response was appropriate if the call was made on a weekend. The analysis unit can also analyze the call late at night, placing emphasis on the promptness of the response. For example, the analysis unit analyzes the call late at night, placing emphasis on the promptness of the response. Thus, weighting the analysis based on the time of day and day of the week of the call enables more appropriate analysis. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input data on the time of day and day of the week of the call into a generation AI, and have the generation AI weight the analysis.

[0085] The analysis unit can estimate the operator's emotions and adjust the display method of the analysis results based on the estimated operator's emotions. For example, if the operator is feeling stressed, the analysis unit provides a simple display method and displays only important information. For example, if the operator is feeling stressed, the analysis unit provides a simple display method and displays only important information. Furthermore, if the operator is relaxed, the analysis unit can display detailed analysis results and clarify areas for improvement. For example, if the operator is relaxed, the analysis unit can display detailed analysis results and clarify areas for improvement. Furthermore, if the operator is nervous, the analysis unit can provide a visually easy-to-understand display method to make the analysis results easier to understand. For example, if the operator is nervous, the analysis unit provides a visually easy-to-understand display method to make the analysis results easier to understand. This allows for adjusting the display method of the analysis results based on the operator's emotions, enabling more appropriate display. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input the operator's emotional data into the generation AI, which may then adjust the display method of the analysis results.

[0086] The analysis unit can take into account the customer's geographical location information when analyzing the content of the call. For example, the analysis unit evaluates the appropriateness of a response to a region-specific problem based on the customer's geographical location information. For example, the analysis unit evaluates the appropriateness of a response to a region-specific problem based on the customer's geographical location information. The analysis unit can also refer to the customer's geographical location information and reflect complaint patterns in a specific region in the analysis. For example, the analysis unit refers to the customer's geographical location information and reflects complaint patterns in a specific region in the analysis. The analysis unit can also evaluate differences in response methods for each region by taking into account the customer's geographical location information. For example, the analysis unit evaluates differences in response methods for each region by taking into account the customer's geographical location information. This enables more appropriate analysis by taking into account the customer's geographical location information. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the customer's geographical location information into a generation AI and have the generation AI perform the analysis.

[0087] When analyzing the content of a call, the analysis unit can analyze the customer's social media activity and reflect related information in the analysis. For example, the analysis unit can analyze the customer's social media posts to understand the background of the complaint. For example, the analysis unit can analyze the customer's social media posts to understand the background of the complaint. The analysis unit can also refer to the customer's social media activity to evaluate the appropriateness of a response to a specific problem. For example, the analysis unit can refer to the customer's social media activity to evaluate the appropriateness of a response to a specific problem. The analysis unit can also refer to the activity of the customer's friends on social media to reflect related information in the analysis. For example, the analysis unit refers to the activity of the customer's friends on social media to reflect related information in the analysis. This enables more appropriate analysis by analyzing the customer's social media activity. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the customer's social media activity into a generation AI and have the generation AI perform the analysis.

[0088] When analyzing the content of a call, the analysis unit can customize the analysis method by reflecting the customer's past feedback. For example, the analysis unit refers to the customer's past feedback and evaluates whether a specific response was appropriate. For example, the analysis unit refers to the customer's past feedback and evaluates whether a specific response was appropriate. The analysis unit can also customize the analysis method based on the customer's past feedback to improve accuracy. For example, the analysis unit customizes the analysis method based on the customer's past feedback to improve accuracy. The analysis unit can also analyze the customer's past feedback and reflect feedback patterns in the analysis. For example, the analysis unit analyzes the customer's past feedback and reflects feedback patterns in the analysis. In this way, by reflecting the customer's past feedback, the analysis method can be customized and accuracy can be improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the customer's past feedback into a generation AI and have the generation AI customize the analysis method.

[0089] The scoring unit can estimate the operator's emotions and adjust the scoring criteria based on the estimated operator's emotions. For example, if the operator is stressed, the scoring unit relaxes the scoring criteria and emphasizes the quality of the response. For example, if the operator is stressed, the scoring unit relaxes the scoring criteria and emphasizes the quality of the response. Furthermore, if the operator is relaxed, the scoring unit can perform detailed scoring to clarify areas for improvement. For example, if the operator is relaxed, the scoring unit can perform detailed scoring to clarify areas for improvement. Furthermore, if the operator is nervous, the scoring unit can perform scoring by emphasizing quick response. For example, if the operator is nervous, the scoring unit performs scoring by emphasizing quick response. In this way, by adjusting the scoring criteria based on the operator's emotions, more appropriate scoring is possible. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit may input the operator's emotional data into the generation AI, which may then adjust the scoring criteria.

