system

Abstract

The system according to this embodiment aims to fully automate the telemarketing process and achieve efficient new customer acquisition. [Solution] The system according to the embodiment comprises a target selection unit, a calling unit, a talk generation unit, a listening unit, and an appointment acquisition unit. The target selection unit selects a target. The calling unit automatically makes a call to the target selected by the target selection unit. The talk generation unit generates introductory talk and transition talk using AI after the call has been made by the calling unit. The listening unit conducts a listening session using the talk generated by the talk generation unit. The appointment acquisition unit acquires an appointment based on the information gathered by the listening unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to fully automate the telemarketing process and efficient new business development is difficult.

[0005] The system according to the embodiment aims to fully automate the telemarketing process and achieve efficient new business development.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a target selection unit, a calling unit, a talk generation unit, a listening unit, and an appointment acquisition unit. The target selection unit selects a target. The calling unit automatically makes a call to the target selected by the target selection unit. The talk generation unit generates introductory and transition talks using AI after the call has been made by the calling unit. The listening unit conducts a listening session using the talk generated by the talk generation unit. The appointment acquisition unit acquires appointments based on the information gathered by the listening unit. [Effects of the Invention]

[0007] The system according to this embodiment can fully automate the telemarketing process and achieve efficient new customer acquisition. [Brief explanation of the drawing]

[0008] [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. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 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.

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

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

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

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0028] (Example of form 1) The novel automated telemarketing system according to an embodiment of the present invention is a system that automatically performs target selection, automatic dialing, AI-generated scripts, interviews, and appointment setting. In this system, the target selection unit selects targets, and the dialing unit makes dialing calls automatically. Next, the script generation unit uses AI to generate introductory and transition scripts, and the interviewing unit uses AI to conduct interviews. Finally, the appointment setting unit uses AI to secure appointments. This system can also be used for inside sales, automating target selection, automatic dialing, AI-generated scripts, interviews, and appointment setting, reducing the time and effort required for these processes, freeing salespeople from stress, and enabling them to conduct sales activities in the best possible state. For example, in the novel automated telemarketing system, the target selection unit collects and analyzes data for selecting targets. The dialing unit makes dialing calls automatically. The script generation unit uses AI to generate introductory and transition scripts. The interviewing unit uses AI to conduct interviews. The appointment setting unit uses AI to secure appointments. This enables the new automated telemarketing system to achieve efficient sales activities.

[0029] The novel automated telemarketing system according to this embodiment comprises a target selection unit, a calling unit, a talk generation unit, a listening unit, and an appointment acquisition unit. The target selection unit selects targets. The target selection unit selects targets based on criteria such as customer attributes, industry, and region. The target selection unit can select targets by collecting and analyzing customer data. The target selection unit can select the optimal target by analyzing customer purchase history and behavioral data, for example. The calling unit makes calls automatically. The calling unit can make calls automatically using, for example, telephone, email, messaging apps, etc. The calling unit can analyze past call history to optimize the timing and method of calling. The talk generation unit generates introductory and transition talks using AI. The talk generation unit can generate talks using, for example, text generation AI (e.g., LLM). The talk generation unit can analyze past call history to optimize the content of introductory and transition talks. The listening unit conducts listening using AI. The listening unit can, for example, record and analyze customer responses using speech recognition technology. The listening unit can generate subsequent questions based on customer responses. The appointment setting unit uses AI to set appointments. The appointment setting unit can, for example, check customer schedules and set appointments at the optimal date and time. The appointment setting unit can adjust appointment details based on customer responses. As a result, the novel telemarketing automation system according to this embodiment can achieve efficient sales activities.

[0030] The target selection department selects targets. For example, it selects targets based on criteria such as customer attributes, industry, and region. Specifically, it collects information from customer databases, including age, gender, occupation, income, past purchase history, and website browsing history, and uses this data to narrow down the target. The target selection department uses machine learning algorithms to learn from past successes and failures, enabling it to predict the most effective targets. For example, it can analyze the attributes of customers who have purchased a specific product and select new customers with similar attributes as targets. It can also analyze regional purchasing trends and optimize campaigns in specific regions. The target selection department can update data in real time and select targets based on the latest information. This allows the target selection department to efficiently and effectively select targets and improve the success rate of sales activities.

[0031] The outbound calling unit makes calls automatically. For example, it can make calls automatically using methods such as phone calls, emails, and messaging apps. Specifically, the unit automatically makes phone calls or sends emails to customers based on a pre-set schedule. The unit can analyze past call history to optimize the timing and method of calls. For example, if the response rate is high when calling during a specific time period, it will concentrate calls during that time. It can also monitor customer responses in real time and respond flexibly, such as attempting to call again if there is no response. The unit can also customize the content of its calls, providing the most suitable message for each customer. This allows the unit to approach customers efficiently and effectively, improving the success rate of sales activities.

[0032] The talk generation unit uses AI to generate introductory and transitional talks. For example, the talk generation unit can generate talks using text generation AI (e.g., LLM). Specifically, the talk generation unit analyzes past talk history and learns successful and unsuccessful talk patterns. This allows it to generate optimal talks in real time based on customer responses. For example, if a customer shows interest, it generates talk providing more detailed information; conversely, if the customer shows no interest, it generates talk attempting a different approach. The talk generation unit can also provide individually customized talks based on customer attributes and past behavioral data. This allows the talk generation unit to facilitate smoother communication with customers and improve the success rate of sales activities.

[0033] The interviewing department uses AI to conduct interviews. For example, the interviewing department can record and analyze customer responses using speech recognition technology. Specifically, the interviewing department analyzes conversations with customers in real time to understand their needs and requests. By using speech recognition technology, customer responses can be recorded as text data and analyzed later. The interviewing department can generate subsequent questions based on customer responses, supporting the smooth flow of conversation. For example, if a customer shows interest in a particular product, it can generate detailed questions related to that product to keep the customer interested. The interviewing department can also analyze customer emotions and tone and respond appropriately. As a result, the interviewing department can accurately understand customer needs and support effective sales activities.

[0034] The appointment scheduling unit uses AI to acquire appointments. For example, it can check a customer's schedule and set an appointment at the optimal time. Specifically, the appointment scheduling unit integrates with the customer's calendar or schedule management system to automatically detect available time slots. It can adjust the details of the appointment based on the customer's response; for example, if a customer prefers a specific date and time, it will set an appointment accordingly. The appointment scheduling unit can also predict the optimal timing for an appointment based on the customer's attributes and past behavioral data. This allows the appointment scheduling unit to acquire appointments efficiently and effectively, improving the success rate of sales activities. Furthermore, the appointment scheduling unit can automatically send appointment reminders to help customers not forget their appointments. This allows the appointment scheduling unit to facilitate smooth communication with customers and maximize the efficiency of sales activities.

[0035] The target selection unit can collect and analyze data for selecting targets. For example, the target selection unit can select targets by collecting and analyzing customer data. The target selection unit can select the optimal target by analyzing customer purchase history and behavioral data. For example, the target selection unit can select targets based on criteria such as customer attributes, industry, and region. This improves the accuracy of target selection. Some or all of the above processes in the target selection unit may be performed using AI, for example, or without AI. For example, the target selection unit can input customer data into AI, which can then analyze the data to select the optimal target.

[0036] The outgoing call unit can make calls automatically. The unit can make calls automatically using methods such as phone calls, emails, and messaging apps. The unit can analyze past call history to optimize the timing and method of calls. For example, it can analyze past successful call methods and apply similar methods. It can also analyze past unsuccessful call methods and avoid similar methods. Based on past call history, the unit can select call methods that are more likely to succeed at specific times or on specific days of the week. This enables efficient sales activities through automated calling. Some or all of the above processes in the outgoing call unit may be performed using AI, or not. For example, the unit can input the timing and method of calls into the AI, which can then select the optimal method.

