system

Abstract

We provide the system. [Solution] A data collection method for collecting customer interaction history, A data analysis means that analyzes the aforementioned dialogue history using natural language processing technology to extract customer interests and needs, A proposal generation means that generates personalized follow-up proposals based on the extracted customer interests and needs, A notification means for notifying the terminal of the generated follow-up proposal, A follow-up execution means that executes a follow-up proposal using the aforementioned terminal and records the results, A system including a learning means to improve the proposal generation means using the execution results.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In sales support that utilizes the interaction history with customers, there is a problem that it is difficult for administrators to unify the quality of individual follow-up proposals and conduct follow-up at an effective timing. In particular, checking all interaction histories manually requires time and resources, and the content of the administrator's instructions varies depending on personal skills, which is also a problem. In such a situation, it is difficult for salespersons to provide consistent high-quality customer service, so there is a problem that the improvement of customer satisfaction and sales volume is hindered.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a data analysis means that collects customer interaction history and analyzes it using natural language processing technology. This automatically extracts customer interests and needs and generates personalized follow-up suggestions. These suggestions are then notified to the terminal, assisting salespeople in timing their follow-ups. Furthermore, by recording the results of the execution and learning from them to improve the accuracy of future suggestions, the system can continuously provide improved suggestions. In this way, the present invention provides a system that enables salespeople to provide efficient, consistent, and high-quality customer service.

[0006] A "customer" refers to someone who is purchasing or considering purchasing a product or service.

[0007] "Dialogue history" refers to the record of all communication that takes place between the customer and the salesperson. This includes data from voice calls and text chats.

[0008] "Natural language processing" refers to the technology of understanding, analyzing, and manipulating human language using computers.

[0009] "Data collection means" refers to a system or device for effectively collecting and storing customer interaction history.

[0010] "Data analysis means" refers to algorithms and software used to process collected conversation history and extract customer needs and interests.

[0011] "Proposal generation means" refers to a process or apparatus for constructing appropriate follow-up measures based on information obtained through analysis.

[0012] "Notification means" refers to methods or devices used to inform salespeople about proposed follow-ups and to assist them in implementing them.

[0013] "Follow-up implementation methods" refer to the processes and mechanisms that enable salespeople to actually take action on proposals presented to customers.

[0014] "Learning method" refers to a method or system for continuously improving the system in order to make more appropriate suggestions based on the results of the follow-up activities that have been carried out. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units 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), and the like.

[0019] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters and the like. Examples of non-volatile storage devices include a flash memory (SSD (Solid State Drive)), a magnetic disk (e.g., a hard disk), or a magnetic tape, and the like.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the 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.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is a system that automatically generates personalized follow-up suggestions based on customer interaction history to support salespeople. The system consists of a server, a salesperson's terminal, and user operation.

[0037] Processes performed by the server:

[0038] The server first collects the customer's interaction history. This information is collected using the terminal and stored in the form of voice calls and text chats. The collected data is analyzed using a natural language processing algorithm built on the server side. This analysis reveals the customer's specific interests and needs, which are recorded in the database. The server also generates the optimal follow-up action to take based on these analysis results.

[0039] Process performed by the terminal:

[0040] The terminal receives follow-up suggestions from the server and notifies the salesperson. By notifying at the appropriate time, it helps salespeople take efficient and quick action. For example, the terminal displays a draft of an automatically generated email for the customer, allowing the salesperson to easily customize and send it. At this stage, the salesperson can fine-tune the suggestion based on the customer's response, providing a more personalized response.

[0041] The process performed by the user:

[0042] Salespeople (users) use follow-up suggestions displayed on their devices to provide actual customer service. For example, if a customer is considering purchasing a new smartphone, the suggestions notified from the device might include an email introducing a smartphone with high-performance camera capabilities. The salesperson sends this email in a timely manner, providing information tailored to the customer's interests. In this way, users can use the provided tools to deliver more consistent and high-quality customer service.

[0043] The results of all actions are sent from the terminal to the server and used as training data to improve the accuracy of future suggestions. This allows the system to continuously improve, not only increasing the efficiency of sales staff but also improving customer satisfaction.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server collects customer interactions. Salespeople's terminals record voice calls and text messages in real time and transfer that data to the server.

[0047] Step 2:

[0048] The server analyzes the collected data using natural language processing technology. It extracts customer interests, needs, and emotions from the conversation content and stores the analysis results as structured data.

[0049] Step 3:

[0050] Based on the analysis results, the server generates follow-up suggestions tailored to the customer's needs. These are automatically created using pre-configured rules and AI models.

[0051] Step 4:

[0052] A follow-up proposal is sent from the server to the salesperson's terminal. The terminal notifies the user of the received proposal and prompts them to take action.

[0053] Step 5:

[0054] Users review follow-up suggestions displayed on their devices and respond to customer inquiries accordingly. For example, they might customize an automatically generated email draft and send it to the customer.

[0055] Step 6:

[0056] The device records the results of user actions and transfers them to the server. These results include follow-up customer feedback and new needs.

[0057] Step 7:

[0058] The server incorporates the collected action results into a learning model, which is then used to improve the accuracy of future suggestions. The system is continuously improved, enabling more effective responses to customers.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] In customer service, it is essential to quickly and accurately understand the interests and needs of individual customers and to provide effective follow-up proposals based on that understanding. However, the current system is time-consuming in terms of data analysis and proposal creation, which reduces the efficiency of sales staff. Furthermore, it is difficult to provide follow-up at the appropriate time, resulting in a failure to adequately improve customer satisfaction.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for accumulating information, means for analyzing the information using processing technology to extract the target's interests and needs, and means for creating personalized suggestions based on the extracted interests and needs. This enables the generation and notification of rapid and accurate follow-up suggestions based on the customer's interests and needs.

[0064] "Means of collecting information" refers to functions for gathering information from an object, recording that data, and storing it.

[0065] "Processing technology" refers to data analysis techniques used to analyze collected information and derive meaningful results.

[0066] "Means for extracting the interests and needs of a subject" refers to a function that uses processing technology to identify the specific interests and needs of a subject from the data obtained from that subject.

[0067] "Means for creating personalized proposals" refers to a function that automatically generates proposals optimized for a specific target based on the interests and needs of the extracted target.

[0068] "Information equipment" refers to electronic devices used for processing, displaying, or transmitting digital data.

[0069] "Means of notifying information" refers to the function of transmitting generated proposals and important information to specific information devices.

[0070] The "function to notify the timing of proposal implementation" refers to a function in which information devices inform the user of the optimal time or situation for implementing a proposal.

[0071] This invention is a system for improving the efficiency of customer service operations and enhancing customer satisfaction. The system consists of a server, a user terminal, and the user's own operations.

[0072] Server operation:

[0073] The server first collects customer interaction history using data aggregation methods. This aggregation includes voice and text information, utilizing general-purpose technologies such as call logs and chat platforms. The collected data is then stored directly in a database. The server then uses processing techniques to perform natural language processing on the data, extracting the target's interests and needs. For example, it uses Python's NLTK library or TENSORFLOW® to perform text tokenization and syntactic analysis using machine learning algorithms. Based on the insights gained from this analysis, it uses a generative AI model (e.g., GPT-3®) to create personalized suggestions. In this process, the following prompt is used as input to the generative AI model: "Create a follow-up email for customers who have shown interest in new products based on recent conversations."

[0074] Device operation:

[0075] The user's device receives generation proposals notified from the server. The device displays the received information and, for example, integrates with a sales support application to inform the user of the optimal timing. Notifications are made in the form of pop-ups or emails to help users respond quickly. This enables seamless implementation of follow-up proposals.

[0076] User actions:

[0077] Users utilize the suggestions displayed on their terminals to handle actual customer interactions. This is achieved, for example, by fine-tuning the content of a proposed email and sending it to the customer. Users also provide feedback to the server via their terminals after implementing the suggestions, contributing to the continuous optimization of the system. The feedback results are used by the server's learning mechanisms to improve the accuracy of future suggestion generation. As a result, the system improves over time, enhancing the user's work efficiency.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The server collects customer interaction history using data aggregation methods. It receives voice and text information as input and stores call records and chat logs in a database. This operation often utilizes real-time data streaming technology.

[0081] Step 2:

[0082] The server analyzes the collected data using natural language processing techniques. Here, the input dialogue data is tokenized and parsed. Using Python libraries and other machine learning tools, it obtains output that extracts customer interests and needs.

[0083] Step 3:

[0084] The server generates personalized suggestions using a generative AI model based on the extracted customer interests and needs. Specifically, it processes the analysis results into prompt sentences as input and passes them to the generative AI model to output suggestion sentences tailored to the customer.

[0085] Step 4:

[0086] The device receives suggestions generated from the server and notifies the user. It receives the suggestion content as input and displays the notification as output. The device provides information to the user at the appropriate time using pop-ups or email notifications.

[0087] Step 5:

[0088] The user reviews the proposal displayed on the terminal and then interacts with the customer. As input, they consider the proposal content and perform data processing such as customization. As output, they send the customized proposal to the customer.

[0089] Step 6:

[0090] The results of user actions are fed back to the server via the terminal. Customer interaction result data is received as input, and the output is stored as training data to improve the accuracy of suggestion generation. This feedback loop continuously improves the overall system performance.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] Follow-up suggestions based on customer interaction history generally have a low degree of personalization, making it difficult to provide consistently high-quality customer service. Furthermore, if the timing or content of follow-up suggestions is inappropriate, they may fail to increase customer purchase intent.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes data collection means for collecting customer interaction history, data analysis means for analyzing the interaction history using natural language processing technology to extract customer preferences and requests, suggestion generation means for generating personalized follow-up suggestions based on the extracted information, notification means, and presentation means for automatically displaying product suggestions and coupons based on the customer interaction history. This makes it possible to provide personalized suggestions at the appropriate time, effectively increasing the customer's willingness to purchase.

[0096] "Data collection means" refers to a device or method for recording the history of conversations with customers, and is a means of collecting conversation content in various forms, including voice communication and text conversations.

[0097] "Data analysis means" refers to a program or device that has the function of analyzing dialogue history collected using natural language processing technology and extracting customer preferences and requests.

[0098] "Proposal generation means" refers to a device or method for automatically generating personalized follow-up proposals based on analyzed customer preferences and requests.

[0099] "Notification means" refers to a device or method for notifying a communication terminal of the generated follow-up proposal, and includes a function for informing the timing of the proposal's implementation.

[0100] "Follow-up execution means" refers to an apparatus or method for carrying out a notified follow-up suggestion and recording the results.

[0101] "Learning means" refers to a device or method that has the function of learning data to improve the accuracy of the proposal generation means using the results of the execution of follow-up proposals.

[0102] "Presentation means" refers to a device or method for automatically displaying personalized product suggestions or coupons on a communication terminal based on the customer's dialogue history.

[0103] This invention is a system that automatically generates personalized follow-up suggestions based on customer interaction history to support salespeople. The system consists of a server, terminals, and user operations.

[0104] The server collects customer interaction history using data collection means. This history is recorded in the form of voice communication or text conversation and stored on the server. Next, data analysis means analyze the collected history using natural language processing algorithms (specifically, Python, NLTK, spaCy, etc.) to extract customer preferences and requests. Based on this, suggestion generation means generates personalized follow-up suggestions and sends them to the communication terminal via notification means.

[0105] The device receives notifications and presents follow-up suggestions to the user at the appropriate time. During this process, personalized options are offered to the customer, such as automatically displaying product suggestions and coupons through the presentation method. Furthermore, sales staff can easily obtain the necessary information to respond to customers based on these suggestions, enabling them to efficiently recommend products.

[0106] All follow-up execution results are fed back to the server using learning tools to continuously improve the accuracy of the suggestion generation tool. It is also possible to utilize the generation AI model with the following example prompt: "Generate personalized product suggestions based on the following customer's dialogue history. Dialogue History: "I want to know more about wireless earphones. I'm concerned about sound quality and battery life." Purchase History: "Smartphone case, mobile battery."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The server collects customer interaction history using data collection methods. Input is voice communication and text conversation data, and output is interaction history data stored on the server. In this process, call recordings and chat logs are automatically uploaded to the server and stored in the database.

[0110] Step 2:

[0111] The server analyzes the collected dialogue history using data analysis tools. The input is the dialogue history data stored on the server, and the output is the analysis results, including customer preferences and requests. Specifically, it executes natural language processing algorithms (such as Python, NLTK, and spaCy) to extract keywords from the text data and identify customer interests.

[0112] Step 3:

[0113] The server generates personalized follow-up suggestions based on the analysis results using a suggestion generation mechanism. The input is the analysis results showing the customer's preferences and requests, and the output is a follow-up plan that includes specific product suggestions and coupon information. When generating suggestions, a generation AI model is used, and a recommendation algorithm based on past data and rules is applied.

[0114] Step 4:

[0115] The server notifies the terminal of follow-up suggestions generated using the notification mechanism. The input is the follow-up suggestion, and the output is the notification displayed on the terminal. The server calculates the appropriate timing and sends the notification in real time.

