System

Abstract

To provide a system which efficiently and accurately deals with claims to an insurance company.SOLUTION: A system includes: a reception part, a specification part, a retrieval part, and a dealing part. The reception part receives an inquiry to an insurance company. The specification part specifies a content of a claim to an insurance company from the inquiry received by the reception part. The retrieval part retrieves a document related to the claim, on the basis of the content of the claim specified by the specification part. The dealing part deals with a claim, on the basis of the document retrieved by the retrieval part.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] With conventional technology, handling claims with insurance companies was often done manually, posing issues with efficiency and accuracy.

[0005] The system according to the embodiment aims to efficiently and accurately handle claims made to insurance companies. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an identification unit, a search unit, and a response unit. The reception unit receives inquiries to the insurance company. The identification unit identifies the contents of a claim to the insurance company from the inquiries received by the reception unit. The search unit searches for documents related to the claim based on the contents of the claim identified by the identification unit. The response unit responds to the claim based on the documents searched for by the search unit. Effect of the Invention

[0007] The system according to the embodiment can efficiently and accurately handle claims to insurance companies. [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) The AI ​​assistant system for insurance company claims handling support according to the embodiment of the present invention is a system that accepts inquiries to an insurance company, identifies the contents of the claim, searches for related documents, and responds to the claim. This system has a reception unit that accepts inquiries to an insurance company, and accepts inquiries from a user. Next, there is an identification unit that identifies the contents of the claim from the inquiry accepted by the reception unit, and identifies the contents of the claim using a machine learning model. There is a search unit that searches for related documents based on the identified contents of the claim, and there is a response unit that responds to the claim based on the searched documents. The response unit predicts the effectiveness of the response measures using AI and proposes optimal responses. Furthermore, there is a support unit that supports the collection of details and evidence of the accident based on the documents searched by the search unit, and acquires location information of the accident site using GPS data. There is also a calculation unit that calculates benefits for the accident based on the documents searched by the search unit, and there is a provision unit that provides information on the details of the policy. The provision unit provides customized policy information based on a user profile. Furthermore, there is an answering unit that answers the inquiries accepted by the reception unit, and there is a protection unit that protects customer information using encryption technology. This enables safe handling of customer information. This allows the AI ​​assistant system for insurance company claims handling support to efficiently handle claims for insurance companies.

[0029] The AI ​​assistant system for insurance company claims handling support according to the embodiment includes a reception unit, an identification unit, a search unit, and a response unit. The reception unit receives inquiries to the insurance company. The inquiries include, for example, telephone, email, online form, etc., but are not limited to such examples. The reception unit receives inquiries by telephone, for example. The reception unit can also receive inquiries by email. The reception unit can also receive inquiries through an online form. The identification unit uses a machine learning model to identify the contents of the claim from the inquiry received by the reception unit. The contents of the claim include, for example, insurance claims, confirmation of contract contents, etc., but are not limited to such examples. The identification unit uses, for example, a neural network to identify the contents of the claim. The identification unit can also use a support vector machine to identify the contents of the claim. The identification unit can also use a decision tree to identify the contents of the claim. The search unit searches for documents related to the claim based on the contents of the claim identified by the identification unit. The documents include, for example, PDF files, text files, image files, etc., but are not limited to such examples. The search unit searches for documents using, for example, a keyword search. The search unit can also search for documents using a full-text search. The search unit can also search for documents using a metadata search. The response unit responds to the complaint based on the documents searched by the search unit. The response includes, for example, telephone response, email response, and in-person response, but is not limited to these examples. The response unit responds by telephone, for example. The response unit can also respond by email. The response unit can also respond by visiting. As a result, the AI ​​assistant system for supporting insurance company complaint handling according to the embodiment can efficiently handle complaints at the insurance company.

[0030] The reception unit accepts inquiries to the insurance company. Examples of inquiries include, but are not limited to, telephone, email, and online forms. The reception unit accepts inquiries by telephone, for example. The reception unit can also accept inquiries by email. The reception unit can also accept inquiries through an online form. Specifically, telephone inquiries are automatically converted into text using voice recognition technology and input into the system. Email inquiries are analyzed using natural language processing technology to extract important information. In the online form, information entered by the user is directly imported into the system and processed immediately. This allows the reception unit to respond to various inquiry means and collect information quickly and accurately. Furthermore, the reception unit can automatically set priorities according to the contents of the inquiries and prioritize claims with high urgency. For example, inquiries regarding serious accidents or disasters are immediately notified to the response unit and require a prompt response. On the other hand, inquiries regarding confirmation or changes to general contract contents are handled according to the normal processing flow. This allows the reception unit to efficiently and effectively handle inquiries and smoothly advance the initial stage of claims handling by the insurance company.

[0031] The identification unit uses a machine learning model to identify the contents of the claim from the inquiry received by the reception unit. The contents of the claim include, for example, insurance claims, confirmation of contract details, etc., but are not limited to such examples. The identification unit uses, for example, a neural network to identify the contents of the claim. The identification unit can also use a support vector machine to identify the contents of the claim. The identification unit can also use a decision tree to identify the contents of the claim. Specifically, the neural network learns a large amount of past claim data and classifies the contents of the claim with high accuracy for a new inquiry. The support vector machine identifies the contents of the claim by vectorizing the features of the claim and finding the optimal classification boundary. The decision tree hierarchically analyzes the contents of the inquiry and identifies the most appropriate claim category. This allows the identification unit to quickly and accurately identify the contents of the inquiry by making full use of various machine learning algorithms. Furthermore, the identification unit can continuously learn and improve the accuracy of the model. For example, the model can be retrained using newly received claim data to respond to the latest trends and patterns. The identification unit can also use an anomaly detection algorithm to detect claims with unusual patterns early and issue an alert when special measures are required. This enables the identification department to improve the efficiency of the insurance company's complaint handling and increase customer satisfaction.

[0032] The search unit searches for documents related to the claim based on the content of the claim identified by the identification unit. The documents include, for example, PDF files, text files, image files, etc., but are not limited to such examples. The search unit searches for documents using, for example, a keyword search. The search unit can also search for documents using a full-text search. The search unit can also search for documents using a metadata search. Specifically, in the keyword search, important keywords related to the content of the claim are extracted and related documents are searched based on the extracted keywords. In the full-text search, the entire document is searched to comprehensively find information related to the claim. In the metadata search, metadata such as the creation date, creator, and category of the document are used to efficiently search for documents that match specific conditions. This allows the search unit to quickly and accurately find documents related to the claim by making full use of various search methods. Furthermore, the search unit can prioritize search results and display the most relevant documents at the top. For example, documents related to similar past claims and important information related to a specific insurance policy are preferentially displayed. Furthermore, the search unit can optimize the search algorithm based on the user's search history and feedback, and continuously improve search accuracy. This enables the search unit to assist insurance companies in handling claims and to respond quickly and appropriately.

[0033] The response department responds to the complaint based on the documents searched by the search department. The responses include, but are not limited to, telephone responses, email responses, and visit responses. For example, the response department responds by telephone. The response department can also respond by email. The response department can also respond by visiting. Specifically, in telephone responses, the AI ​​automatically analyzes the contents of the complaint and provides an appropriate answer. In email responses, the AI ​​automatically generates a reply email and responds quickly. In visit responses, the AI ​​automatically adjusts the visit schedule and notifies the person in charge. This allows the response department to respond to complaints quickly and appropriately by making full use of various response means. Furthermore, the response department can record the response history and use it for future complaint responses. For example, the response department can propose the optimal response method for similar complaints based on the past response history. In addition, the response department can collect customer feedback and continuously improve the quality of response. For example, the response department can conduct a customer satisfaction survey and review the response process based on the feedback. This allows the response department to streamline the insurance company's complaint response and improve customer satisfaction.

[0034] The search unit includes a support unit that supports the collection of details and evidence of the accident based on the searched documents. The support unit supports the collection of details and evidence of the accident based on the documents searched by the search unit. Details of the accident include, for example, the date and time, location, and circumstances of the accident, but are not limited to such examples. The support unit records, for example, the date and time of the accident. The support unit can also record the location of the accident. The support unit can also record the circumstances of the accident. The collection of evidence includes, for example, taking photographs, witness testimony, and document collection, but are not limited to such examples. The support unit takes, for example, photographs of the accident scene. The support unit can also collect witness testimony. The support unit can also collect documents related to the accident. This makes it possible to efficiently collect details and evidence of the accident.

[0035] The search unit includes a calculation unit that calculates a benefit for an accident based on the searched document. The calculation unit calculates a benefit for an accident based on the document searched by the search unit. The benefit includes, for example, medical expenses, repair costs, and compensation, but is not limited to such examples. The calculation unit calculates, for example, medical expenses. The calculation unit can also calculate repair costs. The calculation unit can also calculate compensation. This allows the calculation of the benefit for an accident to be performed efficiently.

[0036] The search unit includes a provision unit that provides information on policy details based on the searched document. The provision unit provides information on policy details based on the document searched by the search unit. The policy details include, for example, insurance contract clauses, special provisions, etc., but are not limited to such examples. The provision unit provides, for example, the insurance contract clauses. The provision unit can also provide special provisions. This makes it possible to efficiently provide detailed policy information.

[0037] The reception unit includes a reply unit that replies to the received inquiry. The reply unit replies to the inquiry received by the reception unit. Responses include, for example, telephone replies, email replies, written replies, and the like, but are not limited to these examples. The reply unit replies, for example, by telephone. The reply unit can also reply by email. The reply unit can also reply in writing. This allows for efficient replying to inquiries.

[0038] The system includes a protection unit that protects the customer information using an encryption technology. The protection unit protects the customer information using an encryption technology. The encryption technology includes, but is not limited to, AES, RSA, TLS, and the like. The protection unit encrypts the customer information using, for example, AES. The protection unit can also encrypt the customer information using RSA. The protection unit can also encrypt the customer information using TLS. This allows the customer information to be handled safely.

[0039] The identification unit can identify the content of the claim by using a machine learning model. The machine learning model includes, but is not limited to, for example, a neural network, a support vector machine, a decision tree, and the like. The identification unit can identify the content of the claim by using, for example, a neural network. The identification unit can also identify the content of the claim by using a support vector machine. The identification unit can also identify the content of the claim by using a decision tree. This makes it possible to identify the content of the claim with high accuracy.

[0040] The providing unit can provide customized policy information based on a user profile. The user profile includes, for example, age, gender, past behavior history, and the like, but is not limited to such examples. The providing unit provides customized policy information based on, for example, age. The providing unit can also provide customized policy information based on gender. The providing unit can also provide customized policy information based on past behavior history. This makes it possible to provide optimal policy information for the user.

