Information processing device, information processing method, and program
The information processing device addresses the issue of unsatisfactory AI responses by allowing customers to choose between AI and human interaction, ensuring appropriate responses and enhancing satisfaction.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- FIXER
- Filing Date
- 2025-03-20
- Publication Date
- 2026-07-09
Smart Images
Figure 2026116100000001_ABST
Abstract
Description
Technical Field
[0006] , , , , , , , , , , ,
[0007] ,
[0005] , ,
[0001] The present disclosure relates to an information processing apparatus, an information processing method, and a program.
Background Art
[0002] In customer support operations such as call centers, the use of automated response systems is becoming increasingly common. There have also been proposals to use AI (Artificial Intelligence) in automated response systems.
[0003] For example, according to Patent Document 1, a customer support system acquires voice information, extracts keywords through voice recognition processing, identifies the type of inquiry and response information, and responds by voice call using AI.
[0004] The method described in Patent Document 2 determines a response sentence based on the customer's utterance content, determines the business content according to the request, and instructs a business execution device.
Prior Art Documents
Patent Documents
[0005]
Patent Document 1
Patent Document 2
Summary of the Invention
Problems to be Solved by the Invention
[0006] However, the above-mentioned technologies may not result in the response intended by the customer. Therefore, there is a risk that customer satisfaction may decrease.
[0007] In view of the above problems, an object of the present disclosure is to provide an information processing apparatus and the like that suppresses a decrease in customer satisfaction in responding to customer inquiries.
Means for Solving the Problems
[0008] The information processing device relating to this disclosure comprises a reception unit, a determination unit, an answer generation unit, and a connection processing unit. The reception unit receives a method selection signal regarding the method of answering from the caller terminal. The determination unit determines, based on the method selection signal, whether the caller is requesting an answer from generative artificial intelligence or an answer from a human. If the answer generation unit determines that the caller is requesting an answer from generative artificial intelligence, it receives the inquiry from the caller and selects one generative artificial intelligence from a plurality of pre-prepared generative artificial intelligences. The answer generation unit causes the selected generative artificial intelligence to generate an answer and transmits the answer generated by the generative artificial intelligence to the caller terminal. If the connection processing unit determines that the caller is requesting an answer from a human, it connects the caller terminal and the staff terminal so that they can communicate.
[0009] The information processing method related to this disclosure involves a computer performing the following processes: The computer receives a method selection signal regarding the method of response from the caller terminal 1. Based on the method selection signal, the computer determines whether the caller is requesting a response from generative artificial intelligence or a response from a human. If the computer determines that the caller is requesting a response from generative artificial intelligence, it receives the caller's inquiry and selects one generative artificial intelligence from several pre-prepared generative artificial intelligences. The computer has the selected generative artificial intelligence generate a response and transmits the response generated by the generative artificial intelligence to the caller terminal 1. If the computer determines that the caller is requesting a response from a human, it connects the caller terminal 1 and the staff terminal 300 so that they can communicate.
[0010] The program relating to this disclosure causes a computer to execute the following information processing method. The computer receives a method selection signal regarding the method of response from the caller terminal 1. Based on the method selection signal, the computer determines whether the caller is requesting a response from generative artificial intelligence or a response from a human. If the computer determines that the caller is requesting a response from generative artificial intelligence, it accepts the caller's inquiry and selects one generative artificial intelligence from several pre-prepared generative artificial intelligences. The computer has the selected generative artificial intelligence generate a response and transmits the response generated by the generative artificial intelligence to the caller terminal 1. If the computer determines that the caller is requesting a response from a human, it connects the caller terminal 1 and the staff terminal 300 so that they can communicate. [Effects of the Invention]
[0011] According to this disclosure, it is possible to provide an information processing device, an information processing method, and a program that can suppress a decline in customer satisfaction when responding to customer inquiries. [Brief explanation of the drawing]
[0012] [Figure 1] This is a block diagram of the information processing system according to the first embodiment. [Figure 2] This is a block diagram of the information processing device according to the first embodiment. [Figure 3] This diagram shows the contents of the selected information. [Figure 4] This is a block diagram illustrating the hardware configuration of a computer. [Figure 5] This is a flowchart of the information processing method according to the first embodiment. [Figure 6] This is a first sequence diagram of an information processing method according to the first embodiment. [Figure 7] This is a second sequence diagram of the information processing method according to the first embodiment. [Figure 8] This is a block diagram of the information processing system according to the second embodiment. [Figure 9]It is a block diagram of an information processing apparatus according to the second embodiment. [Figure 10] It is a sequence diagram of an information processing method according to the second embodiment.
Embodiments for Carrying Out the Invention
[0013] Hereinafter, the present invention will be described through embodiments of the invention, but the invention according to the claims is not limited to the following embodiments. Also, not all of the configurations described in the embodiments are essential as means for solving the problems. For clarity of explanation, the following description and drawings have been appropriately omitted and simplified. In each drawing, the same elements are denoted by the same reference numerals, and duplicate explanations are omitted as necessary.
[0014] <First Embodiment> (Information Processing System 10) The information processing system 10 will be described with reference to FIG. 1. FIG. 1 is a block diagram of the information processing system 10 according to the first embodiment. The information processing system 10 receives an inquiry from the sender P1 and answers the received inquiry. The information processing system 10 is, for example, a system of a call center that responds to inquiries, orders, or claims from customers. The information processing system 10 may alternatively be a system of a contact center, but is not limited thereto.