[0037] The talk generation unit can generate introductory and transition talks using AI. The talk generation unit generates talks using, for example, a text generation AI (e.g., LLM). The talk generation unit can analyze past talk history to optimize the content of introductory and transition talks. For example, the talk generation unit can analyze past successful talk content and generate similar talks. The talk generation unit can also analyze past unsuccessful talk content and avoid similar talks. The talk generation unit can also generate talk content that is more likely to succeed at specific times or days of the week based on past talk history. In this way, talk generation is automated by using AI. Some or all of the above processes in the talk generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the talk generation unit can input talk content into a generation AI, and the generation AI can generate the optimal talk.

[0038] The interviewing unit can conduct interviews using AI. The interviewing unit can, for example, record and analyze customer responses using speech recognition technology. The interviewing unit can generate the next question based on the customer's responses. For example, the interviewing unit can input customer responses into the AI, which then generates the next question. The interviewing unit can also analyze customer responses and select the optimal interviewing method. This improves the accuracy of the interview by using AI. Some or all of the above-described processes in the interviewing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interviewing unit can input customer responses into a generative AI, which then generates the next question.

[0039] The appointment scheduling unit can acquire appointments using AI. For example, the appointment scheduling unit can check the customer's schedule and set an appointment at the optimal date and time. The appointment scheduling unit can adjust the details of the appointment based on the customer's response. For example, the appointment scheduling unit can input the customer's response into the AI, and the AI ​​will set the optimal appointment. The appointment scheduling unit can also analyze the customer's schedule and select the optimal appointment acquisition method. As a result, the efficiency of appointment acquisition is improved by using AI. Some or all of the above processes in the appointment scheduling unit may be performed using, for example, a generating AI, or without a generating AI. For example, the appointment scheduling unit can input the customer's schedule into a generating AI, and the generating AI will set the optimal appointment.

[0040] The target selection unit can analyze past target selection history and apply the optimal target selection algorithm. For example, the target selection unit can analyze past successful target selection patterns and prioritize the selection of targets with similar patterns. The target selection unit can also analyze past unsuccessful target selection patterns and exclude targets with similar patterns. Based on past target selection history, the target selection unit can select targets that are more likely to succeed during specific time periods or days of the week. This enables optimal target selection based on past history. Some or all of the above processes in the target selection unit may be performed using AI, for example, or without AI. For example, the target selection unit can input past target selection history into AI, which can then apply the optimal target selection algorithm.

[0041] The target selection unit can adjust the selection criteria by considering the industry trends and market trends of the target. For example, the target selection unit can analyze current market trends and prioritize the selection of targets that match the trends. The target selection unit can consider industry trends and select targets in industries where growth is expected. The target selection unit can consider the balance of supply and demand in the market and select targets with high demand. This makes it possible to select targets based on industry trends and market trends. Some or all of the above processes in the target selection unit may be performed using AI, for example, or not using AI. For example, the target selection unit can input industry trend and market trend data into AI, and the AI ​​can adjust the selection criteria.

[0042] The target selection unit can adjust the selection criteria by taking into account the geographical location information of the targets. For example, the target selection unit can prioritize selecting nearby targets based on the geographical location information of the targets. The target selection unit can prioritize selecting targets that are easily accessible geographically. The target selection unit can select targets that are concentrated in a particular area by taking into account geographical characteristics. This makes it possible to select targets based on geographical location information. Some or all of the above processing in the target selection unit may be performed using AI, for example, or without using AI. For example, the target selection unit can input geographical location information into AI, and the AI ​​can adjust the selection criteria.

[0043] The target selection unit can analyze the social media activity of targets and prioritize the selection of relevant targets. For example, the target selection unit can analyze the social media activity of targets and prioritize the selection of targets who actively disseminate information. The target selection unit can prioritize the selection of targets who have a good response on social media. The target selection unit can prioritize the selection of targets who are active on social media. This makes it possible to select targets based on social media activity. Some or all of the above processing in the target selection unit may be performed using AI, for example, or without AI. For example, the target selection unit can input social media activity data into AI, and the AI ​​can select relevant targets.

[0044] The calling unit can analyze past calling history and select the optimal calling method. For example, the calling unit can analyze past successful calling methods and apply similar methods. The calling unit can analyze past unsuccessful calling methods and avoid similar methods. From past calling history, the calling unit can select calling methods that are more likely to succeed at specific times or on specific days of the week. This allows the optimal calling method to be selected based on past history. Some or all of the above processing in the calling unit may be performed using AI, for example, or without AI. For example, the calling unit can input past calling history into AI, and the AI ​​can select the optimal calling method.

[0045] The communication unit can adjust its content by considering the target industry trends and market trends. For example, the communication unit can analyze current market trends and set content that matches those trends. The communication unit can consider industry trends and adjust its content for industries where growth is expected. The communication unit can consider the balance of supply and demand in the market and set content that is in high demand. This makes it possible to adjust the content of communications based on industry trends and market trends. Some or all of the above processes in the communication unit may be performed using AI, for example, or not using AI. For example, the communication unit can input data on industry trends and market trends into AI, and the AI ​​can adjust the content of communications.

[0046] The transmitting unit can adjust the content of its messages, taking into account the target's geographical location. For example, the transmitting unit can set region-specific content based on the target's geographical location. The transmitting unit can adjust the content of its messages for targets that are easily accessible geographically. The transmitting unit can set content for targets concentrated in a specific region, taking geographical characteristics into consideration. This makes it possible to adjust the content of messages based on geographical location information. Some or all of the above processing in the transmitting unit may be performed using AI, for example, or without AI. For example, the transmitting unit can input geographical location information into AI, and the AI ​​can adjust the content of its messages.

[0047] The sending unit can analyze the target's social media activity and prioritize sending relevant content. For example, the sending unit can analyze the target's social media activity and prioritize sending content of high interest. The sending unit can prioritize sending content that receives a good response on social media. The sending unit can prioritize sending relevant content to targets with active social media activity. This enables the priority sending of content based on social media activity. Some or all of the above processing in the sending unit may be performed using AI, for example, or not using AI. For example, the sending unit can input social media activity data into AI, and the AI ​​can select relevant content.

[0048] The talk generation unit can adjust the talk content by considering the target industry trends and market trends. For example, the talk generation unit can analyze current market trends and set talk content that matches the trends. The talk generation unit can consider industry trends and adjust the talk content for industries where growth is expected. The talk generation unit can consider the balance of market supply and demand and set talk content that is in high demand. This makes it possible to adjust the talk content based on industry trends and market trends. Some or all of the above processing in the talk generation unit may be performed using AI, for example, or not using AI. For example, the talk generation unit can input industry trend and market trend data into AI, and the AI ​​can adjust the talk content.

[0049] The talk generation unit can analyze the target's past response history and apply the optimal talk algorithm. For example, the talk generation unit can analyze past successful response history and apply a similar talk algorithm. The talk generation unit can analyze past unsuccessful response history and avoid similar talk algorithms. Based on past response history, the talk generation unit can apply a talk algorithm that is more likely to succeed at specific times of day or on specific days of the week. This makes it possible to apply the optimal talk algorithm based on past response history. Some or all of the above processing in the talk generation unit may be performed using AI, for example, or without AI. For example, the talk generation unit can input past response history into AI, and the AI ​​can apply the optimal talk algorithm.