[0041] The support unit can acquire location information of the accident site using GPS data. GPS data includes, for example, location information of a smartphone, an in-vehicle GPS system, and the like, but is not limited to such examples. The support unit acquires location information of the accident site using, for example, location information of a smartphone. The support unit can also acquire location information of the accident site using an in-vehicle GPS system. This makes it possible to accurately acquire location information of the accident site. 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.

[0042] The response unit can predict the effect of the countermeasure using AI and propose the optimal countermeasure. AI includes, but is not limited to, for example, deep learning and reinforcement learning. The response unit can predict the effect of the countermeasure using, for example, deep learning. The response unit can also predict the effect of the countermeasure using reinforcement learning. The response unit can also predict the effect of the countermeasure using generation AI. This makes it possible to propose the optimal countermeasure.

[0043] The reception unit can analyze past inquiry history and select the optimal reception method. The past inquiry history includes, for example, inquiry date and time, contents, and response results, but is not limited to these examples. For example, the reception unit automatically displays frequently inquired contents as candidates based on the past inquiry history. The reception unit can also preferentially suggest reception methods (voice, text, etc.) that have been used in the past. The reception unit can also predict and suggest the reception method to be used in a specific time period from the past inquiry history. This makes it possible to provide the optimal reception method based on the past inquiry history.

[0044] The reception unit can perform filtering based on the user's current situation and field of interest when receiving an inquiry. The current situation includes, for example, a current location, a current activity situation, and the like, but is not limited to such examples. The field of interest includes, for example, hobbies, topics of interest, and the like, but is not limited to such examples. For example, when the user inputs the current situation, the reception unit preferentially displays related inquiry contents. In addition, the reception unit can also filter related inquiry contents based on the user's field of interest. In addition, the reception unit can also suggest optimal inquiry contents based on the user's current situation and field of interest. This makes it possible to provide optimal inquiry contents according to the user's situation and field of interest.

[0045] The reception unit can preferentially receive inquiries with high relevance in consideration of the geographical location information of the user when receiving an inquiry. The geographical location information includes, but is not limited to, for example, GPS data, address information, and the like. For example, when the user is in a specific area, the reception unit preferentially receives inquiries related to the area. The reception unit can also filter related inquiry contents based on the geographical location information of the user. The reception unit can also suggest optimal inquiry contents based on the user's current location. This makes it possible to provide optimal inquiry contents based on the geographical location information of the user.

[0046] The reception unit can analyze the user's social media activity when receiving an inquiry and receive related inquiries. Social media activity includes, but is not limited to, for example, the content of posts, the number of likes, the number of followers, and the like. For example, the reception unit analyzes the user's social media activity and preferentially receives related inquiry content. The reception unit can also suggest optimal inquiry content based on the user's comments on social media. The reception unit can also filter related inquiry content by referring to the user's social media activity. This makes it possible to provide optimal inquiry content based on the user's social media activity.

[0047] When identifying the content of a complaint, the identification unit can improve the accuracy of identification by referring to past complaint data. Past complaint data includes, for example, the date and time of the complaint, the content, and the response results, but is not limited to such examples. For example, the identification unit identifies similar complaint content based on the past complaint data. The identification unit can also analyze the past complaint data to improve the accuracy of identification. The identification unit can also identify the optimal complaint content by referring to the past complaint data. This makes it possible to improve the accuracy of identification of the complaint content based on the past complaint data.

[0048] The identification unit can apply different identification algorithms depending on the category of the claim when identifying the content of the claim. The category of the claim includes, but is not limited to, for example, an insurance claim, confirmation of the contract content, etc. The identification unit selects, for example, an optimal identification algorithm depending on the category of the claim. The identification unit can also adjust the identification algorithm based on the category of the claim. The identification unit can also apply different identification algorithms depending on the category of the claim. This makes it possible to provide an optimal identification algorithm depending on the category of the claim.

[0049] When identifying the complaint content, the identification unit can preferentially identify a complaint with high relevance by taking into consideration the geographical location information of the user. Complaints with high relevance include, but are not limited to, past complaint data, current situations, and the like. For example, when the user is in a specific area, the identification unit preferentially identifies complaint content related to the area. The identification unit can also filter related complaint content based on the geographical location information of the user. The identification unit can also identify optimal complaint content based on the user's current location. This makes it possible to provide optimal complaint content based on the geographical location information of the user.

[0050] When identifying the complaint content, the identification unit can analyze the user's social media activity and identify related complaints. Examples of related complaints include, but are not limited to, past complaint data, current situations, and the like. For example, the identification unit can analyze the user's social media activity and preferentially identify related complaint content. The identification unit can also identify optimal complaint content based on the user's social media comments. The identification unit can also filter the related complaint content with reference to the user's social media activity. This makes it possible to provide optimal complaint content based on the user's social media activity.

[0051] When searching for a document, the search unit can optimize a search algorithm by referring to past search data. The past search data includes, for example, search date and time, search keywords, search results, etc., but is not limited to such examples. For example, the search unit preferentially searches for similar documents based on the past search data. The search unit can also analyze the past search data and optimize the search algorithm. The search unit can also provide optimal search results by referring to the past search data. This makes it possible to optimize the search algorithm based on the past search data.

[0052] The search unit may apply different search algorithms depending on the claim category when searching the document. The search algorithms include, but are not limited to, TF-IDF, BM25, etc. The search unit may select an optimal search algorithm depending on, for example, the claim category. The search unit may also adjust the search algorithm based on the claim category. The search unit may also apply different search algorithms depending on the claim category. This makes it possible to provide an optimal search algorithm depending on the claim category.

[0053] When searching for a document, the search unit can preferentially search for highly relevant documents in consideration of the geographical location information of the user. Highly relevant documents include, but are not limited to, past search data, current situations, and the like. For example, when the user is in a specific area, the search unit preferentially searches for documents related to the area. The search unit can also filter related documents based on the geographical location information of the user. The search unit can also search for the most suitable document based on the user's current location. This makes it possible to provide the most suitable document based on the geographical location information of the user.

[0054] When searching for a document, the search unit can analyze the user's social media activity and search for related documents. Examples of related documents include, but are not limited to, past search data, current status, and the like. For example, the search unit analyzes the user's social media activity and searches for related documents preferentially. The search unit can also search for optimal documents based on the user's comments on social media. The search unit can also filter the relevant documents with reference to the user's social media activity. This makes it possible to provide optimal documents based on the user's social media activity.

[0055] The response unit can optimize the proposed algorithm by referring to past response data when proposing a countermeasure. The past response data includes, for example, the response date and time, the response content, and the result, but is not limited to such examples. The response unit can propose a similar countermeasure based on the past response data, for example. The response unit can also analyze the past response data and optimize the proposed algorithm. The response unit can also propose an optimal countermeasure by referring to the past response data. This makes it possible to optimize the proposed algorithm based on the past response data.

[0056] The correspondence unit can apply different proposal algorithms depending on the category of the claim when proposing a countermeasure. The proposal algorithm includes, but is not limited to, for example, a recommendation system, an optimization algorithm, and the like. The correspondence unit selects, for example, an optimal proposal algorithm depending on the category of the claim. The correspondence unit can also adjust the proposal algorithm based on the category of the claim. The correspondence unit can also apply different proposal algorithms depending on the category of the claim. This makes it possible to provide an optimal proposal algorithm depending on the category of the claim.

[0057] When proposing a countermeasure, the response unit can propose an optimal countermeasure by taking into consideration the geographical location information of the user. The optimal countermeasure includes, for example, past data, a current situation, and the like, but is not limited to such examples. For example, when the user is in a specific area, the response unit preferentially proposes a countermeasure related to the area. The response unit can also filter related countermeasures based on the geographical location information of the user. The response unit can also propose an optimal countermeasure based on the current location of the user. This makes it possible to provide an optimal countermeasure based on the geographical location information of the user.

[0058] When proposing a countermeasure, the response unit can analyze the user's social media activity and propose a relevant countermeasure. The relevant countermeasure includes, but is not limited to, for example, past data, a current situation, and the like. For example, the response unit analyzes the user's social media activity and preferentially proposes a relevant countermeasure. The response unit can also propose an optimal countermeasure based on the user's comments on social media. The response unit can also filter the relevant countermeasures with reference to the user's social media activity. This makes it possible to provide an optimal countermeasure based on the user's social media activity.

[0059] The support unit can optimize the collection algorithm when collecting evidence by referring to past evidence data. The past evidence data includes, for example, the type of evidence, the collection date and time, and the collection method, but is not limited to such examples. For example, the support unit preferentially collects similar evidence based on the past evidence data. The support unit can also analyze the past evidence data and optimize the collection algorithm. The support unit can also suggest an optimal evidence collection method by referring to the past evidence data. This makes it possible to optimize the collection algorithm based on the past evidence data.

[0060] The support unit can collect optimal evidence in consideration of the user's geographical location information when collecting evidence. The optimal evidence includes, but is not limited to, past data, current conditions, and the like. For example, when the user is in a specific area, the support unit preferentially collects evidence related to the area. The support unit can also filter related evidence based on the user's geographical location information. The support unit can also collect optimal evidence based on the user's current location. This makes it possible to provide optimal evidence based on the user's geographical location information.

[0061] The calculation unit can optimize the calculation algorithm when calculating the benefit by referring to past benefit data. The past benefit data includes, for example, the type of benefit, the calculation date and time, the calculation method, and the like, but is not limited to such examples. For example, the calculation unit prioritizes calculation of similar cases based on the past benefit data. The calculation unit can also analyze the past benefit data and optimize the calculation algorithm. The calculation unit can also suggest an optimal calculation method by referring to the past benefit data. This makes it possible to optimize the calculation algorithm based on the past benefit data.

[0062] The calculation unit can calculate the optimal benefit by taking into account the geographical location information of the user when calculating the benefit. The optimal benefit includes, but is not limited to, for example, the terms of the insurance contract, past data, and the like. For example, when the user is in a specific area, the calculation unit preferentially calculates the benefit related to that area. The calculation unit can also filter the related benefit based on the geographical location information of the user. The calculation unit can also calculate the optimal benefit based on the user's current location. This makes it possible to provide the optimal benefit based on the geographical location information of the user.

[0063] The providing unit can optimize the providing algorithm by referring to past policy data when providing policy information. The past policy data includes, for example, the type of policy, the providing date and time, and the providing method, but is not limited to such examples. For example, the providing unit preferentially provides similar policy information based on the past policy data. The providing unit can also analyze the past policy data and optimize the providing algorithm. The providing unit can also provide optimal policy information by referring to the past policy data. This makes it possible to optimize the providing algorithm based on the past policy data.