[0090] The scoring unit can adjust the level of detail of the score based on the importance of the call content when scoring. For example, in the case of an important complaint response, the scoring unit performs detailed scoring to evaluate the quality of the response. For example, in the case of an important complaint response, the scoring unit performs detailed scoring to evaluate the quality of the response. Furthermore, in the case of a general complaint processing, the scoring unit can perform simplified scoring to emphasize speed. For example, in the case of a general complaint processing, the scoring unit can perform simplified scoring to emphasize speed. Furthermore, in the case of a response to a specific issue, the scoring unit can adjust the level of detail of the scoring according to the importance. For example, in the case of a response to a specific issue, the scoring unit adjusts the level of detail of the scoring according to the importance. In this way, adjusting the level of detail of the score based on the importance of the call content enables more appropriate scoring. Some or all of the above-described processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can input importance data of the call content to a generation AI and have the generation AI adjust the level of detail of the score.

[0091] The scoring unit can apply different scoring algorithms depending on the call category when scoring. For example, in the case of handling a complaint, the scoring unit applies a scoring algorithm that emphasizes the quality of the response. For example, in the case of handling a complaint, the scoring unit applies a scoring algorithm that emphasizes the quality of the response. Furthermore, the scoring unit can also apply a scoring algorithm that emphasizes speed in the case of reporting processing. For example, in the case of reporting processing, the scoring unit applies a scoring algorithm that emphasizes speed. Furthermore, the scoring unit can also apply a scoring algorithm according to the category in the case of handling a specific problem. For example, in the case of handling a specific problem, the scoring unit applies a scoring algorithm according to the category. In this way, by applying different scoring algorithms depending on the call category, more appropriate scoring is possible. Some or all of the above-mentioned processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can input call category data into a generation AI and have the generation AI apply a scoring algorithm.

[0092] The scoring unit can improve the accuracy of the score by referring to the operator's past scoring results when scoring. For example, the scoring unit can refer to the operator's past scoring results to evaluate whether a specific response has improved. For example, the scoring unit can refer to the operator's past scoring results to evaluate whether a specific response has improved. The scoring unit can also adjust the scoring criteria based on the operator's past scoring results. For example, the scoring unit can adjust the scoring criteria based on the operator's past scoring results. The scoring unit can also analyze the operator's past scoring results to improve the accuracy of the score. For example, the scoring unit can analyze the operator's past scoring results to improve the accuracy of the score. In this way, the accuracy of the score can be improved by referring to the operator's past scoring results. Some or all of the above-described processing in the scoring unit can be performed using, for example, AI, or can be performed without using AI. For example, the scoring unit can input the operator's past scoring results into a generation AI, which can improve the accuracy of the score.

[0093] The scoring unit can estimate the operator's emotions and adjust the score display method based on the estimated operator's emotions. For example, if the operator is stressed, the scoring unit provides a simple display method and displays only important information. For example, if the operator is stressed, the scoring unit provides a simple display method and displays only important information. Furthermore, if the operator is relaxed, the scoring unit can display a detailed score and clarify areas for improvement. For example, if the operator is relaxed, the scoring unit can display a detailed score and clarify areas for improvement. Furthermore, if the operator is nervous, the scoring unit can provide a visually easy-to-understand display method to make the score easier to understand. For example, if the operator is nervous, the scoring unit provides a visually easy-to-understand display method to make the score easier to understand. This allows for adjusting the score display method based on the operator's emotions, enabling a more appropriate display. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit may input the operator's emotional data into the generation AI, which may then adjust the score display method.

[0094] When scoring, the scoring unit can weight the score based on the time of day and day of the week of the call. For example, the scoring unit weights the call when it is made during a peak time period because a prompt response is required. For example, the scoring unit weights the call when it is made during a peak time period because a prompt response is required. The scoring unit can also evaluate whether a specific response was appropriate when the call was made on a weekend. For example, the scoring unit evaluates whether a specific response was appropriate when the call was made on a weekend. The scoring unit can also score the call late at night by emphasizing the promptness of the response. For example, the scoring unit scores the call late at night by emphasizing the promptness of the response. Thus, weighting the score based on the time of day and day of the week of the call enables more appropriate scoring. Some or all of the above-described processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can input data on the time of day and day of the week of the call into the generation AI, and have the generation AI weight the score.

[0095] The scoring unit can assign a score taking into account customer attribute information when scoring. The scoring unit evaluates an appropriate response method based on, for example, the customer's age. For example, the scoring unit evaluates an appropriate response method based on the customer's age. The scoring unit can also evaluate whether a specific response was appropriate based on the customer's gender. For example, the scoring unit evaluates whether a specific response was appropriate based on the customer's gender. The scoring unit can also evaluate the appropriateness of a response to a problem specific to the region by taking into account the customer's regional information. For example, the scoring unit evaluates the appropriateness of a response to a problem specific to the region by taking into account the customer's regional information. This enables more appropriate scoring by taking into account the customer's attribute information. Some or all of the above-described processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can input customer attribute information into a generation AI and have the generation AI assign a score.

[0096] The scoring unit can improve the accuracy of the score by referring to the customer's past complaint history when scoring. For example, the scoring unit can refer to the customer's past complaint history to check whether a similar problem has recurred. For example, the scoring unit can refer to the customer's past complaint history to check whether a similar problem has recurred. The scoring unit can also evaluate the appropriateness of a response to a specific problem based on the customer's past complaint history. For example, the scoring unit can evaluate the appropriateness of a response to a specific problem based on the customer's past complaint history. The scoring unit can also analyze the customer's past complaint history, identify complaint patterns, and reflect them in the scoring. For example, the scoring unit can analyze the customer's past complaint history, identify complaint patterns, and reflect them in the scoring. In this way, by referring to the customer's past complaint history, the accuracy of the score can be improved. Some or all of the above-mentioned processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can input the customer's past complaint history into a generation AI, which can improve the accuracy of the score.