[0050] The talk generation unit can adjust the talk content considering the target's geographical location information. For example, the talk generation unit can set region-specific talk content based on the target's geographical location information. The talk generation unit can adjust the talk content for targets that are geographically easily accessible. The talk generation unit can set talk content for targets concentrated in a specific region, taking geographical characteristics into consideration. This makes it possible to adjust the talk content based on geographical location information. Some or all of the above processing in the talk generation unit may be performed using AI, for example, or without AI. For example, the talk generation unit can input geographical location information into AI, and the AI ​​can adjust the talk content.

[0051] The talk generation unit can analyze the target's social media activity and prioritize generating relevant talk content. For example, the talk generation unit can analyze the target's social media activity and prioritize incorporating content of high interest into the talk. The talk generation unit can prioritize incorporating content that has received a good response on social media into the talk. The talk generation unit can prioritize generating relevant talk content for targets who are active on social media. This makes it possible to prioritize the generation of talk content based on social media activity. Some or all of the above processing in the talk generation unit may be performed using AI, for example, or without AI. For example, the talk generation unit can input social media activity data into AI, and the AI ​​can generate relevant talk content.

[0052] The interviewing department can adjust the interview content considering the target industry trends and market trends. For example, the interviewing department can analyze current market trends and set interview content that matches those trends. The interviewing department can consider industry trends and adjust the interview content for industries that are expected to grow. The interviewing department can consider the balance of market supply and demand and set interview content that is in high demand. This makes it possible to adjust the interview content based on industry trends and market trends. Some or all of the above processes in the interviewing department may be performed using AI, for example, or not. For example, the interviewing department can input data on industry trends and market trends into AI, and the AI ​​can adjust the interview content.

[0053] The listening unit can analyze the target's past response history and apply the optimal listening algorithm. For example, the listening unit can analyze past successful response histories and apply similar listening algorithms. The listening unit can analyze past unsuccessful response histories and avoid similar listening algorithms. Based on past response histories, the listening unit can apply listening algorithms that are more likely to succeed at specific times of day or on specific days of the week. This makes it possible to apply the optimal listening algorithm based on past response histories. Some or all of the above processing in the listening unit may be performed using AI, for example, or without AI. For example, the listening unit can input past response histories into AI, and the AI ​​can apply the optimal listening algorithm.

[0054] The interviewing unit can adjust the interview content considering the target's geographical location information. For example, the interviewing unit can set region-specific interview content based on the target's geographical location information. The interviewing unit can adjust the interview content for targets that are geographically easily accessible. The interviewing unit can set interview content for targets concentrated in a specific region, taking geographical characteristics into consideration. This makes it possible to adjust the interview content based on geographical location information. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or without AI. For example, the interviewing unit can input geographical location information into AI, and the AI ​​can adjust the interview content.

[0055] The interviewing unit can analyze the target's social media activity and prioritize relevant interview topics. For example, the interviewing unit can analyze the target's social media activity and prioritize interviews on topics of high interest. The interviewing unit can prioritize interviews on topics that have received positive responses on social media. The interviewing unit can prioritize interviews on topics that are active on social media. This makes it possible to prioritize interview content based on social media activity. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or not. For example, the interviewing unit can input social media activity data into AI, and the AI ​​can generate relevant interview content.

[0056] The appointment setting unit can adjust appointment content by considering the target industry trends and market trends. For example, the appointment setting unit can analyze current market trends and set appointment content that matches the trends. The appointment setting unit can consider industry trends and adjust appointment content for industries where growth is expected. The appointment setting unit can consider the balance of market supply and demand and set appointment content with high demand. This makes it possible to adjust appointment content based on industry trends and market trends. Some or all of the above processes in the appointment setting unit may be performed using AI, for example, or not using AI. For example, the appointment setting unit can input industry trend and market trend data into AI, and the AI ​​can adjust the appointment content.

[0057] The appointment setting unit can analyze the target's past response history and apply the optimal appointment setting algorithm. For example, the appointment setting unit can analyze past successful response history and apply a similar appointment setting algorithm. The appointment setting unit can analyze past unsuccessful response history and avoid similar appointment setting algorithms. Based on past response history, the appointment setting unit can apply an appointment setting algorithm that is more likely to succeed at specific times of day or on specific days of the week. This makes it possible to apply the optimal appointment setting algorithm based on past response history. Some or all of the above processing in the appointment setting unit may be performed using AI, for example, or without AI. For example, the appointment setting unit can input past response history into AI, and the AI ​​can apply the optimal appointment setting algorithm.

[0058] The appointment setting unit can adjust appointment setting content considering the target's geographical location information. For example, the appointment setting unit can set region-specific appointment setting content based on the target's geographical location information. The appointment setting unit can adjust appointment setting content for targets that are geographically easily accessible. The appointment setting unit can set appointment setting content for targets concentrated in a specific region, taking geographical characteristics into consideration. This makes it possible to adjust appointment setting content based on geographical location information. Some or all of the above processing in the appointment setting unit may be performed using AI, for example, or without using AI. For example, the appointment setting unit can input geographical location information into AI, and the AI ​​can adjust the appointment setting content.

[0059] The appointment setting unit can analyze the target's social media activity and prioritize relevant appointment setting. For example, the appointment setting unit can analyze the target's social media activity and prioritize incorporating content of high interest into appointment setting. The appointment setting unit can prioritize incorporating content that has received a good response on social media into appointment setting. The appointment setting unit can prioritize relevant appointment setting for targets with active social media activity. This makes it possible to prioritize appointment setting based on social media activity. Some or all of the above processing in the appointment setting unit may be performed using AI, for example, or not using AI. For example, the appointment setting unit can input social media activity data into AI, and the AI ​​can generate relevant appointment setting content.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The target selection unit can analyze past target selection history and apply the optimal target selection algorithm. For example, it can analyze past successful target selection patterns and prioritize the selection of targets with similar patterns. It can also analyze past unsuccessful target selection patterns and exclude targets with similar patterns. Furthermore, it can select targets that are more likely to succeed during specific time periods or days of the week based on past target selection history. This enables optimal target selection based on past history. Some or all of the above processing in the target selection unit may be performed using AI or not.

[0062] The communication unit can adjust its content based on target industry trends and market trends. For example, it can analyze current market trends and set content that aligns with those trends. It can also consider industry trends and adjust content for industries where growth is expected. Furthermore, it can consider the balance of market supply and demand and set content that is in high demand. This makes it possible to adjust communication content based on industry trends and market trends. Some or all of the above processing in the communication unit may be performed using AI, or it may be performed without using AI.

[0063] The talk generation unit can analyze the target's past response history and apply the optimal talk algorithm. For example, it can analyze past successful response history and apply a similar talk algorithm. It can also analyze past unsuccessful response history and avoid similar talk algorithms. Furthermore, it can apply a talk algorithm that is more likely to succeed at specific times of day or on specific days of the week based on past response history. This makes it possible to apply the optimal talk algorithm based on past response history. Some or all of the above processing in the talk generation unit may be performed using AI or not.

[0064] The interviewing unit can adjust the interview content considering the target's geographical location information. For example, it can set region-specific interview content based on the target's geographical location information. It can also adjust the interview content for targets that are geographically easily accessible. Furthermore, it can set interview content for targets concentrated in specific regions, taking geographical characteristics into consideration. This makes it possible to adjust the interview content based on geographical location information. Some or all of the above processing in the interviewing unit may be performed using AI or not.

