Voice call device and voice call program

Abstract

A voice call system improves flexibility or versatility of utilization of a scenario of a voice response.　A voice call device according to the present invention assists in achieving an objective of a caller via a voice call with a user, and comprises: a first prompt input means for inputting, to a language model, a prompt for leading to the achievement of the objective; an answer acquisition means for acquiring, from the language model to which the prompt is input, an answer including a question sentence to the user; a voice conversion means for converting a first text of the question sentence into a first call voice; a call voice transmission means for transmitting the first call voice to a telephone set of the user; a call voice reception means for receiving, from the telephone set, a second call voice that has responded to the first call voice; a text conversion means for converting the second call voice into a second text; and a second prompt input means for inputting, to the language model, a prompt including the second text, wherein the prompt includes a character restriction command for the answer including the question sentence to the user, and when the question sentence exceeds a character restriction, the question sentence is corrected within the character restriction.

Description

Voice communication device and voice communication program

[0001] The present invention relates to a voice communication device and a voice communication program.

[0002] For example, in the case of a manned call center system, there is a limit to the number of operators who can respond simultaneously, and it may not be possible to respond to all incoming calls. To address this, automated voice response systems known as IVRs or voicebots have been known. By playing voice guidance and prompting customers to press telephone buttons, customers can select requirements, answer questions, and be directed to the desired information or department in charge (see, for example, Patent Document 1).

[0003] JP 2010-258855 A

[0004] However, with the above-mentioned conventional automated voice response systems, depending on the customer's reason for calling and the requirements of their inquiry, the question branches of the voice response (voice guidance / scenario) can become long, requiring the user to press buttons multiple times.Furthermore, the system only has a pre-determined voice response scenario as a guide and is limited to fixed, standardized responses to requirements, which can result in a lack of flexibility in the scenarios and versatility in application.

[0005] The present invention has been proposed in view of the above points, and one object of the present invention is to improve the flexibility of voice response scenarios and the versatility of application in a voice call system.

[0006] In order to solve the above problem, the calling device of the present invention is a voice calling device that supports a caller in achieving their goal through a voice call with a user, and includes: a first prompt input means for inputting a prompt to a language model to guide the caller to the achievement of the goal; an answer acquisition means for acquiring an answer including a question for the user from the language model into which the prompt has been input; a voice conversion means for converting a first text of the question into a first call voice; a voice transmission means for transmitting the first call voice to the user's telephone; a voice reception means for receiving a second call voice from the telephone in response to the first call voice; a text conversion means for converting the second call voice into a second text; and a second prompt input means for inputting a prompt including the second text into the language model, wherein the prompt includes a character limit command for an answer including a question for the user, and if the question exceeds the character limit, the question is corrected to within the character limit.

[0007] According to the embodiment of the present invention, it is possible to improve the flexibility of voice response scenarios and the versatility of application in a voice call system.

[0008] FIG. 1 is a diagram illustrating an example of a network configuration of a voice call system according to the present embodiment; FIG. 2 is a diagram illustrating an example of a hardware configuration of a voice call server according to the present embodiment; FIG. 3 is a diagram illustrating an example of a software configuration of a voice call system according to the present embodiment; FIG. 4 is a diagram illustrating an example of a text dialogue between a voice call server and an LLM according to the present embodiment; FIG. 5 is a diagram illustrating an example of a text dialogue between a voice call server and an LLM according to the present embodiment; FIG. 6 is a diagram illustrating an example of a text dialogue between a user and a voice call server according to the present embodiment; FIG. 7 is a diagram illustrating an example of a text dialogue between a user and a voice call server according to the present embodiment; FIG. 8 is a diagram illustrating an example of a text dialogue between a user and a voice call server according to the present embodiment; FIG. 9 is a diagram illustrating an example of a text dialogue between a user and a voice call server according to the present embodiment;

[0009]

[0023] The present invention will be described in detail with reference to the accompanying drawings. [Embodiment 1] <System Configuration> (Network Configuration) Fig. 1 is a diagram showing an example of the network configuration of a voice call system according to this embodiment. The voice call system 100 in Fig. 1 includes a voice call server 10, an LLM 20, and a telephone 30, which are connected via a network 60.

