system

Abstract

To provide a system that responds to customer requirements promptly and efficiently.SOLUTION: A system according to an embodiment comprises: a reception unit; a summarization unit; a collation unit; a response unit; and a connection unit. The reception unit receives customer requirements. The summarization unit summarizes the requirements received by the reception unit. The collation unit collates the summary generated by the summarization unit with a FAQ database. The response unit provides a primary response on the basis of the result obtained by the collation unit. The connection unit connects to a person in charge when the response unit is unable to provide the primary response.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies make it difficult to respond quickly and efficiently to customer requirements, creating a demand for improved customer experience.

[0005] The system of the embodiment aims to respond quickly and efficiently to customer requirements. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a summarization unit, a comparison unit, an answering unit, and a connection unit. The reception unit receives customer requirements. The summarization unit summarizes the requirements received by the reception unit. The comparison unit compares the summary generated by the summarization unit with an FAQ database. The answering unit provides a primary answer based on the result obtained by the comparison unit. The connection unit connects to a person in charge when the answering unit cannot provide a primary answer. Effect of the Invention

[0007] An embodiment of the system can respond quickly and efficiently to customer requirements. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A customer response system according to an embodiment of the present invention is a system that automatically summarizes customer requirements and provides appropriate support. In this customer response system, when a customer calls a call center, a generation AI responds and has the customer talk about the requirements. The generation AI analyzes what the customer said in real time and generates a summary. This summary is compared with an FAQ database, and if a corresponding answer is found, the generation AI provides a first response on the spot. If there is no corresponding answer in the FAQ database or if a staff response is required, the generation AI connects the call to an appropriate person in charge based on the summary. The person in charge can solve the problem efficiently by referring to the summary generated by the generation AI. For example, when a customer calls a call center, the generation AI responds and has the customer talk about the requirements. The generation AI analyzes what the customer said in real time and generates a summary. This summary is compared with an FAQ database, and if a corresponding answer is found, the generation AI provides a first response on the spot. If there is no corresponding answer in the FAQ database or if a staff response is required, the generation AI connects the call to an appropriate person in charge based on the summary. The person in charge can solve the problem efficiently by referring to the summary generated by the generation AI. This allows customers to get a quick answer without having to go through complicated operations, improving the customer experience. In addition, staff can respond based on the summary, improving work efficiency. This allows the customer support system to automatically summarize customer requirements and provide appropriate responses.

[0029] The customer support system according to the embodiment includes a reception unit, a summarization unit, a comparison unit, a response unit, and a connection unit. The reception unit receives customer requirements. The customer requirements include, for example, inquiries, complaints, requests, etc., but are not limited to such examples. The reception unit can receive customer requirements using, for example, means such as telephone, email, and chat. The summarization unit summarizes the requirements received by the reception unit using a generation AI. The summarization is performed, for example, based on the length of the text and the importance of the information to be summarized, but are not limited to such examples. For example, the generation AI uses a text generation AI (for example, LLM) to concisely summarize the requirements. In addition, the summarization unit can also summarize the contents of the requirements using a multimodal generation AI. In addition, the summarization unit can extract and summarize important parts of the text using the generation AI. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modals such as images and voices as well as text. The generation AI uses keyword extraction technology to pick up particularly important information from the requirements and summarizes based on that. The collation unit collates the summary generated by the summarization unit with the FAQ database. The collation is performed by, for example, a method such as cosine similarity or Jaccard coefficient, but is not limited to such examples. The collation unit calculates the similarity between the summary and the answer in the FAQ database by, for example, cosine similarity. The collation unit can also calculate the similarity by using the Jaccard coefficient. The collation unit can also calculate the similarity by using TF-IDF. For example, the collation unit calculates the angle between two vectors in a vector space model as the cosine similarity, and determines that the smaller the angle, the higher the similarity. The Jaccard coefficient is a value obtained by dividing the size of the common part of two sets by the total size, and indicates the degree of overlap of the sets. The TF-IDF is an index for evaluating the importance of words in a document, and is used to calculate the similarity between the summary and the answer in the FAQ database. A part or all of the above-mentioned processing in the collation unit may be performed by, for example, using AI, or may be performed without using AI.For example, the collation unit can calculate the similarity using an AI model that takes the summary generated by the summarization unit and the answer in the FAQ database as input and outputs the similarity. The answering unit makes a primary answer based on the result obtained by the collation unit. For example, the primary answer can be, for example, a method of providing the answer in the FAQ database as it is, or a method of generating an answer using a generation AI, but is not limited to such examples. For example, the answering unit provides the answer in the FAQ database as it is. Also, the answering unit can use a generation AI to generate an answer based on the answer in the FAQ database. Also, the answering unit can use a generation AI to generate an answer that is not in the FAQ database. For example, the answering unit can use an AI model that takes the answer in the FAQ database as input and outputs an answer. The connection unit connects to a person in charge when the answering unit cannot make a primary answer. The connection is made using a means such as, for example, a telephone, an email, or a chat, but is not limited to such examples. For example, the connection unit connects to a person in charge using a telephone. Also, the connection unit can connect to a person in charge using an email. Also, the connection unit can connect to a person in charge using a chat. In this way, the customer support system according to the embodiment can automatically summarize the customer's requirements and take appropriate action. Some or all of the above-mentioned processing in the connection unit may be performed using, for example, AI, or may be performed without using AI. For example, the connection unit may perform the connection using an AI model that takes the summary generated by the summarization unit as input and connects to a person in charge.

[0030] The reception unit accepts customer requirements. Customer requirements include, but are not limited to, inquiries, complaints, requests, etc. The reception unit can accept customer requirements by means of, for example, telephone, email, chat, etc. Specifically, in telephone reception, an automated voice response system is used to classify customer requirements and transfer them to an appropriate department. In email reception, received emails are automatically analyzed and classified according to the type and urgency of the requirements. In chat reception, a chatbot performs initial response and hands over to a human operator as necessary. This allows the reception unit to quickly and efficiently accept customer requirements using a variety of means. In addition, the reception unit records customer requirements in a database so that subsequent processing departments can refer to them. For example, information such as the customer's name, contact information, content of the requirements, and the date and time of reception is managed in a centralized manner so that other departments can respond quickly. Furthermore, when accepting customer requirements, the reception unit can refer to the customer's past inquiry history and purchase history to respond more appropriately. This allows the reception unit to not only efficiently accept customer requirements but also contribute to improving customer satisfaction.

[0031] The summarization unit uses the generation AI to summarize the requirements accepted by the reception unit. The summarization is performed, for example, based on the length of the text and the importance of the information to be summarized, but is not limited to such examples. Specifically, the generation AI uses a text generation AI (for example, LLM) to concisely summarize the requirements. The text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. For example, when a long inquiry email is received from a customer, the generation AI analyzes the content, extracts important points, and generates a short summary. The summarization unit can also summarize the content of the requirements using a multimodal generation AI. The multimodal generation AI can handle multiple modalities such as images and voices as well as text. For example, when a customer makes an inquiry with an image attached, the multimodal generation AI analyzes the content of the image and integrates it with the text to perform a summary. Furthermore, the summarization unit can also extract and summarize important parts of the text using the generation AI. For example, it uses keyword extraction technology to pick up particularly important information from the requirements and perform a summary based on that. This enables the abstraction department to quickly and accurately abstract customer requirements so that subsequent processing can respond efficiently.

[0032] The matching unit matches the summary generated by the summarization unit with the FAQ database. The matching is performed by, for example, a method such as cosine similarity or Jaccard coefficient, but is not limited to such examples. Specifically, the matching unit calculates the similarity between the summary and the answer in the FAQ database using cosine similarity. Cosine similarity calculates the angle between two vectors in a vector space model, and determines that the smaller the angle, the higher the similarity. The matching unit can also calculate the similarity using the Jaccard coefficient. The Jaccard coefficient is a value obtained by dividing the size of the common part of two sets by the total size, and indicates the degree of overlap of the sets. Furthermore, the matching unit can calculate the similarity using TF-IDF. TF-IDF is an index that evaluates the importance of words in a document, and uses this to calculate the similarity between the summary and the answer in the FAQ database. For example, the matching unit can calculate the similarity using an AI model that inputs the summary generated by the summarization unit and the answer in the FAQ database and outputs the similarity. The AI ​​model has learned a large amount of data and has advanced similarity calculation capabilities. This allows the matching unit to quickly and accurately calculate the similarity between the summary and answers in the FAQ database and select the most appropriate answer. Furthermore, the matching unit selects the most appropriate answer from among the answers in the FAQ database based on the results of the similarity calculation and provides it to the subsequent answer unit. This allows the matching unit to build a foundation for providing quick and appropriate answers to customer requirements.

[0033] The answering section provides a primary answer based on the results obtained by the matching section. The primary answer may be, for example, a method of providing an answer in the FAQ database as it is, or a method of generating an answer using a generation AI, but is not limited to such examples. Specifically, the answering section provides the answer in the FAQ database as it is. For example, if an answer that already exists in the FAQ database is appropriate for a customer's inquiry, the answer is provided as it is. The answering section can also generate an answer based on the answer in the FAQ database using the generation AI. For example, if an answer in the FAQ database is only partially applicable, the generation AI generates a more specific and appropriate answer based on that answer. Furthermore, the answering section can also generate an answer that is not in the FAQ database using the generation AI. For example, if a customer's inquiry is new and there is no corresponding answer in the FAQ database, the generation AI generates a new answer based on past data and related information. This allows the answering section to provide a prompt and appropriate answer to the customer's requirements. Furthermore, the answering section can record the history of the answers provided in the database and use it to respond to future inquiries. This allows the answering section to improve the efficiency and quality of customer support.