[0097] The suggestion unit can estimate the operator's emotions and adjust the method of suggesting improvements based on the estimated operator's emotions. For example, if the operator is feeling stressed, the suggestion unit can suggest simple improvements to reduce the operator's workload. For example, if the operator is feeling stressed, the suggestion unit can suggest simple improvements to reduce the operator's workload. Furthermore, if the operator is relaxed, the suggestion unit can suggest detailed improvements to improve the operator's skills. For example, if the operator is relaxed, the suggestion unit can suggest detailed improvements to improve the operator's skills. Furthermore, if the operator is nervous, the suggestion unit can suggest visually easy-to-understand improvements to make the improvements easier to understand. For example, if the operator is nervous, the suggestion unit can suggest visually easy-to-understand improvements to make the improvements easier to understand. This allows for more appropriate suggestions to be made by adjusting the method of suggesting improvements based on the operator's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input the operator's emotion data into the generation AI, which may then adjust the suggestion method.

[0098] When making a proposal, the suggestion unit can adjust the level of detail of the proposal based on the importance of the scoring result. For example, in the case of an important complaint response, the suggestion unit can suggest detailed improvements to improve the quality of the response. For example, in the case of an important complaint response, the suggestion unit can suggest detailed improvements to improve the quality of the response. The suggestion unit can also suggest simplified improvements to emphasize speed in the case of general complaint processing. For example, in the case of general complaint processing, the suggestion unit can suggest simplified improvements to emphasize speed. The suggestion unit can also adjust the level of detail of the proposal based on the importance in the case of a response to a specific problem. For example, in the case of a response to a specific problem, the suggestion unit adjusts the level of detail of the proposal based on the importance. This enables more appropriate proposals to be made by adjusting the level of detail of the proposal based on the importance of the scoring result. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input importance data of the scoring result to a generation AI, causing the generation AI to adjust the level of detail of the proposal.

[0099] When making a proposal, the suggestion unit can improve the accuracy of the proposal by referring to the operator's past improvement history. For example, the suggestion unit can refer to the operator's past improvement history to evaluate whether a specific response has improved. For example, the suggestion unit can refer to the operator's past improvement history to evaluate whether a specific response has improved. The suggestion unit can also adjust the criteria for the proposal based on the operator's past improvement history. For example, the suggestion unit can adjust the criteria for the proposal based on the operator's past improvement history. The suggestion unit can also analyze the operator's past improvement history to improve the accuracy of the proposal. For example, the suggestion unit can analyze the operator's past improvement history to improve the accuracy of the proposal. In this way, the accuracy of the proposal can be improved by referring to the operator's past improvement history. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input the operator's past improvement history into a generation AI, which can improve the accuracy of the proposal.

[0100] When making a proposal, the proposal unit can apply different proposal algorithms depending on the category of the call content. For example, in the case of handling a complaint, the proposal unit applies a proposal algorithm that emphasizes the quality of the response. For example, in the case of handling a complaint, the proposal unit applies a proposal algorithm that emphasizes the quality of the response. The proposal unit can also apply a proposal algorithm that emphasizes speed in the case of reporting processing. For example, in the case of reporting processing, the proposal unit applies a proposal algorithm that emphasizes speed. The proposal unit can also apply a proposal algorithm according to the category in the case of responding to a specific problem. For example, in the case of responding to a specific problem, the proposal unit applies a proposal algorithm according to the category. This enables more appropriate proposals by applying different proposal algorithms depending on the category of the call content. Some or all of the above-mentioned processing in the proposal unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal unit can input category data of the call content to a generation AI, and have the generation AI apply the proposal algorithm.

[0101] The suggestion unit can estimate the operator's emotions and adjust the display method of suggestions based on the estimated operator's emotions. For example, if the operator is feeling stressed, the suggestion unit can provide a simple display method and display only important information. For example, if the operator is feeling stressed, the suggestion unit can provide a simple display method and display only important information. Furthermore, if the operator is relaxed, the suggestion unit can display detailed suggestions and clarify areas for improvement. For example, if the operator is relaxed, the suggestion unit can display detailed suggestions and clarify areas for improvement. Furthermore, if the operator is nervous, the suggestion unit can provide a visually easy-to-understand display method to make the suggestions easier to understand. For example, if the operator is nervous, the suggestion unit can provide a visually easy-to-understand display method to make the suggestions easier to understand. This allows for adjusting the display method of suggestions based on the operator's emotions, enabling more appropriate display. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input the operator's emotional data into the generation AI, and have the generation AI adjust the way the suggestions are displayed.