[0065] The appointment setting unit can analyze the target's social media activity and prioritize relevant appointment setting. For example, it can analyze the target's social media activity and prioritize incorporating content of high interest into appointment setting. It can also prioritize incorporating content that has received a good response on social media. Furthermore, it can prioritize relevant appointment setting for targets who are actively using social media. This makes it possible to prioritize appointment setting based on social media activity. Some or all of the above processing in the appointment setting unit may be performed using AI or not.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The target selection department selects targets. The target selection department selects targets based on criteria such as customer attributes, industry, and region. The target selection department can also select targets by collecting and analyzing customer data. For example, they can analyze customer purchase history and behavioral data to select the optimal targets. Step 2: The calling unit automatically makes calls to the targets selected by the target selection unit. The calling unit can make calls automatically using methods such as phone calls, emails, and messaging apps. The calling unit can analyze past call history to optimize the timing and method of making calls. Step 3: The talk generation unit generates introductory and transitional talks using AI after the message has been sent by the sender. The talk generation unit can generate talks using text generation AI (e.g., LLM). The talk generation unit can analyze past talk history to optimize the content of the introductory and transitional talks. Step 4: The interviewing unit conducts interviews using the talk generated by the talk generation unit. The interviewing unit can record and analyze the customer's responses using speech recognition technology. Based on the customer's responses, the interviewing unit can generate the next questions. Step 5: The appointment scheduling department obtains appointments based on the information gathered by the interviewing department. The appointment scheduling department can check the customer's schedule and set an appointment at the most suitable date and time. The appointment scheduling department can adjust the details of the appointment based on the customer's responses.

[0068] (Example of form 2) The novel automated telemarketing system according to an embodiment of the present invention is a system that automatically performs target selection, automatic dialing, AI-generated scripts, interviews, and appointment setting. In this system, the target selection unit selects targets, and the dialing unit makes dialing calls automatically. Next, the script generation unit uses AI to generate introductory and transition scripts, and the interviewing unit uses AI to conduct interviews. Finally, the appointment setting unit uses AI to secure appointments. This system can also be used for inside sales, automating target selection, automatic dialing, AI-generated scripts, interviews, and appointment setting, reducing the time and effort required for these processes, freeing salespeople from stress, and enabling them to conduct sales activities in the best possible state. For example, in the novel automated telemarketing system, the target selection unit collects and analyzes data for selecting targets. The dialing unit makes dialing calls automatically. The script generation unit uses AI to generate introductory and transition scripts. The interviewing unit uses AI to conduct interviews. The appointment setting unit uses AI to secure appointments. This enables the new automated telemarketing system to achieve efficient sales activities.

[0069] The novel automated telemarketing system according to this embodiment comprises a target selection unit, a calling unit, a talk generation unit, a listening unit, and an appointment acquisition unit. The target selection unit selects targets. The target selection unit selects targets based on criteria such as customer attributes, industry, and region. The target selection unit can select targets by collecting and analyzing customer data. The target selection unit can select the optimal target by analyzing customer purchase history and behavioral data, for example. The calling unit makes calls automatically. The calling unit can make calls automatically using, for example, telephone, email, messaging apps, etc. The calling unit can analyze past call history to optimize the timing and method of calling. The talk generation unit generates introductory and transition talks using AI. The talk generation unit can generate talks using, for example, text generation AI (e.g., LLM). The talk generation unit can analyze past call history to optimize the content of introductory and transition talks. The listening unit conducts listening using AI. The listening unit can, for example, record and analyze customer responses using speech recognition technology. The listening unit can generate subsequent questions based on customer responses. The appointment setting unit uses AI to set appointments. The appointment setting unit can, for example, check customer schedules and set appointments at the optimal date and time. The appointment setting unit can adjust appointment details based on customer responses. As a result, the novel telemarketing automation system according to this embodiment can achieve efficient sales activities.

[0070] The target selection department selects targets. For example, it selects targets based on criteria such as customer attributes, industry, and region. Specifically, it collects information from customer databases, including age, gender, occupation, income, past purchase history, and website browsing history, and uses this data to narrow down the target. The target selection department uses machine learning algorithms to learn from past successes and failures, enabling it to predict the most effective targets. For example, it can analyze the attributes of customers who have purchased a specific product and select new customers with similar attributes as targets. It can also analyze regional purchasing trends and optimize campaigns in specific regions. The target selection department can update data in real time and select targets based on the latest information. This allows the target selection department to efficiently and effectively select targets and improve the success rate of sales activities.

[0071] The outbound calling unit makes calls automatically. For example, it can make calls automatically using methods such as phone calls, emails, and messaging apps. Specifically, the unit automatically makes phone calls or sends emails to customers based on a pre-set schedule. The unit can analyze past call history to optimize the timing and method of calls. For example, if the response rate is high when calling during a specific time period, it will concentrate calls during that time. It can also monitor customer responses in real time and respond flexibly, such as attempting to call again if there is no response. The unit can also customize the content of its calls, providing the most suitable message for each customer. This allows the unit to approach customers efficiently and effectively, improving the success rate of sales activities.

[0072] The talk generation unit uses AI to generate introductory and transitional talks. For example, the talk generation unit can generate talks using text generation AI (e.g., LLM). Specifically, the talk generation unit analyzes past talk history and learns successful and unsuccessful talk patterns. This allows it to generate optimal talks in real time based on customer responses. For example, if a customer shows interest, it generates talk providing more detailed information; conversely, if the customer shows no interest, it generates talk attempting a different approach. The talk generation unit can also provide individually customized talks based on customer attributes and past behavioral data. This allows the talk generation unit to facilitate smoother communication with customers and improve the success rate of sales activities.

[0073] The interviewing department uses AI to conduct interviews. For example, the interviewing department can record and analyze customer responses using speech recognition technology. Specifically, the interviewing department analyzes conversations with customers in real time to understand their needs and requests. By using speech recognition technology, customer responses can be recorded as text data and analyzed later. The interviewing department can generate subsequent questions based on customer responses, supporting the smooth flow of conversation. For example, if a customer shows interest in a particular product, it can generate detailed questions related to that product to keep the customer interested. The interviewing department can also analyze customer emotions and tone and respond appropriately. As a result, the interviewing department can accurately understand customer needs and support effective sales activities.

[0074] The appointment scheduling unit uses AI to acquire appointments. For example, it can check a customer's schedule and set an appointment at the optimal time. Specifically, the appointment scheduling unit integrates with the customer's calendar or schedule management system to automatically detect available time slots. It can adjust the details of the appointment based on the customer's response; for example, if a customer prefers a specific date and time, it will set an appointment accordingly. The appointment scheduling unit can also predict the optimal timing for an appointment based on the customer's attributes and past behavioral data. This allows the appointment scheduling unit to acquire appointments efficiently and effectively, improving the success rate of sales activities. Furthermore, the appointment scheduling unit can automatically send appointment reminders to help customers not forget their appointments. This allows the appointment scheduling unit to facilitate smooth communication with customers and maximize the efficiency of sales activities.

[0075] The target selection unit can collect and analyze data for selecting targets. For example, the target selection unit can select targets by collecting and analyzing customer data. The target selection unit can select the optimal target by analyzing customer purchase history and behavioral data. For example, the target selection unit can select targets based on criteria such as customer attributes, industry, and region. This improves the accuracy of target selection. Some or all of the above processes in the target selection unit may be performed using AI, for example, or without AI. For example, the target selection unit can input customer data into AI, which can then analyze the data to select the optimal target.

[0076] The outgoing call unit can make calls automatically. The unit can make calls automatically using methods such as phone calls, emails, and messaging apps. The unit can analyze past call history to optimize the timing and method of calls. For example, it can analyze past successful call methods and apply similar methods. It can also analyze past unsuccessful call methods and avoid similar methods. Based on past call history, the unit can select call methods that are more likely to succeed at specific times or on specific days of the week. This enables efficient sales activities through automated calling. Some or all of the above processes in the outgoing call unit may be performed using AI, or not. For example, the unit can input the timing and method of calls into the AI, which can then select the optimal method.