[0034] The connection unit connects to a person in charge when the answering unit cannot provide a first response. The connection is performed by using, for example, a telephone, an email, a chat, or other means, but is not limited to such examples. Specifically, the connection unit connects to a person in charge by using a telephone. For example, when a customer's inquiry is complex and cannot be handled by a first response, the connection unit automatically transfers the call to the person in charge. The connection unit can also connect to a person in charge by using an email. For example, the content of the customer's inquiry is summarized and sent to the person in charge by email to encourage a quick response. Furthermore, the connection unit can also connect to a person in charge by using a chat. For example, a chatbot performs an initial response and, if necessary, the chat is handed over to a human operator. This allows the connection unit to respond quickly and appropriately to the customer's requirements. Furthermore, the connection unit can record the connection history to the person in charge in a database and use it for future inquiry responses. For example, by referring to the past connection history, it is possible to quickly respond to similar inquiries. Furthermore, the connection unit can also optimize the connection by using AI. For example, the summary generated by the summarizing unit is used as input, and an AI model that connects to a person in charge is used to select the most suitable person in charge and perform the connection. This enables the connection department to improve the efficiency and quality of customer service.

[0035] The summarization unit includes an algorithm for generating a summary. The summarization unit generates the summary using, for example, a natural language processing technique. For example, the summarization unit generates the summary using a text generation AI (for example, LLM). The summarization unit can also generate the summary using a machine learning algorithm. For example, the summarization unit generates the summary using supervised learning. The summarization unit can also generate the summary using unsupervised learning. For example, the summarization unit generates the summary using a clustering algorithm. This allows the summarization unit to improve the accuracy of the summary generation. A part or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can generate a summary using an AI model that receives a summary generation algorithm as input and outputs a summary.

[0036] The collation unit has a structure of an FAQ database. The structure of the FAQ database includes, for example, a database schema and a data storage method, but is not limited to such examples. For example, the FAQ database is constructed using a relational database. Also, the FAQ database can be constructed using a NoSQL database. For example, the FAQ database is constructed using a key-value store. Also, the FAQ database can be constructed using a document store. For example, the FAQ database has a table that stores pairs of questions and answers as a database schema. The data storage method includes a method of storing questions and answers in a text format and a method of storing questions and answers in a JSON format. This allows the FAQ database to be used efficiently. A part or all of the above-mentioned processing in the FAQ database may be performed, for example, using AI, or may be performed without using AI. For example, the FAQ database can construct a database structure using an AI model that inputs the database schema and outputs a data storage method.

[0037] The customer support system includes an encryption unit for privacy protection. The encryption unit encrypts customer data using, for example, an encryption algorithm. For example, the encryption unit encrypts data using AES (Advanced Encryption Standard). The encryption unit can also encrypt data using RSA (Rivest-Shamir-Adleman). For example, the encryption unit encrypts data using AES and encrypts an encryption key using RSA. The encryption unit can also encrypt data using a hybrid encryption method. For example, the encryption unit encrypts data by combining symmetric key encryption and public key encryption. This makes it possible to protect customer privacy. A part or all of the above-mentioned processing in the encryption unit may be performed using, for example, AI, or may be performed without using AI. For example, the encryption unit can encrypt data using an AI model that receives an encryption algorithm as input and outputs encrypted data.

[0038] The customer support system includes a method of notifying the person in charge. The notification method includes, for example, email notification, push notification, SMS notification, and the like, but is not limited to such examples. For example, the notification method notifies the person in charge using email. Also, the notification method can notify the person in charge using push notification. For example, the notification method performs push notification using a smartphone app. Also, the notification method can notify the person in charge using SMS. For example, the notification method performs emergency notification to the person in charge using SMS. This enables prompt notification to the person in charge. Part or all of the above-mentioned processing in the notification method may be performed using, for example, AI, or may be performed without using AI. For example, the notification method can perform notification using an AI model that receives the notification means as input and outputs the notification content.

[0039] The reception unit can analyze the customer's past inquiry history and select the optimal response method. In the reception unit, for example, the generation AI selects an appropriate response method based on the content of the customer's frequent inquiries in the past. The reception unit can also find a specific pattern from the customer's past inquiry history and the generation AI can respond based on the pattern. Furthermore, the reception unit can preferentially suggest a response method (voice, text, etc.) that the customer has used in the past. This makes it possible to provide an optimal response based on the past inquiry history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the customer's past inquiry history data to the generation AI and have the generation AI select the optimal response method.

[0040] The reception unit can perform filtering based on the customer's current situation and areas of interest at the time of reception. For example, when the customer describes the current situation, the reception unit allows the generation AI to perform appropriate filtering based on the information. The reception unit can also prioritize questions related to the generation AI based on the customer's areas of interest. Furthermore, the reception unit can also allow the generation AI to select an appropriate response method according to the customer's current situation. This enables appropriate filtering according to the customer's situation and areas of interest. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input data on the customer's current situation and areas of interest to the generation AI and have the generation AI perform filtering.

[0041] The reception unit can preferentially receive requirements with high relevance based on the geographical location information of the customer at the time of reception. For example, when the customer is in a specific area, the reception unit preferentially receives requirements related to that area. The reception unit can also select an appropriate response method by the generation AI based on the geographical location information of the customer. Furthermore, when the customer is on the move, the reception unit can also update the geographical location information in real time and receive appropriate requirements. This makes it possible to receive appropriate requirements based on the geographical location information. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the reception unit can input the geographical location information of the customer to the generation AI and cause the generation AI to execute the reception of the requirements.

[0042] The reception unit can analyze the social media activity of the customer and receive the relevant requirements at the time of reception. For example, the reception unit preferentially receives requirements related to the generation AI based on the social media activity of the customer. The reception unit can also select an appropriate response method for the generation AI based on the content mentioned by the customer on social media. Furthermore, the reception unit can analyze the social media activity of the customer and receive requirements related to the generation AI. This makes it possible to receive appropriate requirements based on social media activity. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the social media activity data of the customer to the generation AI and cause the generation AI to execute the reception of the requirements.

[0043] The summarization unit can adjust the level of detail of the summary based on the importance of the requirements when generating a summary. For example, the summarization unit generates a detailed summary for requirements with high importance by the generation AI. The summarization unit can also generate a concise summary for requirements with low importance by the generation AI. Furthermore, the summarization unit can adjust the level of detail of the summary by the generation AI according to the importance of the requirements. This enables an appropriate summary according to the importance of the requirements. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the summarization unit can input requirement importance data to the generation AI and cause the generation AI to adjust the level of detail of the summary.

[0044] The summarization unit can apply different summarization algorithms depending on the category of requirements when generating a summary. For example, the summarization unit causes the generation AI to apply a specialized summarization algorithm to technical requirements. The summarization unit can also cause the generation AI to apply a simple summarization algorithm to general requirements. Furthermore, the summarization unit can also cause the generation AI to select an optimal summarization algorithm depending on the category of requirements. This enables appropriate summarization depending on the category of requirements. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the summarization unit can input requirement category data to the generation AI and cause the generation AI to apply the summarization algorithm.

[0045] The summarization unit can determine the priority of summaries based on the submission time of requirements when generating summaries. For example, the summarization unit can cause the generation AI to generate summaries preferentially for requirements that have been submitted recently. The summarization unit can also cause the generation AI to generate summaries for requirements that have been submitted earlier, but later. Furthermore, the summarization unit can cause the generation AI to determine the priority of summaries according to the submission time of requirements. This enables appropriate prioritization of summaries based on the submission time. Some or all of the above-mentioned processing in the summarization unit can be performed, for example, using AI or without using AI. For example, the summarization unit can input data on the submission time of requirements to the generation AI and cause the generation AI to determine the priority of summaries.

[0046] The summarization unit can adjust the order of summaries based on the relevance of requirements when generating summaries. For example, the summarization unit can have the generation AI generate summaries with priority for highly relevant requirements. The summarization unit can also have the generation AI generate summaries later for less relevant requirements. Furthermore, the summarization unit can also have the generation AI adjust the order of summaries according to the relevance of requirements. This enables appropriate ordering of summaries based on relevance. Some or all of the above-mentioned processing in the summarization unit can be performed, for example, using AI or can be performed without using AI. For example, the summarization unit can input requirement relevance data to the generation AI and have the generation AI adjust the order of summaries.

[0047] The matching unit can improve the accuracy of matching based on the interrelationships of requirements during matching. For example, the matching unit analyzes the interrelationships of requirements, and the generation AI prioritizes matching of related requirements. The matching unit can also improve the accuracy of matching by the generation AI, taking into account the interrelationships of requirements. Furthermore, the matching unit can also select an optimal matching method by the generation AI based on the interrelationships of requirements. This enables appropriate matching based on the interrelationships of requirements. A part or all of the above-mentioned processing in the matching unit may be performed, for example, using AI, or may be performed without using AI. For example, the matching unit can input interrelationship data of requirements to the generation AI, and cause the generation AI to improve the accuracy of matching.

[0048] The matching unit can perform matching based on the attribute information of the submitter of the requirements at the time of matching. For example, the matching unit selects an appropriate matching method based on the attribute information of the submitter by the generation AI. The matching unit can also improve the accuracy of matching by the generation AI by taking into account the attribute information of the submitter. Furthermore, the matching unit can also apply optimal matching criteria based on the attribute information of the submitter by the generation AI. This enables appropriate matching based on the attribute information of the submitter. A part or all of the above-mentioned processing in the matching unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the matching unit can input attribute information data of the submitter to the generation AI and cause the generation AI to perform matching.