[0102] When making a proposal, the suggestion unit can determine the priority of the proposal based on the time of day and day of the week of the call. For example, if a call is made during a peak time period, the suggestion unit sets a high priority because a prompt response is required. For example, if a call is made during a peak time period, the suggestion unit sets a high priority because a prompt response is required. The suggestion unit can also evaluate whether a specific response was appropriate and set a priority when a call is made on a weekend. For example, the suggestion unit evaluates whether a specific response was appropriate and set a priority when a call is made on a weekend. The suggestion unit can also determine the priority of the proposal by emphasizing the speed of the response when a call is made late at night. For example, the suggestion unit determines the priority of the proposal by emphasizing the speed of the response when a call is made late at night. In this way, by determining the priority of the proposal based on the time of day and day of the week of the call, more appropriate proposals can be made. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input data on the time of day and day of the week of the call into the generation AI, and have the generation AI determine the priority of the suggestions.

[0103] When making a proposal, the suggestion unit can take into account the attribute information of the operator. The suggestion unit can make a proposal by taking into account the attribute information of the operator. For example, the suggestion unit can suggest appropriate improvements based on the years of experience of the operator. The suggestion unit can also suggest detailed improvements based on the skill level of the operator. For example, the suggestion unit can suggest detailed improvements based on the skill level of the operator. The suggestion unit can also make individually customized proposals by taking into account the attribute information of the operator. For example, the suggestion unit can make individually customized proposals by taking into account the attribute information of the operator. This enables more appropriate proposals by taking into account the attribute information of the operator. Some or all of the above-mentioned processing in the suggestion unit can be performed using AI, for example, or without using AI. For example, the suggestion unit can input the attribute information of the operator to a generation AI and have the generation AI make a proposal.

[0104] When making a proposal, the suggestion unit can improve the accuracy of the proposal by referring to the customer's past complaint history. For example, the suggestion unit can refer to the customer's past complaint history and propose improvements for a specific problem. For example, the suggestion unit can refer to the customer's past complaint history and propose improvements for a specific problem. The suggestion unit can also adjust the criteria for the proposal based on the customer's past complaint history. For example, the suggestion unit can adjust the criteria for the proposal based on the customer's past complaint history. The suggestion unit can also analyze the customer's past complaint history and improve the accuracy of the proposal. For example, the suggestion unit can analyze the customer's past complaint history and improve the accuracy of the proposal. In this way, the accuracy of the proposal can be improved by referring to the customer's past complaint history. Some or all of the above-mentioned processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input the customer's past complaint history into a generation AI, which can improve the accuracy of the proposal.

[0105] The creation unit can estimate the operator's emotions and adjust the training program creation method based on the estimated operator's emotions. For example, if the operator is feeling stressed, the creation unit creates a simple, low-burden training program. For example, if the operator is feeling stressed, the creation unit creates a simple, low-burden training program. Furthermore, if the operator is relaxed, the creation unit can create a detailed training program to improve the operator's skills. For example, if the operator is relaxed, the creation unit creates a detailed training program to improve the operator's skills. Furthermore, if the operator is nervous, the creation unit can create a visually easy-to-understand training program. For example, if the operator is nervous, the creation unit creates a visually easy-to-understand training program. This allows for adjusting the training program creation method based on the operator's emotions, thereby creating a more appropriate training program. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or without AI. For example, the creation unit can input the operator's emotional data into the generation AI, which can then adjust the way the training program is created.

[0106] When creating a training program, the creation unit can adjust the level of detail of the program based on the importance of the scoring results. For example, when handling an important complaint, the creation unit creates a detailed training program to improve the quality of the response. For example, when handling an important complaint, the creation unit creates a detailed training program to improve the quality of the response. The creation unit can also create a simplified training program for general reporting processes to emphasize speed. For example, the creation unit can create a simplified training program for general reporting processes to emphasize speed. The creation unit can also adjust the level of detail of the training program depending on the importance when responding to a specific problem. For example, when responding to a specific problem, the creation unit adjusts the level of detail of the training program depending on the importance. This enables the creation of a more appropriate training program by adjusting the level of detail of the program based on the importance of the scoring results. Some or all of the above-described processing in the creation unit may be performed using, or without, AI. For example, the creation unit may input importance data of the scoring results into a generation AI, causing the generation AI to adjust the level of detail of the program.

[0107] When creating a training program, the creation unit can improve the accuracy of the program by referring to the operator's past training history. For example, the creation unit can refer to the operator's past training history to evaluate whether a specific skill has improved. For example, the creation unit can refer to the operator's past training history to evaluate whether a specific skill has improved. The creation unit can also adjust the content of the training program based on the operator's past training history. For example, the creation unit can adjust the content of the training program based on the operator's past training history. The creation unit can also analyze the operator's past training history to improve the accuracy of the program. For example, the creation unit can analyze the operator's past training history to improve the accuracy of the program. In this way, the accuracy of the program can be improved by referring to the operator's past training history. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the operator's past training history into a generation AI, and the generation AI can improve the accuracy of the program.