[0064] The providing unit can provide optimal policy information in consideration of the geographical location information of the user when providing the policy information. The optimal policy information includes, for example, past data, a current situation, and the like, but is not limited to such examples. For example, when the user is in a specific area, the providing unit can preferentially provide policy information related to the area. The providing unit can also filter related policy information based on the geographical location information of the user. The providing unit can also provide optimal policy information based on the current location of the user. This makes it possible to provide optimal policy information based on the geographical location information of the user.

[0065] The answer unit can optimize the answer algorithm by referring to past answer data when answering. The past answer data includes, for example, the type of answer, the answer date and time, and the answer method, but is not limited to such examples. For example, the answer unit preferentially provides similar answers based on the past answer data. The answer unit can also analyze the past answer data and optimize the answer algorithm. The answer unit can also provide an optimal answer method by referring to the past answer data. This makes it possible to optimize the answer algorithm based on the past answer data.

[0066] The answer unit can provide an optimal answer by taking into consideration the geographical location information of the user when providing an answer. The optimal answer includes, but is not limited to, past data, current conditions, and the like. For example, when the user is in a specific area, the answer unit can preferentially provide answers related to the area. The answer unit can also filter related answers based on the geographical location information of the user. The answer unit can also provide an optimal answer based on the user's current location. This makes it possible to provide an optimal answer based on the geographical location information of the user.

[0067] The protection unit can optimize the protection algorithm by referring to past protection data when protecting information. The past protection data includes, for example, the type of protection, the protection date and time, and the protection method, but is not limited to such examples. For example, the protection unit preferentially protects similar information based on the past protection data. The protection unit can also analyze the past protection data and optimize the protection algorithm. The protection unit can also suggest an optimal information protection method by referring to the past protection data. This makes it possible to optimize the protection algorithm based on the past protection data.

[0068] The protection unit can provide an optimal protection method in consideration of the geographical location information of the user when protecting information. The optimal protection method includes, but is not limited to, past data, current status, and the like. For example, when the user is in a specific area, the protection unit preferentially protects information related to the area. The protection unit can also filter related information based on the geographical location information of the user. The protection unit can also provide an optimal information protection method based on the user's current location. This makes it possible to provide an optimal information protection method based on the geographical location information of the user.

[0069] The function of acquiring location information of the accident site using GPS data can optimize the acquisition algorithm by referring to past location data when acquiring location information. The past location data includes, for example, the type of location information, the acquisition date and time, the acquisition method, and the like, but is not limited to such examples. The function of acquiring location information of the accident site using GPS data, for example, preferentially acquires similar location information based on past location data. In addition, the function of acquiring location information of the accident site using GPS data can also analyze past location data and optimize the acquisition algorithm. In addition, the function of acquiring location information of the accident site using GPS data can also suggest an optimal location information acquisition method by referring to past location data. This makes it possible to optimize the acquisition algorithm based on past location data.

[0070] The function of acquiring location information of the accident site using GPS data can acquire optimal location information in consideration of the geographical location information of the user when acquiring location information. The optimal location information includes, for example, past data, current situation, etc., but is not limited to such examples. For example, when the user is in a specific area, the function of acquiring location information of the accident site using GPS data preferentially acquires location information related to that area. In addition, the function of acquiring location information of the accident site using GPS data can also filter related location information based on the geographical location information of the user. In addition, the function of acquiring location information of the accident site using GPS data can also acquire optimal location information based on the user's current location. This makes it possible to provide optimal location information based on the geographical location information of the user.

[0071] The function of predicting the effect of a countermeasure using AI and proposing an optimal countermeasure can optimize the proposed algorithm by referring to past response data when proposing the countermeasure. The past response data includes, for example, the response date and time, the response content, and the result, but is not limited to such examples. The function of predicting the effect of a countermeasure using AI and proposing an optimal countermeasure can, for example, propose a similar countermeasure based on past response data. In addition, the function of predicting the effect of a countermeasure using AI and proposing an optimal countermeasure can also analyze past response data and optimize the proposed algorithm. In addition, the function of predicting the effect of a countermeasure using AI and proposing an optimal countermeasure can also propose an optimal countermeasure by referring to past response data. This makes it possible to optimize the proposed algorithm based on past response data.

[0072] The function of predicting the effect of a countermeasure using AI and proposing the optimal countermeasure can propose the optimal countermeasure in consideration of the geographical location information of the user when proposing the countermeasure. The optimal countermeasure includes, for example, past data, the current situation, and the like, but is not limited to such examples. The function of predicting the effect of a countermeasure using AI and proposing the optimal countermeasure preferentially proposes countermeasures related to a specific area, for example, when the user is in that area. In addition, the function of predicting the effect of a countermeasure using AI and proposing the optimal countermeasure can also filter related countermeasures based on the geographical location information of the user. In addition, the function of predicting the effect of a countermeasure using AI and proposing the optimal countermeasure can also propose the optimal countermeasure based on the user's current location. In this way, the optimal countermeasure can be provided based on the geographical location information of the user.

[0073] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0074] The reception unit can automatically convert the contents of a user's inquiry into text using voice recognition technology. For example, when an inquiry is received by phone, the reception unit converts the user's utterance into text in real time using voice recognition technology and transmits it to the identification unit. In addition, by using voice recognition technology, it is also possible to automatically detect the language spoken by the user and respond in an appropriate language. Furthermore, it is also possible to use voice recognition technology to extract important keywords from the user's utterance and transmit them to the identification unit. This allows the reception unit to efficiently process the contents of the user's inquiry.

[0075] The search unit can refer to the user's past search history and prioritize searching for highly relevant documents. For example, if there is a history of searching for a similar claim in the past, related documents can be displayed with priority based on that history. The search unit can also analyze the user's search history and automatically complete frequently searched keywords. Furthermore, the search unit can predict the information the user is looking for and suggest related documents based on the past search history. This allows the search unit to efficiently search for documents based on the user's past search history.

[0076] The support unit can suggest an optimal evidence collection method in consideration of the geographic location information of the user. For example, if the user is in a specific area, the support unit can preferentially suggest an evidence collection method related to that area. In addition, the support unit can filter related evidence based on the geographic location information of the user. Furthermore, the support unit can suggest an optimal evidence collection method based on the user's current location. This allows the support unit to efficiently collect evidence based on the geographic location information of the user.

[0077] The providing unit can provide optimal policy information by referring to the user's past policy information provision history. For example, if there is a history of providing similar policy information in the past, related policy information is preferentially displayed based on that history. The providing unit can also analyze the user's provision history and automatically complement frequently provided policy information. Furthermore, the providing unit can predict policy information required by the user based on the past provision history and suggest related information. This allows the providing unit to efficiently provide policy information based on the user's past provision history.

[0078] The protection unit can provide an optimal information protection method in consideration of the geographical location information of the user. For example, when the user is in a specific area, information related to the area is protected preferentially. Also, related information can be filtered based on the geographical location information of the user. Furthermore, an optimal information protection method can be provided based on the current location of the user. This allows the protection unit to efficiently protect information based on the geographical location information of the user.

[0079] The process flow of the first embodiment will be briefly described below.

[0080] Step 1: The reception department accepts inquiries to the insurance company. The inquiries may include telephone, email, online forms, etc. For example, the reception department accepts inquiries by telephone. It may also accept inquiries by email or through an online form. Step 2: The identification unit uses a machine learning model to identify the contents of the claim from the inquiry received by the reception unit. The contents of the claim include insurance claims and confirmation of contract details. The identification unit can identify the contents of the claim using a neural network, a support vector machine, a decision tree, etc. Step 3: The search unit searches for documents related to the claims based on the content of the claims identified by the identification unit. The documents include PDF files, text files, image files, etc. The search unit can search for documents using keyword search, full-text search, metadata search, etc. Step 4: The response department responds to the complaint based on the documents searched by the search department. Responses include phone calls, emails, and visits. For example, the response department responds by phone. It can also respond by email or by visiting.

[0081] (Example 2) The AI ​​assistant system for insurance company claims handling support according to the embodiment of the present invention is a system that accepts inquiries to an insurance company, identifies the contents of the claim, searches for related documents, and responds to the claim. This system has a reception unit that accepts inquiries to an insurance company, and accepts inquiries from a user. Next, there is an identification unit that identifies the contents of the claim from the inquiry accepted by the reception unit, and identifies the contents of the claim using a machine learning model. There is a search unit that searches for related documents based on the identified contents of the claim, and there is a response unit that responds to the claim based on the searched documents. The response unit predicts the effectiveness of the response measures using AI and proposes optimal responses. Furthermore, there is a support unit that supports the collection of details and evidence of the accident based on the documents searched by the search unit, and acquires location information of the accident site using GPS data. There is also a calculation unit that calculates benefits for the accident based on the documents searched by the search unit, and there is a provision unit that provides information on the details of the policy. The provision unit provides customized policy information based on a user profile. Furthermore, there is an answering unit that answers the inquiries accepted by the reception unit, and there is a protection unit that protects customer information using encryption technology. This enables safe handling of customer information. This allows the AI ​​assistant system for insurance company claims handling support to efficiently handle claims for insurance companies.

[0082] The AI ​​assistant system for insurance company claims handling support according to the embodiment includes a reception unit, an identification unit, a search unit, and a response unit. The reception unit receives inquiries to the insurance company. The inquiries include, for example, telephone, email, online form, etc., but are not limited to such examples. The reception unit receives inquiries by telephone, for example. The reception unit can also receive inquiries by email. The reception unit can also receive inquiries through an online form. The identification unit uses a machine learning model to identify the contents of the claim from the inquiry received by the reception unit. The contents of the claim include, for example, insurance claims, confirmation of contract contents, etc., but are not limited to such examples. The identification unit uses, for example, a neural network to identify the contents of the claim. The identification unit can also use a support vector machine to identify the contents of the claim. The identification unit can also use a decision tree to identify the contents of the claim. The search unit searches for documents related to the claim based on the contents of the claim identified by the identification unit. The documents include, for example, PDF files, text files, image files, etc., but are not limited to such examples. The search unit searches for documents using, for example, a keyword search. The search unit can also search for documents using a full-text search. The search unit can also search for documents using a metadata search. The response unit responds to the complaint based on the documents searched by the search unit. The response includes, for example, telephone response, email response, and in-person response, but is not limited to these examples. The response unit responds by telephone, for example. The response unit can also respond by email. The response unit can also respond by visiting. As a result, the AI ​​assistant system for supporting insurance company complaint handling according to the embodiment can efficiently handle complaints at the insurance company.