[0116] Step 5:

[0117] The device receives notifications and presents follow-up suggestions to the user. The input is notification information from the server, and the output is the suggested content displayed in the user interface. Specifically, the device displays the suggested content on the UI and provides an environment where the user can take action based on it.

[0118] Step 6:

[0119] Users use a terminal to perform follow-up suggestions and record the results. The input is the action performed by the user, and the output is the recorded data of the result that is fed back to the server. For example, users might recommend products or apply coupons.

[0120] Step 7:

[0121] The server improves the accuracy of the proposal generation mechanism based on the feedback received using a learning mechanism. The input is the execution result data, and the output is the improved proposal generation algorithm. Specifically, it uses a machine learning algorithm to analyze the collected data and improve the accuracy of future proposals.

[0122] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0123] This invention is a follow-up suggestion generation system that combines an emotion engine that recognizes customer emotions based on the customer's dialogue history. The system consists of a server, a salesperson's terminal, and user operations.

[0124] Processes performed by the server:

[0125] The server first collects the history of interactions with the customer. This history is recorded as voice calls or text chats and sent from the terminal to the server. The server analyzes this history using natural language processing technology. This analysis includes recognizing the customer's emotional state using an emotion engine. The emotion engine analyzes the tone of voice and linguistic expressions to determine the customer's emotional state. Based on this information, the server constructs personalized follow-up suggestions that combine the customer's interests, needs, and emotional state.

[0126] Process performed by the terminal:

[0127] The terminal notifies salespeople of follow-up suggestions received from the server. These notifications are tailored to the customer's emotional state, helping salespeople respond more appropriately. For example, if a customer is stressed, the terminal displays suggestions recommending a more careful approach to customer service. The terminal also utilizes past emotional history to list products and services that the customer prefers.

[0128] The process performed by the user:

[0129] The user, or salesperson, reviews the suggestions displayed on the device and follows up based on the customer's current emotional state. For example, if a customer is considering purchasing a new smartphone and the emotion engine determines that the customer is feeling excited, the device will recommend positive suggestions that match that emotion (e.g., features for using the smartphone's hobbies). The salesperson can then use these suggestions to take appropriate actions, such as sending an email to the customer or encouraging them to visit the store again.

[0130] This system records the results of follow-up activities on a server and uses them to inform future proposals. This process enables salespeople to consistently provide improved, high-quality customer service, which is expected to increase customer satisfaction.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The server collects the history of interactions with customers. The terminal records voice calls and text chats with customers and sends the data to the server.

[0134] Step 2:

[0135] The server analyzes the received dialogue history data using natural language processing technology. Using an emotion engine, it recognizes the customer's emotions from the tone of voice and the linguistic expressions in the text, and performs analysis to identify that emotional state.

[0136] Step 3:

[0137] Based on the analysis results, the server generates personalized follow-up suggestions that take into account the customer's interests, needs, and emotional state. These suggestions include appropriate language and product information tailored to the customer's emotional state.

[0138] Step 4:

[0139] The server sends the generated follow-up proposal to the terminal. The terminal immediately notifies the salesperson of the proposal content, prompting them to prepare for customer interaction.

[0140] Step 5:

[0141] The user reviews the follow-up suggestions displayed on their device. Based on these suggestions, the user takes follow-up actions appropriate to the customer's emotional state. For example, for a customer experiencing stress, the user might offer gentler suggestions in a calmer tone.

[0142] Step 6:

[0143] The terminal records the results of the follow-up actions performed and sends them to the server. This helps improve the accuracy of future suggestions.

[0144] Step 7:

[0145] The server undergoes a learning process based on feedback. It uses newly acquired data to improve the system and enhance the quality of proposals in future customer interactions.

[0146] (Example 2)

[0147] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0148] There is a challenge in that it is difficult to appropriately and efficiently analyze the emotional state and interests of customers from the vast amount of information obtained through interactions with customers, automatically generate individually optimized follow-up proposals, and improve the quality of customer service.

[0149] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0150] In this invention, the server includes information acquisition means for collecting customer interaction history, data analysis means for analyzing the interaction history using natural language processing technology to recognize the customer's emotional state, and information creation means for generating personalized follow-up proposals based on the recognized customer emotional state, interests, and needs. This enables the rapid and accurate creation of proposals tailored to each customer's characteristics and emotions, thereby improving customer satisfaction.

[0151] "Information acquisition means" refers to a system that has the function of collecting the history of conversations with customers and recording it in data format such as audio or text.

[0152] "Data analysis means" refers to a system that applies natural language processing technology to collected dialogue history and has the function of processing to recognize the customer's emotional state.

[0153] "Information creation means" refers to a system that has the function of generating personalized follow-up proposals based on the customer's emotional state, interests, and needs obtained through analysis.

[0154] A "transmission means" is a device that has the function of transmitting the generated follow-up proposal and related information to the terminal and notifying the user at an appropriate time.

[0155] A "learning tool" is a system that collects feedback on the results of follow-up proposals and uses that feedback to improve future proposals.

[0156] This invention is a system that generates follow-up suggestions by utilizing the history of conversations with customers. The system mainly consists of a server, terminals, and users. Specific embodiments of each component are described below.

[0157] The server receives the history of customer interactions transmitted from the salesperson's terminal. This history is recorded as voice calls and text chats. The server analyzes this history using spaCy, an open-source natural language processing library. Through analysis, it tokenizes the text, understands the context, extracts keywords, and recognizes the customer's emotional state. Furthermore, it uses the Python library OpenAI® to perform tone analysis and sentiment analysis of the voice data, thereby evaluating the customer's emotions in detail.

[0158] Next, the server uses a generative AI model to create personalized follow-up suggestions. This model is inputted with data on the customer's current emotions and past interests and needs, and generates suggestions based on appropriate prompts. An example of a prompt is, "Based on the customer's conversation history, please generate follow-up suggestions focusing on topics that the customer is likely to enjoy."

[0159] The generated suggestions are sent from the server to the terminal. The terminal is a device for notifying salespeople of these suggestions, providing timely information using push notifications and banner displays. The terminal also displays a list of the customer's sentiment history and past interests to the salesperson, visually supporting the relevance of the suggested content.

[0160] The user, or salesperson, follows up with the customer based on the suggestions displayed on the terminal. For example, if a customer shows interest in a new smartphone and sentiment analysis detects enjoyment, it would be appropriate for the salesperson to make suggestions specifically focused on the smartphone's camera features. In this way, salespeople can provide customers with more personalized service.

[0161] Through the specific examples described above, this invention can greatly improve the flexibility and quality of customer service.

[0162] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0163] Step 1:

[0164] The server receives the customer interaction history from the salesperson's terminal. The input data is either audio files or text logs, which are stored in the database. Specifically, audio data is recorded in storage, and text is stored as a log. The output here is a dataset of the interaction history prepared for analysis.

[0165] Step 2:

[0166] The server uses the spaCy library to analyze the conversation history in text format. The input is the text log saved in step 1. Specific operations include sentence splitting, tokenization, and named entity recognition. Through this process, keywords related to customer interests and needs are extracted, and the analysis results are generated as output.

[0167] Step 3:

[0168] The server uses OpenAI to perform tone analysis and sentiment analysis of voice data. The input is the voice data saved in Step 1. Specifically, the voice is converted to text, and the customer's emotional state is analyzed from the tone and manner of speaking. The output is the customer's emotional status.

[0169] Step 4:

[0170] The server combines the analysis results data with the customer's emotional status and inputs it into the generative AI model. The prompt used here is "Generate follow-up suggestions based on the customer's conversation history, focusing on topics that the customer is likely to anticipate." This causes the generative AI model to generate personalized follow-up suggestions, which are then obtained as output.

[0171] Step 5:

[0172] The server sends the generated follow-up proposal to the terminal. The input is the generation result from step 4, and the proposal is transmitted to the salesperson's terminal via the terminal transmission protocol. The output is the follow-up proposal displayed on the terminal.

[0173] Step 6:

[0174] The device notifies the salesperson of the proposed content and displays detailed information. Specific actions include sending alerts to the salesperson using push notifications and displaying a list of the customer's sentiment history on the screen. The output here is quickly accessible and understandable proposal information for the salesperson.

[0175] Step 7:

[0176] The user follows up with customers based on the suggestions displayed on the device. Based on the information obtained in Step 6, they send emails to customers or introduce new products. This allows the user to provide more appropriate responses tailored to each customer. The output of this step is the result of the follow-up actions taken.

[0177] Step 8:

[0178] User feedback is sent to the server and used to improve follow-up suggestions for future interactions. Specifically, it is stored as data to optimize the suggestion generation algorithm based on the effectiveness of the follow-up. This further improves customer service in subsequent interactions. The output is a dataset that helps in generating improved suggestions.

[0179] (Application Example 2)

[0180] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0181] The system for automatically generating personalized follow-up suggestions that take into account the customer's emotional state, using information gathered through customer interactions, and communicating these suggestions to sales staff was insufficient. In this situation, it is difficult to provide customer service that appropriately reflects customer emotions, and improvements in customer satisfaction cannot be expected. Furthermore, a system is needed to accumulate the results of follow-up activities and continuously improve the accuracy of suggestion generation.

[0182] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0183] In this invention, the server includes information gathering means for collecting customer interaction history, emotion recognition means for analyzing the interaction history using natural language processing technology and determining the customer's emotional state, suggestion generation means for generating personalized follow-up suggestions based on the extracted customer interests, needs, and emotional state, communication means for notifying a portable terminal of the generated follow-up suggestions, follow-up execution means for executing the follow-up suggestions using the terminal and recording the results, and experience learning means for improving the suggestion generation means using the execution results. This makes it possible to immediately provide accurate follow-up that takes customer emotions into consideration, enabling salespeople to provide higher quality service.

[0184] "Information gathering means" refers to elements that have the function of recording and collecting the history of interactions with customers.

[0185] An "emotion recognition means" is an element that uses natural language processing technology to analyze dialogue history and determine the customer's emotional state.

[0186] A "proposal generation means" is an element that has the function of generating personalized follow-up proposals based on the extracted customer interests, needs, and emotional state.

[0187] "Communication means" refers to an element that has the function of notifying a portable terminal of the generated follow-up proposal.

[0188] A "follow-up execution means" is an element that has the function of executing follow-up proposals using a terminal and recording the results of those implementations.

[0189] An "experiential learning tool" is an element that has the function of improving the proposal generation tool using the results of follow-up execution and continuously improving the system.

[0190] The system implementing this invention consists of a server, a terminal used by a salesperson, and user interaction.

[0191] First, the server collects a history of interactions with the customer, including voice calls and text chats. The voice and text data are analyzed using natural language processing techniques, and the customer's emotional state is determined using emotion recognition tools. The technologies used include machine learning models built in Python and TensorFlow. Based on this information, the server generates personalized follow-up suggestions that reflect the customer's interests, needs, and emotional state using suggestion generation tools.

[0192] Next, the terminal receives communication from the server and notifies the salesperson of the generated follow-up suggestion. The salesperson can use a smartphone or smart glasses. This allows the salesperson to obtain information hands-free and check the suggestion in real time while interacting with the customer.

[0193] The salesperson (user) executes follow-up suggestions via a terminal, and the results are recorded using the follow-up execution device. This information is used to improve the suggestion generation device through the experiential learning device, and the accuracy of the suggestions improves over time.

[0194] For example, when a salesperson wearing smart glasses interacts with a customer in a store, if the system analyzes that the customer is excited, a follow-up suggestion such as "It would be good to provide information about new products" will be displayed on the terminal's screen.

[0195] An example of a prompt might be a question like, "What product categories did this customer mention as being good in past conversations?" This allows the AI ​​to provide salespeople with information about the customer's past interests and tendencies, enabling more accurate follow-up.

[0196] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0197] Step 1:

[0198] The server collects customer interaction history from voice calls and text chats using information gathering tools. The input for this step is communication data between the customer and the salesperson, and the output is a structured log of that data. The server records this data and stores it in a database.

[0199] Step 2:

[0200] The server analyzes the collected dialogue history using natural language processing techniques and determines the customer's emotional state using emotion recognition. The input is the collected dialogue history, and the output is the customer's emotional state as a result of the analysis (e.g., joy or excitement). Python and TensorFlow are used to evaluate the emotion of the voice tone and text.

[0201] Step 3:

[0202] The server generates personalized follow-up suggestions using a suggestion generation system based on the customer's interests, needs, and emotional state. The input is customer data such as the emotional state and past purchase history determined in step 2, and the output is personalized suggestion content. An AI generation model is used in this process to construct appropriate suggestions.

[0203] Step 4:

[0204] The server sends the generated follow-up proposal to the terminal using a communication method. The input is the proposal content created in step 3, and the output is the proposal information displayed on the terminal. The terminal receives this and notifies the salesperson.

[0205] Step 5:

[0206] Salespeople (users) equipped with a terminal execute follow-up proposals they receive, and the details and results of these executions are recorded using the follow-up execution device. The input is data on how the salesperson utilized the proposal, and the output is a log of the results. Based on this information, the salesperson takes specific actions with the customer.