[0010] The voice call server 10 is a server device that is used, for example, as a call center reception system and realizes voice calls with users. In particular, the voice call server 10 according to this embodiment is a so-called AI telephone server that, when it receives a voice inquiry from a user, obtains a response to the user's inquiry via the LLM 20 and responds to the user's inquiry.

[0011] The LLM (Large Language Models) 20 is a language model that further trains (by fine-tuning or RAG) a knowledge base that aggregates knowledge documents (e.g., product manuals, service manuals, pamphlets, Q&A collections, etc.) for responding to user inquiries on a general-purpose natural language processing model (LLM: Large Language Models) that has been pre-trained on grammar, word meanings, etc. using a large amount of text data. Note that the general-purpose natural language processing model can be, for example, a language model (generative AI) based on BERT (Bidirectional Encoder Representations from Transformers), GPT (Generative Pre-trained Transformer)-3.5, GPT-4, etc.

[0012] The telephone 30 is a telephone capable of making voice calls, such as a regular telephone, a mobile phone, a smartphone, or an IP phone, and is a calling device for a user (caller) who uses the voice call system 100. A user can make an inquiry by voice call by calling a predetermined telephone number using the telephone 30 to the voice call server 10. In particular, when the telephone 30 is a smartphone, a predetermined telephone application program is installed in advance.

[0013] The network 60 is a communication network including wired and wireless networks, and includes, for example, a public line network, the Internet (IP telephone network), and Wi-Fi (registered trademark).

[0014] 2 is a diagram showing an example of the hardware configuration of the voice call server according to this embodiment. The voice call server 10 includes a central processing unit (CPU) 11, a read-only memory (ROM) 12, a random access memory (RAM) 13, a hard disk drive (HDD) 14, and a communication device 15.

[0015] The CPU 11 executes various programs and performs arithmetic processing. The ROM 12 stores programs required at startup, etc. The RAM 13 is a work area for temporarily storing processing by the CPU 11 and storing data. The HDD 14 stores various data and programs. The communication device 15 communicates with other devices via the network 60.

[0016] (Software Configuration) FIG. 3 is a diagram showing an example of the software configuration of the voice call system according to this embodiment.

[0017] The voice call server 10 has a call receiving unit 101, a prompt input unit 102, a response acquisition unit 103, a text-to-speech conversion unit 104, and a call voice transmission / reception unit 105 as main functional units.

[0018] The call receiving unit 101 has a function of receiving a call from a user's telephone and making a call to the user's telephone.

[0019] The prompt input unit 102 has a function of inputting a goal-seek prompt to the language model, and also has a function of inputting a prompt including a text (user response sentence) to the language model.

[0020] The answer acquisition unit 103 has a function of acquiring an answer including a question sentence (AI question sentence) for the user from a language model to which a goal seek prompt has been input.

[0021] The text-to-speech conversion unit 104 has a function of converting text into speech or speech into text.

[0022] The call voice transmission / reception unit 105 has a function of transmitting call voice (AI question voice) to the telephone and receiving call voice (user answer voice) from the telephone.

[0023] Each functional unit is realized by a program executed on hardware resources such as a CPU, ROM, and RAM of a computer constituting the voice call server 10. These functional units may be referred to as "means," "module," "unit," or "circuit." Each functional unit may also be located in a separate device on the network 60. The computer program of the voice call server 10 may be stored in a computer-readable storage medium.

[0024] <System Flow> Fig. 4 is a sequence diagram of the voice call system according to this embodiment. Fig. 5 is a diagram showing an example (part 1) of a text dialogue between the voice call server and the LLM according to this embodiment. Fig. 6 is a diagram showing an example (part 1) of a voice call between a user and the voice call server according to this embodiment. Below, a detailed explanation will be given with reference to Figs. 5 and 6 as appropriate, using an example in which a user makes a telephone inquiry to a call center regarding a printer malfunction. Note that with regard to the voice call server 10, each step (hereinafter abbreviated as "S") can be realized by having the CPU 11 load and execute a program capable of realizing this sequence.

[0025] S1: The user who is the caller uses the telephone 30 to call a predetermined telephone number (for example, the telephone number of a call center).

[0026] S2: The voice communication server 10 receives a call from the user, establishes a voice call, and inputs (transmits) to the LLM 20 a predetermined goal seek prompt 70a to cause the LLM 20 to respond to the user's inquiries and requirements.