[0083] The reception unit accepts inquiries to the insurance company. Examples of inquiries include, but are not limited to, telephone, email, and online forms. The reception unit accepts inquiries by telephone, for example. The reception unit can also accept inquiries by email. The reception unit can also accept inquiries through an online form. Specifically, telephone inquiries are automatically converted into text using voice recognition technology and input into the system. Email inquiries are analyzed using natural language processing technology to extract important information. In the online form, information entered by the user is directly imported into the system and processed immediately. This allows the reception unit to respond to various inquiry means and collect information quickly and accurately. Furthermore, the reception unit can automatically set priorities according to the contents of the inquiries and prioritize claims with high urgency. For example, inquiries regarding serious accidents or disasters are immediately notified to the response unit and require a prompt response. On the other hand, inquiries regarding confirmation or changes to general contract contents are handled according to the normal processing flow. This allows the reception unit to efficiently and effectively handle inquiries and smoothly advance the initial stage of claims handling by the insurance company.

[0084] The identification unit uses a machine learning model to identify the contents of the claim from the inquiry received by the reception unit. The contents of the claim include, for example, insurance claims, confirmation of contract details, etc., but are not limited to such examples. The identification unit uses, for example, a neural network to identify the contents of the claim. The identification unit can also use a support vector machine to identify the contents of the claim. The identification unit can also use a decision tree to identify the contents of the claim. Specifically, the neural network learns a large amount of past claim data and classifies the contents of the claim with high accuracy for a new inquiry. The support vector machine identifies the contents of the claim by vectorizing the features of the claim and finding the optimal classification boundary. The decision tree hierarchically analyzes the contents of the inquiry and identifies the most appropriate claim category. This allows the identification unit to quickly and accurately identify the contents of the inquiry by making full use of various machine learning algorithms. Furthermore, the identification unit can continuously learn and improve the accuracy of the model. For example, the model can be retrained using newly received claim data to respond to the latest trends and patterns. The identification unit can also use an anomaly detection algorithm to detect claims with unusual patterns early and issue an alert when special measures are required. This enables the identification department to improve the efficiency of the insurance company's complaint handling and increase customer satisfaction.

[0085] The search unit searches for documents related to the claim based on the content of the claim identified by the identification unit. The documents include, for example, PDF files, text files, image files, etc., but are not limited to such examples. The search unit searches for documents using, for example, a keyword search. The search unit can also search for documents using a full-text search. The search unit can also search for documents using a metadata search. Specifically, in the keyword search, important keywords related to the content of the claim are extracted and related documents are searched based on the extracted keywords. In the full-text search, the entire document is searched to comprehensively find information related to the claim. In the metadata search, metadata such as the creation date, creator, and category of the document are used to efficiently search for documents that match specific conditions. This allows the search unit to quickly and accurately find documents related to the claim by making full use of various search methods. Furthermore, the search unit can prioritize search results and display the most relevant documents at the top. For example, documents related to similar past claims and important information related to a specific insurance policy are preferentially displayed. Furthermore, the search unit can optimize the search algorithm based on the user's search history and feedback, and continuously improve search accuracy. This enables the search unit to assist insurance companies in handling claims and to respond quickly and appropriately.

[0086] The response department responds to the complaint based on the documents searched by the search department. The responses include, but are not limited to, telephone responses, email responses, and visit responses. For example, the response department responds by telephone. The response department can also respond by email. The response department can also respond by visiting. Specifically, in telephone responses, the AI ​​automatically analyzes the contents of the complaint and provides an appropriate answer. In email responses, the AI ​​automatically generates a reply email and responds quickly. In visit responses, the AI ​​automatically adjusts the visit schedule and notifies the person in charge. This allows the response department to respond to complaints quickly and appropriately by making full use of various response means. Furthermore, the response department can record the response history and use it for future complaint responses. For example, the response department can propose the optimal response method for similar complaints based on the past response history. In addition, the response department can collect customer feedback and continuously improve the quality of response. For example, the response department can conduct a customer satisfaction survey and review the response process based on the feedback. This allows the response department to streamline the insurance company's complaint response and improve customer satisfaction.

[0087] The search unit includes a support unit that supports the collection of details and evidence of the accident based on the searched documents. The support unit supports the collection of details and evidence of the accident based on the documents searched by the search unit. Details of the accident include, for example, the date and time, location, and circumstances of the accident, but are not limited to such examples. The support unit records, for example, the date and time of the accident. The support unit can also record the location of the accident. The support unit can also record the circumstances of the accident. The collection of evidence includes, for example, taking photographs, witness testimony, and document collection, but are not limited to such examples. The support unit takes, for example, photographs of the accident scene. The support unit can also collect witness testimony. The support unit can also collect documents related to the accident. This makes it possible to efficiently collect details and evidence of the accident.

[0088] The search unit includes a calculation unit that calculates a benefit for an accident based on the searched document. The calculation unit calculates a benefit for an accident based on the document searched by the search unit. The benefit includes, for example, medical expenses, repair costs, and compensation, but is not limited to such examples. The calculation unit calculates, for example, medical expenses. The calculation unit can also calculate repair costs. The calculation unit can also calculate compensation. This allows the calculation of the benefit for an accident to be performed efficiently.

[0089] The search unit includes a provision unit that provides information on policy details based on the searched document. The provision unit provides information on policy details based on the document searched by the search unit. The policy details include, for example, insurance contract clauses, special provisions, etc., but are not limited to such examples. The provision unit provides, for example, the insurance contract clauses. The provision unit can also provide special provisions. This makes it possible to efficiently provide detailed policy information.

[0090] The reception unit includes a reply unit that replies to the received inquiry. The reply unit replies to the inquiry received by the reception unit. Responses include, for example, telephone replies, email replies, written replies, and the like, but are not limited to these examples. The reply unit replies, for example, by telephone. The reply unit can also reply by email. The reply unit can also reply in writing. This allows for efficient replying to inquiries.

[0091] The system includes a protection unit that protects the customer information using an encryption technology. The protection unit protects the customer information using an encryption technology. The encryption technology includes, but is not limited to, AES, RSA, TLS, and the like. The protection unit encrypts the customer information using, for example, AES. The protection unit can also encrypt the customer information using RSA. The protection unit can also encrypt the customer information using TLS. This allows the customer information to be handled safely.

[0092] The identification unit can identify the content of the claim by using a machine learning model. The machine learning model includes, but is not limited to, for example, a neural network, a support vector machine, a decision tree, and the like. The identification unit can identify the content of the claim by using, for example, a neural network. The identification unit can also identify the content of the claim by using a support vector machine. The identification unit can also identify the content of the claim by using a decision tree. This makes it possible to identify the content of the claim with high accuracy.

[0093] The providing unit can provide customized policy information based on a user profile. The user profile includes, for example, age, gender, past behavior history, and the like, but is not limited to such examples. The providing unit provides customized policy information based on, for example, age. The providing unit can also provide customized policy information based on gender. The providing unit can also provide customized policy information based on past behavior history. This makes it possible to provide optimal policy information for the user.

[0094] The support unit can acquire location information of the accident site using GPS data. GPS data includes, for example, location information of a smartphone, an in-vehicle GPS system, and the like, but is not limited to such examples. The support unit acquires location information of the accident site using, for example, location information of a smartphone. The support unit can also acquire location information of the accident site using an in-vehicle GPS system. This makes it possible to accurately acquire location information of the accident site. 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.

[0095] The response unit can predict the effect of the countermeasure using AI and propose the optimal countermeasure. AI includes, but is not limited to, for example, deep learning and reinforcement learning. The response unit can predict the effect of the countermeasure using, for example, deep learning. The response unit can also predict the effect of the countermeasure using reinforcement learning. The response unit can also predict the effect of the countermeasure using generation AI. This makes it possible to propose the optimal countermeasure.

[0096] The reception unit can estimate the user's emotion and adjust the reception method of the inquiry based on the estimated user's emotion. The estimation of emotion includes, for example, voice analysis, facial expression recognition, text analysis, etc., but is not limited to such examples. The reception unit estimates the user's emotion using, for example, voice analysis. The reception unit can also estimate the user's emotion using facial expression recognition. The reception unit can also estimate the user's emotion using text analysis. This makes it possible to provide an optimal reception method according to the user's emotion. The estimation of 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.

[0097] The reception unit can analyze past inquiry history and select the optimal reception method. The past inquiry history includes, for example, inquiry date and time, contents, and response results, but is not limited to these examples. For example, the reception unit automatically displays frequently inquired contents as candidates based on the past inquiry history. The reception unit can also preferentially suggest reception methods (voice, text, etc.) that have been used in the past. The reception unit can also predict and suggest the reception method to be used in a specific time period from the past inquiry history. This makes it possible to provide the optimal reception method based on the past inquiry history.

[0098] The reception unit can perform filtering based on the user's current situation and field of interest when receiving an inquiry. The current situation includes, for example, a current location, a current activity situation, and the like, but is not limited to such examples. The field of interest includes, for example, hobbies, topics of interest, and the like, but is not limited to such examples. For example, when the user inputs the current situation, the reception unit preferentially displays related inquiry contents. In addition, the reception unit can also filter related inquiry contents based on the user's field of interest. In addition, the reception unit can also suggest optimal inquiry contents based on the user's current situation and field of interest. This makes it possible to provide optimal inquiry contents according to the user's situation and field of interest.

[0099] The reception unit can estimate the user's emotion and determine the priority of the received inquiry based on the estimated user's emotion. The priority includes, for example, urgency, importance, etc., but is not limited to such examples. For example, when the user is in an emergency situation, the reception unit processes the inquiry with the highest priority. In addition, when the user is relaxed, the reception unit can also process the inquiry with normal priority. In addition, when the user is feeling anxious, the reception unit can also raise the priority to respond quickly. In this way, the inquiry can be processed with the optimal priority according to the user'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.

[0100] The reception unit can preferentially receive inquiries with high relevance in consideration of the geographical location information of the user when receiving an inquiry. The geographical location information includes, but is not limited to, for example, GPS data, address information, and the like. For example, when the user is in a specific area, the reception unit preferentially receives inquiries related to the area. The reception unit can also filter related inquiry contents based on the geographical location information of the user. The reception unit can also suggest optimal inquiry contents based on the user's current location. This makes it possible to provide optimal inquiry contents based on the geographical location information of the user.

[0101] The reception unit can analyze the user's social media activity when receiving an inquiry and receive related inquiries. Social media activity includes, but is not limited to, for example, the content of posts, the number of likes, the number of followers, and the like. For example, the reception unit analyzes the user's social media activity and preferentially receives related inquiry content. The reception unit can also suggest optimal inquiry content based on the user's comments on social media. The reception unit can also filter related inquiry content by referring to the user's social media activity. This makes it possible to provide optimal inquiry content based on the user's social media activity.