[0108] When creating a training program, the creation unit can apply different training algorithms depending on the category of the call content. For example, in the case of handling a complaint, the creation unit applies a training algorithm that emphasizes the quality of the response. For example, in the case of handling a complaint, the creation unit applies a training algorithm that emphasizes the quality of the response. The creation unit can also apply a training algorithm that emphasizes speed in the case of reporting processing. For example, in the case of reporting processing, the creation unit applies a training algorithm that emphasizes speed. The creation unit can also apply a training algorithm according to the category in the case of responding to a specific problem. For example, in the case of responding to a specific problem, the creation unit applies a training algorithm according to the category. This makes it possible to create a more appropriate training program by applying different training algorithms depending on the category of the call content. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input category data of the call content to a generation AI and cause the generation AI to apply a training algorithm.

[0109] The creation unit can estimate the operator's emotions and adjust the display method of the training program based on the estimated operator's emotions. For example, if the operator is feeling stressed, the creation unit can provide a simple display method and display only important information. For example, if the operator is feeling stressed, the creation unit can provide a simple display method and display only important information. Furthermore, if the operator is relaxed, the creation unit can display a detailed training program to help improve the operator's skills. For example, if the operator is relaxed, the creation unit can display a detailed training program to help improve the operator's skills. Furthermore, if the operator is nervous, the creation unit can provide a visually easy-to-understand display method to make the training program easier to understand. For example, if the operator is nervous, the creation unit can provide a visually easy-to-understand display method to make the training program easier to understand. This allows for a more appropriate display by adjusting the display method of the training program based on the operator's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit may input the operator's emotional data into the generation AI, and have the generation AI adjust the display method of the training program.

[0110] When creating a training program, the creation unit can determine the priority of the program based on the time of day and day of the week of the call. For example, if a call is made during a peak time period, the creation unit sets a high priority because a prompt response is required. For example, if a call is made during a peak time period, the creation unit sets a high priority because a prompt response is required. The creation unit can also evaluate whether a specific response was appropriate and set a priority when a call is made on a weekend. For example, the creation unit evaluates whether a specific response was appropriate and set a priority when a call is made on a weekend. The creation unit can also determine the priority of a training program by emphasizing the speed of the response when a call is made late at night. For example, the creation unit determines the priority of a training program by emphasizing the speed of the response when a call is made late at night. In this way, by determining the priority of the program based on the time of day and day of the week of the call, a more appropriate training program can be created. Some or all of the above-described processing in the creation unit may be performed, for example, using AI or without AI. For example, the creation unit can input data on the time of day and day of the week of the call into the generation AI, and have the generation AI determine the priority of the program.

[0111] When creating a training program, the creation unit can create the program taking into account the attribute information of the operator. The creation unit creates an appropriate training program, for example, based on the operator's years of experience. For example, the creation unit creates an appropriate training program based on the operator's years of experience. The creation unit can also create a detailed training program according to the operator's skill level. For example, the creation unit creates a detailed training program according to the operator's skill level. The creation unit can also create an individually customized training program taking into account the operator's attribute information. For example, the creation unit creates an individually customized training program taking into account the operator's attribute information. This makes it possible to create a more appropriate training program by taking into account the operator's attribute information. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the operator's attribute information into a generation AI and cause the generation AI to create a program.

[0112] When creating a training program, the creation unit can refer to the customer's past complaint history to improve the accuracy of the program. For example, the creation unit references the customer's past complaint history to create a training program for a specific problem. For example, the creation unit references the customer's past complaint history to create a training program for a specific problem. The creation unit can also adjust the content of the training program based on the customer's past complaint history. For example, the creation unit adjusts the content of the training program based on the customer's past complaint history. The creation unit can also analyze the customer's past complaint history to improve the accuracy of the program. For example, the creation unit analyzes the customer's past complaint history to improve the accuracy of the program. In this way, the accuracy of the program can be improved by referring to the customer's past complaint history. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the customer's past complaint history into a generation AI, which can improve the accuracy of the program.

[0113] The optimization unit can estimate the emotion of the operator and adjust the optimization method for the placement based on the estimated emotion of the operator. For example, if the operator is feeling stressed, the optimization unit performs a placement that places less strain on the operator. For example, if the operator is feeling stressed, the optimization unit performs a placement that places less strain on the operator. Furthermore, if the operator is relaxed, the optimization unit can perform a placement that maximizes the operator's skills. For example, if the operator is relaxed, the optimization unit performs a placement that maximizes the operator's skills. Furthermore, if the operator is nervous, the optimization unit can perform a placement that allows the operator to receive support. For example, if the operator is nervous, the optimization unit performs a placement that allows the operator to receive support. Thus, by adjusting the optimization method for the placement based on the emotion of the operator, more appropriate placement is possible. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the optimization unit may be performed using, for example, AI, or without AI. For example, the optimization unit can input the operator's emotional data into the generation AI, allowing the generation AI to adjust the placement optimization method.