[0015] The information processing system 10 is communicably connected to the sender terminal 1 used by the sender P1 via the first network N1. The sender terminal 1 is, for example, a mobile phone or a smartphone used by the sender P1. The sender terminal 1 may be a fixed phone or a computer having a communication function. The first network N1 is, for example, a public communication network for fixed or mobile phones. The main components of the information processing system 10 include an information processing apparatus 100, a server 200, and a staff terminal 300.
[0016] The information processing device 100 is communicably connected to the caller terminal 1 via the first network N1. The information processing device 100 is, for example, a computer or a server having a communication function. The information processing device 100 can receive an outgoing call from the caller terminal 1 and make a predetermined response by automatic voice. That is, the information processing system 10 may have at least a part of the function of an IP-PBX (Internet protocol private branch exchange). The information processing device 100 may have at least a part of the function of an IVR (Interactive Voice Response). The information processing device 100 automatically answers an incoming call from the caller terminal 1 and plays a preset response message. Further, the information processing device 100 causes the caller P1 to send a tone signal by pressing a phone number button. The information processing device 100 connects the staff terminal 300 and the caller terminal 1 communicably according to the situation.
[0017] The information processing device 100 is communicably connected to the server 200 and can access the language model possessed by the server 200. Thereby, the information processing device 100 obtains an answer to the prompt generated by the information processing device 100 from the server 200 according to the situation.
[0018] The information processing device 100 can be communicably connected to the staff terminal 300. The information processing device 100 relays the caller terminal 1 and the staff terminal 300 according to the situation, enabling the caller P1 and the staff P2 to communicate. Note that relaying the caller terminal 1 and the staff terminal 300 can also be described as transferring the line connected to the caller terminal 1 to the staff terminal 300.
[0019] Server 200 is connected to information processing device 100 in a communicative manner. Server 200 has a first language model 210 and a second language model 220. The first language model 210 and the second language model 220 are generative AI (Artificial Intelligence) using large language models (LLMs) that generate responses to various user requests. Generative AI can also be rephrased as generative artificial intelligence. In this disclosure, the first language model 210 and the second language model 220 are different language models. Here, "different language models" includes cases where the type of language model itself is different. Also, "different language models" includes cases where the type of language model is the same but the versions are different. The first language model 210 or the second language model 220 receives a prompt from the information processing device 100, generates a response to the received prompt, and supplies the response to the information processing device 100.
[0020] Furthermore, the information processing device 100 and the server 200 may be connected via wired or wireless connections for direct communication. The information processing device 100 and the server 200 may also be connected via an internet connection. The server 200 may be a virtual entity located in the cloud. In addition, although Figure 1 shows one server having a first language model 210 and a second language model 220, multiple servers may have the first language model 210 and the second language model 220. Also, in Figure 1, the server 200 has two generative AIs, the first language model 210 and the second language model 220, but it may have three or more language models.
[0021] The staff terminal 300 is a terminal used by staff member P2 and is connected to the information processing device 100 so as to be able to communicate with it. The staff terminal 300 is, for example, a computer with communication capabilities. The staff terminal 300 is configured to communicate with caller P1, who is using caller terminal 1, via the information processing device 100.
[0022] (Information processing device 100) Next, the information processing device 100 will be described with reference to Figure 2. The information processing device 100 receives an outgoing call from the caller terminal 1 via the first network N1. Upon receiving the outgoing call from the caller terminal 1, the information processing device 100 responds to an inquiry from the caller P1. The main components of the information processing device 100 are a reception unit 110, a determination unit 120, an answer generation unit 130, a connection processing unit 140, a communication unit 150, and a storage unit 160.
[0023] The reception unit 110 receives the outgoing call from the caller terminal 1. After establishing a connection with the caller terminal 1, the reception unit 110 sends a pre-configured reception message to the caller terminal 1. The reception message includes a message prompting the caller P1 to specify how to respond to the inquiry.
[0024] The reception unit 110 receives a method selection signal regarding the response method from the caller terminal 1. The response method is a method of responding to the inquiry received from the caller P1. The response method includes responses by a generating AI and responses by a human. The method selection signal regarding the response method is a signal indicating which response method the caller P1 prefers from responses by a generating AI and responses by a human. This method selection signal is, for example, a tone signal that the caller terminal 1 can transmit. In this disclosure, the tone signal is a tone signal transmitted by a typical telephone or smartphone. The tone signal may also be referred to as DTMF (Dual-Tone Multi-Frequency).
[0025] The method selection signal may be a signal different from the tone signal. The method selection signal may be voice data, which is the utterance of the caller P1. The method selection signal may be a signal transmitted by the caller terminal 1, which is text data input by the caller P1. The method selection signal may also be a combination of these.
[0026] The determination unit 120 determines, based on the method selection signal described above, whether the caller P1 is requesting a response from a generating AI or a human. Specifically, for example, when the method selection signal is set to a tone signal, the determination unit 120 detects the tone signal received from the caller terminal 1 and determines the type of tone signal detected.