[0207] Step 6:

[0208] The server analyzes the follow-up execution results using an empirical learning mechanism and improves the functionality of the proposal generation mechanism. The input is the execution result recorded in step 5, and the output is the adjusted algorithm to improve the accuracy of the next proposal. This improves the overall accuracy and efficiency of the system.

[0209] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0210] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0211] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0212] [Second Embodiment]

[0213] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0214] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0215] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0216] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0217] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0218] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0219] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0220] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0221] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0222] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0223] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0224] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0225] This invention is a system that automatically generates personalized follow-up suggestions based on customer interaction history to support salespeople. The system consists of a server, a salesperson's terminal, and user operation.

[0226] Processes performed by the server:

[0227] The server first collects the customer's interaction history. This information is collected using the terminal and stored in the form of voice calls and text chats. The collected data is analyzed using a natural language processing algorithm built on the server side. This analysis reveals the customer's specific interests and needs, which are recorded in the database. The server also generates the optimal follow-up action to take based on these analysis results.

[0228] Process performed by the terminal:

[0229] The terminal receives follow-up suggestions from the server and notifies the salesperson. By notifying at the appropriate time, it helps salespeople take efficient and quick action. For example, the terminal displays a draft of an automatically generated email for the customer, allowing the salesperson to easily customize and send it. At this stage, the salesperson can fine-tune the suggestion based on the customer's response, providing a more personalized response.

[0230] The process performed by the user:

[0231] Salespeople (users) use follow-up suggestions displayed on their devices to provide actual customer service. For example, if a customer is considering purchasing a new smartphone, the suggestions notified from the device might include an email introducing a smartphone with high-performance camera capabilities. The salesperson sends this email in a timely manner, providing information tailored to the customer's interests. In this way, users can use the provided tools to deliver more consistent and high-quality customer service.

[0232] The results of all actions are sent from the terminal to the server and used as training data to improve the accuracy of future suggestions. This allows the system to continuously improve, not only increasing the efficiency of sales staff but also improving customer satisfaction.

[0233] The following describes the processing flow.

[0234] Step 1:

[0235] The server collects customer interactions. Salespeople's terminals record voice calls and text messages in real time and transfer that data to the server.

[0236] Step 2:

[0237] The server analyzes the collected data using natural language processing technology. It extracts customer interests, needs, and emotions from the conversation content and stores the analysis results as structured data.

[0238] Step 3:

[0239] Based on the analysis results, the server generates follow-up suggestions tailored to the customer's needs. These are automatically created using pre-configured rules and AI models.

[0240] Step 4:

[0241] A follow-up proposal is sent from the server to the salesperson's terminal. The terminal notifies the user of the received proposal and prompts them to take action.

[0242] Step 5:

[0243] Users review follow-up suggestions displayed on their devices and respond to customer inquiries accordingly. For example, they might customize an automatically generated email draft and send it to the customer.

[0244] Step 6:

[0245] The device records the results of user actions and transfers them to the server. These results include follow-up customer feedback and new needs.

[0246] Step 7:

[0247] The server incorporates the collected action results into a learning model, which is then used to improve the accuracy of future suggestions. The system is continuously improved, enabling more effective responses to customers.

[0248] (Example 1)

[0249] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0250] In customer service, it is essential to quickly and accurately understand the interests and needs of individual customers and to provide effective follow-up proposals based on that understanding. However, the current system is time-consuming in terms of data analysis and proposal creation, which reduces the efficiency of sales staff. Furthermore, it is difficult to provide follow-up at the appropriate time, resulting in a failure to adequately improve customer satisfaction.

[0251] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0252] In this invention, the server includes means for accumulating information, means for analyzing the information using processing technology to extract the target's interests and needs, and means for creating personalized suggestions based on the extracted interests and needs. This enables the generation and notification of rapid and accurate follow-up suggestions based on the customer's interests and needs.

[0253] "Means of collecting information" refers to functions for gathering information from an object, recording that data, and storing it.

[0254] "Processing technology" refers to data analysis techniques used to analyze collected information and derive meaningful results.

[0255] "Means for extracting the interests and needs of a subject" refers to a function that uses processing technology to identify the specific interests and needs of a subject from the data obtained from that subject.

[0256] "Means for creating personalized proposals" refers to a function that automatically generates proposals optimized for a specific target based on the interests and needs of the extracted target.

[0257] "Information equipment" refers to electronic devices used for processing, displaying, or transmitting digital data.

[0258] "Means of notifying information" refers to the function of transmitting generated proposals and important information to specific information devices.

[0259] The "function to notify the timing of proposal implementation" refers to a function in which information devices inform the user of the optimal time or situation for implementing a proposal.

[0260] This invention is a system for improving the efficiency of customer service operations and enhancing customer satisfaction. The system consists of a server, a user terminal, and the user's own operations.

[0261] Server operation:

[0262] The server first collects customer interaction history using data aggregation methods. This aggregation includes voice and text information, utilizing general-purpose technologies such as call logs and chat platforms. The collected data is then stored directly in a database. The server then uses processing techniques to perform natural language processing on the data, extracting the target's interests and needs. For example, it uses Python's NLTK library or TensorFlow to perform text tokenization and syntactic analysis using machine learning algorithms. Based on the insights gained from this analysis, it uses a generative AI model (e.g., GPT-3) to create personalized suggestions. In this process, the following prompt is used as input to the generative AI model: "Create a follow-up email for customers who showed interest in the new product based on recent conversations."

[0263] Device operation:

[0264] The user's device receives generation proposals notified from the server. The device displays the received information and, for example, integrates with a sales support application to inform the user of the optimal timing. Notifications are made in the form of pop-ups or emails to help users respond quickly. This enables seamless implementation of follow-up proposals.

[0265] User actions:

[0266] Users utilize the suggestions displayed on their terminals to handle actual customer interactions. This is achieved, for example, by fine-tuning the content of a proposed email and sending it to the customer. Users also provide feedback to the server via their terminals after implementing the suggestions, contributing to the continuous optimization of the system. The feedback results are used by the server's learning mechanisms to improve the accuracy of future suggestion generation. As a result, the system improves over time, enhancing the user's work efficiency.

[0267] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0268] Step 1:

[0269] The server collects customer interaction history using data aggregation methods. It receives voice and text information as input and stores call records and chat logs in a database. This operation often utilizes real-time data streaming technology.

[0270] Step 2:

[0271] The server analyzes the collected data using natural language processing techniques. Here, the input dialogue data is tokenized and parsed. Using Python libraries and other machine learning tools, it obtains output that extracts customer interests and needs.

[0272] Step 3:

[0273] The server generates personalized suggestions using a generative AI model based on the extracted customer interests and needs. Specifically, it processes the analysis results into prompt sentences as input and passes them to the generative AI model to output suggestion sentences tailored to the customer.

[0274] Step 4:

[0275] The device receives suggestions generated from the server and notifies the user. It receives the suggestion content as input and displays the notification as output. The device provides information to the user at the appropriate time using pop-ups or email notifications.

[0276] Step 5:

[0277] The user reviews the proposal displayed on the terminal and then interacts with the customer. As input, they consider the proposal content and perform data processing such as customization. As output, they send the customized proposal to the customer.

[0278] Step 6:

[0279] The user's action results are fed back to the server through the terminal. Receiving customer service result data as input, it is saved as learning data for improving the accuracy of proposal generation as output. Through this feedback loop, the performance of the entire system is continuously improved.

[0280] (Application Example 1)

[0281] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0282] Follow-up proposals using the interaction history with customers generally have the problem of low personalization and difficulty in providing consistent high-quality customer service. Also, if the timing and content of the follow-up proposals are inappropriate, the customer's purchasing desire cannot be enhanced.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0284] In this invention, the server includes data collection means for collecting the interaction history with customers, data analysis means for analyzing the interaction history by natural language processing technology to extract the customer's preferences and requirements, proposal generation means for generating individualized follow-up proposals based on the extracted information, notification means, and presentation means for automatically displaying product proposals and coupons based on the customer's interaction history. Thereby, it becomes possible to make personalized proposals at an appropriate timing and effectively enhance the customer's purchasing desire.

[0285] The "data collection means" is a device or method for recording the interaction history with customers, and is a means for collecting the interaction content in various forms including voice communication and text conversations.

[0286] The "data analysis means" is a program or device that analyzes the conversation history collected using natural language processing technology and extracts the preferences and requirements of customers.

[0287] The "proposal generation means" is a device or method for automatically generating personalized follow-up proposals based on the analyzed preferences and requirements of customers.

[0288] The "notification means" is a device or method for notifying the generated follow-up proposals to a communication terminal, and includes a function of informing the implementation timing of the proposals.

[0289] The "follow-up execution means" is a device or method for executing the notified follow-up proposals and recording the results.

[0290] The "learning means" is a device or method having a function of learning data for improving the accuracy of the proposal generation means using the execution results of the follow-up proposals.

[0291] The "presentation means" is a device or method for automatically displaying personalized product proposals and coupons on a communication terminal based on the customer's conversation history.

[0292] This invention is a system that automatically generates personalized follow-up proposals based on the conversation history with customers and supports salespersons. This system is composed of a server, a terminal, and user operations.

[0293] The server collects the conversation history with customers using the data collection means. This history is recorded in the form of voice communication or text conversation and stored in the server. Next, the history collected using the data analysis means is analyzed using natural language processing algorithms (specifically, Python, NLTK, spaCy, etc.) to extract the preferences and requirements of customers. Based on this, the proposal generation means generates personalized follow-up proposals and transmits them to the communication terminal via the notification means.

[0294] The device receives notifications and presents follow-up suggestions to the user at the appropriate time. During this process, personalized options are offered to the customer, such as automatically displaying product suggestions and coupons through the presentation method. Furthermore, sales staff can easily obtain the necessary information to respond to customers based on these suggestions, enabling them to efficiently recommend products.

[0295] All follow-up execution results are fed back to the server using learning tools to continuously improve the accuracy of the suggestion generation tool. It is also possible to utilize the generation AI model with the following example prompt: "Generate personalized product suggestions based on the following customer's dialogue history. Dialogue History: "I want to know more about wireless earphones. I'm concerned about sound quality and battery life." Purchase History: "Smartphone case, mobile battery."

[0296] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0297] Step 1:

[0298] The server collects customer interaction history using data collection methods. Input is voice communication and text conversation data, and output is interaction history data stored on the server. In this process, call recordings and chat logs are automatically uploaded to the server and stored in the database.

[0299] Step 2:

[0300] The server analyzes the collected dialogue history using data analysis tools. The input is the dialogue history data stored on the server, and the output is the analysis results, including customer preferences and requests. Specifically, it executes natural language processing algorithms (such as Python, NLTK, and spaCy) to extract keywords from the text data and identify customer interests.

[0301] Step 3:

[0302] The server uses the proposal generation means to generate individualized follow-up proposals based on the analysis results. The input is the analysis result indicating the customer's preferences and requirements, and the output is a follow-up plan including specific product proposals and coupon information. When generating proposals, the generation AI model is utilized, and a recommendation algorithm based on past data and rules is applied.

[0303] Step 4:

[0304] The server notifies the terminal of the generated follow-up proposals using the notification means. The input is the follow-up proposal, and the output is the notification displayed on the terminal. The server calculates the appropriate timing and sends the notification in real time.

[0305] Step 5:

[0306] The terminal receives the notification and presents the follow-up proposal to the user. The input is the notification information from the server, and the output is the proposal content displayed on the user interface. As a specific operation, the terminal displays the proposal content on the UI and provides an environment where the user can execute actions based on it.

[0307] Step 6:

[0308] The user uses the terminal to execute the follow-up proposal and records the result. The input is the content of the action executed by the user, and the output is the recorded data whose result is fed back to the server. For example, the user recommends a product or applies a coupon.

[0309] Step 7:

[0310] The server uses the learning means to improve the accuracy of the proposal generation means based on the results fed back. The input is the data of the execution result, and the output is the improved proposal generation algorithm. As a specific operation, the collected data is analyzed using a machine learning algorithm to enhance the future proposal accuracy.

[0311] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0312] This invention is a follow-up suggestion generation system that combines an emotion engine that recognizes customer emotions based on the customer's dialogue history. The system consists of a server, a salesperson's terminal, and user operations.

[0313] Processes performed by the server:

[0314] The server first collects the history of interactions with the customer. This history is recorded as voice calls or text chats and sent from the terminal to the server. The server analyzes this history using natural language processing technology. This analysis includes recognizing the customer's emotional state using an emotion engine. The emotion engine analyzes the tone of voice and linguistic expressions to determine the customer's emotional state. Based on this information, the server constructs personalized follow-up suggestions that combine the customer's interests, needs, and emotional state.

[0315] Process performed by the terminal:

[0316] The terminal notifies salespeople of follow-up suggestions received from the server. These notifications are tailored to the customer's emotional state, helping salespeople respond more appropriately. For example, if a customer is stressed, the terminal displays suggestions recommending a more careful approach to customer service. The terminal also utilizes past emotional history to list products and services that the customer prefers.

[0317] The process performed by the user:

[0318] The user, or salesperson, reviews the suggestions displayed on the device and follows up based on the customer's current emotional state. For example, if a customer is considering purchasing a new smartphone and the emotion engine determines that the customer is feeling excited, the device will recommend positive suggestions that match that emotion (e.g., features for using the smartphone's hobbies). The salesperson can then use these suggestions to take appropriate actions, such as sending an email to the customer or encouraging them to visit the store again.