[0027] For example, as shown in Figure 5, the goal-seek prompt 70a is a type of prompt that issues instructions to the LLM 20. It can guide the user toward achieving a goal the user desires, such as resolving a request, by repeatedly asking the user questions (sometimes with the LLM 20 creating its own prompts) to achieve the user's desired goal. In other words, the goal-seek prompt 70a is a prompt that sets a goal to be achieved and instructs the LLM 20 to guide the user toward that goal. Note that while the goal to be achieved is set in the goal-seek prompt, no intermediate scenario (guidance) is set to the goal.

[0028] When a goal-seek prompt 70a is input, the LLM 20 replies with a question (sentence) to guide the user toward the goal as a response to the input goal-seek prompt. The user responds to the question, and this process is repeated until the user's purpose is finally achieved. Normally, when a user tries to reach a desired goal, a considerable amount of work is required, such as creating a prompt each time. However, with the goal-seek prompt, the user does not need to create a new prompt each time. By answering the questions output by the LLM 20 in the goal-seek prompt, it is possible to efficiently move toward the goal.

[0029] S3: When the goal seek prompt 70a is input, the LLM 20 immediately replies with a response including a question (i.e., an AI question) 71a as a response to the input goal seek prompt. In this embodiment, the response to the goal seek prompt 70a includes, for example, a question 71a directed to the user, such as "This is the XX call center. Please tell us the details of your inquiry." Furthermore, if the goal seek prompt instructs the LLM 20 to create a prompt, the response may include a prompt generated by the LLM 20 (such as a prompt including a user answer 72a in S8, which will be described later, or an example or template of the prompt).

[0030] S4: Since the answer question 71a received from the LLM 20 is text data, the voice call server 10 converts the text data of the question 71a into call voice data (so to speak, AI question voice).

[0031] In addition, since the LLM 20 may provide an unexpected or inappropriate answer, for example, the voice communication server 10 may modify (process) the text data of the question 71a before converting it into voice data. For example, even if a prompt is issued to limit the answer to 100 characters or less, if the answer is 200 characters, the answer may be modified to 100 characters or less. In this case, the voice communication server 10 may have the LLM 20 modify or summarize the answer to 100 characters or less before converting the text data of the question 71a into voice data.

[0032] S5: The voice call server 10 responds with the converted call voice data (AI question voice) 71b to the telephone 30. The call voice data 71b is a voice indicating an AI question, such as "This is the XX call center. Please tell us the details of your inquiry." In this case, the voice data 71b asks the user the specific details of the inquiry and prompts the user to make the call (utterance).

[0033] S6: The user receives the AI ​​question voice 71b and freely speaks the inquiry he / she wants to make as the user answer voice 72b, for example, "I have a question about the product."

[0034] S7: The voice call server 10 receives the user's response voice 72b to the AI ​​question voice 71b of S5 as call voice data, and converts the received call voice data into text data (user's response sentence).

[0035] In addition, for example, the user may give an unexpected or inappropriate answer, and in that case, the voice communication server 10 may correct (process) the user's answer voice 72b and convert it into text data. Alternatively, the voice communication server 10 may prompt the user to make a correction again, and then convert the user's answer voice 72b into text data.

[0036] S8: The voice communication server 10 generates a prompt including the user answer sentence 72a (prompt based on the user answer sentence 72a) as the user's answer to the AI ​​question voice 71b of S5, and inputs it to the LLM 20.

[0037] S9: The LLM 20 receives the prompt containing the user's answer 72a in S8 and immediately replies with a response containing a question 73a. For example, the response may contain a question 73a for the user, such as "This is the XX call center. Please tell us the details of your inquiry."

[0038] S10: The voice call server 10 converts the text data of the answer question sentence (AI question sentence) 73a received from the LLM 20 into call voice data (AI question voice).

[0039] S11: The voice call server 10 responds with the converted call voice data (AI question voice) 73b to the telephone 30. The call voice data 73b is, for example, an AI question voice saying, "Thank you for speaking. So, which product specifically are you interested in?", and prompts the user to make a further call (utterance) to answer.