[0027] More specifically, suppose a tone signal requesting a human response corresponds to "1" on a push-button telephone line, and a tone signal requesting a response from a generating AI corresponds to "2" on a push-button telephone line. In this case, the determination unit 120 determines whether the method selection signal is "1", "2", or something else.
[0028] In the determination described above, the determination unit 120 refers to the selection information 161 stored in the storage unit 160. Here, the selection information 161 includes information linking the type of tone signal and the response method.
[0029] The determination unit 120 may be configured to select which of the multiple generating AIs possessed by the information processing system 10 should provide the response. In this case, for example, the response from the first language model 210 may be set to "2" and the response from the second language model 220 may be set to "3". In this case, the determination unit 120 determines whether the method selection signal is "1", "2", "3", or something else. In this case, the selection information 161 stored in the storage unit 160 may include information about the type of generating AI to provide the response, as it links the type of tone signal with the response method.
[0030] The determination of whether to request a response from a generating AI or from a human may be set to be made by recognizing the utterance of the caller P1. In this case, the determination unit 120 detects the utterance of the caller P1 and determines from the content of the detected utterance whether the caller P1 requests a response from a generating AI or from a human. Alternatively, the determination unit 120 may determine from the content of the utterance of the caller P1 which of the multiple generating AIs possessed by the information processing system 10 should provide the response. In this case, the selection information 161 stored in the storage unit 160 may include information about the type of generating AI to provide the response, as it links the content of the utterance of the caller P1 with the response method.
[0031] If the determination unit 120 determines that caller P1 is requesting an answer from the AI-generated response unit 130, the response generation unit 130 accepts the inquiry from caller P1. In this case, the response generation unit 130 sends voice data to caller terminal 1 to prompt caller P1 to speak the content of the inquiry. If the response generation unit 130 detects voice data that is a speech from caller P1, it converts the received voice data into text data in order to recognize the content of the inquiry. The response generation unit 130 then performs tokenization and other operations on the text data to generate a prompt from the content of the inquiry.
[0032] In other words, the response generation unit 130 converts the inquiry, which is the utterance of the caller P1, into text, and generates a prompt for a generating AI to generate a response based on the converted text. The prompt is an instruction sentence to be input to the generating AI. The prompt contains specific content for generating a response to the caller P1's inquiry.
[0033] The response generation unit 130 also selects one generation AI from several pre-prepared generation AIs. That is, the response generation unit 130 selects either the first language model 210 or the second language model 220 that the server 200 has. The response generation unit 130 makes this selection in response to either a method selection signal or an utterance from the caller P1. For example, if the method selection signal includes the selection of the first language model 210 among the generation AIs, the response generation unit 130 selects the first language model 210 according to the method selection signal.
[0034] Alternatively, the response generation unit 130 selects a generation AI from the content of the data obtained by converting the utterance of caller P1 into text. In this case, the response generation unit 130 refers to the selection information 161 stored in the memory unit 160. In this case, the selection information 161 is information that links text related to the content of the inquiry with the type of generation AI. The response generation unit 130 compares the data obtained by converting the utterance of caller P1 into text with the text contained in the selection information 161 and extracts the same text or text with a similar meaning. Furthermore, the response generation unit 130 selects a language model that has a strong connection to the utterance of caller P1 from the extracted results.
[0035] The response generation unit 130 causes the selected generating AI to generate a response and sends the response generated by the generating AI to the sender terminal 1. In other words, the response generation unit 130 generates a prompt to cause the selected language model to generate a response. The response generation unit 130 supplies the generated prompt to either the first language model 210 or the second language model 220. The response generation unit 130 receives the response generated in response to the prompt.
[0036] The response generation unit 130 also converts the response generated by the generation AI into voice data and sends it to the caller terminal 1. In other words, the response generation unit 130 converts the content of the response received from the language model into voice data in order to convey it to the caller P1. The response generation unit 130 then sends the converted voice data to the caller terminal 1. At this time, the information processing device 100 transmits the voice data to the caller terminal 1 via the communication unit 150.
[0037] To realize the above-described functions, the response generation unit 130 mainly consists of a signal conversion unit 131, a prompt generation unit 132, and a language model selection unit 133.
[0038] The signal conversion unit 131 converts text data into audio data. The signal conversion unit 131 also converts audio data into text data. For example, the signal conversion unit 131 converts audio data, which is the utterance of the caller P1, into text data. Furthermore, the signal conversion unit 131 converts the response, which is text data received from the language model, into audio data.
[0039] The prompt generation unit 132 generates a prompt to cause a single generation AI to generate an answer based on the text containing the inquiry content, which is the utterance of the caller P1.
[0040] The language model selection unit 133 selects a generation AI based on a method selection signal, which is either a tone signal in the caller terminal 1's telephone function or voice data from the caller's utterance. Alternatively, the language model selection unit 133 selects a generation AI based on the content of words included in the inquiry, which is the utterance of the caller P1. The language model selection unit 133 refers to the selection information 161 stored in the memory unit 160.
[0041] If the determination unit 120 determines that caller P1 is requesting a human response, the connection processing unit 140 connects caller terminal 1 and staff terminal 300 to enable communication. In other words, if the method selection signal indicates a request for a human response, the connection processing unit 140 connects the incoming line from caller terminal 1 to staff terminal 300. By the connection processing unit 140 relaying the call between caller terminal 1 and staff terminal 300, caller P1 and staff P2 become able to communicate.