[0077] The talk generation unit can generate introductory and transition talks using AI. The talk generation unit generates talks using, for example, a text generation AI (e.g., LLM). The talk generation unit can analyze past talk history to optimize the content of introductory and transition talks. For example, the talk generation unit can analyze past successful talk content and generate similar talks. The talk generation unit can also analyze past unsuccessful talk content and avoid similar talks. The talk generation unit can also generate talk content that is more likely to succeed at specific times or days of the week based on past talk history. In this way, talk generation is automated by using AI. Some or all of the above processes in the talk generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the talk generation unit can input talk content into a generation AI, and the generation AI can generate the optimal talk.

[0078] The interviewing unit can conduct interviews using AI. The interviewing unit can, for example, record and analyze customer responses using speech recognition technology. The interviewing unit can generate the next question based on the customer's responses. For example, the interviewing unit can input customer responses into the AI, which then generates the next question. The interviewing unit can also analyze customer responses and select the optimal interviewing method. This improves the accuracy of the interview by using AI. Some or all of the above-described processes in the interviewing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interviewing unit can input customer responses into a generative AI, which then generates the next question.

[0079] The appointment scheduling unit can acquire appointments using AI. For example, the appointment scheduling unit can check the customer's schedule and set an appointment at the optimal date and time. The appointment scheduling unit can adjust the details of the appointment based on the customer's response. For example, the appointment scheduling unit can input the customer's response into the AI, and the AI ​​will set the optimal appointment. The appointment scheduling unit can also analyze the customer's schedule and select the optimal appointment acquisition method. As a result, the efficiency of appointment acquisition is improved by using AI. Some or all of the above processes in the appointment scheduling unit may be performed using, for example, a generating AI, or without a generating AI. For example, the appointment scheduling unit can input the customer's schedule into a generating AI, and the generating AI will set the optimal appointment.

[0080] The target selection unit can estimate the user's emotions and adjust the target selection criteria based on the estimated emotions. For example, if the user is stressed, the target selection unit can set target selection criteria that promote relaxation. If the user is excited, the target selection unit can set proactive target selection criteria. If the user is tired, the target selection unit can prioritize selecting targets that are easy to respond to. This enables target selection that is appropriate to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the target selection unit may be performed using AI, or not using AI. For example, the target selection unit can input user emotion data into the generative AI, which can estimate the emotions and adjust the target selection criteria.

[0081] The target selection unit can analyze past target selection history and apply the optimal target selection algorithm. For example, the target selection unit can analyze past successful target selection patterns and prioritize the selection of targets with similar patterns. The target selection unit can also analyze past unsuccessful target selection patterns and exclude targets with similar patterns. Based on past target selection history, the target selection unit can select targets that are more likely to succeed during specific time periods or days of the week. This enables optimal target selection based on past history. Some or all of the above processes in the target selection unit may be performed using AI, for example, or without AI. For example, the target selection unit can input past target selection history into AI, which can then apply the optimal target selection algorithm.

[0082] The target selection unit can adjust the selection criteria by considering the industry trends and market trends of the target. For example, the target selection unit can analyze current market trends and prioritize the selection of targets that match the trends. The target selection unit can consider industry trends and select targets in industries where growth is expected. The target selection unit can consider the balance of supply and demand in the market and select targets with high demand. This makes it possible to select targets based on industry trends and market trends. Some or all of the above processes in the target selection unit may be performed using AI, for example, or not using AI. For example, the target selection unit can input industry trend and market trend data into AI, and the AI ​​can adjust the selection criteria.

[0083] The target selection unit can estimate the user's emotions and determine the priority of target selection based on the estimated user emotions. For example, if the user is relaxed, the target selection unit may prioritize selecting targets with higher difficulty levels. If the user is stressed, the target selection unit may prioritize selecting targets that are easy to handle. If the user is excited, the target selection unit may prioritize selecting proactive targets. This allows for the determination of target selection priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the target selection unit may be performed using AI, or not using AI. For example, the target selection unit can input user emotion data into a generative AI, which can estimate the emotions and determine the priority of target selection.

[0084] The target selection unit can adjust the selection criteria by taking into account the geographical location information of the targets. For example, the target selection unit can prioritize selecting nearby targets based on the geographical location information of the targets. The target selection unit can prioritize selecting targets that are easily accessible geographically. The target selection unit can select targets that are concentrated in a particular area by taking into account geographical characteristics. This makes it possible to select targets based on geographical location information. Some or all of the above processing in the target selection unit may be performed using AI, for example, or without using AI. For example, the target selection unit can input geographical location information into AI, and the AI ​​can adjust the selection criteria.

[0085] The target selection unit can analyze the social media activity of targets and prioritize the selection of relevant targets. For example, the target selection unit can analyze the social media activity of targets and prioritize the selection of targets who actively disseminate information. The target selection unit can prioritize the selection of targets who have a good response on social media. The target selection unit can prioritize the selection of targets who are active on social media. This makes it possible to select targets based on social media activity. Some or all of the above processing in the target selection unit may be performed using AI, for example, or without AI. For example, the target selection unit can input social media activity data into AI, and the AI ​​can select relevant targets.

[0086] The transmitting unit can estimate the user's emotions and adjust the transmission timing based on the estimated emotions. For example, if the user is relaxed, the transmitting unit will transmit at the optimal time. If the user is stressed, the transmitting unit can delay the transmission timing. If the user is excited, the transmitting unit can transmit quickly. This makes it possible to adjust the transmission timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the transmitting unit may be performed using AI, or not using AI. For example, the transmitting unit can input user emotion data into the generative AI, which can estimate the emotions and adjust the transmission timing.

[0087] The calling unit can analyze past calling history and select the optimal calling method. For example, the calling unit can analyze past successful calling methods and apply similar methods. The calling unit can analyze past unsuccessful calling methods and avoid similar methods. From past calling history, the calling unit can select calling methods that are more likely to succeed at specific times or on specific days of the week. This allows the optimal calling method to be selected based on past history. Some or all of the above processing in the calling unit may be performed using AI, for example, or without AI. For example, the calling unit can input past calling history into AI, and the AI ​​can select the optimal calling method.

[0088] The communication unit can adjust its content by considering the target industry trends and market trends. For example, the communication unit can analyze current market trends and set content that matches those trends. The communication unit can consider industry trends and adjust its content for industries where growth is expected. The communication unit can consider the balance of supply and demand in the market and set content that is in high demand. This makes it possible to adjust the content of communications based on industry trends and market trends. Some or all of the above processes in the communication unit may be performed using AI, for example, or not using AI. For example, the communication unit can input data on industry trends and market trends into AI, and the AI ​​can adjust the content of communications.

[0089] The sending unit can estimate the user's emotions and determine the priority of messages based on the estimated emotions. For example, if the user is relaxed, the sending unit will prioritize important messages. If the user is stressed, the sending unit will prioritize simple messages. If the user is excited, the sending unit will send messages quickly. This allows for the determination of message priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the sending unit may be performed using AI or not using AI. For example, the sending unit can input user emotion data into a generative AI, which can estimate the emotions and determine the priority of messages.

[0090] The transmitting unit can adjust the content of its messages, taking into account the target's geographical location. For example, the transmitting unit can set region-specific content based on the target's geographical location. The transmitting unit can adjust the content of its messages for targets that are easily accessible geographically. The transmitting unit can set content for targets concentrated in a specific region, taking geographical characteristics into consideration. This makes it possible to adjust the content of messages based on geographical location information. Some or all of the above processing in the transmitting unit may be performed using AI, for example, or without AI. For example, the transmitting unit can input geographical location information into AI, and the AI ​​can adjust the content of its messages.