[0114] During placement optimization, the optimization unit can adjust the level of detail of placement based on the importance of the scoring results. For example, the optimization unit assigns an experienced operator when handling an important complaint. For example, the optimization unit assigns an experienced operator when handling an important complaint. The optimization unit can also assign an operator who can respond quickly when processing a general complaint. For example, the optimization unit assigns an operator who can respond quickly when processing a general complaint. The optimization unit can also assign the optimal operator based on the scoring results when responding to a specific problem. For example, the optimization unit assigns the optimal operator based on the scoring results when responding to a specific problem. This enables more appropriate placement by adjusting the level of detail of placement based on the importance of the scoring results. Some or all of the above-mentioned processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input importance data of the scoring results to the generation AI, causing the generation AI to adjust the level of detail of placement.

[0115] During placement optimization, the optimization unit can improve placement accuracy by referring to the operator's past placement history. The optimization unit, for example, refers to the operator's past placement history and evaluates whether a specific response has improved. For example, the optimization unit refers to the operator's past placement history and evaluates whether a specific response has improved. The optimization unit can also adjust placement criteria based on the operator's past placement history. For example, the optimization unit adjusts placement criteria based on the operator's past placement history. The optimization unit can also analyze the operator's past placement history and improve placement accuracy. For example, the optimization unit analyzes the operator's past placement history and improves placement accuracy. In this way, the placement accuracy can be improved by referring to the operator's past placement history. Some or all of the above-described processing in the optimization unit may be performed using AI, for example, or may be performed without using AI. For example, the optimization unit can input the operator's past placement history into a generation AI, which can improve the placement accuracy.

[0116] The optimization unit can apply different allocation algorithms depending on the category of call content during allocation optimization. For example, in the case of complaint handling, the optimization unit applies an allocation algorithm that emphasizes the quality of the response. For example, in the case of complaint handling, the optimization unit applies an allocation algorithm that emphasizes the quality of the response. The optimization unit can also apply an allocation algorithm that emphasizes speed in the case of reporting processing. For example, in the case of reporting processing, the optimization unit applies an allocation algorithm that emphasizes speed. The optimization unit can also apply an allocation algorithm according to the category in the case of handling a specific problem. For example, in the case of handling a specific problem, the optimization unit applies an allocation algorithm according to the category. In this way, applying different allocation algorithms depending on the category of call content enables more appropriate allocation. Some or all of the above-mentioned processing in the optimization unit may be performed using, for example, AI, or may be performed without using AI. For example, the optimization unit can input call content category data into a generation AI and cause the generation AI to apply the allocation algorithm.

[0117] The optimization unit can estimate the operator's emotions and adjust the display method of the placement based on the estimated operator's emotions. For example, when the operator is stressed, the optimization unit provides a simple display method and displays only important information. For example, when the operator is stressed, the optimization unit provides a simple display method and displays only important information. Furthermore, when the operator is relaxed, the optimization unit can display detailed placement information to improve the operator's skills. For example, when the operator is relaxed, the optimization unit can display detailed placement information to improve the operator's skills. Furthermore, when the operator is nervous, the optimization unit can provide a visually easy-to-understand display method to make the placement information easier to understand. For example, when the operator is nervous, the optimization unit provides a visually easy-to-understand display method to make the placement information easier to understand. This allows for adjusting the display method of the placement based on the operator's emotions, enabling a more appropriate display. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the optimization unit may be performed using, for example, AI, or may be performed without using AI. For example, the optimization unit may input operator emotion data into the generation AI, causing the generation AI to adjust the display method of the placement.

[0118] During allocation optimization, the optimization unit can determine allocation priorities based on the time period and day of the week of the call. For example, if a call is made during a peak time period, the optimization unit sets a high priority because a prompt response is required. For example, if a call is made during a peak time period, the optimization unit sets a high priority because a prompt response is required. The optimization unit can also evaluate whether a specific response was appropriate and set a priority when a call is made on a weekend. For example, the optimization unit evaluates whether a specific response was appropriate and set a priority when a call is made on a weekend. The optimization unit can also determine allocation priorities by emphasizing speed of response when a call is made late at night. For example, the optimization unit determines allocation priorities by emphasizing speed of response when a call is made late at night. This enables more appropriate allocation by determining allocation priorities based on the time period and day of the week of the call. Some or all of the above-described processing in the optimization unit may be performed using, for example, AI, or may be performed without using AI. For example, the optimization unit can input data on the time of day and day of the week when calls are made into the generation AI, allowing the generation AI to determine placement priorities.

[0119] The optimization unit can perform the placement optimization by taking into account the attribute information of the operators. The optimization unit performs appropriate placement based on, for example, the years of experience of the operators. For example, the optimization unit performs appropriate placement based on the years of experience of the operators. The optimization unit can also perform detailed placement according to the skill level of the operators. For example, the optimization unit performs detailed placement according to the skill level of the operators. The optimization unit can also perform individually customized placement by taking into account the attribute information of the operators. For example, the optimization unit performs individually customized placement by taking into account the attribute information of the operators. This enables more appropriate placement by taking into account the attribute information of the operators. Some or all of the above-described processing in the optimization unit may be performed using AI, or may be performed without using AI. For example, the optimization unit can input the attribute information of the operators into the generation AI and have the generation AI perform the placement.