[0042] The communication unit 150 is responsible for functions related to communication with the first network N1, communication with the server 200, and communication with the staff terminal 300. In other words, the communication unit 150 performs signal processing related to the transmission and reception of signals in these communication functions.
[0043] The memory unit 160 stores various information necessary to realize the functions of the information processing device 100. For example, the memory unit 160 stores the reception message that the reception unit 110 sends to the caller terminal 1. The memory unit 160 also stores selection information 161. The selection information 161 is information used by the response generation unit 130 when selecting a generation AI.
[0044] The information processing device 100 has been described above. With the above configuration, the information processing device 100 can provide both human interaction and AI-generated responses in accordance with customer requests. Furthermore, the information processing device 100 selects an AI-generated response from multiple AI-generated responses that matches the content of the inquiry and provides the caller with a response that matches the content of the inquiry. Therefore, the information processing device 100 can suppress a decline in customer satisfaction when responding to customer inquiries.
[0045] (Selection Information) Next, we will explain the selection information 161 with reference to Figure 3. Figure 3 is a diagram showing the contents of the selection information 161. The selection information 161 shown in Figure 3 is information that links the type of language model with multiple words that are expected to be included in the query content.
[0046] Specifically, the inquiry words associated with the "first language model" include "specs," "specifications," "product lineup," "how to use," and "what color." In this case, the first language model 210 is a language model that has learned about product inquiries and answers. The inquiry words associated with the "second language model" include "malfunction," "broken," "strange," "not working," and "abnormal." In this case, the second language model 220 is a language model that has learned about after-sales service inquiries and answers.
[0047] The response generation unit 130 compares the words contained in the inquiry uttered by the caller P1 with the words contained in the selection information 161. The response generation unit 130 then selects the option that contains more words that are closer to the content of the caller P1's inquiry.
[0048] Furthermore, the selection information 161 is not limited to the contents described above. If the information processing system 10 includes content that causes the method selection signal to select a generation AI, the selection information 161 may include, for example, information linking the type of tone signal with the type of generation AI. In addition, the selection information 161 may be made available for addition, deletion, and updating as appropriate.
[0049] (Example hardware configuration) Figure 4 is a block diagram illustrating the hardware configuration of a computer. The information processing device 100 described above may have the configuration shown in Figure 4. The computer 1000 has a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input / output interface 1050, and a network interface 1060.
[0050] Bus 1010 is a data transmission path for the processor 1020, memory 1030, storage device 1040, input / output interface 1050, and network interface 1060 to send and receive data to and from each other. However, the method of connecting the processor 1020 and the other components to each other is not limited to bus connection.
[0051] Processor 1020 is a circuit that includes arithmetic units such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit).
[0052] Memory 1030 is a main memory device implemented using RAM (Random Access Memory), etc.
[0053] The storage device 1040 is an auxiliary storage device such as an HDD (Hard Disk Drive), SSD (Solid State Drive), flash memory, or ROM (Read Only Memory). The storage device 1040 stores a program for realizing the functions of this disclosure.
[0054] The processor 1020 reads this program into memory 1030 and executes it. This causes the processor 1020 to perform the function corresponding to this program. In other words, the program stored in memory 1030 causes the computer 1000 to perform the function of this disclosure.
[0055] The input / output interface 1050 connects the computer 1000 to a predetermined input / output device. The input / output device is, for example, an input device such as a keyboard, an output device such as a display, or an input / output device in which a touch panel is superimposed on a display.
[0056] The network interface 1060 is an interface for connecting the computer 1000 to a predetermined communication network.
[0057] The computer 1000 has been described above, but in addition to the above configuration, the computer 1000 may have an information input device for the user to input various information into the computer 1000 through operation. The information input device may be, for example, a keyboard, mouse, or touch panel. The computer 1000 may also have a display, speaker, vibration motor, or LED (light-emitting diode) for showing various information to the user.
[0058] (Information processing methods) Next, the processing performed by the information processing device 100 will be described with reference to Figure 5. Figure 5 is a flowchart of the information processing method according to the first embodiment. In Figure 5, the processing performed by the information processing device 100 begins, for example, when the information processing system 10 receives an outgoing call from the caller terminal 1.
[0059] In step S11, the information processing device 100 sends an acknowledgment message to the caller terminal 1 with which communication has been established. The acknowledgment message includes a message prompting the caller to send a method selection signal to choose how they want to receive a response. For example, the acknowledgment message might say, "Thank you for calling. If you would like a response from a staff member, please press "1" and "#". If you would like a response from a generating AI, please press "2" and "#".
[0060] In step S12, the reception unit 110 receives a method selection signal regarding the response method from the caller terminal 1. The reception unit 110 supplies the received information regarding the response method to the determination unit 120.
[0061] In step S13, the determination unit 120 determines, based on the method selection signal, whether the caller P1 is requesting a response from a generating AI or a response from a human. More specifically, for example, the determination unit 120 determines whether or not the caller P1 is requesting a response from a generating AI. If the determination unit 120 determines that the caller P1 is requesting a response from a generating AI (step S13: YES), the information processing device 100 proceeds to step S14. On the other hand, if the determination unit 120 does not determine that the caller P1 is requesting a response from a generating AI (step S13: NO), the information processing device 100 proceeds to step S20.