[0091] The sending unit can analyze the target's social media activity and prioritize sending relevant content. For example, the sending unit can analyze the target's social media activity and prioritize sending content of high interest. The sending unit can prioritize sending content that receives a good response on social media. The sending unit can prioritize sending relevant content to targets with active social media activity. This enables the priority sending of content based on social media activity. Some or all of the above processing in the sending unit may be performed using AI, for example, or not using AI. For example, the sending unit can input social media activity data into AI, and the AI ​​can select relevant content.

[0092] The talk generation unit can estimate the user's emotions and adjust the way the talk is expressed based on the estimated emotions. For example, if the user is relaxed, the talk generation unit can use a soft expression. If the user is stressed, the talk generation unit can use a concise and clear expression. If the user is excited, the talk generation unit can use an assertive expression. This makes it possible to adjust the way the talk is expressed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the talk generation unit may be performed using AI, for example, or without AI. For example, the talk generation unit can input user emotion data into the generative AI, which can estimate the emotions and adjust the way the talk is expressed.

[0093] The talk generation unit can adjust the talk content by considering the target industry trends and market trends. For example, the talk generation unit can analyze current market trends and set talk content that matches the trends. The talk generation unit can consider industry trends and adjust the talk content for industries where growth is expected. The talk generation unit can consider the balance of market supply and demand and set talk content that is in high demand. This makes it possible to adjust the talk content based on industry trends and market trends. Some or all of the above processing in the talk generation unit may be performed using AI, for example, or not using AI. For example, the talk generation unit can input industry trend and market trend data into AI, and the AI ​​can adjust the talk content.

[0094] The talk generation unit can analyze the target's past response history and apply the optimal talk algorithm. For example, the talk generation unit can analyze past successful response history and apply a similar talk algorithm. The talk generation unit can analyze past unsuccessful response history and avoid similar talk algorithms. Based on past response history, the talk generation unit can apply a talk algorithm that is more likely to succeed at specific times of day or on specific days of the week. This makes it possible to apply the optimal talk algorithm based on past response history. Some or all of the above processing in the talk generation unit may be performed using AI, for example, or without AI. For example, the talk generation unit can input past response history into AI, and the AI ​​can apply the optimal talk algorithm.

[0095] The talk generation unit can estimate the user's emotions and adjust the length of the talk based on the estimated emotions. For example, if the user is relaxed, the talk generation unit can generate a detailed talk. If the user is stressed, the talk generation unit can generate a short, concise talk. If the user is excited, the talk generation unit can generate an assertive, longer talk. This allows for adjustment of the talk length according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the talk generation unit may be performed using AI, for example, or not using AI. For example, the talk generation unit can input user emotion data into a generation AI, which can estimate the emotions and adjust the length of the talk.

[0096] The talk generation unit can adjust the talk content considering the target's geographical location information. For example, the talk generation unit can set region-specific talk content based on the target's geographical location information. The talk generation unit can adjust the talk content for targets that are geographically easily accessible. The talk generation unit can set talk content for targets concentrated in a specific region, taking geographical characteristics into consideration. This makes it possible to adjust the talk content based on geographical location information. Some or all of the above processing in the talk generation unit may be performed using AI, for example, or without AI. For example, the talk generation unit can input geographical location information into AI, and the AI ​​can adjust the talk content.

[0097] The talk generation unit can analyze the target's social media activity and prioritize generating relevant talk content. For example, the talk generation unit can analyze the target's social media activity and prioritize incorporating content of high interest into the talk. The talk generation unit can prioritize incorporating content that has received a good response on social media into the talk. The talk generation unit can prioritize generating relevant talk content for targets who are active on social media. This makes it possible to prioritize the generation of talk content based on social media activity. Some or all of the above processing in the talk generation unit may be performed using AI, for example, or without AI. For example, the talk generation unit can input social media activity data into AI, and the AI ​​can generate relevant talk content.

[0098] The listening unit can estimate the user's emotions and adjust its listening method based on the estimated emotions. For example, if the user is relaxed, the listening unit will conduct the interview in a gentle tone. If the user is stressed, the listening unit can ask concise and clear questions. If the user is agitated, the listening unit can conduct the interview in an assertive tone. This allows for adjustment of the listening method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the listening unit may be performed using AI, or not using AI. For example, the listening unit can input user emotion data into the generative AI, which can estimate the emotions and adjust the listening method.

[0099] The interviewing department can adjust the interview content considering the target industry trends and market trends. For example, the interviewing department can analyze current market trends and set interview content that matches those trends. The interviewing department can consider industry trends and adjust the interview content for industries that are expected to grow. The interviewing department can consider the balance of market supply and demand and set interview content that is in high demand. This makes it possible to adjust the interview content based on industry trends and market trends. Some or all of the above processes in the interviewing department may be performed using AI, for example, or not. For example, the interviewing department can input data on industry trends and market trends into AI, and the AI ​​can adjust the interview content.

[0100] The listening unit can analyze the target's past response history and apply the optimal listening algorithm. For example, the listening unit can analyze past successful response histories and apply similar listening algorithms. The listening unit can analyze past unsuccessful response histories and avoid similar listening algorithms. Based on past response histories, the listening unit can apply listening algorithms that are more likely to succeed at specific times of day or on specific days of the week. This makes it possible to apply the optimal listening algorithm based on past response histories. Some or all of the above processing in the listening unit may be performed using AI, for example, or without AI. For example, the listening unit can input past response histories into AI, and the AI ​​can apply the optimal listening algorithm.

[0101] The listening unit can estimate the user's emotions and determine the priority of the listening session based on the estimated emotions. For example, if the user is relaxed, the listening unit will prioritize important listening sessions. If the user is stressed, the listening unit will prioritize simple listening sessions. If the user is agitated, the listening unit will conduct listening sessions quickly. This allows for the determination of listening session priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the listening unit may be performed using AI, for example, or not using AI. For example, the listening unit can input user emotion data into a generative AI, which can estimate emotions and determine the priority of the listening session.

[0102] The interviewing unit can adjust the interview content considering the target's geographical location information. For example, the interviewing unit can set region-specific interview content based on the target's geographical location information. The interviewing unit can adjust the interview content for targets that are geographically easily accessible. The interviewing unit can set interview content for targets concentrated in a specific region, taking geographical characteristics into consideration. This makes it possible to adjust the interview content based on geographical location information. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or without AI. For example, the interviewing unit can input geographical location information into AI, and the AI ​​can adjust the interview content.

[0103] The interviewing unit can analyze the target's social media activity and prioritize relevant interview topics. For example, the interviewing unit can analyze the target's social media activity and prioritize interviews on topics of high interest. The interviewing unit can prioritize interviews on topics that have received positive responses on social media. The interviewing unit can prioritize interviews on topics that are active on social media. This makes it possible to prioritize interview content based on social media activity. Some or all of the above processing in the interviewing unit may be performed using AI, for example, or not. For example, the interviewing unit can input social media activity data into AI, and the AI ​​can generate relevant interview content.

[0104] The appointment setting unit can estimate the user's emotions and adjust the appointment setting method based on the estimated emotions. For example, if the user is relaxed, the appointment setting unit can set appointments in a gentle tone. If the user is stressed, the appointment setting unit can use a concise and clear method of setting appointments. If the user is excited, the appointment setting unit can set appointments in an assertive tone. This makes it possible to adjust the appointment setting method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the appointment setting unit may be performed using AI, for example, or not using AI. For example, the appointment setting unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the appointment setting method.