[0120] During allocation optimization, the optimization unit can improve the accuracy of allocation by referring to the customer's past complaint history. For example, the optimization unit refers to the customer's past complaint history and performs allocation for a specific problem. For example, the optimization unit refers to the customer's past complaint history and performs allocation for a specific problem. The optimization unit can also adjust the allocation criteria based on the customer's past complaint history. For example, the optimization unit adjusts the allocation criteria based on the customer's past complaint history. The optimization unit can also analyze the customer's past complaint history and improve the accuracy of allocation. For example, the optimization unit analyzes the customer's past complaint history and improves the accuracy of allocation. In this way, the accuracy of allocation can be improved by referring to the customer's past complaint history. Some or all of the above-mentioned processing in the optimization unit may be performed using, for example, AI, or may be performed without using AI. For example, the optimization unit can input the customer's past complaint history into a generation AI, which can improve the accuracy of allocation. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, scoring unit, proposing unit, creating unit, and optimizing unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit can convert the contents of the call into text using the control unit 46A of the smart device 14 and perform sentiment analysis. The scoring unit, for example, performs scoring based on the evaluation results using the specific processing unit 290 of the data processing device 12. The proposing unit, for example, suggests improvements based on the scores using the specific processing unit 290 of the data processing device 12. The creating unit, for example, creates a training program using the specific processing unit 290 of the data processing device 12. The optimizing unit, for example, optimizes the allocation of operators using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned analysis unit, scoring unit, suggestion unit, creation unit, and optimization unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit can convert the contents of the call into text and perform sentiment analysis using the control unit 46A of the smart glasses 214. The scoring unit, for example, performs scoring based on the evaluation results using the specific processing unit 290 of the data processing device 12. The suggestion unit, for example, suggests improvements based on the scores using the specific processing unit 290 of the data processing device 12. The creation unit, for example, creates a training program using the specific processing unit 290 of the data processing device 12. The optimization unit, for example, optimizes the allocation of operators using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, scoring unit, proposing unit, creation unit, and optimization unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit can convert the contents of the call into text using the control unit 46A of the headset type terminal 314 and perform sentiment analysis. The scoring unit, for example, performs scoring based on the evaluation results using the specific processing unit 290 of the data processing device 12. The suggestion unit, for example, suggests improvements based on the score using the specific processing unit 290 of the data processing device 12. The creation unit, for example, creates a training program using the specific processing unit 290 of the data processing device 12. The optimization unit, for example, optimizes the allocation of operators using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, scoring unit, suggestion unit, creation unit, and optimization unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit can convert the contents of the call into text using the control unit 46A of the robot 414 and perform sentiment analysis. The scoring unit, for example, performs scoring based on the evaluation results using the specific processing unit 290 of the data processing device 12. The suggestion unit, for example, suggests improvements based on the score using the specific processing unit 290 of the data processing device 12. The creation unit, for example, creates a training program using the specific processing unit 290 of the data processing device 12. The optimization unit, for example, optimizes the allocation of operators using the specific processing unit 290 of the data processing device 12.

[0121] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0122] When analyzing the content of a call, the analysis unit can improve the accuracy of the analysis by referring to the customer's past purchase history. For example, the analysis unit can refer to the customer's past purchase history to check the frequency of complaints about a specific product. The analysis unit can also evaluate the appropriateness of the response to a specific product based on the customer's purchase history. Furthermore, the analysis unit can analyze the customer's purchase history, identify purchasing patterns, and reflect these in the analysis. In this way, by referring to the customer's past purchase history, the accuracy of the analysis can be improved.

[0123] When analyzing the content of a call, the scoring unit can refer to the results of a customer satisfaction survey to improve the accuracy of the score. For example, the scoring unit can refer to the results of a customer satisfaction survey to evaluate how a specific response affected customer satisfaction. The scoring unit can also adjust the scoring criteria based on the results of the satisfaction survey. Furthermore, the scoring unit can analyze the results of the satisfaction survey to improve the accuracy of the score. In this way, the accuracy of the score can be improved by referring to the results of the customer satisfaction survey.

[0124] The suggestion unit can estimate the operator's emotions and adjust the priority of suggestions based on the estimated operator's emotions. For example, if the operator is feeling stressed, the priority of suggestions can be set low to reduce the burden on the operator. Also, if the operator is relaxed, detailed suggestions can be given priority to improve the operator's skills. Furthermore, if the operator is nervous, suggestions that are visually easy to understand can be given priority to make them easier to understand. In this way, by adjusting the priority of suggestions based on the operator's emotions, more appropriate suggestions can be made.

[0125] When creating a training program, the creation unit can adjust the program content by reflecting the operator's past feedback. For example, the creation unit can refer to the operator's past feedback to evaluate whether a specific skill has improved. The creation unit can also customize the training program content based on the feedback content. Furthermore, the creation unit can analyze feedback patterns and improve the accuracy of the program. This makes it possible to adjust the program content and improve accuracy by reflecting the operator's past feedback.