[0062] In step S14, if the determination unit 120 determines that caller P1 is requesting an answer from the AI, the answer generation unit 130 requests the content of the inquiry from caller P1. That is, the answer generation unit 130 sends a message to caller terminal 1 as voice data, for example, "Please tell us the content of your inquiry."
[0063] In step S15, the response generation unit 130 receives an inquiry from the caller P1. Upon receiving the inquiry, the signal conversion unit 131 of the response generation unit 130 converts the received inquiry into text data. The language model selection unit 133 selects from the text data whether to have the first language model 210 or the second language model 220 respond to the inquiry. That is, the language model selection unit 133 selects one generation AI from several generation AIs that have been prepared in advance.
[0064] In step S16, the prompt generation unit 132 determines, based on the selection result by the language model selection unit 133, whether or not to have the first language model 210 respond to the query. If the response generation unit 130 determines that the first language model 210 should respond (step S16: YES), the response generation unit 130 proceeds to step S17. On the other hand, if the response generation unit 130 does not determine that the first language model 210 should respond (step S16: NO), the response generation unit 130 proceeds to step S22.
[0065] In step S17, the response generation unit 130 causes the selected generation AI to generate a response. That is, the prompt generation unit 132 of the response generation unit 130 sends a prompt to the first language model 210 to generate a response to the inquiry.
[0066] In step S18, the response generation unit 130 sends the response generated by the generating AI to the caller terminal 1. The response generation unit 130 converts the response generated by the first language model 210 or the second language model 220 into voice data and sends the converted voice data to the caller terminal 1. In this process, the information processing device 100 may send voice data to the caller terminal 1 saying, "If the answer is satisfactory, please hang up. If you have further questions, please state your additional questions." By sending such voice data, the information processing device 100 can continue the response generated by the generating AI if the caller P1 wishes to continue the inquiry.
[0067] In step S19, the information processing device 100 determines whether or not to terminate the series of processes. Termination of the series of processes occurs, for example, when communication with the caller terminal 1 is completed. Conversely, failure to terminate the series of processes occurs when communication with the caller terminal 1 is not completed. If the information processing device 100 determines that the series of processes should be terminated (step S19: YES), the information processing device 100 terminates the series of processes. On the other hand, if the information processing device 100 does not determine that the series of processes should be terminated (step S19: NO), the information processing device 100 returns to step S14 and requests the inquiry content again. The information processing device 100 may also record a history of inquiries and answers if the caller P1 repeatedly makes inquiries. In this case, the information processing device 100 may also have a function to generate prompt content from the recorded history information. This reduces the effort required for the caller P1 to repeatedly make inquiries.
[0068] In step S13, if the determination unit 120 does not determine that caller P1 is requesting a response from the generated AI (step S13: NO), it can be said that caller P1 is requesting a response from a human. Therefore, in step S20, the connection processing unit 140 connects caller terminal 1 and staff terminal 300 so that they can communicate.
[0069] In step S21, the connection processing unit 140 determines whether the call between the caller terminal 1 and the staff terminal 300 has ended. If it is determined that the call between the caller terminal 1 and the staff terminal 300 has ended (step S21: NO), the connection processing unit 140 repeats step S21. On the other hand, if it is determined that the call between the caller terminal 1 and the staff terminal 300 has ended (step S21: YES), the information processing device 100 terminates the series of processes.
[0070] In step S16, if the response generation unit 130 does not determine that the first language model 210 should provide a response (step S16: NO), the response generation unit 130 proceeds to step S22. In step S22, the response generation unit 130 causes the selected generation AI to generate a response. That is, the prompt generation unit 132 sends a prompt to the second language model 220 to generate a response to the inquiry. Once the response generation unit 130 has caused the second language model 220 to generate a response, it proceeds to step S18.
[0071] The processes performed by the information processing device 100 have been described above. Through the processes described above, the information processing device 100 listens to the content of the inquiry from the caller P1, selects a generation AI from multiple generation AIs that corresponds to the content of the inquiry, and generates a response. Therefore, the information processing device 100 can suppress a decrease in customer satisfaction when responding to customer inquiries.
[0072] The processing performed by the information processing device 100 is not limited to the configuration described above. For example, in step S11, the reception message sent by the reception unit 110 may accept three options: "Answer by staff," "Answer by the generating AI about the product," and "Answer by the generating AI about after-sales service." In this case, the information processing device 100 may, for example, have the first language model 210 answer the inquiry about the product. The first language model 210 is a language model that has learned about inquiries and answers about the product. The information processing device 100 may have the second language model 220 answer the inquiry about after-sales service. The second language model 220 is a language model that has learned about inquiries and answers about after-sales service.
[0073] Furthermore, in step S11, the reception unit 110 may include the staff's operational status in the reception message. The staff's operational status may include information indicating whether or not there is a staff member available for a call. This allows the information processing device 100 to provide caller P1 with information on whether or not a call with staff member P2 is immediately possible. In this case, the information processing device 100 can facilitate a smooth decision-making process for caller P1 when selecting a response method.
[0074] Furthermore, if the information processing device 100 does not determine in step S19 that the series of processes has ended (step S19: NO), the information processing device 100 may return to step S12 instead of step S14 and process the response method again. This allows the information processing device 100 to change the setting so that a human responds if the sender P1 is not satisfied with the response from the generated AI.