[0102] The identification unit can estimate the user's emotion and adjust the method of identifying the complaint content based on the estimated user's emotion. The method of identifying the complaint content includes, for example, text analysis, voice analysis, etc., but is not limited to such examples. For example, when the user is stressed, the identification unit identifies the complaint content in a simple question format. Also, when the user is relaxed, the identification unit can identify the complaint content in a detailed question format. Also, when the user is in a hurry, the identification unit can prioritize voice input and quickly identify the complaint content. This makes it possible to provide an optimal method of identifying the complaint content according to the user'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.

[0103] When identifying the content of a complaint, the identification unit can improve the accuracy of identification by referring to past complaint data. Past complaint data includes, for example, the date and time of the complaint, the content, and the response results, but is not limited to such examples. For example, the identification unit identifies similar complaint content based on the past complaint data. The identification unit can also analyze the past complaint data to improve the accuracy of identification. The identification unit can also identify the optimal complaint content by referring to the past complaint data. This makes it possible to improve the accuracy of identification of the complaint content based on the past complaint data.

[0104] The identification unit can apply different identification algorithms depending on the category of the claim when identifying the content of the claim. The category of the claim includes, but is not limited to, for example, an insurance claim, confirmation of the contract content, etc. The identification unit selects, for example, an optimal identification algorithm depending on the category of the claim. The identification unit can also adjust the identification algorithm based on the category of the claim. The identification unit can also apply different identification algorithms depending on the category of the claim. This makes it possible to provide an optimal identification algorithm depending on the category of the claim.

[0105] The identification unit can estimate the user's emotion and determine the priority of the identified complaint contents based on the estimated user's emotion. The priority of the complaint contents includes, for example, urgency and importance, but is not limited to such examples. For example, when the user is in an emergency situation, the identification unit identifies the complaint contents with the highest priority. Also, when the user is relaxed, the identification unit can identify the complaint contents with normal priority. Also, when the user is feeling anxious, the identification unit can raise the priority to respond quickly. This makes it possible to identify the complaint contents with the optimal priority according to the user'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.

[0106] When identifying the complaint content, the identification unit can preferentially identify a complaint with high relevance by taking into consideration the geographical location information of the user. Complaints with high relevance include, but are not limited to, past complaint data, current situations, and the like. For example, when the user is in a specific area, the identification unit preferentially identifies complaint content related to the area. The identification unit can also filter related complaint content based on the geographical location information of the user. The identification unit can also identify optimal complaint content based on the user's current location. This makes it possible to provide optimal complaint content based on the geographical location information of the user.

[0107] When identifying the complaint content, the identification unit can analyze the user's social media activity and identify related complaints. Examples of related complaints include, but are not limited to, past complaint data, current situations, and the like. For example, the identification unit can analyze the user's social media activity and preferentially identify related complaint content. The identification unit can also identify optimal complaint content based on the user's social media comments. The identification unit can also filter the related complaint content with reference to the user's social media activity. This makes it possible to provide optimal complaint content based on the user's social media activity.

[0108] The search unit can estimate the user's emotion and adjust the document search method based on the estimated user's emotion. The document search method includes, for example, keyword search, full-text search, and the like, but is not limited to such examples. For example, when the user is stressed, the search unit provides a simple search interface and minimizes the search procedure. In addition, when the user is relaxed, the search unit can provide detailed search options and suggest a customizable search method. In addition, when the user is in a hurry, the search unit can prioritize voice search and quickly search for documents. This makes it possible to provide an optimal search method according to the user'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.

[0109] When searching for a document, the search unit can optimize a search algorithm by referring to past search data. The past search data includes, for example, search date and time, search keywords, search results, etc., but is not limited to such examples. For example, the search unit preferentially searches for similar documents based on the past search data. The search unit can also analyze the past search data and optimize the search algorithm. The search unit can also provide optimal search results by referring to the past search data. This makes it possible to optimize the search algorithm based on the past search data.

[0110] The search unit may apply different search algorithms depending on the claim category when searching the document. The search algorithms include, but are not limited to, TF-IDF, BM25, etc. The search unit may select an optimal search algorithm depending on, for example, the claim category. The search unit may also adjust the search algorithm based on the claim category. The search unit may also apply different search algorithms depending on the claim category. This makes it possible to provide an optimal search algorithm depending on the claim category.

[0111] The search unit can estimate the user's emotion and determine the priority of documents to be searched based on the estimated user's emotion. The priority of documents includes, for example, relevance and importance, but is not limited to such examples. For example, when the user is in an emergency situation, the search unit searches for related documents with the highest priority. In addition, when the user is relaxed, the search unit can also search for documents with normal priority. In addition, when the user is feeling anxious, the search unit can also raise the priority to respond quickly. This makes it possible to search for documents with optimal priority according to the user's emotion. The emotion estimation is realized using, for example, an emotion estimation function using 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.

[0112] When searching for a document, the search unit can preferentially search for highly relevant documents in consideration of the geographical location information of the user. Highly relevant documents include, but are not limited to, past search data, current situations, and the like. For example, when the user is in a specific area, the search unit preferentially searches for documents related to the area. The search unit can also filter related documents based on the geographical location information of the user. The search unit can also search for the most suitable document based on the user's current location. This makes it possible to provide the most suitable document based on the geographical location information of the user.

[0113] When searching for a document, the search unit can analyze the user's social media activity and search for related documents. Examples of related documents include, but are not limited to, past search data, current status, and the like. For example, the search unit analyzes the user's social media activity and searches for related documents preferentially. The search unit can also search for optimal documents based on the user's comments on social media. The search unit can also filter the relevant documents with reference to the user's social media activity. This makes it possible to provide optimal documents based on the user's social media activity.

[0114] The response unit can estimate the user's emotion and adjust the countermeasure suggestion method based on the estimated user's emotion. The countermeasure suggestion method includes, for example, an AI algorithm, past data, and the like, but is not limited to such examples. For example, the response unit can suggest a simple countermeasure when the user is stressed. The response unit can also suggest a detailed countermeasure when the user is relaxed. The response unit can also suggest a countermeasure that can be quickly implemented when the user is in a hurry. This makes it possible to provide an optimal countermeasure according to the user'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.

[0115] The response unit can optimize the proposed algorithm by referring to past response data when proposing a countermeasure. The past response data includes, for example, the response date and time, the response content, and the result, but is not limited to such examples. The response unit can propose a similar countermeasure based on the past response data, for example. The response unit can also analyze the past response data and optimize the proposed algorithm. The response unit can also propose an optimal countermeasure by referring to the past response data. This makes it possible to optimize the proposed algorithm based on the past response data.

[0116] The correspondence unit can apply different proposal algorithms depending on the category of the claim when proposing a countermeasure. The proposal algorithm includes, but is not limited to, for example, a recommendation system, an optimization algorithm, and the like. The correspondence unit selects, for example, an optimal proposal algorithm depending on the category of the claim. The correspondence unit can also adjust the proposal algorithm based on the category of the claim. The correspondence unit can also apply different proposal algorithms depending on the category of the claim. This makes it possible to provide an optimal proposal algorithm depending on the category of the claim.

[0117] The response unit can estimate the user's emotion and determine the priority of countermeasures to be proposed based on the estimated user's emotion. The priority of countermeasures includes, for example, urgency and importance, but is not limited to such examples. For example, when the user is in an emergency situation, the response unit proposes a countermeasure with the highest priority. In addition, when the user is relaxed, the response unit can also propose a countermeasure with normal priority. In addition, when the user is feeling anxious, the response unit can also raise the priority to respond quickly. In this way, it is possible to provide a countermeasure with an optimal priority according to the user's emotion. The estimation of 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.

[0118] When proposing a countermeasure, the response unit can propose an optimal countermeasure by taking into consideration the geographical location information of the user. The optimal countermeasure includes, for example, past data, a current situation, and the like, but is not limited to such examples. For example, when the user is in a specific area, the response unit preferentially proposes a countermeasure related to the area. The response unit can also filter related countermeasures based on the geographical location information of the user. The response unit can also propose an optimal countermeasure based on the current location of the user. This makes it possible to provide an optimal countermeasure based on the geographical location information of the user.

[0119] When proposing a countermeasure, the response unit can analyze the user's social media activity and propose a relevant countermeasure. The relevant countermeasure includes, but is not limited to, for example, past data, a current situation, and the like. For example, the response unit analyzes the user's social media activity and preferentially proposes a relevant countermeasure. The response unit can also propose an optimal countermeasure based on the user's comments on social media. The response unit can also filter the relevant countermeasures with reference to the user's social media activity. This makes it possible to provide an optimal countermeasure based on the user's social media activity.

[0120] The support unit can estimate the user's emotion and adjust the evidence collection support method based on the estimated user's emotion. The evidence collection support method includes, for example, taking a photograph, witness testimony, document collection, etc., but is not limited to such examples. For example, the support unit provides a simple evidence collection procedure when the user is stressed. The support unit can also provide a detailed evidence collection procedure when the user is relaxed. The support unit can also suggest a method for quickly collecting evidence when the user is in a hurry. This makes it possible to provide an optimal evidence collection method according to the user'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.

[0121] The support unit can optimize the collection algorithm when collecting evidence by referring to past evidence data. The past evidence data includes, for example, the type of evidence, the collection date and time, and the collection method, but is not limited to such examples. For example, the support unit preferentially collects similar evidence based on the past evidence data. The support unit can also analyze the past evidence data and optimize the collection algorithm. The support unit can also suggest an optimal evidence collection method by referring to the past evidence data. This makes it possible to optimize the collection algorithm based on the past evidence data.

[0122] The support unit can estimate the user's emotion and determine the priority of evidence to be collected based on the estimated user's emotion. The priority of evidence includes, for example, importance and relevance, but is not limited to such examples. For example, when the user is in an emergency situation, the support unit performs evidence collection with the highest priority. Also, when the user is relaxed, the support unit can also collect evidence with normal priority. Also, when the user feels anxious, the support unit can raise the priority to respond quickly. This makes it possible to collect evidence with optimal priority according to the user'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.

[0123] The support unit can collect optimal evidence in consideration of the user's geographical location information when collecting evidence. The optimal evidence includes, but is not limited to, past data, current conditions, and the like. For example, when the user is in a specific area, the support unit preferentially collects evidence related to the area. The support unit can also filter related evidence based on the user's geographical location information. The support unit can also collect optimal evidence based on the user's current location. This makes it possible to provide optimal evidence based on the user's geographical location information.