[0319] This system records the results of follow-up activities on a server and uses them to inform future proposals. This process enables salespeople to consistently provide improved, high-quality customer service, which is expected to increase customer satisfaction.

[0320] The following describes the processing flow.

[0321] Step 1:

[0322] The server collects the history of interactions with customers. The terminal records voice calls and text chats with customers and sends the data to the server.

[0323] Step 2:

[0324] The server analyzes the received dialogue history data using natural language processing technology. Using an emotion engine, it recognizes the customer's emotions from the tone of voice and the linguistic expressions in the text, and performs analysis to identify that emotional state.

[0325] Step 3:

[0326] Based on the analysis results, the server generates personalized follow-up suggestions that take into account the customer's interests, needs, and emotional state. These suggestions include appropriate language and product information tailored to the customer's emotional state.

[0327] Step 4:

[0328] The server sends the generated follow-up proposal to the terminal. The terminal immediately notifies the salesperson of the proposal content, prompting them to prepare for customer interaction.

[0329] Step 5:

[0330] The user reviews the follow-up suggestions displayed on their device. Based on these suggestions, the user takes follow-up actions appropriate to the customer's emotional state. For example, for a customer experiencing stress, the user might offer gentler suggestions in a calmer tone.

[0331] Step 6:

[0332] The terminal records the results of the follow-up actions performed and sends them to the server. This helps improve the accuracy of future suggestions.

[0333] Step 7:

[0334] The server undergoes a learning process based on feedback. It uses newly acquired data to improve the system and enhance the quality of proposals in future customer interactions.

[0335] (Example 2)

[0336] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0337] There is a challenge in that it is difficult to appropriately and efficiently analyze the emotional state and interests of customers from the vast amount of information obtained through interactions with customers, automatically generate individually optimized follow-up proposals, and improve the quality of customer service.

[0338] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0339] In this invention, the server includes information acquisition means for collecting customer interaction history, data analysis means for analyzing the interaction history using natural language processing technology to recognize the customer's emotional state, and information creation means for generating personalized follow-up proposals based on the recognized customer emotional state, interests, and needs. This enables the rapid and accurate creation of proposals tailored to each customer's characteristics and emotions, thereby improving customer satisfaction.

[0340] "Information acquisition means" refers to a system that has the function of collecting the history of conversations with customers and recording it in data format such as audio or text.

[0341] "Data analysis means" refers to a system that applies natural language processing technology to collected dialogue history and has the function of processing to recognize the customer's emotional state.

[0342] "Information creation means" refers to a system that has the function of generating personalized follow-up proposals based on the customer's emotional state, interests, and needs obtained through analysis.

[0343] A "transmission means" is a device that has the function of transmitting the generated follow-up proposal and related information to the terminal and notifying the user at an appropriate time.

[0344] A "learning tool" is a system that collects feedback on the results of follow-up proposals and uses that feedback to improve future proposals.

[0345] This invention is a system that generates follow-up suggestions by utilizing the history of conversations with customers. The system mainly consists of a server, terminals, and users. Specific embodiments of each component are described below.

[0346] The server receives the history of customer interactions transmitted from the salesperson's terminal. This history is recorded as voice calls and text chats. The server analyzes this history using spaCy, an open-source natural language processing library. Through analysis, it tokenizes the text, understands the context, extracts keywords, and recognizes the customer's emotional state. Furthermore, it uses the Python library OpenAI to perform tone analysis and sentiment analysis of the voice data, thereby evaluating the customer's emotions in detail.

[0347] Next, the server uses a generative AI model to create personalized follow-up suggestions. This model is inputted with data on the customer's current emotions and past interests and needs, and generates suggestions based on appropriate prompts. An example of a prompt is, "Based on the customer's conversation history, please generate follow-up suggestions focusing on topics that the customer is likely to enjoy."

[0348] The generated suggestions are sent from the server to the terminal. The terminal is a device for notifying salespeople of these suggestions, providing timely information using push notifications and banner displays. The terminal also displays a list of the customer's sentiment history and past interests to the salesperson, visually supporting the relevance of the suggested content.

[0349] The user, or salesperson, follows up with the customer based on the suggestions displayed on the terminal. For example, if a customer shows interest in a new smartphone and sentiment analysis detects enjoyment, it would be appropriate for the salesperson to make suggestions specifically focused on the smartphone's camera features. In this way, salespeople can provide customers with more personalized service.

[0350] Through the specific examples described above, this invention can greatly improve the flexibility and quality of customer service.

[0351] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0352] Step 1:

[0353] The server receives the customer interaction history from the salesperson's terminal. The input data is either audio files or text logs, which are stored in the database. Specifically, audio data is recorded in storage, and text is stored as a log. The output here is a dataset of the interaction history prepared for analysis.

[0354] Step 2:

[0355] The server uses the spaCy library to analyze the conversation history in text format. The input is the text log saved in step 1. Specific operations include sentence splitting, tokenization, and named entity recognition. Through this process, keywords related to customer interests and needs are extracted, and the analysis results are generated as output.

[0356] Step 3:

[0357] The server uses OpenAI to perform tone analysis and sentiment analysis of voice data. The input is the voice data saved in Step 1. Specifically, the voice is converted to text, and the customer's emotional state is analyzed from the tone and manner of speaking. The output is the customer's emotional status.

[0358] Step 4:

[0359] The server combines the analysis results data with the customer's emotional status and inputs it into the generative AI model. The prompt used here is "Generate follow-up suggestions based on the customer's conversation history, focusing on topics that the customer is likely to anticipate." This causes the generative AI model to generate personalized follow-up suggestions, which are then obtained as output.

[0360] Step 5:

[0361] The server sends the generated follow-up proposal to the terminal. The input is the generation result from step 4, and the proposal is transmitted to the salesperson's terminal via the terminal transmission protocol. The output is the follow-up proposal displayed on the terminal.

[0362] Step 6:

[0363] The device notifies the salesperson of the proposed content and displays detailed information. Specific actions include sending alerts to the salesperson using push notifications and displaying a list of the customer's sentiment history on the screen. The output here is quickly accessible and understandable proposal information for the salesperson.

[0364] Step 7:

[0365] The user follows up with customers based on the suggestions displayed on the device. Based on the information obtained in Step 6, they send emails to customers or introduce new products. This allows the user to provide more appropriate responses tailored to each customer. The output of this step is the result of the follow-up actions taken.

[0366] Step 8:

[0367] User feedback is sent to the server and used to improve follow-up suggestions for future interactions. Specifically, it is stored as data to optimize the suggestion generation algorithm based on the effectiveness of the follow-up. This further improves customer service in subsequent interactions. The output is a dataset that helps in generating improved suggestions.

[0368] (Application Example 2)

[0369] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0370] The system for automatically generating personalized follow-up suggestions that take into account the customer's emotional state, using information gathered through customer interactions, and communicating these suggestions to sales staff was insufficient. In this situation, it is difficult to provide customer service that appropriately reflects customer emotions, and improvements in customer satisfaction cannot be expected. Furthermore, a system is needed to accumulate the results of follow-up activities and continuously improve the accuracy of suggestion generation.

[0371] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0372] In this invention, the server includes information gathering means for collecting customer interaction history, emotion recognition means for analyzing the interaction history using natural language processing technology and determining the customer's emotional state, suggestion generation means for generating personalized follow-up suggestions based on the extracted customer interests, needs, and emotional state, communication means for notifying a portable terminal of the generated follow-up suggestions, follow-up execution means for executing the follow-up suggestions using the terminal and recording the results, and experience learning means for improving the suggestion generation means using the execution results. This makes it possible to immediately provide accurate follow-up that takes customer emotions into consideration, enabling salespeople to provide higher quality service.

[0373] "Information gathering means" refers to elements that have the function of recording and collecting the history of interactions with customers.

[0374] An "emotion recognition means" is an element that uses natural language processing technology to analyze dialogue history and determine the customer's emotional state.

[0375] A "proposal generation means" is an element that has the function of generating personalized follow-up proposals based on the extracted customer interests, needs, and emotional state.

[0376] "Communication means" refers to an element that has the function of notifying a portable terminal of the generated follow-up proposal.

[0377] A "follow-up execution means" is an element that has the function of executing follow-up proposals using a terminal and recording the results of those implementations.

[0378] An "experiential learning tool" is an element that has the function of improving the proposal generation tool using the results of follow-up execution and continuously improving the system.

[0379] The system implementing this invention consists of a server, a terminal used by a salesperson, and user interaction.

[0380] First, the server collects a history of interactions with the customer, including voice calls and text chats. The voice and text data are analyzed using natural language processing techniques, and the customer's emotional state is determined using emotion recognition tools. The technologies used include machine learning models built in Python and TensorFlow. Based on this information, the server generates personalized follow-up suggestions that reflect the customer's interests, needs, and emotional state using suggestion generation tools.

[0381] Next, the terminal receives communication from the server and notifies the salesperson of the generated follow-up suggestion. The salesperson can use a smartphone or smart glasses. This allows the salesperson to obtain information hands-free and check the suggestion in real time while interacting with the customer.

[0382] The salesperson (user) executes follow-up suggestions via a terminal, and the results are recorded using the follow-up execution device. This information is used to improve the suggestion generation device through the experiential learning device, and the accuracy of the suggestions improves over time.

[0383] For example, when a salesperson wearing smart glasses interacts with a customer in a store, if the system analyzes that the customer is excited, a follow-up suggestion such as "It would be good to provide information about new products" will be displayed on the terminal's screen.

[0384] An example of a prompt might be a question like, "What product categories did this customer mention as being good in past conversations?" This allows the AI ​​to provide salespeople with information about the customer's past interests and tendencies, enabling more accurate follow-up.

[0385] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0386] Step 1:

[0387] The server collects customer interaction history from voice calls and text chats using information gathering tools. The input for this step is communication data between the customer and the salesperson, and the output is a structured log of that data. The server records this data and stores it in a database.

[0388] Step 2:

[0389] The server analyzes the collected dialogue history using natural language processing techniques and determines the customer's emotional state using emotion recognition. The input is the collected dialogue history, and the output is the customer's emotional state as a result of the analysis (e.g., joy or excitement). Python and TensorFlow are used to evaluate the emotion of the voice tone and text.

[0390] Step 3:

[0391] The server generates personalized follow-up suggestions using a suggestion generation system based on the customer's interests, needs, and emotional state. The input is customer data such as the emotional state and past purchase history determined in step 2, and the output is personalized suggestion content. An AI generation model is used in this process to construct appropriate suggestions.

[0392] Step 4:

[0393] The server sends the generated follow-up proposal to the terminal using a communication method. The input is the proposal content created in step 3, and the output is the proposal information displayed on the terminal. The terminal receives this and notifies the salesperson.

[0394] Step 5:

[0395] Salespeople (users) equipped with a terminal execute follow-up proposals they receive, and the details and results of these executions are recorded using the follow-up execution device. The input is data on how the salesperson utilized the proposal, and the output is a log of the results. Based on this information, the salesperson takes specific actions with the customer.

[0396] Step 6:

[0397] The server analyzes the follow-up execution results using an empirical learning mechanism and improves the functionality of the proposal generation mechanism. The input is the execution result recorded in step 5, and the output is the adjusted algorithm to improve the accuracy of the next proposal. This improves the overall accuracy and efficiency of the system.

[0398] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0399] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0400] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0401] [Third Embodiment]

[0402] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0403] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0404] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0405] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0406] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0407] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0408] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0409] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0410] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0411] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0412] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0413] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0414] This invention is a system that automatically generates personalized follow-up suggestions based on customer interaction history to support salespeople. The system consists of a server, a salesperson's terminal, and user operation.

[0415] Processes performed by the server:

[0416] The server first collects the customer's interaction history. This information is collected using the terminal and stored in the form of voice calls and text chats. The collected data is analyzed using a natural language processing algorithm built on the server side. This analysis reveals the customer's specific interests and needs, which are recorded in the database. The server also generates the optimal follow-up action to take based on these analysis results.

[0417] Process performed by the terminal:

[0418] The terminal receives follow-up suggestions from the server and notifies the salesperson. By notifying at the appropriate time, it helps salespeople take efficient and quick action. For example, the terminal displays a draft of an automatically generated email for the customer, allowing the salesperson to easily customize and send it. At this stage, the salesperson can fine-tune the suggestion based on the customer's response, providing a more personalized response.

[0419] The process performed by the user:

[0420] Salespeople (users) use follow-up suggestions displayed on their devices to provide actual customer service. For example, if a customer is considering purchasing a new smartphone, the suggestions notified from the device might include an email introducing a smartphone with high-performance camera capabilities. The salesperson sends this email in a timely manner, providing information tailored to the customer's interests. In this way, users can use the provided tools to deliver more consistent and high-quality customer service.

[0421] The results of all actions are sent from the terminal to the server and used as training data to improve the accuracy of future suggestions. This allows the system to continuously improve, not only increasing the efficiency of sales staff but also improving customer satisfaction.