[0075] Next, an example of interaction between the caller terminal 1 and the information processing system 10 will be explained with reference to Figure 6. Figure 6 is a first sequence diagram of the information processing method according to the first embodiment. The sequence diagram shown in Figure 6 shows the interaction between the caller terminal 1 and the information processing system 10 when the caller P1 requests a response from the generated AI.
[0076] In step S101, the caller terminal 1 makes a call to the information processing system 10. That is, the caller terminal 1 sends a call signal to the information processing system 10. The information processing device 100 of the information processing system 10 receives this signal and it becomes an incoming call.
[0077] In step S102, the information processing device 100 receives an incoming call and sends an acceptance message to the caller terminal 1. The acceptance message includes content prompting the caller to select a response method.
[0078] In step S103, the caller P1 selects a response method. As a result, the caller terminal 1 transmits a method selection signal to the information processing device 100. The sequence diagram shown in Figure 6 illustrates the case where the caller P1 selects a response generated by the AI.
[0079] In step S104, the information processing device 100, having received a method selection signal for selecting an answer generated by the AI, sends a response message to the caller terminal 1 requesting the content of the inquiry.
[0080] In step S105, caller P1 speaks the inquiry. Caller terminal 1 transmits the voice data containing the inquiry spoken by caller P1 to information processing device 100.
[0081] In step S106, the information processing device 100 selects a language model. Here, as an example, the information processing device 100 selects the first language model 210. The information processing device 100 generates a prompt to cause the first language model 210 to generate an answer.
[0082] In step S107, the information processing device 100 prompts the first language model 210 to generate an answer. The instruction to generate an answer includes the content of the inquiry spoken by the caller P1.
[0083] In step S108, the first language model 210 generates a response to the prompt and supplies it to the information processing device 100.
[0084] In step S109, the information processing device 100 generates audio data from the response received from the first language model 210. Alternatively, the information processing device 100 may generate a response sentence containing the response generated by the first language model 210, and then convert the response sentence into audio data.
[0085] In step S110, the information processing device 100 transmits voice data including the response to the caller terminal 1.
[0086] Next, another example of the interaction between the caller terminal 1 and the information processing system 10 will be described with reference to Figure 7. Figure 7 is a second sequence diagram of the information processing method according to the first embodiment. The sequence diagram shown in Figure 7 shows the interaction between the caller terminal 1 and the information processing system 10 when the caller P1 requests a response from a human. Note that the interactions in steps S101 and S102 are the same as those in the sequence diagram shown in Figure 6. Therefore, their explanation will be omitted here.
[0087] In step S103, the caller P1 selects a response method. The caller terminal 1 then transmits a method selection signal to the information processing device 100. The sequence diagram shown in Figure 7 illustrates the case where the caller P1 selects a human response.
[0088] In step S201, the information processing device 100, having received a method selection signal for selecting a human response, connects the caller terminal 1 and the staff terminal 300.
[0089] In step S202, the information processing device 100 transmits a call signal to the staff terminal 300. Staff member P2, who is using the staff terminal 300, receives the call signal transmitted by the information processing device 100 and sets the staff terminal 300 to a state where communication is possible. From this point onward, the caller terminal 1 and the staff terminal 300 are in a state where communication is possible.
[0090] The above describes the interaction between the caller terminal 1 and the information processing system 10. As described above, the information processing system 10 appropriately sets whether to provide a response using a language model or a response provided by a human, in accordance with the method selection signal sent from the caller terminal 1. Furthermore, if a response using a generating AI is selected, the information processing system 10 selects one generating AI from among several generating AIs to generate the response.
[0091] The first embodiment has been described above. However, the information processing system 10 is not limited to the configuration described above. The information processing device 100 can be connected to multiple caller terminals 1. The number of connectable lines may be set in advance. The information processing system 10 may also include multiple staff terminals 300. In this case, the communication unit 150 recognizes the connection status of each of the multiple staff terminals 300 and connects to the caller terminal 1 according to the connection status. With the above configuration, the information processing device 100 can respond using generated AI even when the number of staff is small compared to the number of inquiries.
[0092] The generation AI of server 200 may support multimodal communication. In this case, the response generation unit 130 may supply the voice data, including the caller P1's inquiry, to server 200 without converting it to text data. Also, if the generation AI outputs a response using voice data, the response generation unit 130 may transmit the voice data output by the generation AI to the caller terminal 1.
[0093] The information processing system 10 and the information processing device 100 have been described above. Each component of the information processing device 100 may be implemented with dedicated hardware. In addition, some or all of each component may be implemented by general-purpose or dedicated circuits, processors, etc., or combinations thereof. These may be configured by a single chip or by multiple chips connected via a bus. Some or all of each component may be implemented by a combination of the above-mentioned circuits, etc., and programs. In addition, a CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (field-programmable gate array), etc. can be used as the processor. Furthermore, at least some of the functions of this embodiment may be provided in the form of IaaS (Infrastructure as a Service), PaaS (Platform as a Service), or SaaS (Software as a Service).
[0094] As described above, this embodiment provides an information processing device 100, an information processing method, and a program that can suppress a decline in customer satisfaction when responding to customer inquiries.