[0049] The matching unit can perform matching based on the geographic distribution of the requirements at the time of matching. For example, the matching unit allows the generation AI to select an appropriate matching method based on the geographic distribution of the requirements. The matching unit can also allow the generation AI to improve the accuracy of matching by taking into account the geographic distribution of the requirements. Furthermore, the matching unit can also allow the generation AI to apply optimal matching criteria based on the geographic distribution of the requirements. This enables appropriate matching based on the geographic distribution. A part or all of the above-mentioned processing in the matching unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the matching unit can input geographic distribution data of the requirements to the generation AI and cause the generation AI to perform matching.

[0050] The matching unit can improve the accuracy of matching by referring to related literature of the requirements during matching. For example, the matching unit allows the generation AI to select an appropriate matching method based on the related literature. The matching unit can also improve the accuracy of matching by the generation AI by referring to the related literature. Furthermore, the matching unit can also allow the generation AI to apply optimal matching criteria based on the related literature. This enables appropriate matching based on the related literature. Some or all of the above-mentioned processing in the matching unit may be performed, for example, using AI, or may be performed without using AI. For example, the matching unit can input related literature data to the generation AI and cause the generation AI to improve the accuracy of matching.

[0051] The answering section can adjust the level of detail of the answer based on the importance of the requirement when answering. For example, the answering section can have the generation AI provide a detailed answer to a requirement with high importance. The answering section can also have the generation AI provide a concise answer to a requirement with low importance. Furthermore, the answering section can have the generation AI adjust the level of detail of the answer according to the importance of the requirement. This enables an appropriate answer according to the importance of the requirement. A part or all of the above-mentioned processing in the answering section can be performed using, for example, an AI, or can be performed without using an AI. For example, the answering section can input the importance data of the requirement to the generation AI and cause the generation AI to adjust the level of detail of the answer.

[0052] The answering section can apply different answering algorithms depending on the category of the requirement when answering. For example, the answering section has the generating AI apply a specialized answering algorithm to technical requirements. Also, the answering section can have the generating AI apply a simple answering algorithm to general requirements. Furthermore, the answering section can have the generating AI select an optimal answering algorithm depending on the category of the requirement. This enables an appropriate answer depending on the category of the requirement. Some or all of the above-mentioned processing in the answering section may be performed using, for example, an AI, or may be performed without using an AI. For example, the answering section can input requirement category data to the generating AI and have the generating AI apply the answering algorithm.

[0053] The answering section can determine the priority of the answers based on the submission time of the requirements when answering. For example, the answering section allows the generation AI to provide answers preferentially to requirements that have been submitted recently. The answering section can also allow the generation AI to provide answers later to requirements that have been submitted earlier. Furthermore, the answering section can allow the generation AI to determine the priority of the answers according to the submission time of the requirements. This makes it possible to appropriately prioritize answers based on the submission time. Some or all of the above-mentioned processing in the answering section may be performed using, for example, an AI, or may be performed without using an AI. For example, the answering section can input requirement submission time data to the generation AI and have the generation AI execute the determination of the priority of the answers.

[0054] The answering section can adjust the order of answers based on the relevance of the requirements when answering. For example, the answering section allows the generation AI to provide answers preferentially to requirements with high relevance. Also, the answering section can allow the generation AI to provide answers later to requirements with low relevance. Furthermore, the answering section allows the generation AI to adjust the order of answers according to the relevance of the requirements. This enables appropriate ordering of answers based on relevance. A part or all of the above-mentioned processing in the answering section may be performed, for example, using an AI, or may be performed without using an AI. For example, the answering section can input requirement relevance data to the generation AI and cause the generation AI to adjust the order of answers.

[0055] The connection unit can determine the priority of the connection based on the importance of the requirement at the time of connection. For example, the connection unit preferentially connects to the person in charge of a requirement with high importance. The connection unit can also connect to a requirement with low importance by a normal procedure. Furthermore, the connection unit can adjust the priority of the connection according to the importance of the requirement. This enables appropriate prioritization of the connection according to the importance of the requirement. A part or all of the above-mentioned processing in the connection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the connection unit can input the importance data of the requirement to the generation AI and cause the generation AI to execute the determination of the priority of the connection.

[0056] The connection unit can apply different connection methods depending on the category of the requirement at the time of connection. For example, the connection unit can connect to a specialized person for a technical requirement. Also, the connection unit can connect to a general person for a general requirement. Furthermore, the connection unit can select an optimal connection method depending on the category of the requirement. This enables an appropriate connection depending on the category of the requirement. A part or all of the above-mentioned processing in the connection unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the connection unit can input requirement category data to the generation AI and cause the generation AI to apply the connection method.

[0057] The connection unit can determine the priority of the connection based on the submission time of the requirement at the time of connection. For example, the connection unit preferentially connects to the person in charge of the most recently submitted requirement. The connection unit can also connect to the requirement submitted earlier by the normal procedure. Furthermore, the connection unit can adjust the priority of the connection according to the submission time of the requirement. This enables appropriate prioritization of the connection based on the submission time. A part or all of the above-mentioned processing in the connection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the connection unit can input the submission time data of the requirement to the generation AI and cause the generation AI to execute the determination of the priority of the connection.

[0058] The connection unit can adjust the order of connections based on the relevance of requirements at the time of connection. For example, the connection unit preferentially connects to a person in charge of a highly relevant requirement. The connection unit can also connect to a less relevant requirement in a normal procedure. Furthermore, the connection unit can adjust the order of connections according to the relevance of requirements. This enables appropriate ordering of connections based on the relevance. A part or all of the above-mentioned processing in the connection unit may be performed, for example, using AI, or may be performed without using AI. For example, the connection unit can input the relevance data of requirements to the generation AI and cause the generation AI to adjust the connection order.

[0059] The encryption unit can adjust the level of detail of encryption based on the importance of the requirement at the time of encryption. For example, the encryption unit applies detailed encryption to requirements with high importance. The encryption unit can also apply simple encryption to requirements with low importance. Furthermore, the encryption unit can adjust the level of detail of encryption according to the importance of the requirement. This enables appropriate encryption according to the importance of the requirement. A part or all of the above-mentioned processing in the encryption unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the encryption unit can input the importance data of the requirement to the generation AI and cause the generation AI to adjust the level of detail of encryption.

[0060] The encryption unit can determine the encryption priority based on the submission time of the requirements at the time of encryption. For example, the encryption unit prioritizes encryption for recently submitted requirements. The encryption unit can also encrypt requirements submitted earlier in the normal procedure. Furthermore, the encryption unit can adjust the encryption priority according to the submission time of the requirements. This enables appropriate encryption prioritization based on the submission time. A part or all of the above-mentioned processing in the encryption unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the encryption unit can input requirement submission time data to the generation AI and cause the generation AI to determine the encryption priority.

[0061] The notification method can adjust the level of detail of the notification based on the importance of the requirement at the time of notification. For example, the notification method provides a detailed notification for a requirement with high importance. The notification method can also provide a concise notification for a requirement with low importance. Furthermore, the notification method can adjust the level of detail of the notification according to the importance of the requirement. This enables appropriate notification according to the importance of the requirement. A part or all of the above-mentioned processing in the notification method may be performed, for example, using AI or may be performed without using AI. For example, the notification method can input the importance data of the requirement to the generation AI and cause the generation AI to adjust the level of detail of the notification.

[0062] The notification method can determine the priority of notifications based on the submission time of the requirements at the time of notification. For example, the notification method can give priority to recently submitted requirements. The notification method can also notify older submitted requirements in the normal procedure. Furthermore, the notification method can adjust the priority of notifications according to the submission time of the requirements. This enables appropriate prioritization of notifications based on the submission time. A part or all of the above-mentioned processing in the notification method can be performed using, for example, AI, or can be performed without using AI. For example, the notification method can input the submission time data of the requirements to the generation AI and cause the generation AI to determine the priority of notifications.

[0063] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0064] The customer care system can further analyze the customer's past purchase history and reflect it in the summary generated by the summarization unit. For example, if a customer has requirements related to products or services purchased in the past, the summarization unit can include that information in the summary. Also, if a customer frequently purchases products of a particular brand or category, the summarization unit can generate a summary based on that information. Furthermore, the customer's purchase history can be used to find certain trends or patterns and adjust the summary based on them. This allows for more accurate summaries based on the customer's past purchase history.

[0065] The customer response system can further analyze the customer's social media activity and incorporate it into the summary generated by the summarization unit. For example, the summary can include what the customer mentioned on social media and topics of interest. Also, if the customer frequently uses certain hashtags or keywords, the summary can be generated based on that information. Furthermore, the customer response system can find certain trends or patterns in the customer's social media activity and adjust the summary based on them. This allows for more accurate summaries based on the customer's social media activity.

[0066] The customer response system can further analyze the geographic location information of the customer and reflect it in the summary generated by the summarization unit. For example, if the customer is in a particular area, information related to that area can be included in the summary. Also, if the customer is on the move, the geographic location information can be updated in real time and the summary can be generated based on it. Furthermore, certain trends or patterns can be found from the geographic location information of the customer and the summary can be adjusted based on them. This allows for more accurate summaries based on the geographic location information of the customer.

[0067] The customer support system can further analyze the customer's past inquiry history and reflect this in the summary generated by the summarization unit. For example, the summary can include the content of the customer's past inquiries and the solutions. Also, if a customer frequently inquires about a particular problem or question, the summary can be generated based on that information. Furthermore, the customer support system can find specific trends or patterns from the customer's inquiry history and adjust the summary based on those trends or patterns. This allows for more accurate summaries based on the customer's past inquiry history.

[0068] The customer support system can further analyze the customer's current situation and areas of interest and reflect them in the summary generated by the summarization unit. For example, when the customer describes his / her current situation, the information can be included in the summary. Also, based on the customer's areas of interest, related information can be included in the summary. Furthermore, the customer support system can find certain trends or patterns from the customer's current situation and areas of interest and adjust the summary based on them. This allows for more accurate summaries based on the customer's current situation and areas of interest.