[0040] Then, the exchange of AI question voice (AI question sentence) and user answer voice (user answer sentence) is repeated until the user's goal is achieved (S6-S11). Figure 7 is a diagram showing an example (part 2) of a text dialogue between the voice call server and LLM according to this embodiment. Figure 8 is a diagram showing an example (part 2) of a voice call between the user and the voice call server according to this embodiment. The LLM 20 according to this embodiment has studied, for example, a printer service manual, and is therefore able to identify the user's printer problem and provide a solution in accordance with the service manual. Furthermore, user answer voices can vary from person to person and sometimes include unexpected answers, but the LLM 20 can flexibly respond with a question voice that corresponds to the user answer voice each time.

[0041] The voice call server 10 can also link with various systems and databases (see FIG. 1). For example, it can query the customer management database for the phone number of the user who made the call, identify the user information, and use the user information for the voice call. Furthermore, if it is necessary to identify past response history, it can link with a response history system or the like and use the past response history for the voice call.

[0042] [Embodiment 2] A description will be given of embodiment 2. In embodiment 1, an example of responding to an inquiry based on a call from a user (inbound response) was shown (S1 in FIG. 4). In embodiment 2, an example of responding to guidance and sales based on a call from the voice communication server 10 to the user (outbound response) is shown.

[0043] FIG. 9 is a sequence diagram of the voice call system according to this embodiment. FIG. 10 is a diagram showing an example (part 3) of a text dialogue between a voice call server and an LLM according to this embodiment. FIG. 11 is a diagram showing an example (part 4) of a text dialogue between a voice call server and an LLM according to this embodiment. FIG. 12 is a diagram showing an example (part 3) of a voice call between a user and a voice call server according to this embodiment. FIG. 13 is a diagram showing an example (part 4) of a voice call between a user and a voice call server according to this embodiment. An example of providing sales information about an insurance product to a user will be described in detail with reference to FIG. 9 and, where appropriate, to FIGS. 10-13.

[0044] S1-2: The voice call server 10, which corresponds to the caller, calls the user, i.e., a predetermined telephone number (for example, a telephone number listed in a customer list). Compared with S1 in Fig. 4, in S1, S2: When the user answers the phone, the voice call server 10 establishes a voice call and inputs a predetermined goal seek prompt 80a to the LLM 20 to have the LLM 20 respond to the user's inquiries and requirements.

[0045] S3: When the goal seek prompt 80a is input, the LLM 20 immediately returns a response including a question (i.e., an AI question) 81a as a response to the input goal seek prompt. The response includes a question 71a for the user, such as "This is the XX call center. Please tell us the details of your inquiry."

[0046] S4: The voice call server 10 converts the text data of the answer question sentence 81a received from the LLM 20 into call voice data (AI question voice).

[0047] S5: The voice call server 10 responds to the telephone 30 with the converted call voice data (AI question voice) 81b.

[0048] S6: The user receives the AI ​​question voice 81b and freely speaks as a user answer voice 82b.

[0049] S7: The voice call server 10 receives the user's response voice 82b to the AI ​​question voice 81b of S5 as call voice data, and converts the received call voice data into text data (user's response sentence).

[0050] S8: The voice communication server 10 generates a prompt including the user answer sentence 82a (prompt based on the user answer sentence 82a) as the user's answer to the AI ​​question voice 81b of S5, and inputs it to the LLM 20.

[0051] S9: The LLM 20 receives the prompt containing the user's answer 82a from S8 and immediately replies with a question 83a.

[0052] S10: The voice call server 10 converts the text data of the answer question sentence (AI question sentence) 83a received from the LLM 20 into call voice data (AI question voice).

[0053] S11: The voice call server 10 responds to the telephone 30 with the converted call voice data (AI question voice) 83b.

[0054] Then, the exchange of AI question voice (AI question sentence) and user answer voice (user answer sentence) is repeated until the user's goal is achieved (S6 to S11). The LLM 20 according to this embodiment has learned, for example, the insurance product brochure or sales manual, and is therefore capable of outputting information about the insurance product.

[0055] [Modification] Fig. 14 is a sequence diagram of a voice call system according to this modification. Fig. 15 is a diagram showing an example (part 5) of a text dialogue between a voice call server and an LLM according to this modification. Fig. 15 is a diagram showing an example (part 5) of a text dialogue between a voice call server and an LLM according to this modification. Specific user inquiries and requirements may be explicitly set as goals that the user wishes to achieve in the goal seek prompt.