[0105] The appointment setting unit can adjust appointment content by considering the target industry trends and market trends. For example, the appointment setting unit can analyze current market trends and set appointment content that matches the trends. The appointment setting unit can consider industry trends and adjust appointment content for industries where growth is expected. The appointment setting unit can consider the balance of market supply and demand and set appointment content with high demand. This makes it possible to adjust appointment content based on industry trends and market trends. Some or all of the above processes in the appointment setting unit may be performed using AI, for example, or not using AI. For example, the appointment setting unit can input industry trend and market trend data into AI, and the AI ​​can adjust the appointment content.

[0106] The appointment setting unit can analyze the target's past response history and apply the optimal appointment setting algorithm. For example, the appointment setting unit can analyze past successful response history and apply a similar appointment setting algorithm. The appointment setting unit can analyze past unsuccessful response history and avoid similar appointment setting algorithms. Based on past response history, the appointment setting unit can apply an appointment setting algorithm that is more likely to succeed at specific times of day or on specific days of the week. This makes it possible to apply the optimal appointment setting algorithm based on past response history. Some or all of the above processing in the appointment setting unit may be performed using AI, for example, or without AI. For example, the appointment setting unit can input past response history into AI, and the AI ​​can apply the optimal appointment setting algorithm.

[0107] The appointment scheduling unit can estimate the user's emotions and determine appointment scheduling priorities based on the estimated emotions. For example, if the user is relaxed, the appointment scheduling unit will prioritize important appointments. If the user is stressed, the appointment scheduling unit will prioritize easy appointments. If the user is excited, the appointment scheduling unit will schedule appointments quickly. This allows for the determination of appointment scheduling priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the appointment scheduling unit may be performed using AI or not. For example, the appointment scheduling unit can input user emotion data into a generative AI, which can estimate the emotions and determine appointment scheduling priorities.

[0108] The appointment setting unit can adjust appointment setting content considering the target's geographical location information. For example, the appointment setting unit can set region-specific appointment setting content based on the target's geographical location information. The appointment setting unit can adjust appointment setting content for targets that are geographically easily accessible. The appointment setting unit can set appointment setting content for targets concentrated in a specific region, taking geographical characteristics into consideration. This makes it possible to adjust appointment setting content based on geographical location information. Some or all of the above processing in the appointment setting unit may be performed using AI, for example, or without using AI. For example, the appointment setting unit can input geographical location information into AI, and the AI ​​can adjust the appointment setting content.

[0109] The appointment setting unit can analyze the target's social media activity and prioritize relevant appointment setting. For example, the appointment setting unit can analyze the target's social media activity and prioritize incorporating content of high interest into appointment setting. The appointment setting unit can prioritize incorporating content that has received a good response on social media into appointment setting. The appointment setting unit can prioritize relevant appointment setting for targets with active social media activity. This makes it possible to prioritize appointment setting based on social media activity. Some or all of the above processing in the appointment setting unit may be performed using AI, for example, or not using AI. For example, the appointment setting unit can input social media activity data into AI, and the AI ​​can generate relevant appointment setting content.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The target selection unit can estimate the user's emotions and adjust the target selection criteria based on the estimated emotions. For example, if the user is stressed, target selection criteria that promote relaxation can be set. If the user is excited, proactive target selection criteria can be set. Furthermore, if the user is tired, targets that can be easily dealt with can be prioritized. This enables target selection that is appropriate to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Some or all of the above-described processes in the target selection unit may be performed using AI or not.

[0112] The transmitting unit can estimate the user's emotions and adjust the transmission timing based on the estimated emotions. For example, if the user is relaxed, the transmission can be made at the optimal time. If the user is stressed, the transmission timing can be delayed. Furthermore, if the user is excited, the transmission can be made quickly. This makes it possible to adjust the transmission timing according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Some or all of the above processing in the transmitting unit may be performed using AI or not.

[0113] The talk generation unit can estimate the user's emotions and adjust the way the talk is expressed based on the estimated emotions. For example, if the user is relaxed, a softer way of expressing emotions can be used. If the user is stressed, a concise and clear way of expressing emotions can be used. Furthermore, if the user is excited, an assertive way of expressing emotions can be used. This makes it possible to adjust the way the talk is expressed according to the user's emotions. Emotion estimation is achieved using an emotion engine or a generation AI. Some or all of the above processing in the talk generation unit may be performed using AI or not.

[0114] The listening unit can estimate the user's emotions and adjust the listening method based on the estimated emotions. For example, if the user is relaxed, the listening can be conducted in a gentle tone. If the user is stressed, concise and clear questions can be asked. Furthermore, if the user is excited, the listening can be conducted in an assertive tone. This makes it possible to adjust the listening method according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Some or all of the above processing in the listening unit may be performed using AI or not.

[0115] The appointment setting unit can estimate the user's emotions and adjust the appointment setting method based on the estimated emotions. For example, if the user is relaxed, the system can set appointments in a gentle tone. If the user is stressed, a concise and clear appointment setting method can be used. Furthermore, if the user is excited, an assertive tone can be used. This makes it possible to adjust the appointment setting method according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Some or all of the above processing in the appointment setting unit may be performed using AI or not.

[0116] The target selection unit can analyze past target selection history and apply the optimal target selection algorithm. For example, it can analyze past successful target selection patterns and prioritize the selection of targets with similar patterns. It can also analyze past unsuccessful target selection patterns and exclude targets with similar patterns. Furthermore, it can select targets that are more likely to succeed during specific time periods or days of the week based on past target selection history. This enables optimal target selection based on past history. Some or all of the above processing in the target selection unit may be performed using AI or not.

[0117] The communication unit can adjust its content based on target industry trends and market trends. For example, it can analyze current market trends and set content that aligns with those trends. It can also consider industry trends and adjust content for industries where growth is expected. Furthermore, it can consider the balance of market supply and demand and set content that is in high demand. This makes it possible to adjust communication content based on industry trends and market trends. Some or all of the above processing in the communication unit may be performed using AI, or it may be performed without using AI.

[0118] The talk generation unit can analyze the target's past response history and apply the optimal talk algorithm. For example, it can analyze past successful response history and apply a similar talk algorithm. It can also analyze past unsuccessful response history and avoid similar talk algorithms. Furthermore, it can apply a talk algorithm that is more likely to succeed at specific times of day or on specific days of the week based on past response history. This makes it possible to apply the optimal talk algorithm based on past response history. Some or all of the above processing in the talk generation unit may be performed using AI or not.

[0119] The interviewing unit can adjust the interview content considering the target's geographical location information. For example, it can set region-specific interview content based on the target's geographical location information. It can also adjust the interview content for targets that are geographically easily accessible. Furthermore, it can set interview content for targets concentrated in specific regions, taking geographical characteristics into consideration. This makes it possible to adjust the interview content based on geographical location information. Some or all of the above processing in the interviewing unit may be performed using AI or not.

[0120] The appointment setting unit can analyze the target's social media activity and prioritize relevant appointment setting. For example, it can analyze the target's social media activity and prioritize incorporating content of high interest into appointment setting. It can also prioritize incorporating content that has received a good response on social media. Furthermore, it can prioritize relevant appointment setting for targets who are actively using social media. This makes it possible to prioritize appointment setting based on social media activity. Some or all of the above processing in the appointment setting unit may be performed using AI or not.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The target selection department selects targets. The target selection department selects targets based on criteria such as customer attributes, industry, and region. The target selection department can also select targets by collecting and analyzing customer data. For example, they can analyze customer purchase history and behavioral data to select the optimal targets. Step 2: The calling unit automatically makes calls to the targets selected by the target selection unit. The calling unit can make calls automatically using methods such as phone calls, emails, and messaging apps. The calling unit can analyze past call history to optimize the timing and method of making calls. Step 3: The talk generation unit generates introductory and transitional talks using AI after the message has been sent by the sender. The talk generation unit can generate talks using text generation AI (e.g., LLM). The talk generation unit can analyze past talk history to optimize the content of the introductory and transitional talks. Step 4: The interviewing unit conducts interviews using the talk generated by the talk generation unit. The interviewing unit can record and analyze the customer's responses using speech recognition technology. Based on the customer's responses, the interviewing unit can generate the next questions. Step 5: The appointment scheduling department obtains appointments based on the information gathered by the interviewing department. The appointment scheduling department can check the customer's schedule and set an appointment at the most suitable date and time. The appointment scheduling department can adjust the details of the appointment based on the customer's responses.