[0069] The process flow of the first embodiment will be briefly described below.

[0070] Step 1: The reception department accepts customer requirements. Customer requirements include inquiries, complaints, requests, etc. The reception department can accept customer requirements by means of telephone, email, chat, etc. Step 2: The summarization unit uses the generation AI to summarize the requirements received by the reception unit. The summarization is based on the length of the text and the importance of the information to be summarized. The generation AI uses a text generation AI (e.g., LLM) or a multimodal generation AI to concisely summarize the requirements. Step 3: The matcher matches the summary generated by the summarizer with the FAQ database. Matching is performed using methods such as cosine similarity, Jaccard coefficient, and TF-IDF. The matcher uses these methods to calculate the similarity between the summary and the answers in the FAQ database. Step 4: The answering section provides a primary answer based on the results obtained by the matching section. The primary answer can be provided directly from the FAQ database or generated using a generation AI. Step 5: The connection section connects the person in charge if the answering section cannot provide a first response. The connection is made by means of telephone, email, chat, etc.

[0071] (Example 2) A customer response system according to an embodiment of the present invention is a system that automatically summarizes customer requirements and provides appropriate support. In this customer response system, when a customer calls a call center, a generation AI responds and has the customer talk about the requirements. The generation AI analyzes what the customer said in real time and generates a summary. This summary is compared with an FAQ database, and if a corresponding answer is found, the generation AI provides a first response on the spot. If there is no corresponding answer in the FAQ database or if a staff response is required, the generation AI connects the call to an appropriate person in charge based on the summary. The person in charge can solve the problem efficiently by referring to the summary generated by the generation AI. For example, when a customer calls a call center, the generation AI responds and has the customer talk about the requirements. The generation AI analyzes what the customer said in real time and generates a summary. This summary is compared with an FAQ database, and if a corresponding answer is found, the generation AI provides a first response on the spot. If there is no corresponding answer in the FAQ database or if a staff response is required, the generation AI connects the call to an appropriate person in charge based on the summary. The person in charge can solve the problem efficiently by referring to the summary generated by the generation AI. This allows customers to get a quick answer without having to go through complicated operations, improving the customer experience. In addition, staff can respond based on the summary, improving work efficiency. This allows the customer support system to automatically summarize customer requirements and provide appropriate responses.

[0072] The customer support system according to the embodiment includes a reception unit, a summarization unit, a comparison unit, a response unit, and a connection unit. The reception unit receives customer requirements. The customer requirements include, for example, inquiries, complaints, requests, etc., but are not limited to such examples. The reception unit can receive customer requirements using, for example, means such as telephone, email, and chat. The summarization unit summarizes the requirements received by the reception unit using a generation AI. The summarization is performed, for example, based on the length of the text and the importance of the information to be summarized, but are not limited to such examples. For example, the generation AI uses a text generation AI (for example, LLM) to concisely summarize the requirements. In addition, the summarization unit can also summarize the contents of the requirements using a multimodal generation AI. In addition, the summarization unit can extract and summarize important parts of the text using the generation AI. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modals such as images and voices as well as text. The generation AI uses keyword extraction technology to pick up particularly important information from the requirements and summarizes based on that. The collation unit collates the summary generated by the summarization unit with the FAQ database. The collation is performed by, for example, a method such as cosine similarity or Jaccard coefficient, but is not limited to such examples. The collation unit calculates the similarity between the summary and the answer in the FAQ database by, for example, cosine similarity. The collation unit can also calculate the similarity by using the Jaccard coefficient. The collation unit can also calculate the similarity by using TF-IDF. For example, the collation unit calculates the angle between two vectors in a vector space model as the cosine similarity, and determines that the smaller the angle, the higher the similarity. The Jaccard coefficient is a value obtained by dividing the size of the common part of two sets by the total size, and indicates the degree of overlap of the sets. The TF-IDF is an index for evaluating the importance of words in a document, and is used to calculate the similarity between the summary and the answer in the FAQ database. A part or all of the above-mentioned processing in the collation unit may be performed by, for example, using AI, or may be performed without using AI.For example, the collation unit can calculate the similarity using an AI model that takes the summary generated by the summarization unit and the answer in the FAQ database as input and outputs the similarity. The answering unit makes a primary answer based on the result obtained by the collation unit. For example, the primary answer can be, for example, a method of providing the answer in the FAQ database as it is, or a method of generating an answer using a generation AI, but is not limited to such examples. For example, the answering unit provides the answer in the FAQ database as it is. Also, the answering unit can use a generation AI to generate an answer based on the answer in the FAQ database. Also, the answering unit can use a generation AI to generate an answer that is not in the FAQ database. For example, the answering unit can use an AI model that takes the answer in the FAQ database as input and outputs an answer. The connection unit connects to a person in charge when the answering unit cannot make a primary answer. The connection is made using a means such as, for example, a telephone, an email, or a chat, but is not limited to such examples. For example, the connection unit connects to a person in charge using a telephone. Also, the connection unit can connect to a person in charge using an email. Also, the connection unit can connect to a person in charge using a chat. In this way, the customer support system according to the embodiment can automatically summarize the customer's requirements and take appropriate action. Some or all of the above-mentioned processing in the connection unit may be performed using, for example, AI, or may be performed without using AI. For example, the connection unit may perform the connection using an AI model that takes the summary generated by the summarization unit as input and connects to a person in charge.

[0073] The reception unit accepts customer requirements. Customer requirements include, but are not limited to, inquiries, complaints, requests, etc. The reception unit can accept customer requirements by means of, for example, telephone, email, chat, etc. Specifically, in telephone reception, an automated voice response system is used to classify customer requirements and transfer them to an appropriate department. In email reception, received emails are automatically analyzed and classified according to the type and urgency of the requirements. In chat reception, a chatbot performs initial response and hands over to a human operator as necessary. This allows the reception unit to quickly and efficiently accept customer requirements using a variety of means. In addition, the reception unit records customer requirements in a database so that subsequent processing departments can refer to them. For example, information such as the customer's name, contact information, content of the requirements, and the date and time of reception is managed in a centralized manner so that other departments can respond quickly. Furthermore, when accepting customer requirements, the reception unit can refer to the customer's past inquiry history and purchase history to respond more appropriately. This allows the reception unit to not only efficiently accept customer requirements but also contribute to improving customer satisfaction.

[0074] The summarization unit uses the generation AI to summarize the requirements accepted by the reception unit. The summarization is performed, for example, based on the length of the text and the importance of the information to be summarized, but is not limited to such examples. Specifically, the generation AI uses a text generation AI (for example, LLM) to concisely summarize the requirements. The text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. For example, when a long inquiry email is received from a customer, the generation AI analyzes the content, extracts important points, and generates a short summary. The summarization unit can also summarize the content of the requirements using a multimodal generation AI. The multimodal generation AI can handle multiple modalities such as images and voices as well as text. For example, when a customer makes an inquiry with an image attached, the multimodal generation AI analyzes the content of the image and integrates it with the text to perform a summary. Furthermore, the summarization unit can also extract and summarize important parts of the text using the generation AI. For example, it uses keyword extraction technology to pick up particularly important information from the requirements and perform a summary based on that. This enables the abstraction department to quickly and accurately abstract customer requirements so that subsequent processing can respond efficiently.

[0075] The matching unit matches the summary generated by the summarization unit with the FAQ database. The matching is performed by, for example, a method such as cosine similarity or Jaccard coefficient, but is not limited to such examples. Specifically, the matching unit calculates the similarity between the summary and the answer in the FAQ database using cosine similarity. Cosine similarity calculates the angle between two vectors in a vector space model, and determines that the smaller the angle, the higher the similarity. The matching unit can also calculate the similarity using the Jaccard coefficient. The Jaccard coefficient is a value obtained by dividing the size of the common part of two sets by the total size, and indicates the degree of overlap of the sets. Furthermore, the matching unit can calculate the similarity using TF-IDF. TF-IDF is an index that evaluates the importance of words in a document, and uses this to calculate the similarity between the summary and the answer in the FAQ database. For example, the matching unit can calculate the similarity using an AI model that inputs the summary generated by the summarization unit and the answer in the FAQ database and outputs the similarity. The AI ​​model has learned a large amount of data and has advanced similarity calculation capabilities. This allows the matching unit to quickly and accurately calculate the similarity between the summary and answers in the FAQ database and select the most appropriate answer. Furthermore, the matching unit selects the most appropriate answer from among the answers in the FAQ database based on the results of the similarity calculation and provides it to the subsequent answer unit. This allows the matching unit to build a foundation for providing quick and appropriate answers to customer requirements.

[0076] The answering section provides a primary answer based on the results obtained by the matching section. The primary answer may be, for example, a method of providing an answer in the FAQ database as it is, or a method of generating an answer using a generation AI, but is not limited to such examples. Specifically, the answering section provides the answer in the FAQ database as it is. For example, if an answer that already exists in the FAQ database is appropriate for a customer's inquiry, the answer is provided as it is. The answering section can also generate an answer based on the answer in the FAQ database using the generation AI. For example, if an answer in the FAQ database is only partially applicable, the generation AI generates a more specific and appropriate answer based on that answer. Furthermore, the answering section can also generate an answer that is not in the FAQ database using the generation AI. For example, if a customer's inquiry is new and there is no corresponding answer in the FAQ database, the generation AI generates a new answer based on past data and related information. This allows the answering section to provide a prompt and appropriate answer to the customer's requirements. Furthermore, the answering section can record the history of the answers provided in the database and use it to respond to future inquiries. This allows the answering section to improve the efficiency and quality of customer support.