[0422] The following describes the processing flow.

[0423] Step 1:

[0424] The server collects customer interactions. Salespeople's terminals record voice calls and text messages in real time and transfer that data to the server.

[0425] Step 2:

[0426] The server analyzes the collected data using natural language processing technology. It extracts customer interests, needs, and emotions from the conversation content and stores the analysis results as structured data.

[0427] Step 3:

[0428] Based on the analysis results, the server generates follow-up suggestions tailored to the customer's needs. These are automatically created using pre-configured rules and AI models.

[0429] Step 4:

[0430] A follow-up proposal is sent from the server to the salesperson's terminal. The terminal notifies the user of the received proposal and prompts them to take action.

[0431] Step 5:

[0432] Users review follow-up suggestions displayed on their devices and respond to customer inquiries accordingly. For example, they might customize an automatically generated email draft and send it to the customer.

[0433] Step 6:

[0434] The device records the results of user actions and transfers them to the server. These results include follow-up customer feedback and new needs.

[0435] Step 7:

[0436] The server incorporates the collected action results into a learning model, which is then used to improve the accuracy of future suggestions. The system is continuously improved, enabling more effective responses to customers.

[0437] (Example 1)

[0438] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0439] In customer service, it is essential to quickly and accurately understand the interests and needs of individual customers and to provide effective follow-up proposals based on that understanding. However, the current system is time-consuming in terms of data analysis and proposal creation, which reduces the efficiency of sales staff. Furthermore, it is difficult to provide follow-up at the appropriate time, resulting in a failure to adequately improve customer satisfaction.

[0440] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0441] In this invention, the server includes means for accumulating information, means for analyzing the information using processing technology to extract the target's interests and needs, and means for creating personalized suggestions based on the extracted interests and needs. This enables the generation and notification of rapid and accurate follow-up suggestions based on the customer's interests and needs.

[0442] "Means of collecting information" refers to functions for gathering information from an object, recording that data, and storing it.

[0443] "Processing technology" refers to data analysis techniques used to analyze collected information and derive meaningful results.

[0444] "Means for extracting the interests and needs of a subject" refers to a function that uses processing technology to identify the specific interests and needs of a subject from the data obtained from that subject.

[0445] "Means for creating personalized proposals" refers to a function that automatically generates proposals optimized for a specific target based on the interests and needs of the extracted target.

[0446] "Information equipment" refers to electronic devices used for processing, displaying, or transmitting digital data.

[0447] "Means of notifying information" refers to the function of transmitting generated proposals and important information to specific information devices.

[0448] The "function to notify the timing of proposal implementation" refers to a function in which information devices inform the user of the optimal time or situation for implementing a proposal.

[0449] This invention is a system for improving the efficiency of customer service operations and enhancing customer satisfaction. The system consists of a server, a user terminal, and the user's own operations.

[0450] Server operation:

[0451] The server first collects customer interaction history using data aggregation methods. This aggregation includes voice and text information, utilizing general-purpose technologies such as call logs and chat platforms. The collected data is then stored directly in a database. The server then uses processing techniques to perform natural language processing on the data, extracting the target's interests and needs. For example, it uses Python's NLTK library or TensorFlow to perform text tokenization and syntactic analysis using machine learning algorithms. Based on the insights gained from this analysis, it uses a generative AI model (e.g., GPT-3) to create personalized suggestions. In this process, the following prompt is used as input to the generative AI model: "Create a follow-up email for customers who showed interest in the new product based on recent conversations."

[0452] Device operation:

[0453] The user's device receives generation proposals notified from the server. The device displays the received information and, for example, integrates with a sales support application to inform the user of the optimal timing. Notifications are made in the form of pop-ups or emails to help users respond quickly. This enables seamless implementation of follow-up proposals.

[0454] User actions:

[0455] Users utilize the suggestions displayed on their terminals to handle actual customer interactions. This is achieved, for example, by fine-tuning the content of a proposed email and sending it to the customer. Users also provide feedback to the server via their terminals after implementing the suggestions, contributing to the continuous optimization of the system. The feedback results are used by the server's learning mechanisms to improve the accuracy of future suggestion generation. As a result, the system improves over time, enhancing the user's work efficiency.

[0456] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0457] Step 1:

[0458] The server collects customer interaction history using data aggregation methods. It receives voice and text information as input and stores call records and chat logs in a database. This operation often utilizes real-time data streaming technology.

[0459] Step 2:

[0460] The server analyzes the collected data using natural language processing techniques. Here, the input dialogue data is tokenized and parsed. Using Python libraries and other machine learning tools, it obtains output that extracts customer interests and needs.

[0461] Step 3:

[0462] The server generates personalized suggestions using a generative AI model based on the extracted customer interests and needs. Specifically, it processes the analysis results into prompt sentences as input and passes them to the generative AI model to output suggestion sentences tailored to the customer.

[0463] Step 4:

[0464] The device receives suggestions generated from the server and notifies the user. It receives the suggestion content as input and displays the notification as output. The device provides information to the user at the appropriate time using pop-ups or email notifications.

[0465] Step 5:

[0466] The user reviews the proposal displayed on the terminal and then interacts with the customer. As input, they consider the proposal content and perform data processing such as customization. As output, they send the customized proposal to the customer.

[0467] Step 6:

[0468] The results of user actions are fed back to the server via the terminal. Customer interaction result data is received as input, and the output is stored as training data to improve the accuracy of suggestion generation. This feedback loop continuously improves the overall system performance.

[0469] (Application Example 1)

[0470] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0471] Follow-up suggestions based on customer interaction history generally have a low degree of personalization, making it difficult to provide consistently high-quality customer service. Furthermore, if the timing or content of follow-up suggestions is inappropriate, they may fail to increase customer purchase intent.

[0472] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0473] In this invention, the server includes data collection means for collecting customer interaction history, data analysis means for analyzing the interaction history using natural language processing technology to extract customer preferences and requests, suggestion generation means for generating personalized follow-up suggestions based on the extracted information, notification means, and presentation means for automatically displaying product suggestions and coupons based on the customer interaction history. This makes it possible to provide personalized suggestions at the appropriate time, effectively increasing the customer's willingness to purchase.

[0474] "Data collection means" refers to a device or method for recording the history of conversations with customers, and is a means of collecting conversation content in various forms, including voice communication and text conversations.

[0475] "Data analysis means" refers to a program or device that has the function of analyzing dialogue history collected using natural language processing technology and extracting customer preferences and requests.

[0476] "Proposal generation means" refers to a device or method for automatically generating personalized follow-up proposals based on analyzed customer preferences and requests.

[0477] "Notification means" refers to a device or method for notifying a communication terminal of the generated follow-up proposal, and includes a function for informing the timing of the proposal's implementation.

[0478] "Follow-up execution means" refers to an apparatus or method for carrying out a notified follow-up suggestion and recording the results.

[0479] "Learning means" refers to a device or method that has the function of learning data to improve the accuracy of the proposal generation means using the results of the execution of follow-up proposals.

[0480] "Presentation means" refers to a device or method for automatically displaying personalized product suggestions or coupons on a communication terminal based on the customer's dialogue history.

[0481] This invention is a system that automatically generates personalized follow-up suggestions based on customer interaction history to support salespeople. The system consists of a server, terminals, and user operations.

[0482] The server collects customer interaction history using data collection means. This history is recorded in the form of voice communication or text conversation and stored on the server. Next, data analysis means analyze the collected history using natural language processing algorithms (specifically, Python, NLTK, spaCy, etc.) to extract customer preferences and requests. Based on this, suggestion generation means generates personalized follow-up suggestions and sends them to the communication terminal via notification means.

[0483] The device receives notifications and presents follow-up suggestions to the user at the appropriate time. During this process, personalized options are offered to the customer, such as automatically displaying product suggestions and coupons through the presentation method. Furthermore, sales staff can easily obtain the necessary information to respond to customers based on these suggestions, enabling them to efficiently recommend products.

[0484] All follow-up execution results are fed back to the server using learning tools to continuously improve the accuracy of the suggestion generation tool. It is also possible to utilize the generation AI model with the following example prompt: "Generate personalized product suggestions based on the following customer's dialogue history. Dialogue History: "I want to know more about wireless earphones. I'm concerned about sound quality and battery life." Purchase History: "Smartphone case, mobile battery."

[0485] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0486] Step 1:

[0487] The server collects customer interaction history using data collection methods. Input is voice communication and text conversation data, and output is interaction history data stored on the server. In this process, call recordings and chat logs are automatically uploaded to the server and stored in the database.

[0488] Step 2:

[0489] The server analyzes the collected dialogue history using data analysis tools. The input is the dialogue history data stored on the server, and the output is the analysis results, including customer preferences and requests. Specifically, it executes natural language processing algorithms (such as Python, NLTK, and spaCy) to extract keywords from the text data and identify customer interests.

[0490] Step 3:

[0491] The server generates personalized follow-up suggestions based on the analysis results using a suggestion generation mechanism. The input is the analysis results showing the customer's preferences and requests, and the output is a follow-up plan that includes specific product suggestions and coupon information. When generating suggestions, a generation AI model is used, and a recommendation algorithm based on past data and rules is applied.

[0492] Step 4:

[0493] The server notifies the terminal of follow-up suggestions generated using the notification mechanism. The input is the follow-up suggestion, and the output is the notification displayed on the terminal. The server calculates the appropriate timing and sends the notification in real time.

[0494] Step 5:

[0495] The device receives notifications and presents follow-up suggestions to the user. The input is notification information from the server, and the output is the suggested content displayed in the user interface. Specifically, the device displays the suggested content on the UI and provides an environment where the user can take action based on it.

[0496] Step 6:

[0497] Users use a terminal to perform follow-up suggestions and record the results. The input is the action performed by the user, and the output is the recorded data of the result that is fed back to the server. For example, users might recommend products or apply coupons.

[0498] Step 7:

[0499] The server improves the accuracy of the proposal generation mechanism based on the feedback received using a learning mechanism. The input is the execution result data, and the output is the improved proposal generation algorithm. Specifically, it uses a machine learning algorithm to analyze the collected data and improve the accuracy of future proposals.

[0500] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0501] This invention is a follow-up suggestion generation system that combines an emotion engine that recognizes customer emotions based on the customer's dialogue history. The system consists of a server, a salesperson's terminal, and user operations.

[0502] Processes performed by the server:

[0503] The server first collects the history of interactions with the customer. This history is recorded as voice calls or text chats and sent from the terminal to the server. The server analyzes this history using natural language processing technology. This analysis includes recognizing the customer's emotional state using an emotion engine. The emotion engine analyzes the tone of voice and linguistic expressions to determine the customer's emotional state. Based on this information, the server constructs personalized follow-up suggestions that combine the customer's interests, needs, and emotional state.

[0504] Process performed by the terminal:

[0505] The terminal notifies salespeople of follow-up suggestions received from the server. These notifications are tailored to the customer's emotional state, helping salespeople respond more appropriately. For example, if a customer is stressed, the terminal displays suggestions recommending a more careful approach to customer service. The terminal also utilizes past emotional history to list products and services that the customer prefers.

[0506] The process performed by the user:

[0507] The user, or salesperson, reviews the suggestions displayed on the device and follows up based on the customer's current emotional state. For example, if a customer is considering purchasing a new smartphone and the emotion engine determines that the customer is feeling excited, the device will recommend positive suggestions that match that emotion (e.g., features for using the smartphone's hobbies). The salesperson can then use these suggestions to take appropriate actions, such as sending an email to the customer or encouraging them to visit the store again.

[0508] This system records the results of follow-up activities on a server and uses them to inform future proposals. This process enables salespeople to consistently provide improved, high-quality customer service, which is expected to increase customer satisfaction.

[0509] The following describes the processing flow.

[0510] Step 1:

[0511] The server collects the history of interactions with customers. The terminal records voice calls and text chats with customers and sends the data to the server.

[0512] Step 2:

[0513] The server analyzes the received dialogue history data using natural language processing technology. Using an emotion engine, it recognizes the customer's emotions from the tone of voice and the linguistic expressions in the text, and performs analysis to identify that emotional state.

[0514] Step 3:

[0515] Based on the analysis results, the server generates personalized follow-up suggestions that take into account the customer's interests, needs, and emotional state. These suggestions include appropriate language and product information tailored to the customer's emotional state.

[0516] Step 4:

[0517] The server sends the generated follow-up proposal to the terminal. The terminal immediately notifies the salesperson of the proposal content, prompting them to prepare for customer interaction.

[0518] Step 5:

[0519] The user reviews the follow-up suggestions displayed on their device. Based on these suggestions, the user takes follow-up actions appropriate to the customer's emotional state. For example, for a customer experiencing stress, the user might offer gentler suggestions in a calmer tone.

[0520] Step 6:

[0521] The terminal records the results of the follow-up actions performed and sends them to the server. This helps improve the accuracy of future suggestions.

[0522] Step 7:

[0523] The server undergoes a learning process based on feedback. It uses newly acquired data to improve the system and enhance the quality of proposals in future customer interactions.