[0126] The optimization unit can estimate the emotions of the operators and adjust the priorities of deployment based on the estimated emotions of the operators. For example, if the operator is feeling stressed, it can prioritize deployment that places less strain on the operator. Also, if the operator is relaxed, it can prioritize deployment that makes the most of the operator's skills. Furthermore, if the operator is nervous, it can prioritize deployment that allows the operator to receive support. In this way, by adjusting the priorities of deployment based on the emotions of the operators, it becomes possible to achieve more appropriate deployment.

[0127] When analyzing the content of a call, the analysis unit can improve the accuracy of the analysis by referring to the customer's social media activity. For example, the analysis unit can analyze the customer's social media posts to understand the background of a complaint. It can also evaluate the appropriateness of a response to a specific problem based on social media activity. It can also incorporate related information into the analysis by referring to the activity of friends on social media. In this way, the accuracy of the analysis can be improved by referring to the customer's social media activity.

[0128] The scoring unit can estimate the emotion of the operator and adjust the weighting of the score based on the estimated emotion of the operator. For example, if the operator is feeling stressed, the weighting of the score can be relaxed and emphasis can be placed on the quality of the response. Also, if the operator is relaxed, detailed scoring can be performed to clarify areas for improvement. Furthermore, if the operator is nervous, scoring can be performed with emphasis on quick response. In this way, adjusting the weighting of the score based on the emotion of the operator makes it possible to perform more appropriate scoring.

[0129] When making a proposal, the proposal unit can improve the accuracy of the proposal by referring to the operator's past performance data. For example, the proposal unit can refer to the operator's past performance data to evaluate whether a specific response has improved. The proposal standard can also be adjusted based on the performance data. Furthermore, the performance data can be analyzed to improve the accuracy of the proposal. In this way, the accuracy of the proposal can be improved by referring to the operator's past performance data.

[0130] When creating a training program, the creation unit can estimate the operator's emotions and adjust the priority of the programs based on the estimated operator's emotions. For example, if the operator is feeling stressed, a training program with less burden can be created with priority. Also, if the operator is relaxed, a detailed training program can be created with priority to improve the operator's skills. Furthermore, if the operator is nervous, a training program that is visually easy to understand can be created with priority. In this way, by adjusting the priority of programs based on the operator's emotions, more appropriate training programs can be created.

[0131] During placement optimization, the optimization unit can improve placement accuracy by referring to the operator's past training history. For example, the optimization unit can refer to the operator's past training history to evaluate whether a specific skill has improved. It can also adjust placement criteria based on the training history. Furthermore, it can analyze the training history to improve placement accuracy. In this way, it is possible to improve placement accuracy by referring to the operator's past training history.

[0132] The processing flow of the second embodiment will be briefly explained below.

[0133] Step 1: The analysis unit analyzes the call content. The call content includes voice calls, video calls, text chats, etc. The analysis unit converts the call content into text using voice recognition technology and performs emotion analysis using an emotion recognition algorithm. Step 2: The scoring department assigns a score based on the evaluation results analyzed by the analysis department. The score is determined based on the appropriateness of the complaint handling and the speed of the declaration processing. Step 3: The suggestion unit suggests improvements based on the scores obtained by the scoring unit. Suggestions are made automatically based on the scoring results. Step 4: The development department creates a training program based on the improvements proposed by the proposal department. The training program is created based on the evaluation results. Step 5: The optimization unit adjusts the allocation of operators based on the training program created by the creation unit. The adjustment of the allocation is made based on the evaluation results.

[0134] 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.

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

[0136] 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.

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

[0138] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0139] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0141] The 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.

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

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

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

[0145] Fig. 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.

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

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

[0148] In the 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.

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

[0150] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0152] 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.

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

[0154] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0155] 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.

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

[0157] The 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.

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

[0159] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (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).

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

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0171] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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).

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0185] 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.

[0186] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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).

[0191] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0192] 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."

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] [Explanation of symbols]

[0206] 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. an analysis unit that analyzes the contents of the call; a scoring unit that performs scoring based on the evaluation results analyzed by the analysis unit; a suggestion unit that suggests improvements based on the scores obtained by the scoring unit; a creation unit that creates a training program based on the improvements suggested by the suggestion unit; an optimization unit that optimizes the allocation of operators based on the training program created by the creation unit; Equipped with A system characterized by:

2. The analysis unit Transcribe calls or analyze their sentiment 2. The system of claim 1.

3. The scoring unit Scores are awarded based on the appropriateness of complaint handling and the speed of reporting.

2. The system of claim 1.

4. The proposal unit Automatically suggest improvements based on scoring results 2. The system of claim 1.

5. The creation unit Create a training program based on the assessment results 2. The system of claim 1.

6. The optimization unit Optimize operator deployment based on evaluation results 2. The system of claim 1.

7. The analysis unit Estimate the emotions of the operator and adjust the analysis method of the call content based on the estimated emotions of the operator.

2. The system of claim 1.

8. The analysis unit When analyzing call content, improve the accuracy of the analysis by referring to the customer's past complaint history.

2. The system of claim 1.

9. The analysis unit When analyzing call content, analysis is performed based on customer attribute information 2. The system of claim 1.

10. The analysis unit When analyzing call content, the analysis is weighted based on the time of day and day of the week the call was made.

2. The system of claim 1.

Images