[0077] The connection unit connects to a person in charge when the answering unit cannot provide a first response. The connection is performed by using, for example, a telephone, an email, a chat, or other means, but is not limited to such examples. Specifically, the connection unit connects to a person in charge by using a telephone. For example, when a customer's inquiry is complex and cannot be handled by a first response, the connection unit automatically transfers the call to the person in charge. The connection unit can also connect to a person in charge by using an email. For example, the content of the customer's inquiry is summarized and sent to the person in charge by email to encourage a quick response. Furthermore, the connection unit can also connect to a person in charge by using a chat. For example, a chatbot performs an initial response and, if necessary, the chat is handed over to a human operator. This allows the connection unit to respond quickly and appropriately to the customer's requirements. Furthermore, the connection unit can record the connection history to the person in charge in a database and use it for future inquiry responses. For example, by referring to the past connection history, it is possible to quickly respond to similar inquiries. Furthermore, the connection unit can also optimize the connection by using AI. For example, the summary generated by the summarizing unit is used as input, and an AI model that connects to a person in charge is used to select the most suitable person in charge and perform the connection. This enables the connection department to improve the efficiency and quality of customer service.

[0078] The summarization unit includes an algorithm for generating a summary. The summarization unit generates the summary using, for example, a natural language processing technique. For example, the summarization unit generates the summary using a text generation AI (for example, LLM). The summarization unit can also generate the summary using a machine learning algorithm. For example, the summarization unit generates the summary using supervised learning. The summarization unit can also generate the summary using unsupervised learning. For example, the summarization unit generates the summary using a clustering algorithm. This allows the summarization unit to improve the accuracy of the summary generation. A part or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can generate a summary using an AI model that receives a summary generation algorithm as input and outputs a summary.

[0079] The collation unit has a structure of an FAQ database. The structure of the FAQ database includes, for example, a database schema and a data storage method, but is not limited to such examples. For example, the FAQ database is constructed using a relational database. Also, the FAQ database can be constructed using a NoSQL database. For example, the FAQ database is constructed using a key-value store. Also, the FAQ database can be constructed using a document store. For example, the FAQ database has a table that stores pairs of questions and answers as a database schema. The data storage method includes a method of storing questions and answers in a text format and a method of storing questions and answers in a JSON format. This allows the FAQ database to be used efficiently. A part or all of the above-mentioned processing in the FAQ database may be performed, for example, using AI, or may be performed without using AI. For example, the FAQ database can construct a database structure using an AI model that inputs the database schema and outputs a data storage method.

[0080] The customer support system includes an encryption unit for privacy protection. The encryption unit encrypts customer data using, for example, an encryption algorithm. For example, the encryption unit encrypts data using AES (Advanced Encryption Standard). The encryption unit can also encrypt data using RSA (Rivest-Shamir-Adleman). For example, the encryption unit encrypts data using AES and encrypts an encryption key using RSA. The encryption unit can also encrypt data using a hybrid encryption method. For example, the encryption unit encrypts data by combining symmetric key encryption and public key encryption. This makes it possible to protect customer privacy. A part or all of the above-mentioned processing in the encryption unit may be performed using, for example, AI, or may be performed without using AI. For example, the encryption unit can encrypt data using an AI model that receives an encryption algorithm as input and outputs encrypted data.

[0081] The customer support system includes a method of notifying the person in charge. The notification method includes, for example, email notification, push notification, SMS notification, and the like, but is not limited to such examples. For example, the notification method notifies the person in charge using email. Also, the notification method can notify the person in charge using push notification. For example, the notification method performs push notification using a smartphone app. Also, the notification method can notify the person in charge using SMS. For example, the notification method performs emergency notification to the person in charge using SMS. This enables prompt notification to the person in charge. Part or all of the above-mentioned processing in the notification method may be performed using, for example, AI, or may be performed without using AI. For example, the notification method can perform notification using an AI model that receives the notification means as input and outputs the notification content.

[0082] The reception unit can estimate the customer's emotions and adjust the response method based on the estimated customer's emotions. For example, when the customer is stressed, the reception unit has the generation AI respond in a calm voice and ask simple questions. Also, when the customer is relaxed, the reception unit can have the generation AI respond in a friendly voice and ask detailed questions. Furthermore, when the customer is in a hurry, the reception unit can also ask short questions to quickly elicit the customer's requirements. This enables an appropriate response according to the customer's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the customer's voice data to the generation AI and have the generation AI execute the estimation of the customer's emotions.

[0083] The reception unit can analyze the customer's past inquiry history and select the optimal response method. In the reception unit, for example, the generation AI selects an appropriate response method based on the content of the customer's frequent inquiries in the past. The reception unit can also find a specific pattern from the customer's past inquiry history and the generation AI can respond based on the pattern. Furthermore, the reception unit can preferentially suggest a response method (voice, text, etc.) that the customer has used in the past. This makes it possible to provide an optimal response based on the past inquiry history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the customer's past inquiry history data to the generation AI and have the generation AI select the optimal response method.

[0084] The reception unit can perform filtering based on the customer's current situation and areas of interest at the time of reception. For example, when the customer describes the current situation, the reception unit allows the generation AI to perform appropriate filtering based on the information. The reception unit can also prioritize questions related to the generation AI based on the customer's areas of interest. Furthermore, the reception unit can also allow the generation AI to select an appropriate response method according to the customer's current situation. This enables appropriate filtering according to the customer's situation and areas of interest. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input data on the customer's current situation and areas of interest to the generation AI and have the generation AI perform filtering.

[0085] The reception unit can estimate the emotion of the customer and determine the priority of the requirements to be received based on the estimated emotion of the customer. For example, when the customer has an urgent requirement, the reception unit allows the generation AI to receive the requirement with priority. In addition, when the customer is relaxed, the reception unit can also allow the generation AI to treat the requirement equally to other requirements. Furthermore, when the customer is stressed, the reception unit can also receive the requirement with priority so that the generation AI can respond quickly. This enables the prioritization of requirements according to the emotion of the customer. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the voice data of the customer to the generation AI and cause the generation AI to execute the determination of the priority of the requirements.

[0086] The reception unit can preferentially receive requirements with high relevance based on the geographical location information of the customer at the time of reception. For example, when the customer is in a specific area, the reception unit preferentially receives requirements related to that area. The reception unit can also select an appropriate response method by the generation AI based on the geographical location information of the customer. Furthermore, when the customer is on the move, the reception unit can also update the geographical location information in real time and receive appropriate requirements. This makes it possible to receive appropriate requirements based on the geographical location information. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the reception unit can input the geographical location information of the customer to the generation AI and cause the generation AI to execute the reception of the requirements.

[0087] The reception unit can analyze the social media activity of the customer and receive the relevant requirements at the time of reception. For example, the reception unit preferentially receives requirements related to the generation AI based on the social media activity of the customer. The reception unit can also select an appropriate response method for the generation AI based on the content mentioned by the customer on social media. Furthermore, the reception unit can analyze the social media activity of the customer and receive requirements related to the generation AI. This makes it possible to receive appropriate requirements based on social media activity. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the social media activity data of the customer to the generation AI and cause the generation AI to execute the reception of the requirements.

[0088] The summarizing unit can estimate the customer's emotions and adjust the way the summary is expressed based on the estimated customer's emotions. For example, when the customer is feeling stressed, the summarizing unit allows the generation AI to generate a simple and easy-to-understand summary. In addition, when the customer is relaxed, the summarizing unit can also allow the generation AI to generate a detailed summary. Furthermore, when the customer is in a hurry, the summarizing unit can also allow the generation AI to generate a short summary that covers the main points. This enables an appropriate summary according to the customer's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the summarizing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the summarizing unit can input the customer's voice data to the generation AI and cause the generation AI to adjust the way the summary is expressed.

[0089] The summarization unit can adjust the level of detail of the summary based on the importance of the requirements when generating a summary. For example, the summarization unit generates a detailed summary for requirements with high importance by the generation AI. The summarization unit can also generate a concise summary for requirements with low importance by the generation AI. Furthermore, the summarization unit can adjust the level of detail of the summary by the generation AI according to the importance of the requirements. This enables an appropriate summary according to the importance of the requirements. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the summarization unit can input requirement importance data to the generation AI and cause the generation AI to adjust the level of detail of the summary.

[0090] The summarization unit can apply different summarization algorithms depending on the category of requirements when generating a summary. For example, the summarization unit causes the generation AI to apply a specialized summarization algorithm to technical requirements. The summarization unit can also cause the generation AI to apply a simple summarization algorithm to general requirements. Furthermore, the summarization unit can also cause the generation AI to select an optimal summarization algorithm depending on the category of requirements. This enables appropriate summarization depending on the category of requirements. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the summarization unit can input requirement category data to the generation AI and cause the generation AI to apply the summarization algorithm.

[0091] The summarization unit can estimate the customer's emotion and adjust the length of the summary based on the estimated customer's emotion. For example, when the customer is stressed, the summarization unit can cause the generation AI to generate a short summary that covers the main points. In addition, when the customer is relaxed, the summarization unit can also cause the generation AI to generate a detailed summary. In addition, when the customer is in a hurry, the summarization unit can also cause the generation AI to generate a short and concise summary. This enables an appropriate length of the summary according to the customer's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the summarization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the summarization unit can input the customer's voice data to the generation AI and cause the generation AI to adjust the length of the summary.

[0092] The summarization unit can determine the priority of summaries based on the submission time of requirements when generating summaries. For example, the summarization unit can cause the generation AI to generate summaries preferentially for requirements that have been submitted recently. The summarization unit can also cause the generation AI to generate summaries for requirements that have been submitted earlier, but later. Furthermore, the summarization unit can cause the generation AI to determine the priority of summaries according to the submission time of requirements. This enables appropriate prioritization of summaries based on the submission time. Some or all of the above-mentioned processing in the summarization unit can be performed, for example, using AI or without using AI. For example, the summarization unit can input data on the submission time of requirements to the generation AI and cause the generation AI to determine the priority of summaries.