[0524] (Example 2)

[0525] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0526] There is a challenge in that it is difficult to appropriately and efficiently analyze the emotional state and interests of customers from the vast amount of information obtained through interactions with customers, automatically generate individually optimized follow-up proposals, and improve the quality of customer service.

[0527] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0528] In this invention, the server includes information acquisition means for collecting customer interaction history, data analysis means for analyzing the interaction history using natural language processing technology to recognize the customer's emotional state, and information creation means for generating personalized follow-up proposals based on the recognized customer emotional state, interests, and needs. This enables the rapid and accurate creation of proposals tailored to each customer's characteristics and emotions, thereby improving customer satisfaction.

[0529] "Information acquisition means" refers to a system that has the function of collecting the history of conversations with customers and recording it in data format such as audio or text.

[0530] "Data analysis means" refers to a system that applies natural language processing technology to collected dialogue history and has the function of processing to recognize the customer's emotional state.

[0531] "Information creation means" refers to a system that has the function of generating personalized follow-up proposals based on the customer's emotional state, interests, and needs obtained through analysis.

[0532] A "transmission means" is a device that has the function of transmitting the generated follow-up proposal and related information to the terminal and notifying the user at an appropriate time.

[0533] A "learning tool" is a system that collects feedback on the results of follow-up proposals and uses that feedback to improve future proposals.

[0534] This invention is a system that generates follow-up suggestions by utilizing the history of conversations with customers. The system mainly consists of a server, terminals, and users. Specific embodiments of each component are described below.

[0535] The server receives the history of customer interactions transmitted from the salesperson's terminal. This history is recorded as voice calls and text chats. The server analyzes this history using spaCy, an open-source natural language processing library. Through analysis, it tokenizes the text, understands the context, extracts keywords, and recognizes the customer's emotional state. Furthermore, it uses the Python library OpenAI to perform tone analysis and sentiment analysis of the voice data, thereby evaluating the customer's emotions in detail.

[0536] Next, the server uses a generative AI model to create personalized follow-up suggestions. This model is inputted with data on the customer's current emotions and past interests and needs, and generates suggestions based on appropriate prompts. An example of a prompt is, "Based on the customer's conversation history, please generate follow-up suggestions focusing on topics that the customer is likely to enjoy."

[0537] The generated suggestions are sent from the server to the terminal. The terminal is a device for notifying salespeople of these suggestions, providing timely information using push notifications and banner displays. The terminal also displays a list of the customer's sentiment history and past interests to the salesperson, visually supporting the relevance of the suggested content.

[0538] The user, or salesperson, follows up with the customer based on the suggestions displayed on the terminal. For example, if a customer shows interest in a new smartphone and sentiment analysis detects enjoyment, it would be appropriate for the salesperson to make suggestions specifically focused on the smartphone's camera features. In this way, salespeople can provide customers with more personalized service.

[0539] Through the specific examples described above, this invention can greatly improve the flexibility and quality of customer service.

[0540] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0541] Step 1:

[0542] The server receives the customer interaction history from the salesperson's terminal. The input data is either audio files or text logs, which are stored in the database. Specifically, audio data is recorded in storage, and text is stored as a log. The output here is a dataset of the interaction history prepared for analysis.

[0543] Step 2:

[0544] The server uses the spaCy library to analyze the conversation history in text format. The input is the text log saved in step 1. Specific operations include sentence splitting, tokenization, and named entity recognition. Through this process, keywords related to customer interests and needs are extracted, and the analysis results are generated as output.

[0545] Step 3:

[0546] The server uses OpenAI to perform tone analysis and sentiment analysis of voice data. The input is the voice data saved in Step 1. Specifically, the voice is converted to text, and the customer's emotional state is analyzed from the tone and manner of speaking. The output is the customer's emotional status.

[0547] Step 4:

[0548] The server combines the analysis results data with the customer's emotional status and inputs it into the generative AI model. The prompt used here is "Generate follow-up suggestions based on the customer's conversation history, focusing on topics that the customer is likely to anticipate." This causes the generative AI model to generate personalized follow-up suggestions, which are then obtained as output.

[0549] Step 5:

[0550] The server sends the generated follow-up proposal to the terminal. The input is the generation result from step 4, and the proposal is transmitted to the salesperson's terminal via the terminal transmission protocol. The output is the follow-up proposal displayed on the terminal.

[0551] Step 6:

[0552] The device notifies the salesperson of the proposed content and displays detailed information. Specific actions include sending alerts to the salesperson using push notifications and displaying a list of the customer's sentiment history on the screen. The output here is quickly accessible and understandable proposal information for the salesperson.

[0553] Step 7:

[0554] The user follows up with customers based on the suggestions displayed on the device. Based on the information obtained in Step 6, they send emails to customers or introduce new products. This allows the user to provide more appropriate responses tailored to each customer. The output of this step is the result of the follow-up actions taken.

[0555] Step 8:

[0556] User feedback is sent to the server and used to improve follow-up suggestions for future interactions. Specifically, it is stored as data to optimize the suggestion generation algorithm based on the effectiveness of the follow-up. This further improves customer service in subsequent interactions. The output is a dataset that helps in generating improved suggestions.

[0557] (Application Example 2)

[0558] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0559] The system for automatically generating personalized follow-up suggestions that take into account the customer's emotional state, using information gathered through customer interactions, and communicating these suggestions to sales staff was insufficient. In this situation, it is difficult to provide customer service that appropriately reflects customer emotions, and improvements in customer satisfaction cannot be expected. Furthermore, a system is needed to accumulate the results of follow-up activities and continuously improve the accuracy of suggestion generation.

[0560] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0561] In this invention, the server includes information gathering means for collecting customer interaction history, emotion recognition means for analyzing the interaction history using natural language processing technology and determining the customer's emotional state, suggestion generation means for generating personalized follow-up suggestions based on the extracted customer interests, needs, and emotional state, communication means for notifying a portable terminal of the generated follow-up suggestions, follow-up execution means for executing the follow-up suggestions using the terminal and recording the results, and experience learning means for improving the suggestion generation means using the execution results. This makes it possible to immediately provide accurate follow-up that takes customer emotions into consideration, enabling salespeople to provide higher quality service.

[0562] "Information gathering means" refers to elements that have the function of recording and collecting the history of interactions with customers.

[0563] An "emotion recognition means" is an element that uses natural language processing technology to analyze dialogue history and determine the customer's emotional state.

[0564] A "proposal generation means" is an element that has the function of generating personalized follow-up proposals based on the extracted customer interests, needs, and emotional state.

[0565] "Communication means" refers to an element that has the function of notifying a portable terminal of the generated follow-up proposal.

[0566] A "follow-up execution means" is an element that has the function of executing follow-up proposals using a terminal and recording the results of those implementations.

[0567] An "experiential learning tool" is an element that has the function of improving the proposal generation tool using the results of follow-up execution and continuously improving the system.

[0568] The system implementing this invention consists of a server, a terminal used by a salesperson, and user interaction.

[0569] First, the server collects a history of interactions with the customer, including voice calls and text chats. The voice and text data are analyzed using natural language processing techniques, and the customer's emotional state is determined using emotion recognition tools. The technologies used include machine learning models built in Python and TensorFlow. Based on this information, the server generates personalized follow-up suggestions that reflect the customer's interests, needs, and emotional state using suggestion generation tools.

[0570] Next, the terminal receives communication from the server and notifies the salesperson of the generated follow-up suggestion. The salesperson can use a smartphone or smart glasses. This allows the salesperson to obtain information hands-free and check the suggestion in real time while interacting with the customer.

[0571] The salesperson (user) executes follow-up suggestions via a terminal, and the results are recorded using the follow-up execution device. This information is used to improve the suggestion generation device through the experiential learning device, and the accuracy of the suggestions improves over time.

[0572] For example, when a salesperson wearing smart glasses interacts with a customer in a store, if the system analyzes that the customer is excited, a follow-up suggestion such as "It would be good to provide information about new products" will be displayed on the terminal's screen.

[0573] An example of a prompt might be a question like, "What product categories did this customer mention as being good in past conversations?" This allows the AI ​​to provide salespeople with information about the customer's past interests and tendencies, enabling more accurate follow-up.

[0574] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0575] Step 1:

[0576] The server collects customer interaction history from voice calls and text chats using information gathering tools. The input for this step is communication data between the customer and the salesperson, and the output is a structured log of that data. The server records this data and stores it in a database.

[0577] Step 2:

[0578] The server analyzes the collected dialogue history using natural language processing techniques and determines the customer's emotional state using emotion recognition. The input is the collected dialogue history, and the output is the customer's emotional state as a result of the analysis (e.g., joy or excitement). Python and TensorFlow are used to evaluate the emotion of the voice tone and text.

[0579] Step 3:

[0580] The server generates personalized follow-up suggestions using a suggestion generation system based on the customer's interests, needs, and emotional state. The input is customer data such as the emotional state and past purchase history determined in step 2, and the output is personalized suggestion content. An AI generation model is used in this process to construct appropriate suggestions.

[0581] Step 4:

[0582] The server sends the generated follow-up proposal to the terminal using a communication method. The input is the proposal content created in step 3, and the output is the proposal information displayed on the terminal. The terminal receives this and notifies the salesperson.

[0583] Step 5:

[0584] Salespeople (users) equipped with a terminal execute follow-up proposals they receive, and the details and results of these executions are recorded using the follow-up execution device. The input is data on how the salesperson utilized the proposal, and the output is a log of the results. Based on this information, the salesperson takes specific actions with the customer.

[0585] Step 6:

[0586] The server analyzes the follow-up execution results using an empirical learning mechanism and improves the functionality of the proposal generation mechanism. The input is the execution result recorded in step 5, and the output is the adjusted algorithm to improve the accuracy of the next proposal. This improves the overall accuracy and efficiency of the system.

[0587] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0588] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0589] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0590] [Fourth Embodiment]

[0591] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0592] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0593] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0594] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0595] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0596] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0597] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0598] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0599] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0600] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0601] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0602] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0603] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0604] This invention is a system that automatically generates personalized follow-up suggestions based on customer interaction history to support salespeople. The system consists of a server, a salesperson's terminal, and user operation.

[0605] Processes performed by the server:

[0606] The server first collects the customer's interaction history. This information is collected using the terminal and stored in the form of voice calls and text chats. The collected data is analyzed using a natural language processing algorithm built on the server side. This analysis reveals the customer's specific interests and needs, which are recorded in the database. The server also generates the optimal follow-up action to take based on these analysis results.

[0607] Process performed by the terminal:

[0608] The terminal receives follow-up suggestions from the server and notifies the salesperson. By notifying at the appropriate time, it helps salespeople take efficient and quick action. For example, the terminal displays a draft of an automatically generated email for the customer, allowing the salesperson to easily customize and send it. At this stage, the salesperson can fine-tune the suggestion based on the customer's response, providing a more personalized response.

[0609] The process performed by the user:

[0610] Salespeople (users) use follow-up suggestions displayed on their devices to provide actual customer service. For example, if a customer is considering purchasing a new smartphone, the suggestions notified from the device might include an email introducing a smartphone with high-performance camera capabilities. The salesperson sends this email in a timely manner, providing information tailored to the customer's interests. In this way, users can use the provided tools to deliver more consistent and high-quality customer service.

[0611] The results of all actions are sent from the terminal to the server and used as training data to improve the accuracy of future suggestions. This allows the system to continuously improve, not only increasing the efficiency of sales staff but also improving customer satisfaction.

[0612] The following describes the processing flow.

[0613] Step 1:

[0614] The server collects customer interactions. Salespeople's terminals record voice calls and text messages in real time and transfer that data to the server.

[0615] Step 2:

[0616] The server analyzes the collected data using natural language processing technology. It extracts customer interests, needs, and emotions from the conversation content and stores the analysis results as structured data.

[0617] Step 3:

[0618] Based on the analysis results, the server generates follow-up suggestions tailored to the customer's needs. These are automatically created using pre-configured rules and AI models.

[0619] Step 4:

[0620] A follow-up proposal is sent from the server to the salesperson's terminal. The terminal notifies the user of the received proposal and prompts them to take action.

[0621] Step 5:

[0622] Users review follow-up suggestions displayed on their devices and respond to customer inquiries accordingly. For example, they might customize an automatically generated email draft and send it to the customer.

[0623] Step 6:

[0624] The device records the results of user actions and transfers them to the server. These results include follow-up customer feedback and new needs.

[0625] Step 7:

[0626] The server incorporates the collected action results into a learning model, which is then used to improve the accuracy of future suggestions. The system is continuously improved, enabling more effective responses to customers.

[0627] (Example 1)

[0628] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0629] In customer service, it is essential to quickly and accurately understand the interests and needs of individual customers and to provide effective follow-up proposals based on that understanding. However, the current system is time-consuming in terms of data analysis and proposal creation, which reduces the efficiency of sales staff. Furthermore, it is difficult to provide follow-up at the appropriate time, resulting in a failure to adequately improve customer satisfaction.

[0630] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0631] In this invention, the server includes means for accumulating information, means for analyzing the information using processing technology to extract the target's interests and needs, and means for creating personalized suggestions based on the extracted interests and needs. This enables the generation and notification of rapid and accurate follow-up suggestions based on the customer's interests and needs.