[0056] S1: The user uses the telephone 30 to call a predetermined telephone number (for example, the telephone number of a call center).

[0057] S1-3: The voice call server 10 receives a call from the user, establishes a voice call, and responds with guidance to solicit the user's inquiry or requirements, such as, "This is the XX call center. Please tell us your inquiry requirements."

[0058] S1-4: The user listens to the guidance and freely speaks about the inquiry he or she wants to make, for example, "I have a question about a product."

[0059] S1-5: The voice communication server 10 executes a voice analysis process and extracts keywords to identify the requirements that the user wishes to inquire about (identification means for identifying the user's desired purpose).

[0060] S2: The voice communication server 10 inputs a goal-seek prompt 90a to the LLM 20, which sets the user's inquiry requirements as a goal. Compared to the goal-seek prompt 70a in Fig. 5, the goal-seek prompt 90a in Fig. 15 sets the goal specifically to the user's inquiry requirements, such as "First, I would like to ask about a product. Please create a prompt using the goal-seek prompt, ask me detailed questions, and guide me to achieve my goal." This increases the likelihood that the user will achieve their goal (e.g., resolve their inquiry).

[0061] <Summary> According to the voice call system 100 of this embodiment, manned operators are not required, and the number of users that can be simultaneously handled can be dramatically increased. Furthermore, the free voice call (answer) provided by the LLM (AI) eliminates the need for pre-determined response voices (voice guidance) as in the past, and the response voices are not limited to fixed, standardized response to requirements, enabling more flexible response voice guidance to achieve the user's goal in accordance with the user's response. Furthermore, the range and versatility of the application fields and uses of the voice response system can be improved.

[0062] Although the present invention has been described with reference to specific examples according to the preferred embodiments of the present invention, it is apparent that various modifications and changes can be made to these examples without departing from the broad spirit and scope of the present invention as defined in the appended claims. In other words, the details of the examples and the accompanying drawings should not be construed as limiting the present invention.

[0063] The voice communication system according to this embodiment can be used for both inbound responses based on calls from users and outbound responses based on calls to users, and can be used in situations such as various consultation and inquiry hotlines, procedures, product reservations, product purchase applications, product orders, complaint hotlines, guidance (sales), telephone research / surveys, etc. Multilingual support is also possible.

[0064] 10 Voice call server 20 LLM 30 Telephone 60 Network 100 Voice call system 101 Call receiving unit 102 Prompt input unit 103 Answer acquisition unit 104 Text-to-speech conversion unit 105 Call voice transmission / reception unit

Claims

1. A voice communication device that assists a caller in achieving their goal through a voice call with a user, comprising: a first prompt input means for inputting a prompt to a language model to guide the caller to the achievement of the goal; an answer acquisition means for acquiring an answer including a question for the user from the language model into which the prompt has been input; a voice conversion means for converting a first text of the question into a first voice call; a voice transmission means for transmitting the first voice call to the user's telephone; a voice reception means for receiving a second voice call from the telephone in response to the first voice call; a text conversion means for converting the second voice call into a second text; and a second prompt input means for inputting a prompt including the second text into the language model, wherein the prompt includes a character limit command for an answer including a question for the user, and if the question exceeds the character limit, the voice communication device modifies the question to fit within the character limit.

2. The voice communication device according to claim 1, wherein the prompt input by said first prompt input means is a goal seek prompt.

3. The voice communication device according to claim 1 or 2, further comprising: a specifying means for specifying the purpose desired by the user through a voice analysis process via a voice call with the user.

4. A voice call program that causes a computer that assists a caller in achieving their goal through a voice call with a user to function as: a first prompt input means for inputting a prompt to a language model to guide the caller toward the achievement of the goal; an answer acquisition means for acquiring an answer including a question for the user from the language model into which the prompt has been input; a voice conversion means for converting a first text of the question into a first call voice; a call voice sending means for sending the first call voice to the user's telephone; a call voice receiving means for receiving a second call voice from the telephone in response to the first call voice; a text conversion means for converting the second call voice into a second text; and a second prompt input means for inputting a prompt including the second text into the language model, wherein the prompt includes a character limit command for an answer including a question for the user, and wherein, if the question exceeds the character limit, the question is corrected to fit within the character limit.

Images