[0093] The summarization unit can adjust the order of summaries based on the relevance of requirements when generating summaries. For example, the summarization unit can have the generation AI generate summaries with priority for highly relevant requirements. The summarization unit can also have the generation AI generate summaries later for less relevant requirements. Furthermore, the summarization unit can also have the generation AI adjust the order of summaries according to the relevance of requirements. This enables appropriate ordering of summaries based on relevance. Some or all of the above-mentioned processing in the summarization unit can be performed, for example, using AI or can be performed without using AI. For example, the summarization unit can input requirement relevance data to the generation AI and have the generation AI adjust the order of summaries.

[0094] The matching unit can estimate the customer's emotions and adjust the matching criteria based on the estimated customer's emotions. For example, when the customer is stressed, the matching unit allows the generation AI to apply simple matching criteria. Also, when the customer is relaxed, the matching unit can also allow the generation AI to apply detailed matching criteria. Furthermore, when the customer is in a hurry, the matching unit can also apply criteria for the generation AI to perform matching quickly. This enables appropriate matching criteria according to the customer's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the matching unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the matching unit can input the customer's voice data to the generation AI and cause the generation AI to adjust the matching criteria.

[0095] The matching unit can improve the accuracy of matching based on the interrelationships of requirements during matching. For example, the matching unit analyzes the interrelationships of requirements, and the generation AI prioritizes matching of related requirements. The matching unit can also improve the accuracy of matching by the generation AI, taking into account the interrelationships of requirements. Furthermore, the matching unit can also select an optimal matching method by the generation AI based on the interrelationships of requirements. This enables appropriate matching based on the interrelationships of requirements. A part or all of the above-mentioned processing in the matching unit may be performed, for example, using AI, or may be performed without using AI. For example, the matching unit can input interrelationship data of requirements to the generation AI, and cause the generation AI to improve the accuracy of matching.

[0096] The matching unit can perform matching based on the attribute information of the submitter of the requirements at the time of matching. For example, the matching unit selects an appropriate matching method based on the attribute information of the submitter by the generation AI. The matching unit can also improve the accuracy of matching by the generation AI by taking into account the attribute information of the submitter. Furthermore, the matching unit can also apply optimal matching criteria based on the attribute information of the submitter by the generation AI. This enables appropriate matching based on the attribute information of the submitter. A part or all of the above-mentioned processing in the matching unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the matching unit can input attribute information data of the submitter to the generation AI and cause the generation AI to perform matching.

[0097] The collation unit can estimate the customer's emotions and adjust the order in which the collation results are displayed based on the estimated customer's emotions. For example, when the customer is stressed, the collation unit causes the generation AI to prioritize displaying important results. In addition, when the customer is relaxed, the collation unit can also cause the generation AI to display detailed results in an orderly manner. Furthermore, when the customer is in a hurry, the collation unit can also adjust the order in which the generation AI quickly displays results. This enables an appropriate display order of collation results according to the customer's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collation unit can input the customer's voice data to the generation AI and cause the generation AI to adjust the display order of the collation results.

[0098] The matching unit can perform matching based on the geographic distribution of the requirements at the time of matching. For example, the matching unit allows the generation AI to select an appropriate matching method based on the geographic distribution of the requirements. The matching unit can also allow the generation AI to improve the accuracy of matching by taking into account the geographic distribution of the requirements. Furthermore, the matching unit can also allow the generation AI to apply optimal matching criteria based on the geographic distribution of the requirements. This enables appropriate matching based on the geographic distribution. A part or all of the above-mentioned processing in the matching unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the matching unit can input geographic distribution data of the requirements to the generation AI and cause the generation AI to perform matching.

[0099] The matching unit can improve the accuracy of matching by referring to related literature of the requirements during matching. For example, the matching unit allows the generation AI to select an appropriate matching method based on the related literature. The matching unit can also improve the accuracy of matching by the generation AI by referring to the related literature. Furthermore, the matching unit can also allow the generation AI to apply optimal matching criteria based on the related literature. This enables appropriate matching based on the related literature. Some or all of the above-mentioned processing in the matching unit may be performed, for example, using AI, or may be performed without using AI. For example, the matching unit can input related literature data to the generation AI and cause the generation AI to improve the accuracy of matching.

[0100] The answering unit can estimate the customer's emotions and adjust the way of expressing the answer based on the estimated customer's emotions. For example, when the customer is stressed, the generation AI can provide a simple and easy-to-understand answer. In addition, when the customer is relaxed, the answering unit can also provide a detailed answer. Furthermore, when the customer is in a hurry, the generation AI can also provide a short and to the point answer. This enables an appropriate answer according to the customer's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the answering unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the answering unit can input the customer's voice data to the generation AI and cause the generation AI to adjust the way of expressing the answer.

[0101] The answering section can adjust the level of detail of the answer based on the importance of the requirement when answering. For example, the answering section can have the generation AI provide a detailed answer to a requirement with high importance. The answering section can also have the generation AI provide a concise answer to a requirement with low importance. Furthermore, the answering section can have the generation AI adjust the level of detail of the answer according to the importance of the requirement. This enables an appropriate answer according to the importance of the requirement. A part or all of the above-mentioned processing in the answering section can be performed using, for example, an AI, or can be performed without using an AI. For example, the answering section can input the importance data of the requirement to the generation AI and cause the generation AI to adjust the level of detail of the answer.

[0102] The answering section can apply different answering algorithms depending on the category of the requirement when answering. For example, the answering section has the generating AI apply a specialized answering algorithm to technical requirements. Also, the answering section can have the generating AI apply a simple answering algorithm to general requirements. Furthermore, the answering section can have the generating AI select an optimal answering algorithm depending on the category of the requirement. This enables an appropriate answer depending on the category of the requirement. Some or all of the above-mentioned processing in the answering section may be performed using, for example, an AI, or may be performed without using an AI. For example, the answering section can input requirement category data to the generating AI and have the generating AI apply the answering algorithm.

[0103] The answering unit can estimate the customer's emotions and adjust the length of the answer based on the estimated customer's emotions. For example, when the customer is stressed, the answering unit can cause the generation AI to provide a short, to-the-point answer. Also, when the customer is relaxed, the answering unit can cause the generation AI to provide a detailed answer. Furthermore, when the customer is in a hurry, the answering unit can cause the generation AI to provide a short, concise answer. This enables the length of the answer to be appropriate according to the customer's emotions. The estimation of emotions 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 (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the answering unit can be performed, for example, using an AI or can be performed without using an AI. For example, the answering unit can input the customer's voice data to the generation AI and cause the generation AI to adjust the length of the answer.

[0104] The answering section can determine the priority of the answers based on the submission time of the requirements when answering. For example, the answering section allows the generation AI to provide answers preferentially to requirements that have been submitted recently. The answering section can also allow the generation AI to provide answers later to requirements that have been submitted earlier. Furthermore, the answering section can allow the generation AI to determine the priority of the answers according to the submission time of the requirements. This makes it possible to appropriately prioritize answers based on the submission time. Some or all of the above-mentioned processing in the answering section may be performed using, for example, an AI, or may be performed without using an AI. For example, the answering section can input requirement submission time data to the generation AI and have the generation AI execute the determination of the priority of the answers.

[0105] The answering section can adjust the order of answers based on the relevance of the requirements when answering. For example, the answering section allows the generation AI to provide answers preferentially to requirements with high relevance. Also, the answering section can allow the generation AI to provide answers later to requirements with low relevance. Furthermore, the answering section allows the generation AI to adjust the order of answers according to the relevance of the requirements. This enables appropriate ordering of answers based on relevance. A part or all of the above-mentioned processing in the answering section may be performed, for example, using an AI, or may be performed without using an AI. For example, the answering section can input requirement relevance data to the generation AI and cause the generation AI to adjust the order of answers.

[0106] The connection unit can estimate the customer's emotion and adjust the connection method based on the estimated customer's emotion. For example, when the customer is stressed, the connection unit quickly connects the customer to the agent. Also, when the customer is relaxed, the connection unit can connect the customer to the agent through a normal procedure. Furthermore, when the customer is in a hurry, the connection unit can connect the customer to the agent through the shortest route. This enables an appropriate connection method according to the customer's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the connection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the connection unit can input the customer's voice data to the generation AI and cause the generation AI to adjust the connection method.

[0107] The connection unit can determine the priority of the connection based on the importance of the requirement at the time of connection. For example, the connection unit preferentially connects to the person in charge of a requirement with high importance. The connection unit can also connect to a requirement with low importance by a normal procedure. Furthermore, the connection unit can adjust the priority of the connection according to the importance of the requirement. This enables appropriate prioritization of the connection according to the importance of the requirement. A part or all of the above-mentioned processing in the connection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the connection unit can input the importance data of the requirement to the generation AI and cause the generation AI to execute the determination of the priority of the connection.

[0108] The connection unit can apply different connection methods depending on the category of the requirement at the time of connection. For example, the connection unit can connect to a specialized person for a technical requirement. Also, the connection unit can connect to a general person for a general requirement. Furthermore, the connection unit can select an optimal connection method depending on the category of the requirement. This enables an appropriate connection depending on the category of the requirement. A part or all of the above-mentioned processing in the connection unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the connection unit can input requirement category data to the generation AI and cause the generation AI to apply the connection method.

[0109] The connection unit can estimate the emotion of the customer and adjust the order of connections based on the estimated emotion of the customer. For example, when the customer is stressed, the connection unit quickly connects the customer to the agent. Also, when the customer is relaxed, the connection unit can connect the customer to the agent by the normal procedure. Furthermore, when the customer is in a hurry, the connection unit can connect the customer to the agent by the shortest route. This enables appropriate ordering of connections according to the emotion of the customer. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the connection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the connection unit can input the customer's voice data to the generation AI and cause the generation AI to adjust the connection order.