[0632] "Means of collecting information" refers to functions for gathering information from an object, recording that data, and storing it.

[0633] "Processing technology" refers to data analysis techniques used to analyze collected information and derive meaningful results.

[0634] "Means for extracting the interests and needs of a subject" refers to a function that uses processing technology to identify the specific interests and needs of a subject from the data obtained from that subject.

[0635] "Means for creating personalized proposals" refers to a function that automatically generates proposals optimized for a specific target based on the interests and needs of the extracted target.

[0636] "Information equipment" refers to electronic devices used for processing, displaying, or transmitting digital data.

[0637] "Means of notifying information" refers to the function of transmitting generated proposals and important information to specific information devices.

[0638] The "function to notify the timing of proposal implementation" refers to a function in which information devices inform the user of the optimal time or situation for implementing a proposal.

[0639] This invention is a system for improving the efficiency of customer service operations and enhancing customer satisfaction. The system consists of a server, a user terminal, and the user's own operations.

[0640] Server operation:

[0641] The server first collects customer interaction history using data aggregation methods. This aggregation includes voice and text information, utilizing general-purpose technologies such as call logs and chat platforms. The collected data is then stored directly in a database. The server then uses processing techniques to perform natural language processing on the data, extracting the target's interests and needs. For example, it uses Python's NLTK library or TensorFlow to perform text tokenization and syntactic analysis using machine learning algorithms. Based on the insights gained from this analysis, it uses a generative AI model (e.g., GPT-3) to create personalized suggestions. In this process, the following prompt is used as input to the generative AI model: "Create a follow-up email for customers who showed interest in the new product based on recent conversations."

[0642] Device operation:

[0643] The user's device receives generation proposals notified from the server. The device displays the received information and, for example, integrates with a sales support application to inform the user of the optimal timing. Notifications are made in the form of pop-ups or emails to help users respond quickly. This enables seamless implementation of follow-up proposals.

[0644] User actions:

[0645] Users utilize the suggestions displayed on their terminals to handle actual customer interactions. This is achieved, for example, by fine-tuning the content of a proposed email and sending it to the customer. Users also provide feedback to the server via their terminals after implementing the suggestions, contributing to the continuous optimization of the system. The feedback results are used by the server's learning mechanisms to improve the accuracy of future suggestion generation. As a result, the system improves over time, enhancing the user's work efficiency.

[0646] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0647] Step 1:

[0648] The server collects customer interaction history using data aggregation methods. It receives voice and text information as input and stores call records and chat logs in a database. This operation often utilizes real-time data streaming technology.

[0649] Step 2:

[0650] The server analyzes the collected data using natural language processing techniques. Here, the input dialogue data is tokenized and parsed. Using Python libraries and other machine learning tools, it obtains output that extracts customer interests and needs.

[0651] Step 3:

[0652] The server generates personalized suggestions using a generative AI model based on the extracted customer interests and needs. Specifically, it processes the analysis results into prompt sentences as input and passes them to the generative AI model to output suggestion sentences tailored to the customer.

[0653] Step 4:

[0654] The device receives suggestions generated from the server and notifies the user. It receives the suggestion content as input and displays the notification as output. The device provides information to the user at the appropriate time using pop-ups or email notifications.

[0655] Step 5:

[0656] The user reviews the proposal displayed on the terminal and then interacts with the customer. As input, they consider the proposal content and perform data processing such as customization. As output, they send the customized proposal to the customer.

[0657] Step 6:

[0658] The results of user actions are fed back to the server via the terminal. Customer interaction result data is received as input, and the output is stored as training data to improve the accuracy of suggestion generation. This feedback loop continuously improves the overall system performance.

[0659] (Application Example 1)

[0660] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0661] Follow-up suggestions based on customer interaction history generally have a low degree of personalization, making it difficult to provide consistently high-quality customer service. Furthermore, if the timing or content of follow-up suggestions is inappropriate, they may fail to increase customer purchase intent.

[0662] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0663] In this invention, the server includes data collection means for collecting customer interaction history, data analysis means for analyzing the interaction history using natural language processing technology to extract customer preferences and requests, suggestion generation means for generating personalized follow-up suggestions based on the extracted information, notification means, and presentation means for automatically displaying product suggestions and coupons based on the customer interaction history. This makes it possible to provide personalized suggestions at the appropriate time, effectively increasing the customer's willingness to purchase.

[0664] "Data collection means" refers to a device or method for recording the history of conversations with customers, and is a means of collecting conversation content in various forms, including voice communication and text conversations.

[0665] "Data analysis means" refers to a program or device that has the function of analyzing dialogue history collected using natural language processing technology and extracting customer preferences and requests.

[0666] "Proposal generation means" refers to a device or method for automatically generating personalized follow-up proposals based on analyzed customer preferences and requests.

[0667] "Notification means" refers to a device or method for notifying a communication terminal of the generated follow-up proposal, and includes a function for informing the timing of the proposal's implementation.

[0668] "Follow-up execution means" refers to an apparatus or method for carrying out a notified follow-up suggestion and recording the results.

[0669] "Learning means" refers to a device or method that has the function of learning data to improve the accuracy of the proposal generation means using the results of the execution of follow-up proposals.

[0670] "Presentation means" refers to a device or method for automatically displaying personalized product suggestions or coupons on a communication terminal based on the customer's dialogue history.

[0671] This invention is a system that automatically generates personalized follow-up suggestions based on customer interaction history to support salespeople. The system consists of a server, terminals, and user operations.

[0672] The server collects customer interaction history using data collection means. This history is recorded in the form of voice communication or text conversation and stored on the server. Next, data analysis means analyze the collected history using natural language processing algorithms (specifically, Python, NLTK, spaCy, etc.) to extract customer preferences and requests. Based on this, suggestion generation means generates personalized follow-up suggestions and sends them to the communication terminal via notification means.

[0673] The device receives notifications and presents follow-up suggestions to the user at the appropriate time. During this process, personalized options are offered to the customer, such as automatically displaying product suggestions and coupons through the presentation method. Furthermore, sales staff can easily obtain the necessary information to respond to customers based on these suggestions, enabling them to efficiently recommend products.

[0674] All follow-up execution results are fed back to the server using learning tools to continuously improve the accuracy of the suggestion generation tool. It is also possible to utilize the generation AI model with the following example prompt: "Generate personalized product suggestions based on the following customer's dialogue history. Dialogue History: "I want to know more about wireless earphones. I'm concerned about sound quality and battery life." Purchase History: "Smartphone case, mobile battery."

[0675] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0676] Step 1:

[0677] The server collects customer interaction history using data collection methods. Input is voice communication and text conversation data, and output is interaction history data stored on the server. In this process, call recordings and chat logs are automatically uploaded to the server and stored in the database.

[0678] Step 2:

[0679] The server analyzes the collected dialogue history using data analysis tools. The input is the dialogue history data stored on the server, and the output is the analysis results, including customer preferences and requests. Specifically, it executes natural language processing algorithms (such as Python, NLTK, and spaCy) to extract keywords from the text data and identify customer interests.

[0680] Step 3:

[0681] The server generates personalized follow-up suggestions based on the analysis results using a suggestion generation mechanism. The input is the analysis results showing the customer's preferences and requests, and the output is a follow-up plan that includes specific product suggestions and coupon information. When generating suggestions, a generation AI model is used, and a recommendation algorithm based on past data and rules is applied.

[0682] Step 4:

[0683] The server notifies the terminal of follow-up suggestions generated using the notification mechanism. The input is the follow-up suggestion, and the output is the notification displayed on the terminal. The server calculates the appropriate timing and sends the notification in real time.

[0684] Step 5:

[0685] The device receives notifications and presents follow-up suggestions to the user. The input is notification information from the server, and the output is the suggested content displayed in the user interface. Specifically, the device displays the suggested content on the UI and provides an environment where the user can take action based on it.

[0686] Step 6:

[0687] Users use a terminal to perform follow-up suggestions and record the results. The input is the action performed by the user, and the output is the recorded data of the result that is fed back to the server. For example, users might recommend products or apply coupons.

[0688] Step 7:

[0689] The server improves the accuracy of the proposal generation mechanism based on the feedback received using a learning mechanism. The input is the execution result data, and the output is the improved proposal generation algorithm. Specifically, it uses a machine learning algorithm to analyze the collected data and improve the accuracy of future proposals.

[0690] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0691] This invention is a follow-up suggestion generation system that combines an emotion engine that recognizes customer emotions based on the customer's dialogue history. The system consists of a server, a salesperson's terminal, and user operations.

[0692] Processes performed by the server:

[0693] The server first collects the history of interactions with the customer. This history is recorded as voice calls or text chats and sent from the terminal to the server. The server analyzes this history using natural language processing technology. This analysis includes recognizing the customer's emotional state using an emotion engine. The emotion engine analyzes the tone of voice and linguistic expressions to determine the customer's emotional state. Based on this information, the server constructs personalized follow-up suggestions that combine the customer's interests, needs, and emotional state.

[0694] Process performed by the terminal:

[0695] The terminal notifies salespeople of follow-up suggestions received from the server. These notifications are tailored to the customer's emotional state, helping salespeople respond more appropriately. For example, if a customer is stressed, the terminal displays suggestions recommending a more careful approach to customer service. The terminal also utilizes past emotional history to list products and services that the customer prefers.

[0696] The process performed by the user:

[0697] The user, or salesperson, reviews the suggestions displayed on the device and follows up based on the customer's current emotional state. For example, if a customer is considering purchasing a new smartphone and the emotion engine determines that the customer is feeling excited, the device will recommend positive suggestions that match that emotion (e.g., features for using the smartphone's hobbies). The salesperson can then use these suggestions to take appropriate actions, such as sending an email to the customer or encouraging them to visit the store again.

[0698] This system records the results of follow-up activities on a server and uses them to inform future proposals. This process enables salespeople to consistently provide improved, high-quality customer service, which is expected to increase customer satisfaction.

[0699] The following describes the processing flow.

[0700] Step 1:

[0701] The server collects the history of interactions with customers. The terminal records voice calls and text chats with customers and sends the data to the server.

[0702] Step 2:

[0703] The server analyzes the received dialogue history data using natural language processing technology. Using an emotion engine, it recognizes the customer's emotions from the tone of voice and the linguistic expressions in the text, and performs analysis to identify that emotional state.

[0704] Step 3:

[0705] Based on the analysis results, the server generates personalized follow-up suggestions that take into account the customer's interests, needs, and emotional state. These suggestions include appropriate language and product information tailored to the customer's emotional state.

[0706] Step 4:

[0707] The server sends the generated follow-up proposal to the terminal. The terminal immediately notifies the salesperson of the proposal content, prompting them to prepare for customer interaction.

[0708] Step 5:

[0709] The user reviews the follow-up suggestions displayed on their device. Based on these suggestions, the user takes follow-up actions appropriate to the customer's emotional state. For example, for a customer experiencing stress, the user might offer gentler suggestions in a calmer tone.

[0710] Step 6:

[0711] The terminal records the results of the follow-up actions performed and sends them to the server. This helps improve the accuracy of future suggestions.

[0712] Step 7:

[0713] The server undergoes a learning process based on feedback. It uses newly acquired data to improve the system and enhance the quality of proposals in future customer interactions.

[0714] (Example 2)

[0715] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0716] There is a challenge in that it is difficult to appropriately and efficiently analyze the emotional state and interests of customers from the vast amount of information obtained through interactions with customers, automatically generate individually optimized follow-up proposals, and improve the quality of customer service.

[0717] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0718] In this invention, the server includes information acquisition means for collecting customer interaction history, data analysis means for analyzing the interaction history using natural language processing technology to recognize the customer's emotional state, and information creation means for generating personalized follow-up proposals based on the recognized customer emotional state, interests, and needs. This enables the rapid and accurate creation of proposals tailored to each customer's characteristics and emotions, thereby improving customer satisfaction.

[0719] "Information acquisition means" refers to a system that has the function of collecting the history of conversations with customers and recording it in data format such as audio or text.

[0720] "Data analysis means" refers to a system that applies natural language processing technology to collected dialogue history and has the function of processing to recognize the customer's emotional state.

[0721] "Information creation means" refers to a system that has the function of generating personalized follow-up proposals based on the customer's emotional state, interests, and needs obtained through analysis.

[0722] A "transmission means" is a device that has the function of transmitting the generated follow-up proposal and related information to the terminal and notifying the user at an appropriate time.

[0723] A "learning tool" is a system that collects feedback on the results of follow-up proposals and uses that feedback to improve future proposals.

[0724] This invention is a system that generates follow-up suggestions by utilizing the history of conversations with customers. The system mainly consists of a server, terminals, and users. Specific embodiments of each component are described below.

[0725] The server receives the history of customer interactions transmitted from the salesperson's terminal. This history is recorded as voice calls and text chats. The server analyzes this history using spaCy, an open-source natural language processing library. Through analysis, it tokenizes the text, understands the context, extracts keywords, and recognizes the customer's emotional state. Furthermore, it uses the Python library OpenAI to perform tone analysis and sentiment analysis of the voice data, thereby evaluating the customer's emotions in detail.