[0124] The calculation unit can estimate the user's emotion and adjust the calculation method of the benefit based on the estimated user's emotion. The calculation method of the benefit includes, for example, but is not limited to, the clauses of the insurance contract, past data, etc. For example, the calculation unit provides a simple calculation procedure when the user is stressed. The calculation unit can also provide a detailed calculation procedure when the user is relaxed. The calculation unit can also suggest a method for quickly calculating the benefit when the user is in a hurry. This makes it possible to provide an optimal benefit calculation method according to the user'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.

[0125] The calculation unit can optimize the calculation algorithm when calculating the benefit by referring to past benefit data. The past benefit data includes, for example, the type of benefit, the calculation date and time, the calculation method, and the like, but is not limited to such examples. For example, the calculation unit prioritizes calculation of similar cases based on the past benefit data. The calculation unit can also analyze the past benefit data and optimize the calculation algorithm. The calculation unit can also suggest an optimal calculation method by referring to the past benefit data. This makes it possible to optimize the calculation algorithm based on the past benefit data.

[0126] The calculation unit can estimate the user's emotion and determine the priority of the benefit to be calculated based on the estimated user's emotion. The priority of the benefit includes, for example, urgency, importance, etc., but is not limited to such examples. For example, when the user is in an emergency situation, the calculation unit performs the calculation of the benefit with the highest priority. In addition, when the user is relaxed, the calculation unit can also calculate the benefit with normal priority. In addition, when the user is feeling anxious, the calculation unit can also raise the priority to respond quickly. In this way, the benefit can be calculated with the optimal priority according to the user'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.

[0127] The calculation unit can calculate the optimal benefit by taking into account the geographical location information of the user when calculating the benefit. The optimal benefit includes, but is not limited to, for example, the terms of the insurance contract, past data, and the like. For example, when the user is in a specific area, the calculation unit preferentially calculates the benefit related to that area. The calculation unit can also filter the related benefit based on the geographical location information of the user. The calculation unit can also calculate the optimal benefit based on the user's current location. This makes it possible to provide the optimal benefit based on the geographical location information of the user.

[0128] The providing unit can estimate the user's emotion and adjust the method of providing the policy information based on the estimated user's emotion. The method of providing the policy information includes, for example, email, written document, online, etc., but is not limited to such examples. For example, the providing unit provides simple policy information when the user is stressed. The providing unit can also provide detailed policy information when the user is relaxed. The providing unit can also suggest a method for quickly providing policy information when the user is in a hurry. This makes it possible to provide optimal policy information according to the user'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.

[0129] The providing unit can optimize the providing algorithm by referring to past policy data when providing policy information. The past policy data includes, for example, the type of policy, the providing date and time, and the providing method, but is not limited to such examples. For example, the providing unit preferentially provides similar policy information based on the past policy data. The providing unit can also analyze the past policy data and optimize the providing algorithm. The providing unit can also provide optimal policy information by referring to the past policy data. This makes it possible to optimize the providing algorithm based on the past policy data.

[0130] The providing unit can estimate the user's emotion and determine the priority of the policy information to be provided based on the estimated user's emotion. The priority of the policy information includes, for example, importance and relevance, but is not limited to such examples. For example, when the user is in an emergency situation, the providing unit provides the policy information with the highest priority. In addition, when the user is relaxed, the providing unit can also provide the policy information with normal priority. In addition, when the user is feeling anxious, the providing unit can also raise the priority to respond quickly. This makes it possible to provide the policy information with an optimal priority according to the user'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.

[0131] The providing unit can provide optimal policy information in consideration of the geographical location information of the user when providing the policy information. The optimal policy information includes, for example, past data, a current situation, and the like, but is not limited to such examples. For example, when the user is in a specific area, the providing unit can preferentially provide policy information related to the area. The providing unit can also filter related policy information based on the geographical location information of the user. The providing unit can also provide optimal policy information based on the current location of the user. This makes it possible to provide optimal policy information based on the geographical location information of the user.

[0132] The answering unit can estimate the user's emotion and adjust the answering method based on the estimated user's emotion. The answering method includes, for example, telephone, email, written document, etc., but is not limited to such examples. For example, the answering unit provides a simple answering method when the user is stressed. The answering unit can also provide a detailed answering method when the user is relaxed. The answering unit can also suggest a method that allows the user to answer quickly when the user is in a hurry. This makes it possible to provide an optimal answering method according to the user'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.

[0133] The answer unit can optimize the answer algorithm by referring to past answer data when answering. The past answer data includes, for example, the type of answer, the answer date and time, and the answer method, but is not limited to such examples. For example, the answer unit preferentially provides similar answers based on the past answer data. The answer unit can also analyze the past answer data and optimize the answer algorithm. The answer unit can also provide an optimal answer method by referring to the past answer data. This makes it possible to optimize the answer algorithm based on the past answer data.

[0134] The answering unit can estimate the user's emotion and determine the priority of the answer based on the estimated user's emotion. The priority of the answer includes, for example, urgency, importance, etc., but is not limited to such examples. For example, when the user is in an emergency situation, the answering unit gives the answer with the highest priority. Also, when the user is relaxed, the answering unit can also give the answer with normal priority. Also, when the user is feeling anxious, the answering unit can raise the priority to respond quickly. This makes it possible to provide an answer with an optimal priority according to the user's emotion. The emotion estimation is realized using, for example, an emotion estimation function using 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.

[0135] The answer unit can provide an optimal answer by taking into consideration the geographical location information of the user when providing an answer. The optimal answer includes, but is not limited to, past data, current conditions, and the like. For example, when the user is in a specific area, the answer unit can preferentially provide answers related to the area. The answer unit can also filter related answers based on the geographical location information of the user. The answer unit can also provide an optimal answer based on the user's current location. This makes it possible to provide an optimal answer based on the geographical location information of the user.

[0136] The protection unit can estimate the user's emotion and adjust the information protection method based on the estimated user's emotion. The information protection method includes, for example, a simple information protection procedure, a detailed information protection procedure, a quick information protection procedure, and the like, but is not limited to such examples. For example, the protection unit provides a simple information protection procedure when the user is stressed. The protection unit can also provide a detailed information protection procedure when the user is relaxed. The protection unit can also suggest a method that can quickly protect information when the user is in a hurry. This makes it possible to provide an optimal information protection method according to the user'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.

[0137] The protection unit can optimize the protection algorithm by referring to past protection data when protecting information. The past protection data includes, for example, the type of protection, the protection date and time, and the protection method, but is not limited to such examples. For example, the protection unit preferentially protects similar information based on the past protection data. The protection unit can also analyze the past protection data and optimize the protection algorithm. The protection unit can also suggest an optimal information protection method by referring to the past protection data. This makes it possible to optimize the protection algorithm based on the past protection data.

[0138] The protection unit can estimate the user's emotion and determine the priority of information to be protected based on the estimated user's emotion. The priority of information includes, for example, importance and relevance, but is not limited to such examples. For example, when the user is in an emergency situation, the protection unit gives top priority to information protection. In addition, when the user is relaxed, the protection unit can also protect information with normal priority. In addition, when the user feels anxious, the protection unit can also raise the priority to respond quickly. This makes it possible to protect information with optimal priority according to the user'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.

[0139] The protection unit can provide an optimal protection method in consideration of the geographical location information of the user when protecting information. The optimal protection method includes, but is not limited to, past data, current status, and the like. For example, when the user is in a specific area, the protection unit preferentially protects information related to the area. The protection unit can also filter related information based on the geographical location information of the user. The protection unit can also provide an optimal information protection method based on the user's current location. This makes it possible to provide an optimal information protection method based on the geographical location information of the user.

[0140] The function of acquiring location information of the accident site using GPS data can estimate the user's emotion and adjust the method of acquiring location information based on the estimated emotion of the user. The method of acquiring location information includes, for example, a simple location information acquisition procedure, a detailed location information acquisition procedure, a quick location information acquisition procedure, and the like, but is not limited to such examples. The function of acquiring location information of the accident site using GPS data can provide a simple location information acquisition procedure, for example, when the user is stressed. In addition, the function of acquiring location information of the accident site using GPS data can also provide a detailed location information acquisition procedure, when the user is relaxed. In addition, the function of acquiring location information of the accident site using GPS data can also suggest a method that can quickly acquire location information, when the user is in a hurry. This makes it possible to provide an optimal location information acquisition method according to the user's emotion. The estimation of emotion is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0141] The function of acquiring location information of the accident site using GPS data can optimize the acquisition algorithm by referring to past location data when acquiring location information. The past location data includes, for example, the type of location information, the acquisition date and time, the acquisition method, and the like, but is not limited to such examples. The function of acquiring location information of the accident site using GPS data, for example, preferentially acquires similar location information based on past location data. In addition, the function of acquiring location information of the accident site using GPS data can also analyze past location data and optimize the acquisition algorithm. In addition, the function of acquiring location information of the accident site using GPS data can also suggest an optimal location information acquisition method by referring to past location data. This makes it possible to optimize the acquisition algorithm based on past location data.

[0142] The function of acquiring location information of the accident site using GPS data can estimate the user's emotion and determine the priority of the location information to be acquired based on the estimated emotion of the user. The priority of the location information includes, for example, importance and relevance, but is not limited to such examples. The function of acquiring location information of the accident site using GPS data can acquire location information with the highest priority, for example, when the user is in an emergency situation. In addition, the function of acquiring location information of the accident site using GPS data can also acquire location information with normal priority when the user is relaxed. In addition, the function of acquiring location information of the accident site using GPS data can also raise the priority to respond quickly when the user feels anxious. This makes it possible to acquire location information with optimal priority according to the emotion of the user. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0143] The function of acquiring location information of the accident site using GPS data can acquire optimal location information in consideration of the geographical location information of the user when acquiring location information. The optimal location information includes, for example, past data, current situation, etc., but is not limited to such examples. For example, when the user is in a specific area, the function of acquiring location information of the accident site using GPS data preferentially acquires location information related to that area. In addition, the function of acquiring location information of the accident site using GPS data can also filter related location information based on the geographical location information of the user. In addition, the function of acquiring location information of the accident site using GPS data can also acquire optimal location information based on the user's current location. This makes it possible to provide optimal location information based on the geographical location information of the user.