[0110] The connection unit can determine the priority of the connection based on the submission time of the requirement at the time of connection. For example, the connection unit preferentially connects to the person in charge of the most recently submitted requirement. The connection unit can also connect to the requirement submitted earlier by the normal procedure. Furthermore, the connection unit can adjust the priority of the connection according to the submission time of the requirement. This enables appropriate prioritization of the connection based on the submission time. A part or all of the above-mentioned processing in the connection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the connection unit can input the submission time data of the requirement to the generation AI and cause the generation AI to execute the determination of the priority of the connection.

[0111] The connection unit can adjust the order of connections based on the relevance of requirements at the time of connection. For example, the connection unit preferentially connects to a person in charge of a highly relevant requirement. The connection unit can also connect to a less relevant requirement in a normal procedure. Furthermore, the connection unit can adjust the order of connections according to the relevance of requirements. This enables appropriate ordering of connections based on the relevance. A part or all of the above-mentioned processing in the connection unit may be performed, for example, using AI, or may be performed without using AI. For example, the connection unit can input the relevance data of requirements to the generation AI and cause the generation AI to adjust the connection order.

[0112] The encryption unit can estimate the customer's emotions and adjust the strength of encryption based on the estimated customer's emotions. For example, when the customer is stressed, the encryption unit applies high-strength encryption. Also, when the customer is relaxed, the encryption unit can also apply normal encryption. Furthermore, when the customer is in a hurry, the encryption unit can adjust the strength to perform encryption quickly. This enables appropriate encryption strength according to the customer's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the encryption unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the encryption unit can input the customer's voice data to the generation AI and cause the generation AI to adjust the encryption strength.

[0113] The encryption unit can adjust the level of detail of encryption based on the importance of the requirement at the time of encryption. For example, the encryption unit applies detailed encryption to requirements with high importance. The encryption unit can also apply simple encryption to requirements with low importance. Furthermore, the encryption unit can adjust the level of detail of encryption according to the importance of the requirement. This enables appropriate encryption according to the importance of the requirement. A part or all of the above-mentioned processing in the encryption unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the encryption unit can input the importance data of the requirement to the generation AI and cause the generation AI to adjust the level of detail of encryption.

[0114] The encryption unit can estimate the customer's emotions and determine the priority of encryption based on the estimated customer's emotions. For example, when the customer is stressed, the encryption unit prioritizes encryption. Also, when the customer is relaxed, the encryption unit can also perform encryption in a normal procedure. Furthermore, when the customer is in a hurry, the encryption unit can adjust the priority to perform encryption quickly. This enables appropriate prioritization of encryption according to the customer's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the encryption unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the encryption unit can input the customer's voice data to the generation AI and cause the generation AI to execute the determination of the encryption priority.

[0115] The encryption unit can determine the encryption priority based on the submission time of the requirements at the time of encryption. For example, the encryption unit prioritizes encryption for recently submitted requirements. The encryption unit can also encrypt requirements submitted earlier in the normal procedure. Furthermore, the encryption unit can adjust the encryption priority according to the submission time of the requirements. This enables appropriate encryption prioritization based on the submission time. A part or all of the above-mentioned processing in the encryption unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the encryption unit can input requirement submission time data to the generation AI and cause the generation AI to determine the encryption priority.

[0116] The notification method can estimate the customer's emotion and adjust the notification method based on the estimated customer's emotion. For example, the notification method can provide a simple and easy-to-understand notification method when the customer is stressed. The notification method can also provide a detailed notification method when the customer is relaxed. Furthermore, the notification method can adjust the method for quickly notifying the customer when the customer is in a hurry. This enables an appropriate notification method according to the customer's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification method may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification method can input the customer's voice data into the generation AI and cause the generation AI to adjust the notification method.

[0117] The notification method can adjust the level of detail of the notification based on the importance of the requirement at the time of notification. For example, the notification method provides a detailed notification for a requirement with high importance. The notification method can also provide a concise notification for a requirement with low importance. Furthermore, the notification method can adjust the level of detail of the notification according to the importance of the requirement. This enables appropriate notification according to the importance of the requirement. A part or all of the above-mentioned processing in the notification method may be performed, for example, using AI or may be performed without using AI. For example, the notification method can input the importance data of the requirement to the generation AI and cause the generation AI to adjust the level of detail of the notification.

[0118] The notification method can estimate the emotion of the customer and determine the priority of the notification based on the estimated emotion of the customer. For example, the notification method can give priority to the notification when the customer is stressed. Also, the notification method can give the notification in a normal procedure when the customer is relaxed. Furthermore, the notification method can adjust the priority to give the notification quickly when the customer is in a hurry. This enables the prioritization of the notification appropriately according to the emotion of the customer. The estimation of the emotion is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification method may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification method can input the voice data of the customer to the generation AI and cause the generation AI to execute the determination of the priority of the notification.

[0119] The notification method can determine the priority of notifications based on the submission time of the requirements at the time of notification. For example, the notification method can give priority to recently submitted requirements. The notification method can also notify older submitted requirements in the normal procedure. Furthermore, the notification method can adjust the priority of notifications according to the submission time of the requirements. This enables appropriate prioritization of notifications based on the submission time. A part or all of the above-mentioned processing in the notification method can be performed using, for example, AI, or can be performed without using AI. For example, the notification method can input the submission time data of the requirements to the generation AI and cause the generation AI to determine the priority of notifications.

[0120] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0121] The customer care system can further analyze the customer's past purchase history and reflect it in the summary generated by the summarization unit. For example, if a customer has requirements related to products or services purchased in the past, the summarization unit can include that information in the summary. Also, if a customer frequently purchases products of a particular brand or category, the summarization unit can generate a summary based on that information. Furthermore, the customer's purchase history can be used to find certain trends or patterns and adjust the summary based on them. This allows for more accurate summaries based on the customer's past purchase history.

[0122] The customer response system can further analyze the customer's social media activity and incorporate it into the summary generated by the summarization unit. For example, the summary can include what the customer mentioned on social media and topics of interest. Also, if the customer frequently uses certain hashtags or keywords, the summary can be generated based on that information. Furthermore, the customer response system can find certain trends or patterns in the customer's social media activity and adjust the summary based on them. This allows for more accurate summaries based on the customer's social media activity.

[0123] The customer response system can further analyze the geographic location information of the customer and reflect it in the summary generated by the summarization unit. For example, if the customer is in a particular area, information related to that area can be included in the summary. Also, if the customer is on the move, the geographic location information can be updated in real time and the summary can be generated based on it. Furthermore, certain trends or patterns can be found from the geographic location information of the customer and the summary can be adjusted based on them. This allows for more accurate summaries based on the geographic location information of the customer.

[0124] The customer support system can further analyze the customer's past inquiry history and reflect this in the summary generated by the summarization unit. For example, the summary can include the content of the customer's past inquiries and the solutions. Also, if a customer frequently inquires about a particular problem or question, the summary can be generated based on that information. Furthermore, the customer support system can find specific trends or patterns from the customer's inquiry history and adjust the summary based on those trends or patterns. This allows for more accurate summaries based on the customer's past inquiry history.

[0125] The customer support system can further analyze the customer's current situation and areas of interest and reflect them in the summary generated by the summarization unit. For example, when the customer describes his / her current situation, the information can be included in the summary. Also, based on the customer's areas of interest, related information can be included in the summary. Furthermore, the customer support system can find certain trends or patterns from the customer's current situation and areas of interest and adjust the summary based on them. This allows for more accurate summaries based on the customer's current situation and areas of interest.

[0126] The reception department can estimate the customer's emotions and adjust the response method based on the estimated customer's emotions. For example, if the customer is feeling stressed, the generation AI can respond in a calm voice and ask simple questions. If the customer is relaxed, the generation AI can respond in a friendly voice and ask detailed questions. Furthermore, if the customer is in a hurry, the generation AI can ask short questions to quickly find out the customer's requirements. This makes it possible to respond appropriately according to the customer's emotions.

[0127] The summarization unit can estimate the customer's emotions and adjust the way the summary is presented based on the estimated customer's emotions. For example, if the customer is feeling stressed, the generation AI can generate a simple and easy-to-understand summary. If the customer is relaxed, the generation AI can also generate a detailed summary. Furthermore, if the customer is in a hurry, the generation AI can generate a short summary that hits the main points. This makes it possible to generate an appropriate summary according to the customer's emotions.

[0128] The matching unit can estimate the customer's emotions and adjust the matching criteria based on the estimated customer's emotions. For example, if the customer is stressed, the generation AI can apply simple matching criteria. If the customer is relaxed, the generation AI can also apply detailed matching criteria. Furthermore, if the customer is in a hurry, the generation AI can also apply criteria for quick matching. This enables appropriate matching criteria according to the customer's emotions.

[0129] The answering part can estimate the customer's emotions and adjust the way the answer is expressed based on the estimated customer's emotions. For example, if the customer is feeling stressed, the generation AI can provide a simple and easy-to-understand answer. If the customer is relaxed, the generation AI can also provide a detailed answer. Furthermore, if the customer is in a hurry, the generation AI can provide a short and to-the-point answer. This makes it possible to provide an appropriate answer according to the customer's emotions.

[0130] The connection unit can estimate the emotion of the customer and adjust the connection method based on the estimated emotion of the customer. For example, if the customer is stressed, the connection unit can quickly connect the customer to a representative. If the customer is relaxed, the connection unit can also use a normal procedure. Furthermore, if the customer is in a hurry, the connection unit can also use the shortest route to connect the customer to a representative. This makes it possible to use an appropriate connection method according to the emotion of the customer.