[0095] <Second Embodiment> Next, a second embodiment will be described. Figure 8 is a block diagram of the information processing system 10 according to the second embodiment. The information processing system 10 according to this embodiment differs from the information processing system 10 according to the first embodiment in that it has a reference information storage unit 400. Furthermore, the information processing system 10 according to this embodiment differs from the information processing system 10 according to the first embodiment in that it is connected to the second network N2 in addition to the first network N1 so that it can communicate.
[0096] The information processing device 100 according to the second embodiment connects to a second network N2 in addition to the first network N1. The first network N1 is a public communication network for landlines or mobile phones. On the other hand, the second network N2 is, for example, an internet connection. That is, the information processing device 100 can connect to the caller terminal 1 so as to be able to make calls, and furthermore, it can communicate with the caller terminal 1 by means of information communication other than calls. More specifically, for example, the information processing device 100 can transmit information using any data, such as text data or image data.
[0097] The information processing device 100 according to the second embodiment is communicatively connected to a reference information storage unit 400. The reference information storage unit 400 stores information related to inquiries from caller P1. For example, if it is expected that an inquiry regarding a specific product will be received from caller P1, the reference information storage unit 400 stores information related to the product being inquired about. The reference information storage unit 400 can provide the information to be stored to the information processing device 100. When the information processing device 100 has the first language model 210 or the second language model 220 respond to an inquiry received from caller P1, it can generate a prompt by referring to the information in the reference information storage unit 400. In other words, the information processing device 100 has a RAG function (Retrieval-Augmented Generation). Note that the information processing device 100 and the reference information storage unit 400 may be configured as an integrated unit. In other words, the information processing device 100 may include the reference information storage unit 400.
[0098] Figure 9 is a block diagram of the information processing device according to the second embodiment. The information processing device 100 according to this embodiment differs from the information processing device 100 according to the first embodiment mainly in the configuration of the receiving unit 110, the response generation unit 130, the connection processing unit 140, and the storage unit 160.
[0099] In this embodiment, the reception unit 110 performs verification to identify the caller P1 as a customer. The purpose of identifying the customer is to send the answer to the caller P1's inquiry as text data to the caller terminal 1. The information processing system 10 may authenticate the caller terminal 1 or caller P1 via the first network N1 and the second network N2. That is, the reception unit 110 may have a function to authenticate caller P1.
[0100] The response generation unit 130 according to this embodiment includes a search function unit 134. The search function unit 134 is configured to implement RAG functionality. The search function unit 134 refers to the content of the caller P1's inquiry, extracts information related to the content of the inquiry from the reference information storage unit 400, and supplies the extracted information to the prompt generation unit 132. The prompt generation unit 132 generates a prompt that includes the content of the caller P1's inquiry in addition to the reference information received from the search function unit 134. In other words, the response generation unit 130 searches a predetermined database for information related to the inquiry and generates a prompt using the search results. As a result, the first language model 210 or second language model 220 of the server 200 generates a response to the inquiry after referring to the reference information.
[0101] In this embodiment, the response generation unit 130 transmits text data to the caller terminal 1 via the second network N2. At this time, the response generation unit 130 refers to the customer information 162 stored in the storage unit 160 and identifies a means for transmitting text data to caller P1 from the caller P1's personal information. The means for transmitting text data to caller P1 is, for example, an email address. The caller P1's email address may also be included in the voice data acquired by the information processing device 100 when caller P1 speaks. The means for transmitting text data to caller P1 may also be the caller P1's account information on a predetermined SNS. By transmitting text data to the caller terminal 1, the information processing system 10 can convey a message to caller P1 not only through voice data but also through text data. The text data transmitted by the response generation unit 130 may include information about the type of language model that generated the response. Therefore, the information processing system 10 can provide a response that is highly satisfactory to customers.
[0102] The storage unit 160 according to this embodiment has customer information 162. The customer information 162 includes a unique identifier for the customer and information regarding means of contacting the customer.
[0103] Next, with reference to Figure 10, the interaction between the caller terminal 1 and the information processing system 10 will be described. Figure 10 is a sequence diagram of the information processing method according to the second embodiment. The sequence diagram shown in Figure 10 differs from the sequence diagram in Figure 6 in that the processing after step S108 is different.
[0104] After receiving a response from the first language model 210 in step S108, in step S301, the information processing device 100 generates audio data and text data of the response. The audio data is for transmission to the caller terminal 1 via the first network N1. The text data is for transmission to the caller terminal 1 via the second network N2. The content of the audio data and the text data may be the same or may differ. For example, the text data may contain more detailed information than the audio data. The text data may also include a predetermined URL (Uniform Resource Locator) related to the response. Furthermore, the audio data may include content explaining the differences between it and the text data. This allows the information processing device 100 to provide a more detailed response to the customer.
[0105] In step S302, the information processing system 10 transmits voice data related to the response to the caller terminal 1 via the first network N1.
[0106] In step S303, the information processing system 10 transmits text data related to the response to the sender terminal 1 via the second network N2. That is, the response generation unit 130 of the information processing device 100 transmits the response generated by the generation AI as text data to the sender terminal 1.