[0144] The function of predicting the effect of a countermeasure using AI and proposing an optimal countermeasure can estimate the user's emotion and adjust the method of proposing the countermeasure based on the estimated emotion of the user. The method of proposing the countermeasure includes, for example, a simple countermeasure, a detailed countermeasure, a quick countermeasure, and the like, but is not limited to such examples. The function of predicting the effect of a countermeasure using AI and proposing an optimal countermeasure can, for example, propose a simple countermeasure when the user is stressed. In addition, the function of predicting the effect of a countermeasure using AI and proposing an optimal countermeasure can also propose a detailed countermeasure when the user is relaxed. In addition, the function of predicting the effect of a countermeasure using AI and proposing an optimal countermeasure can also propose a countermeasure that can be quickly implemented when the user is in a hurry. This makes it possible to provide an optimal countermeasure according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0145] The function of predicting the effect of a countermeasure using AI and proposing an optimal countermeasure can optimize the proposed algorithm by referring to past response data when proposing the countermeasure. The past response data includes, for example, the response date and time, the response content, and the result, but is not limited to such examples. The function of predicting the effect of a countermeasure using AI and proposing an optimal countermeasure can, for example, propose a similar countermeasure based on past response data. In addition, the function of predicting the effect of a countermeasure using AI and proposing an optimal countermeasure can also analyze past response data and optimize the proposed algorithm. In addition, the function of predicting the effect of a countermeasure using AI and proposing an optimal countermeasure can also propose an optimal countermeasure by referring to past response data. This makes it possible to optimize the proposed algorithm based on past response data.

[0146] The function of predicting the effect of a countermeasure using AI and proposing the optimal countermeasure can estimate the user's emotion and determine the priority of the countermeasure to be proposed based on the estimated emotion of the user. The priority of the countermeasure includes, for example, urgency and importance, but is not limited to such examples. The function of predicting the effect of a countermeasure using AI and proposing the optimal countermeasure proposes the countermeasure with the highest priority, for example, when the user is in an emergency situation. In addition, the function of predicting the effect of a countermeasure using AI and proposing the optimal countermeasure can also propose the countermeasure with normal priority when the user is relaxed. In addition, the function of predicting the effect of a countermeasure using AI and proposing the optimal countermeasure can also raise the priority to respond quickly when the user feels anxious. In this way, it is possible to provide the countermeasure with the optimal priority according to the emotion of the user. 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.

[0147] The function of predicting the effect of a countermeasure using AI and proposing the optimal countermeasure can propose the optimal countermeasure in consideration of the geographical location information of the user when proposing the countermeasure. The optimal countermeasure includes, for example, past data, the current situation, and the like, but is not limited to such examples. The function of predicting the effect of a countermeasure using AI and proposing the optimal countermeasure preferentially proposes countermeasures related to a specific area, for example, when the user is in that area. In addition, the function of predicting the effect of a countermeasure using AI and proposing the optimal countermeasure can also filter related countermeasures based on the geographical location information of the user. In addition, the function of predicting the effect of a countermeasure using AI and proposing the optimal countermeasure can also propose the optimal countermeasure based on the user's current location. In this way, the optimal countermeasure can be provided based on the geographical location information of the user.

[0148] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0149] The reception unit can automatically convert the contents of a user's inquiry into text using voice recognition technology. For example, when an inquiry is received by phone, the reception unit converts the user's utterance into text in real time using voice recognition technology and transmits it to the identification unit. In addition, by using voice recognition technology, it is also possible to automatically detect the language spoken by the user and respond in an appropriate language. Furthermore, it is also possible to use voice recognition technology to extract important keywords from the user's utterance and transmit them to the identification unit. This allows the reception unit to efficiently process the contents of the user's inquiry.

[0150] The identification unit can estimate the user's emotions and adjust the method of identifying the complaint content based on the estimated user's emotions. For example, if the user is stressed, the complaint content can be identified in the form of a simple question. If the user is relaxed, the complaint content can also be identified in the form of a detailed question. Furthermore, if the user is in a hurry, voice input can be prioritized to quickly identify the complaint content. This makes it possible to provide an optimal method of identifying the complaint content according to the user's emotions.

[0151] The search unit can refer to the user's past search history and prioritize searching for highly relevant documents. For example, if there is a history of searching for a similar claim in the past, related documents can be displayed with priority based on that history. The search unit can also analyze the user's search history and automatically complete frequently searched keywords. Furthermore, the search unit can predict the information the user is looking for and suggest related documents based on the past search history. This allows the search unit to efficiently search for documents based on the user's past search history.

[0152] The response unit can estimate the user's emotions and adjust the method of proposing countermeasures based on the estimated user's emotions. For example, if the user is feeling stressed, a simple countermeasure can be proposed. If the user is relaxed, a detailed countermeasure can be proposed. Furthermore, if the user is in a hurry, a countermeasure that can be quickly implemented can be proposed. In this way, it is possible to provide the optimal countermeasure according to the user's emotions.

[0153] The support unit can suggest an optimal evidence collection method in consideration of the geographic location information of the user. For example, if the user is in a specific area, the support unit can preferentially suggest an evidence collection method related to that area. In addition, the support unit can filter related evidence based on the geographic location information of the user. Furthermore, the support unit can suggest an optimal evidence collection method based on the user's current location. This allows the support unit to efficiently collect evidence based on the geographic location information of the user.

[0154] The calculation unit can estimate the user's emotions and adjust the calculation method of the benefit based on the estimated user's emotions. For example, if the user is stressed, a simple calculation procedure can be provided. Also, if the user is relaxed, a detailed calculation procedure can be provided. Furthermore, if the user is in a hurry, a method for quickly calculating the benefit can be proposed. In this way, it is possible to provide an optimal benefit calculation method according to the user's emotions.

[0155] The providing unit can provide optimal policy information by referring to the user's past policy information provision history. For example, if there is a history of providing similar policy information in the past, related policy information is preferentially displayed based on that history. The providing unit can also analyze the user's provision history and automatically complement frequently provided policy information. Furthermore, the providing unit can predict policy information required by the user based on the past provision history and suggest related information. This allows the providing unit to efficiently provide policy information based on the user's past provision history.

[0156] The answering unit can estimate the user's emotions and adjust the answering method based on the estimated user's emotions. For example, if the user is stressed, a simple answering method can be provided. Also, if the user is relaxed, a detailed answering method can be provided. Furthermore, if the user is in a hurry, a method that allows a quick answer can be suggested. In this way, it is possible to provide the optimal answering method according to the user's emotions.

[0157] The protection unit can provide an optimal information protection method in consideration of the geographical location information of the user. For example, when the user is in a specific area, information related to the area is protected preferentially. Also, related information can be filtered based on the geographical location information of the user. Furthermore, an optimal information protection method can be provided based on the current location of the user. This allows the protection unit to efficiently protect information based on the geographical location information of the user.

[0158] The function for acquiring location information of the accident site using GPS data can estimate the user's emotions and adjust the method for acquiring location information based on the estimated user's emotions. For example, if the user is stressed, a simple procedure for acquiring location information can be provided. Also, if the user is relaxed, a detailed procedure for acquiring location information can be provided. Furthermore, if the user is in a hurry, a method for acquiring location information quickly can be proposed. This makes it possible to provide the optimal method for acquiring location information according to the user's emotions.

[0159] The process flow of the second embodiment will be briefly described below.

[0160] Step 1: The reception department accepts inquiries to the insurance company. The inquiries may include telephone, email, online forms, etc. For example, the reception department accepts inquiries by telephone. It may also accept inquiries by email or through an online form. Step 2: The identification unit uses a machine learning model to identify the contents of the claim from the inquiry received by the reception unit. The contents of the claim include insurance claims and confirmation of contract details. The identification unit can identify the contents of the claim using a neural network, a support vector machine, a decision tree, etc. Step 3: The search unit searches for documents related to the claims based on the content of the claims identified by the identification unit. The documents include PDF files, text files, image files, etc. The search unit can search for documents using keyword search, full-text search, metadata search, etc. Step 4: The response department responds to the complaint based on the documents searched by the search department. Responses include phone calls, emails, and visits. For example, the response department responds by phone. It can also respond by email or by visiting.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] For example, the reception unit receives an inquiry using the reception device 38 of the smart device 14 or the communication I / F 26 of the data processing device 12. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies the contents of the complaint using a machine learning model. The search unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and searches for related documents based on the identified contents of the complaint. The response unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and predicts the effect of countermeasures using AI and proposes optimal countermeasures. The support unit is realized, for example, by the camera 42 of the smart device 14 or the identification processing unit 290 of the data processing device 12, and supports the collection of details and evidence of the accident. The calculation unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and calculates the benefit for the accident. The provision unit is realized, for example, by the output device 40 of the smart device 14 or the identification processing unit 290 of the data processing device 12, and provides detailed information on the policy. The answering unit is realized, for example, by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12, and answers the inquiry. The protection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and protects the customer information using encryption technology. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0165] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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).

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] For example, the reception unit receives an inquiry using the microphone 238 of the smart glasses 214 or the communication I / F 26 of the data processing device 12. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies the contents of the complaint using a machine learning model. The search unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and searches for related documents based on the identified contents of the complaint. The response unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and predicts the effect of countermeasures using AI and proposes optimal countermeasures. The support unit is realized, for example, by the camera 42 of the smart glasses 214 or the identification processing unit 290 of the data processing device 12, and supports the collection of details and evidence of the accident. The calculation unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and calculates the benefit for the accident. The provision unit is realized, for example, by the speaker 240 of the smart glasses 214 or the identification processing unit 290 of the data processing device 12, and provides detailed information on the policy. The answering unit is realized, for example, by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and answers the inquiry. The protection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and protects the customer information using encryption technology. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0181] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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).

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] For example, the reception unit receives an inquiry using the microphone 238 of the headset terminal 314 or the communication I / F 26 of the data processing device 12. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies the contents of the complaint using a machine learning model. The search unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and searches for related documents based on the identified contents of the complaint. The response unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and predicts the effect of countermeasures using AI and proposes optimal countermeasures. The support unit is realized, for example, by the camera 42 of the headset terminal 314 or the identification processing unit 290 of the data processing device 12, and supports the collection of details and evidence of the accident. The calculation unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and calculates the benefit for the accident. The provision unit is realized, for example, by the display 343 of the headset terminal 314 or the identification processing unit 290 of the data processing device 12, and provides detailed information on the policy. The answering unit is realized, for example, by the speaker 240 of the headset terminal 314 or the specific processing unit 290 of the data processing device 12, and answers the inquiry. The protection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and protects customer information using encryption technology. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0197] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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).