[0123] 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.

[0124] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the target selection unit, transmission unit, talk generation unit, hearing unit, and appointment acquisition unit, is implemented by at least one of the smart device 14 and the data processing device 12. For example, the target selection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The transmission unit is implemented by the communication I / F 44 of the smart device 14 or the communication I / F 26 of the data processing device 12. The talk generation unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The hearing unit is implemented by the microphone 38B of the smart device 14 and the control unit 46A or the specific processing unit 290 of the data processing device 12. The appointment acquisition unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] 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.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0130] 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.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0132] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] 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.

[0134] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] 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.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the target selection unit, transmission unit, talk generation unit, listening unit, and appointment acquisition unit, is implemented by at least one of the smart glasses 214 and the data processing device 12. For example, the target selection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The transmission unit is implemented by the communication I / F 44 of the smart glasses 214 or the communication I / F 26 of the data processing device 12. The talk generation unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The listening unit is implemented by the microphone 238 of the smart glasses 214 and the control unit 46A or the specific processing unit 290 of the data processing device 12. The appointment acquisition unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] 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.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0146] 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.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0148] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] 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.

[0150] 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.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] 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.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the target selection unit, transmission unit, talk generation unit, listening unit, and appointment acquisition unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the target selection unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The transmission unit is implemented by the communication I / F 44 of the headset terminal 314 or the communication I / F 26 of the data processing unit 12. The talk generation unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The listening unit is implemented by the microphone 238 of the headset terminal 314 and the control unit 46A or the specific processing unit 290 of the data processing unit 12. The appointment acquisition unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] 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.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0162] 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.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0164] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] 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.

[0166] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] 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.

[0168] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] 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.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the target selection unit, transmission unit, talk generation unit, listening unit, and appointment acquisition unit, is implemented by at least one of the robot 414 and the data processing unit 12. For example, the target selection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The transmission unit is implemented by the communication I / F 44 of the robot 414 or the communication I / F 26 of the data processing unit 12. The talk generation unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The listening unit is implemented by the microphone 238 of the robot 414 and the control unit 46A or the specific processing unit 290 of the data processing unit 12. The appointment acquisition unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0176] 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.

[0177] Figure 9 shows the 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.

[0178] 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.

[0179] 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.

[0180] 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, and motorcycles, 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 based, for example, 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.

[0181] 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."

[0182] 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.

[0183] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] 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 other things 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.

[0193] 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 to be incorporated by reference.

[0194] (Note 1) A target selection unit that selects the target, A transmitting unit that automatically transmits to the target selected by the aforementioned target selection unit, A talk generation unit that generates introductory talk and transition talk using AI after the transmission unit has transmitted the message, A hearing unit that conducts hearings using talks generated by the talk generation unit, The system includes an appointment acquisition unit that acquires appointments based on information gathered by the aforementioned hearing unit. A system characterized by the following features. (Note 2) The aforementioned target selection unit, Collect and analyze data to select targets. The system described in Appendix 1, characterized by the features described herein. (Note 3) The transmitting unit is Make an automatic call The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned talk generation unit, Use AI to generate introductory and follow-up speeches. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned hearing section is, Conduct interviews using AI. The system described in Appendix 1, characterized by the features described herein. (Note 6) The appointment acquisition unit, Using AI to schedule appointments The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned target selection unit, We estimate user emotions and adjust target selection criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned target selection unit, We analyze past target selection history and apply the optimal target selection algorithm. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned target selection unit, Adjust selection criteria considering the target industry trends and market trends. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned target selection unit, The system estimates user emotions and determines target selection priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned target selection unit, Adjust the selection criteria to take into account the target's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned target selection unit, Analyze the target audience's social media activity and prioritize selecting relevant targets. The system described in Appendix 1, characterized by the features described herein. (Note 13) The transmitting unit is It estimates the user's emotions and adjusts the timing of communication based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The transmitting unit is Analyze past communication history and select the optimal communication method. The system described in Appendix 1, characterized by the features described herein. (Note 15) The transmitting unit is We adjust our communication content to take into account the target industry trends and market trends. The system described in Appendix 1, characterized by the features described herein. (Note 16) The transmitting unit is It estimates the user's emotions and determines the priority of communication based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The transmitting unit is The content of the message will be adjusted considering the target's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The transmitting unit is Analyze the target audience's social media activity and prioritize sending relevant content. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned talk generation unit, It estimates the user's emotions and adjusts the way the conversation is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned talk generation unit, Adjust the content of your talk to take into account the target industry trends and market trends. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned talk generation unit, Analyze the target's past response history and apply the optimal talk algorithm. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned talk generation unit, It estimates the user's emotions and adjusts the length of the conversation based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned talk generation unit, Adjust the content of the conversation to take the target's geographical location into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned talk generation unit, Analyze the target audience's social media activity and prioritize generating relevant content. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned hearing section is, We estimate the user's emotions and adjust the interview method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned hearing section is, We adjust the interview content to take into account the target industry trends and market trends. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned hearing section is, Analyze the target's past response history and apply the optimal listening algorithm. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned hearing section is, The system estimates the user's emotions and determines the priority of interviews based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned hearing section is, Adjust the interview content to take into account the target's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned hearing section is, Analyze the target audience's social media activity and prioritize relevant interview topics. The system described in Appendix 1, characterized by the features described herein. (Note 31) The appointment acquisition unit, The system estimates the user's emotions and adjusts the appointment setting method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The appointment acquisition unit, Adjust appointment scheduling based on the target industry trends and market trends. The system described in Appendix 1, characterized by the features described herein. (Note 33) The appointment acquisition unit, Analyze the target's past response history and apply the optimal appointment setting algorithm. The system described in Appendix 1, characterized by the features described herein. (Note 34) The appointment acquisition unit, The system estimates user emotions and determines appointment priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The appointment acquisition unit, Adjust appointment scheduling based on the target's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 36) The appointment acquisition unit, Analyze the target's social media activity and prioritize appointments related to that activity. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A target selection unit that selects the target, A transmitting unit that automatically transmits to the target selected by the aforementioned target selection unit, A talk generation unit that generates introductory talk and transition talk using AI after the transmission unit has been transmitted, A hearing unit that conducts hearings using talks generated by the talk generation unit, The system includes an appointment acquisition unit that acquires appointments based on information gathered by the aforementioned hearing unit. A system characterized by the following features.

2. The aforementioned target selection unit, Collect and analyze data to select targets. The system according to feature 1.

3. The transmitting unit is Make an automatic call The system according to feature 1.

4. The aforementioned talk generation unit, Use AI to generate introductory and transitional speeches. The system according to feature 1.

5. The aforementioned hearing section is, Conduct interviews using AI. The system according to feature 1.

6. The appointment acquisition unit, Using AI to schedule appointments The system according to feature 1.

7. The aforementioned target selection unit, We estimate user emotions and adjust target selection criteria based on those estimated emotions. The system according to feature 1.

8. The aforementioned target selection unit, We analyze past target selection history and apply the optimal target selection algorithm. The system according to feature 1.

Images