[0131] The process flow of the second embodiment will be briefly described below.

[0132] Step 1: The reception department accepts customer requirements. Customer requirements include inquiries, complaints, requests, etc. The reception department can accept customer requirements by means of telephone, email, chat, etc. Step 2: The summarization unit uses the generation AI to summarize the requirements received by the reception unit. The summarization is based on the length of the text and the importance of the information to be summarized. The generation AI uses a text generation AI (e.g., LLM) or a multimodal generation AI to concisely summarize the requirements. Step 3: The matcher matches the summary generated by the summarizer with the FAQ database. Matching is performed using methods such as cosine similarity, Jaccard coefficient, and TF-IDF. The matcher uses these methods to calculate the similarity between the summary and the answers in the FAQ database. Step 4: The answering section provides a primary answer based on the results obtained by the matching section. The primary answer can be provided directly from the FAQ database or generated using a generation AI. Step 5: The connection section connects the person in charge if the answering section cannot provide a first response. The connection is made by means of telephone, email, chat, etc.

[0133] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0134] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0135] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0136] Each of the multiple elements including the above-mentioned reception unit, summary unit, comparison unit, answer unit, and connection unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives customer requirements. The summary unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and summarizes the requirements using a generation AI. The comparison unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and compares the summary with the FAQ database. The answer unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and provides a primary answer. The connection unit is realized by, for example, the control unit 46A of the smart device 14 and connects to a person in charge. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0137] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0138] 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.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0140] 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.

[0141] 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 the voice according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0143] 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 performed in a secure state.

[0144] Fig. 4 shows an example of 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.

[0145] 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.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0147] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0148] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0149] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0150] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0151] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0152] Each of the multiple elements including the above-mentioned reception unit, summary unit, comparison unit, answer unit, and connection unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives customer requirements. The summary unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the requirements using a generation AI. The comparison unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and compares the summary with an FAQ database. The answer unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides a primary answer. The connection unit is realized, for example, by the control unit 46A of the smart glasses 214 and connects to a person in charge. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 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.

[0155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0156] 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.

[0157] 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 the voice according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0159] 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 performed in a secure state.

[0160] 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.

[0161] 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.

[0162] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0163] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific 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.

[0164] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0165] 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 voice indicating a user input for 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.

[0166] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0167] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0168] Each of the multiple elements including the above-mentioned reception unit, summary unit, comparison unit, answer unit, and connection unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 and receives customer requirements. The summary unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the requirements using a generation AI. The comparison unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and compares the summary with the FAQ database. The answer unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides a primary answer. The connection unit is realized, for example, by the control unit 46A of the headset type terminal 314 and connects to a person in charge. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0169] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0170] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0171] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0172] 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.

[0173] 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 the voice according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0175] 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 performed in a secure state.

[0176] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0177] 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.

[0178] 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.

[0179] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0180] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0181] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0182] 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 a voice indicating a user input for 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.

[0183] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0184] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0185] Each of the multiple elements including the above-mentioned reception unit, summary unit, comparison unit, answer unit, and connection unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives customer requirements. The summary unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the requirements using a generation AI. The comparison unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and compares the summary with an FAQ database. The answer unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides a primary answer. The connection unit is realized, for example, by the control unit 46A of the robot 414 and connects to a person in charge. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0186] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0187] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0188] These emotions are distributed in the three o'clock direction of emotion map 400 and usually 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.

[0189] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0190] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0191] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0192] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0193] 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.

[0194] 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 Universal Serial Bus (USB) 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.

[0195] In addition, 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 upon request from the data processing device 12.

[0196] 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.

[0197] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0198] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0199] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0200] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0201] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0202] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0203] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0204] (Appendix 1) a reception section for receiving customer requirements; a summarizing unit that summarizes the requirements accepted by the accepting unit; a comparison unit for comparing the summary generated by the summarization unit with an FAQ database; a response unit that provides a primary response based on the result obtained by the collation unit; A connection unit that connects the user to a person in charge if the response unit is unable to provide a primary response. (Appendix 2) Equipped with an algorithm to generate summaries 2. The system of claim 1, (Appendix 3) Have a FAQ database structure 2. The system of claim 1, (Appendix 4) Equipped with encryption for privacy protection 2. The system of claim 1, (Appendix 5) Provide a method for notifying the person in charge 2. The system of claim 1, (Appendix 6) The reception unit is A system for estimating customer sentiment and adjusting response methods based on the estimated customer sentiment. (Appendix 7) The reception unit is A system that analyzes a customer's past inquiry history and selects the appropriate response method. (Appendix 8) The reception unit is At the check-in stage, filter based on the customer's current situation and interests 2. The system of claim 1, (Appendix 9) The reception unit is A system that estimates customer emotions and prioritizes the requirements to be received based on the estimated customer emotions. (Appendix 10) The reception unit is A system that prioritizes relevant requests based on the customer's geographic location at the time of reception. (Appendix 11) The reception unit is Upon receipt, analyze the customer's social media activity and receive relevant requirements 2. The system of claim 1, (Appendix 12) The summary portion comprises: A system that estimates customer sentiment and adjusts the way a summary is presented based on the estimated customer sentiment. (Appendix 13) The summary portion comprises: While generating the summary, adjust the level of detail in the summary based on the importance of the requirements 2. The system of claim 1, (Appendix 14) The summary portion comprises: Apply different summarization algorithms depending on the requirement category during summary generation 2. The system of claim 1, (Appendix 15) The summary portion comprises: A system for estimating customer sentiment and adjusting the length of a summary based on the estimated customer sentiment. (Appendix 16) The summary portion comprises: During abstract generation, prioritize abstracts based on when requirements were submitted 2. The system of claim 1, (Appendix 17) The summary portion comprises: Adjust the order of summaries based on requirement relevance during summary generation 2. The system of claim 1, (Appendix 18) The collation unit is A system that estimates customer sentiment and adjusts matching criteria based on the estimated customer sentiment. (Appendix 19) The collation unit is A system that improves accuracy of matching based on interrelationships of requirements during matching. (Appendix 20) The collation unit is A system that performs matching based on attribute information of the person submitting the requirements. (Appendix 21) The collation unit is A system that estimates customer sentiment and adjusts the order in which matching results are displayed based on the estimated customer sentiment. (Appendix 22) The collation unit is A system that, at the time of matching, matches are made based on the geographical distribution of requirements. (Appendix 23) The collation unit is A system that improves the accuracy of matching based on the relevant literature of the requirements during matching. (Appendix 24) The answering section: A system that estimates customer sentiment and adjusts the way responses are expressed based on the estimated customer sentiment. (Appendix 25) The answering section: When responding, adjust the level of detail in your response based on the importance of the requirement 2. The system of claim 1, (Appendix 26) The answering section: When answering, apply different answering algorithms depending on the requirement category 2. The system of claim 1, (Appendix 27) The answering section: A system that estimates customer sentiment and adjusts the length of responses based on the estimated customer sentiment. (Appendix 28) The answering section: When responding, we will prioritize responses based on when the requirements were submitted 2. The system of claim 1, (Appendix 29) The answering section: While answering, adjust the order of answers based on the relevance of the requirement 2. The system of claim 1, (Appendix 30) The connection portion is A system that estimates customer sentiment and adjusts connection methods based on the estimated customer sentiment. (Appendix 31) The connection portion is When connecting, prioritize connections based on the importance of the requirements 2. The system of claim 1, (Appendix 32) The connection portion is When connecting, apply different connection methods depending on the category of requirements 2. The system of claim 1, (Appendix 33) The connection portion is A system that estimates customer sentiment and adjusts connection order based on the estimated customer sentiment. (Appendix 34) The connection portion is When connecting, prioritize connections based on when requirements were submitted 2. The system of claim 1, (Appendix 35) The connection portion is When connecting, adjust the order of connections based on the relevance of requirements 2. The system of claim 1, (Appendix 36) The encryption unit includes: A system that estimates customer sentiment and adjusts encryption strength based on the estimated customer sentiment. (Appendix 37) The encryption unit includes: During encryption, adjust encryption granularity based on the severity of the requirement 2. The system of claim 1, (Appendix 38) The encryption unit includes: A system that estimates customer sentiment and prioritizes encryption based on the estimated customer sentiment. (Appendix 39) The encryption unit includes: During encryption, prioritize encryption based on when requirements are submitted 2. The system of claim 1, (Appendix 40) The notification method includes: A system that estimates customer sentiment and adjusts notification methods based on the estimated customer sentiment. (Appendix 41) The notification method includes: When notifying, adjust the level of detail in notifications based on the importance of the requirement 2. The system of claim 1, (Appendix 42) The notification method includes: A system that estimates customer sentiment and prioritizes notifications based on the estimated customer sentiment. (Appendix 43) The notification method includes: At the time of notification, we will prioritize notifications based on when the requirements were submitted 2. The system of claim 1, [Explanation of symbols]

[0205] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception section for receiving customer requirements; a summarizing unit that summarizes the requirements accepted by the accepting unit; a comparison unit for comparing the summary generated by the summarization unit with an FAQ database; a response unit that provides a primary response based on the result obtained by the collation unit; A connection unit that connects the user to a person in charge if the response unit is unable to provide a primary response.

2. Equipped with an algorithm to generate summaries 2. The system of claim 1 .

3. Have a FAQ database structure 2. The system of claim 1 .

4. Equipped with encryption for privacy protection 2. The system of claim 1 .

5. The reception unit is Infer customer sentiment and tailor your response based on that sentiment 2. The system of claim 1 .

6. The reception unit is Analyze the customer's past inquiry history and choose the appropriate response method 2. The system of claim 1 .

7. The reception unit is Filtering at the check-in based on the customer's current situation and interests 2. The system of claim 1 .

Images