[0726] Next, the server uses a generative AI model to create personalized follow-up suggestions. This model is inputted with data on the customer's current emotions and past interests and needs, and generates suggestions based on appropriate prompts. An example of a prompt is, "Based on the customer's conversation history, please generate follow-up suggestions focusing on topics that the customer is likely to enjoy."

[0727] The generated suggestions are sent from the server to the terminal. The terminal is a device for notifying salespeople of these suggestions, providing timely information using push notifications and banner displays. The terminal also displays a list of the customer's sentiment history and past interests to the salesperson, visually supporting the relevance of the suggested content.

[0728] The user, or salesperson, follows up with the customer based on the suggestions displayed on the terminal. For example, if a customer shows interest in a new smartphone and sentiment analysis detects enjoyment, it would be appropriate for the salesperson to make suggestions specifically focused on the smartphone's camera features. In this way, salespeople can provide customers with more personalized service.

[0729] Through the specific examples described above, this invention can greatly improve the flexibility and quality of customer service.

[0730] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0731] Step 1:

[0732] The server receives the customer interaction history from the salesperson's terminal. The input data is either audio files or text logs, which are stored in the database. Specifically, audio data is recorded in storage, and text is stored as a log. The output here is a dataset of the interaction history prepared for analysis.

[0733] Step 2:

[0734] The server uses the spaCy library to analyze the conversation history in text format. The input is the text log saved in step 1. Specific operations include sentence splitting, tokenization, and named entity recognition. Through this process, keywords related to customer interests and needs are extracted, and the analysis results are generated as output.

[0735] Step 3:

[0736] The server uses OpenAI to perform tone analysis and sentiment analysis of voice data. The input is the voice data saved in Step 1. Specifically, the voice is converted to text, and the customer's emotional state is analyzed from the tone and manner of speaking. The output is the customer's emotional status.

[0737] Step 4:

[0738] The server combines the analysis results data with the customer's emotional status and inputs it into the generative AI model. The prompt used here is "Generate follow-up suggestions based on the customer's conversation history, focusing on topics that the customer is likely to anticipate." This causes the generative AI model to generate personalized follow-up suggestions, which are then obtained as output.

[0739] Step 5:

[0740] The server sends the generated follow-up proposal to the terminal. The input is the generation result from step 4, and the proposal is transmitted to the salesperson's terminal via the terminal transmission protocol. The output is the follow-up proposal displayed on the terminal.

[0741] Step 6:

[0742] The device notifies the salesperson of the proposed content and displays detailed information. Specific actions include sending alerts to the salesperson using push notifications and displaying a list of the customer's sentiment history on the screen. The output here is quickly accessible and understandable proposal information for the salesperson.

[0743] Step 7:

[0744] The user follows up with customers based on the suggestions displayed on the device. Based on the information obtained in Step 6, they send emails to customers or introduce new products. This allows the user to provide more appropriate responses tailored to each customer. The output of this step is the result of the follow-up actions taken.

[0745] Step 8:

[0746] User feedback is sent to the server and used to improve follow-up suggestions for future interactions. Specifically, it is stored as data to optimize the suggestion generation algorithm based on the effectiveness of the follow-up. This further improves customer service in subsequent interactions. The output is a dataset that helps in generating improved suggestions.

[0747] (Application Example 2)

[0748] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0749] The system for automatically generating personalized follow-up suggestions that take into account the customer's emotional state, using information gathered through customer interactions, and communicating these suggestions to sales staff was insufficient. In this situation, it is difficult to provide customer service that appropriately reflects customer emotions, and improvements in customer satisfaction cannot be expected. Furthermore, a system is needed to accumulate the results of follow-up activities and continuously improve the accuracy of suggestion generation.

[0750] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0751] In this invention, the server includes information gathering means for collecting customer interaction history, emotion recognition means for analyzing the interaction history using natural language processing technology and determining the customer's emotional state, suggestion generation means for generating personalized follow-up suggestions based on the extracted customer interests, needs, and emotional state, communication means for notifying a portable terminal of the generated follow-up suggestions, follow-up execution means for executing the follow-up suggestions using the terminal and recording the results, and experience learning means for improving the suggestion generation means using the execution results. This makes it possible to immediately provide accurate follow-up that takes customer emotions into consideration, enabling salespeople to provide higher quality service.

[0752] "Information gathering means" refers to elements that have the function of recording and collecting the history of interactions with customers.

[0753] An "emotion recognition means" is an element that uses natural language processing technology to analyze dialogue history and determine the customer's emotional state.

[0754] A "proposal generation means" is an element that has the function of generating personalized follow-up proposals based on the extracted customer interests, needs, and emotional state.

[0755] "Communication means" refers to an element that has the function of notifying a portable terminal of the generated follow-up proposal.

[0756] A "follow-up execution means" is an element that has the function of executing follow-up proposals using a terminal and recording the results of those implementations.

[0757] An "experiential learning tool" is an element that has the function of improving the proposal generation tool using the results of follow-up execution and continuously improving the system.

[0758] The system implementing this invention consists of a server, a terminal used by a salesperson, and user interaction.

[0759] First, the server collects a history of interactions with the customer, including voice calls and text chats. The voice and text data are analyzed using natural language processing techniques, and the customer's emotional state is determined using emotion recognition tools. The technologies used include machine learning models built in Python and TensorFlow. Based on this information, the server generates personalized follow-up suggestions that reflect the customer's interests, needs, and emotional state using suggestion generation tools.

[0760] Next, the terminal receives communication from the server and notifies the salesperson of the generated follow-up suggestion. The salesperson can use a smartphone or smart glasses. This allows the salesperson to obtain information hands-free and check the suggestion in real time while interacting with the customer.

[0761] The salesperson (user) executes follow-up suggestions via a terminal, and the results are recorded using the follow-up execution device. This information is used to improve the suggestion generation device through the experiential learning device, and the accuracy of the suggestions improves over time.

[0762] For example, when a salesperson wearing smart glasses interacts with a customer in a store, if the system analyzes that the customer is excited, a follow-up suggestion such as "It would be good to provide information about new products" will be displayed on the terminal's screen.

[0763] An example of a prompt might be a question like, "What product categories did this customer mention as being good in past conversations?" This allows the AI ​​to provide salespeople with information about the customer's past interests and tendencies, enabling more accurate follow-up.

[0764] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0765] Step 1:

[0766] The server collects customer interaction history from voice calls and text chats using information gathering tools. The input for this step is communication data between the customer and the salesperson, and the output is a structured log of that data. The server records this data and stores it in a database.

[0767] Step 2:

[0768] The server analyzes the collected dialogue history using natural language processing techniques and determines the customer's emotional state using emotion recognition. The input is the collected dialogue history, and the output is the customer's emotional state as a result of the analysis (e.g., joy or excitement). Python and TensorFlow are used to evaluate the emotion of the voice tone and text.

[0769] Step 3:

[0770] The server generates personalized follow-up suggestions using a suggestion generation system based on the customer's interests, needs, and emotional state. The input is customer data such as the emotional state and past purchase history determined in step 2, and the output is personalized suggestion content. An AI generation model is used in this process to construct appropriate suggestions.

[0771] Step 4:

[0772] The server sends the generated follow-up proposal to the terminal using a communication method. The input is the proposal content created in step 3, and the output is the proposal information displayed on the terminal. The terminal receives this and notifies the salesperson.

[0773] Step 5:

[0774] Salespeople (users) equipped with a terminal execute follow-up proposals they receive, and the details and results of these executions are recorded using the follow-up execution device. The input is data on how the salesperson utilized the proposal, and the output is a log of the results. Based on this information, the salesperson takes specific actions with the customer.

[0775] Step 6:

[0776] The server analyzes the follow-up execution results using an empirical learning mechanism and improves the functionality of the proposal generation mechanism. The input is the execution result recorded in step 5, and the output is the adjusted algorithm to improve the accuracy of the next proposal. This improves the overall accuracy and efficiency of the system.

[0777] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0778] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0779] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0780] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0781] Figure 9 shows an emotion map 400 in 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 the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0782] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0783] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0784] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0785] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it 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 emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0786] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0787] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0788] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0789] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0790] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0791] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0792] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0793] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0794] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0795] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0796] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0797] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0798] The following is further disclosed regarding the embodiments described above.

[0799] (Claim 1)

[0800] A data collection method for collecting customer interaction history,

[0801] A data analysis means that analyzes the aforementioned dialogue history using natural language processing technology to extract customer interests and needs,

[0802] A proposal generation means that generates personalized follow-up proposals based on the extracted customer interests and needs,

[0803] A notification means for notifying the terminal of the generated follow-up proposal,

[0804] A follow-up execution means that executes a follow-up proposal using the aforementioned terminal and records the results,

[0805] A system including a learning means to improve the proposal generation means using the execution results.

[0806] (Claim 2)

[0807] The system according to claim 1, wherein the data collection means records voice calls and text chats with customers.

[0808] (Claim 3)

[0809] The system according to claim 1, wherein the notification means has a function to inform the terminal of the timing for performing follow-up.

[0810] "Example 1"

[0811] (Claim 1)

[0812] Means of collecting information,

[0813] A means for analyzing the aforementioned information using processing technology and extracting the subject's interests and needs,

[0814] A means of generating personalized proposals based on the identified interests and needs,

[0815] Means for notifying information devices of the aforementioned generated proposals,

[0816] A means for executing the proposal using the aforementioned information device and recording the results,

[0817] A system including a learning means to improve the proposal generation means using the execution results described above.

[0818] (Claim 2)

[0819] The system according to claim 1, wherein the means for accumulating the aforementioned information records audio information and text information of the subject.

[0820] (Claim 3)

[0821] The system according to claim 1, wherein the means for notifying the aforementioned information has a function for informing an information device of the timing of the implementation of the proposal.

[0822] "Application Example 1"

[0823] (Claim 1)

[0824] A data collection method for collecting customer interaction history,

[0825] A data analysis means that analyzes the aforementioned dialogue history using natural language processing technology to extract customer preferences and requests,

[0826] A proposal generation means that generates personalized follow-up proposals based on the extracted customer preferences and requests,

[0827] A notification means for notifying a communication terminal of the generated follow-up proposal,

[0828] A follow-up execution means that executes a follow-up proposal using the aforementioned communication terminal and records the results,

[0829] A learning means for improving the proposal generation means using the execution results,

[0830] A presentation method that automatically displays product suggestions and coupons based on the customer's conversation history,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, wherein the data collection means records voice communication and text conversations with the customer, and generates suggestions taking into account the customer's purchase history.

[0834] (Claim 3)

[0835] The system according to claim 1, wherein the notification means has a function to inform the communication terminal of the timing of follow-up and includes content that promotes purchase based on the proposal.

[0836] "Example 2 of combining an emotion engine"

[0837] (Claim 1)

[0838] A means of acquiring information to collect the history of conversations with customers,

[0839] A data analysis means that analyzes the aforementioned dialogue history using natural language processing technology to recognize the customer's emotional state,

[0840] Information generation means for generating personalized follow-up proposals based on recognized customer emotional states, interests, and needs,

[0841] A transmission means for notifying the terminal of the generated follow-up proposal and related information,

[0842] A system that includes a learning mechanism for executing follow-up proposals using the aforementioned terminal, recording the results, and reflecting them in subsequent proposals.

[0843] (Claim 2)

[0844] The system according to claim 1, wherein the information acquisition means records voice communication and text dialogue with the customer.

[0845] (Claim 3)

[0846] The system according to claim 1, wherein the transmission means has a function to notify the terminal of the timing for performing follow-up.

[0847] "Application example 2 when combining with an emotional engine"

[0848] (Claim 1)

[0849] Information gathering methods for collecting customer interaction history,

[0850] The aforementioned dialogue history is analyzed using natural language processing technology to determine the customer's emotional state, and an emotion recognition means is provided.

[0851] A proposal generation means that generates personalized follow-up proposals based on the extracted customer interests, needs, and emotional state,

[0852] A communication means for notifying a portable terminal of the generated follow-up proposal,

[0853] A follow-up execution means that executes a follow-up proposal using the aforementioned terminal and records the results,

[0854] A system including an experiential learning means for improving the proposal generation means using the execution results.

[0855] (Claim 2)

[0856] The system according to claim 1, wherein the emotion recognition means has a configuration for analyzing audio and video data in real time.

[0857] (Claim 3)

[0858] The system according to claim 1, wherein the communication means has a function to inform a portable terminal of the timing of follow-up and the corresponding proposed content. [Explanation of Symbols]

[0859] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A data collection method for collecting customer interaction history, A data analysis means that analyzes the aforementioned dialogue history using natural language processing technology to extract customer interests and needs, A proposal generation means that generates personalized follow-up proposals based on the extracted customer interests and needs, A notification means for notifying the terminal of the generated follow-up proposal, A follow-up execution means that executes a follow-up proposal using the aforementioned terminal and records the results, A system including a learning means to improve the proposal generation means using the execution results.

2. The system according to claim 1, wherein the data collection means records voice calls and text chats with customers.

3. The system according to claim 1, wherein the notification means has a function to inform the terminal of the timing for performing follow-up.

Images