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] For example, the reception unit receives an inquiry using the microphone 238 of the robot 414 or the communication I / F 26 of the data processing device 12. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies the contents of the complaint using a machine learning model. The search unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and searches for related documents based on the identified contents of the complaint. The response unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and predicts the effect of countermeasures using AI and proposes optimal countermeasures. The support unit is realized, for example, by the camera 42 of the robot 414 or the identification processing unit 290 of the data processing device 12, and supports the collection of details and evidence of the accident. The calculation unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and calculates the benefit for the accident. The provision unit is realized, for example, by the speaker 240 of the robot 414 or the identification processing unit 290 of the data processing device 12, and provides detailed information on the policy. The answering unit is realized, for example, by the speaker 240 of the robot 414 or the specific processing unit 290 of the data processing device 12, and answers the inquiry. The protection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and protects the customer information using encryption technology. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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).

[0218] 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.

[0219] 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."

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] (Appendix 1) A reception department that receives inquiries to insurance companies; an identification unit that identifies the contents of a claim to the insurance company from the inquiry received by the reception unit; a search unit that searches for documents related to the claims based on the contents of the claims identified by the identification unit; a response unit that responds to the claim based on the documents searched by the search unit. A system characterized by: (Appendix 2) A support unit supports collection of details and evidence of an accident based on documents searched by the search unit. 2. The system of claim 1, (Appendix 3) A calculation unit for calculating a benefit for an accident based on the documents searched by the search unit. 2. The system of claim 1, (Appendix 4) A provision unit that provides detailed information of a policy based on the document searched by the search unit. 2. The system of claim 1, (Appendix 5) A reply unit that replies to the inquiry received by the reception unit is provided. 2. The system of claim 1, (Appendix 6) Equipped with a protection section that uses encryption technology to protect customer information 2. The system of claim 1, (Appendix 7) The identification unit is Using machine learning models to identify claims 2. The system of claim 1, (Appendix 8) The providing unit is Providing customized policy information based on user profile 5. The system of claim 4. (Appendix 9) The support portion is Use GPS data to get the location of the accident scene 3. The system of claim 2, (Appendix 10) The corresponding portion is Use AI to predict the effectiveness of countermeasures and propose optimal countermeasures 2. The system of claim 1, (Appendix 11) The reception unit is To estimate a user's emotions and adjust a method of accepting an inquiry based on the estimated user's emotions 2. The system of claim 1, (Appendix 12) The reception unit is Analyze past inquiry history and choose the most appropriate reception method 2. The system of claim 1, (Appendix 13) The reception unit is Filtering incoming inquiries based on the user's current situation and interests 2. The system of claim 1, (Appendix 14) The reception unit is Estimate the user's emotions and prioritize inquiries based on the estimated user emotions. 2. The system of claim 1, (Appendix 15) The reception unit is When accepting inquiries, the system takes into account the user's geographic location information to prioritize inquiries that are more relevant to the user. 2. The system of claim 1, (Appendix 16) The reception unit is When receiving an inquiry, analyze the user's social media activity and receive related inquiries 2. The system of claim 1, (Appendix 17) The identification unit is To estimate a user's emotion and adjust a method for identifying the content of a complaint based on the estimated user's emotion. 2. The system of claim 1, (Appendix 18) The identification unit is When identifying the content of a claim, refer to past claim data to improve the accuracy of identification. 2. The system of claim 1, (Appendix 19) The identification unit is When identifying claims, different identification algorithms are applied depending on the category of claims. 2. The system of claim 1, (Appendix 20) The identification unit is To estimate a user's emotion and determine a priority order of a complaint content to be identified based on the estimated user's emotion. 2. The system of claim 1, (Appendix 21) The identification unit is When identifying the content of a complaint, the geographic location of the user is taken into consideration to prioritize identifying more relevant complaints. 2. The system of claim 1, (Appendix 22) The identification unit is When identifying the content of a complaint, analyze the user's social media activity to identify related complaints 2. The system of claim 1, (Appendix 23) The search unit is Infer user sentiment and adjust document retrieval methods based on the inferred user sentiment 2. The system of claim 1, (Appendix 24) The search unit is When searching for documents, the search algorithm is optimized by referencing past search data. 2. The system of claim 1, (Appendix 25) The search unit is When searching for documents, apply different search algorithms depending on the category of claims 2. The system of claim 1, (Appendix 26) The search unit is Infer user sentiment and prioritize documents to be searched based on the estimated user sentiment 2. The system of claim 1, (Appendix 27) The search unit is When searching for documents, the geographic location of the user is taken into account to prioritize the most relevant documents. 2. The system of claim 1, (Appendix 28) The search unit is When searching for documents, analyze users' social media activity to find relevant documents 2. The system of claim 1, (Appendix 29) The corresponding portion is Inferring user emotions and adjusting the method of proposing countermeasures based on the estimated user emotions 2. The system of claim 1, (Appendix 30) The corresponding portion is When proposing countermeasures, the algorithm is optimized by referencing past response data. 2. The system of claim 1, (Appendix 31) The corresponding portion is When proposing solutions, different suggestion algorithms are applied depending on the category of the complaint. 2. The system of claim 1, (Appendix 32) The corresponding portion is Estimate user emotions and prioritize suggested actions based on the estimated user emotions 2. The system of claim 1, (Appendix 33) The corresponding portion is When proposing countermeasures, the system takes into account the user's geographic location information to suggest the optimal countermeasure. 2. The system of claim 1, (Appendix 34) The corresponding portion is When suggesting countermeasures, analyze the user's social media activity and suggest relevant countermeasures. 2. The system of claim 1, (Appendix 35) The support portion is To estimate a user's emotion and adjust a method of supporting evidence collection based on the estimated user's emotion. 3. The system of claim 2, (Appendix 36) The support portion is When collecting evidence, optimize collection algorithms by referencing past evidence data 3. The system of claim 2, (Appendix 37) The support portion is Inferring user emotions and prioritizing evidence to be collected based on the inferred user emotions 3. The system of claim 2, (Appendix 38) The support portion is When collecting evidence, the geographic location of the user is taken into consideration to collect optimal evidence. 3. The system of claim 2, (Appendix 39) The calculation unit is Inferring user sentiment and adjusting benefit calculations based on the inferred user sentiment 4. The system of claim 3. (Appendix 40) The calculation unit is When calculating benefits, the calculation algorithm is optimized by referencing past benefit data. 4. The system of claim 3. (Appendix 41) The calculation unit is Inferring user emotions and determining priority of benefits to be calculated based on the estimated user emotions 4. The system of claim 3. (Appendix 42) The calculation unit is When calculating benefits, the geographic location of the user is taken into account to calculate the optimal benefit. 4. The system of claim 3. (Appendix 43) The providing unit is To estimate a user's emotion and adjust a method of providing policy information based on the estimated user's emotion. 5. The system of claim 4. (Appendix 44) The providing unit is When providing policy information, the provision algorithm is optimized by referencing past policy data. 5. The system of claim 4. (Appendix 45) The providing unit is A user's emotion is estimated, and a priority of policy information to be provided is determined based on the estimated user's emotion. 5. The system of claim 4. (Appendix 46) The providing unit is When providing policy information, the most appropriate policy information is provided taking into account the user's geographic location information. 5. The system of claim 4. (Appendix 47) The answering section: Infer user emotions and adjust answering methods based on the estimated user emotions 6. The system of claim 5, (Appendix 48) The answering section: When answering, the answering algorithm is optimized by referring to past answer data. 6. The system of claim 5, (Appendix 49) The answering section: Infer user sentiment and prioritize answers based on the inferred sentiment 6. The system of claim 5, (Appendix 50) The answering section: When answering, it takes into account the user's geographic location to provide the best answer 6. The system of claim 5, (Appendix 51) The protective part is To estimate a user's emotion and adjust a method of protecting information based on the estimated user's emotion. 7. The system of claim 6, (Appendix 52) The protective part is When protecting information, the protection algorithm is optimized by referencing past protection data. 7. The system of claim 6, (Appendix 53) The protective part is A user's feelings are estimated, and a priority order of information to be protected is determined based on the estimated user's feelings. 7. The system of claim 6, (Appendix 54) The protective part is When protecting information, the system provides optimal protection methods by taking into account the user's geographic location information. 7. The system of claim 6, (Appendix 55) The function of obtaining location information of the accident site using the GPS data is Estimate user emotions and adjust location information acquisition methods based on the estimated user emotions 10. The system of claim 9, (Appendix 56) The function of obtaining location information of the accident site using the GPS data is When acquiring location information, the acquisition algorithm is optimized by referencing past location data. 10. The system of claim 9, (Appendix 57) The function of obtaining location information of the accident site using the GPS data is A user's emotion is estimated, and a priority order of location information to be acquired is determined based on the estimated user's emotion. 10. The system of claim 9, (Appendix 58) The function of obtaining location information of the accident site using the GPS data is When obtaining location information, the most appropriate location information is obtained by taking into account the user's geographical location information. 10. The system of claim 9, (Appendix 59) The function that uses the AI ​​to predict the effectiveness of countermeasures and propose optimal countermeasures is: Inferring user emotions and adjusting the method of proposing countermeasures based on the estimated user emotions 11. The system of claim 10, (Appendix 60) The function that uses the AI ​​to predict the effectiveness of countermeasures and propose optimal countermeasures is: When proposing countermeasures, the algorithm is optimized by referencing past response data. 11. The system of claim 10, (Appendix 61) The function that uses the AI ​​to predict the effectiveness of countermeasures and propose optimal countermeasures is: Estimate user emotions and prioritize suggested actions based on the estimated user emotions 11. The system of claim 10, (Appendix 62) The function that uses the AI ​​to predict the effectiveness of countermeasures and propose optimal countermeasures is: When proposing countermeasures, the system takes into account the user's geographic location information to suggest the optimal countermeasure. 11. The system of claim 10, [Explanation of symbols]

[0233] 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 department that receives inquiries to insurance companies; an identification unit that identifies the contents of a claim to the insurance company from the inquiry received by the reception unit; a search unit that searches for documents related to the claims based on the contents of the claims identified by the identification unit; a response unit that responds to the claim based on the documents searched by the search unit. A system characterized by:

2. A support unit supports collection of details and evidence of an accident based on documents searched by the search unit.

2. The system of claim 1 .

3. A calculation unit for calculating a benefit for an accident based on the documents searched by the search unit.

2. The system of claim 1 .

4. A provision unit that provides detailed information of a policy based on the document searched by the search unit.

2. The system of claim 1 .

5. A reply unit that replies to the inquiry received by the reception unit is provided.

2. The system of claim 1 .

6. Equipped with a protection section that uses encryption technology to protect customer information 2. The system of claim 1 .

7. The identification unit is Using machine learning models to identify the content of the claims 2. The system of claim 1 .

8. The providing unit is Providing customized policy information based on user profile 5. The system of claim 4.

9. The support portion is Use GPS data to get the location of the accident scene 3. The system of claim 2.

Images