[0107] The second embodiment has been described above. This embodiment allows for the rapid provision of detailed answers to customer inquiries by using the RAG function. Furthermore, this embodiment enables the provision of answers in text data in addition to voice data. As a result, this embodiment can provide an information processing device 100, an information processing method, and a program that provide high customer satisfaction.
[0108] The program described above includes a set of instructions (or software code) that, when loaded into a computer, causes the computer to perform one or more of the functions described in the embodiments. The program may be stored on a non-temporary computer-readable medium or a physical storage medium. Examples, but not limited to, include computer-readable mediums or physical storage mediums such as RAM (random-access memory), ROM (read-only memory), flash memory, SSD (solid-state drive), or other memory technologies. Examples, but not limited to, include CD-ROMs, DVDs (digital versatile discs), Blu-ray discs, or other optical disc storage. Examples, but not limited to, include magnetic tape, magnetic disk storage, or other magnetic storage devices. The program may be transmitted over a temporary computer-readable medium or a communication medium. Examples, but not limited to, include temporary computer-readable mediums or communication mediums such as electrical, optical, acoustic, or other forms of propagating signals.
[0109] The embodiments have been described above, but the configurations of the embodiments described above may be combined with each other, or some of the configurations may be replaced with other configurations. Furthermore, the configurations of the embodiments described above may be modified in various ways without departing from the spirit of the invention.
[0110] Each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated with one or more other embodiments rather than with only one specific embodiment. As those skilled in the art will understand, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings, for example, to create embodiments not explicitly shown or described. Not all features or steps shown in any one drawing to illustrate an exemplary embodiment are necessarily required, and some features or steps may be omitted. The order of steps shown in any of the drawings may be changed as appropriate. [Explanation of Symbols]
[0111] 1. Caller's terminal 10 Information Processing Systems 100 Information Processing Devices 110 Reception Department 120 Judgment section 130 Answer generation part 131 Signal conversion section 132 Prompt generation unit 133 Language Model Selection Section 134 Search Function Section 140 Connection Processing Unit 150 Communications Department 160 Storage section 161 Selection Information 162 Customer information 200 servers 210 First Language Model 220 Second Language Models 300 staff terminals 400 Reference Information Storage Unit 1000 computers 1010 Bus 1020 Processor 1030 memory 1040 Storage Devices 1050 Input / Output Interface 1060 Network Interfaces N1 First Network N2 Second Network P1 Sender P2 Staff
Claims
1. A receiving unit that receives a method selection signal regarding the response method from the caller's terminal, A determination unit that determines, based on the method selection signal, whether the caller is requesting a response from generative artificial intelligence or from a human, If the system determines that the caller is requesting the response from the generative artificial intelligence, the system receives the caller's inquiry, selects one generative artificial intelligence from a pre-prepared set of generative artificial intelligences, has the selected generative artificial intelligence generate the response, and transmits the response generated by the generative artificial intelligence to the caller's terminal. If it is determined that the caller is requesting the aforementioned response from a person, the system includes a connection processing unit that connects the caller's terminal and the staff terminal in a way that enables communication. Information processing device.
2. In the information processing apparatus according to claim 1, The response generation unit selects one of the generative artificial intelligences based on the method selection signal, which is either a tone signal in the caller terminal's telephone function or voice data from the caller's speech. Information processing device.
3. In the information processing apparatus according to claim 1, The response generation unit selects one of the generative artificial intelligences based on the content of the words included in the inquiry, which is the utterance of the caller. Information processing device.
4. In the information processing apparatus according to claim 1, The response generation unit transmits the response generated by the generative artificial intelligence as text data to the caller terminal. Information processing device.
5. In the information processing apparatus according to claim 1, The response generation unit converts the response generated by the generative artificial intelligence into voice data and transmits it to the caller terminal, and then, in response to the caller's response, accepts further inquiries from the caller. Information processing device.
6. In the information processing apparatus according to any one of claims 1 to 5, The response generation unit converts the inquiry, which is the utterance of the caller, into text, and generates a prompt for a generative artificial intelligence to generate the response based on the converted text. Information processing device.
7. The information processing device described in claim 6 is The response generation unit searches a predetermined database for information related to the inquiry and generates the prompt using the search results. Information processing device.
8. Computers The caller's terminal receives a method selection signal regarding the response method. Based on the method selection signal, it is determined whether the caller is requesting a response from generative artificial intelligence or from a human. If it is determined that the caller is requesting the response from the generative artificial intelligence, the system accepts the caller's inquiry, selects one generative artificial intelligence from a set of pre-prepared generative artificial intelligences, has the selected generative artificial intelligence generate the response, and transmits the response generated by the generative artificial intelligence to the caller's terminal. If it is determined that the caller is requesting the response from a human, the caller's terminal and the staff terminal are connected to enable communication. Information processing methods.
9. The caller's terminal receives a method selection signal regarding the response method. Based on the method selection signal, it is determined whether the caller is requesting a response from generative artificial intelligence or from a human. If it is determined that the caller is requesting the response from the generative artificial intelligence, the system accepts the caller's inquiry, selects one generative artificial intelligence from a set of pre-prepared generative artificial intelligences, has the selected generative artificial intelligence generate the response, and transmits the response generated by the generative artificial intelligence to the caller's terminal. If it is determined that the caller is requesting the response from a human, the caller's terminal and the staff terminal are connected to enable communication. To have a computer execute an information processing method. program.