method

Abstract

To improve techniques for analyzing dialogue. [Solution] A method executed by the information processing device 10, which includes acquiring voice data relating to a conversation between a salesperson and a customer, extracting customer information from the voice data, generating a report containing the extracted customer information, and notifying the customer's referral destination of the report.

Description

Technical Field

[0001] This disclosure relates to a method.

Background Art

[0002] Conventionally, techniques related to the analysis of conversations are known. For example, Patent Document 1 discloses a conversation analysis system that records conversation data based on voice data obtained by recording conversation contents, extracts conversations that match conditions specified by a user from the conversation data, and displays them in a list.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] For example, when a salesperson has a conversation with a customer at a specific vehicle dealership and then escorts the customer to another store, it is desirable that the customer information obtained during the conversation be shared with the other store. However, conventionally, since staff manually compiled customer information into a report in a predetermined format, there was room for improvement from the perspectives of information accuracy and the number of processes.

[0005] In view of such circumstances, an object of the present disclosure is to improve techniques related to the analysis of conversations.

Means for Solving the Problems

[0006] A method executed by an information processing apparatus according to an embodiment of the present disclosure includes: obtaining voice data related to a conversation between a salesperson and a customer; extracting customer information of the customer from the voice data; generating a report including the extracted customer information; and To notify the customer referred by the aforementioned customer of the aforementioned report, Includes. [Effects of the Invention]

[0007] According to one embodiment of this disclosure, the technology for analyzing dialogue is improved. [Brief explanation of the drawing]

[0008] [Figure 1] This block diagram shows a schematic configuration of a system according to one embodiment of the present disclosure. [Figure 2] This is a flowchart showing the operation of an information processing device. [Modes for carrying out the invention]

[0009] (Summary of this embodiment) Referring to Figure 1, an overview of System 1 according to one embodiment of this disclosure will be described. System 1 comprises an information processing device 10 and a terminal device 20. The information processing device 10 and the terminal device 20 are connected to each other via a network 30 such as the Internet or a mobile communication network.

[0010] The information processing device 10 includes one server device or multiple computers that can communicate with each other. The information processing device 10 generates reports from voice data related to conversations (business negotiations) with customers.

[0011] The terminal device 20 includes any information processing terminal such as a PC (Personal Computer), tablet, or smartphone. The terminal device 20 is operated, for example, by a salesperson at a vehicle dealership.

[0012] First, an overview of this embodiment will be described, and details will be described later. The method according to this embodiment is performed by the information processing device 10. The method includes acquiring voice data relating to the conversation between the salesperson and the customer. The method also includes extracting customer information from the voice data. The method also includes generating a report containing the extracted customer information. The method also includes notifying the customer's referral destination of the report.

[0013] According to the method of this embodiment, customer information is automatically extracted from audio data related to customer interactions and a report is generated. This improves the accuracy of customer information and reduces the workload of sales staff compared to, for example, an embodiment in which sales staff manually compile customer information into a report.

[0014] (Configuration of the information processing device 10) As shown in Figure 1, the information processing device 10 comprises a control unit 11, a communication unit 12, and a storage unit 13.

[0015] The control unit 11 includes one or more processors, one or more programmable circuits, one or more dedicated circuits, or a combination thereof. The processor is, for example, a general-purpose processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or a dedicated processor specialized for a specific process, but is not limited to these. The programmable circuit is, for example, an FPGA (Field-Programmable Gate Array), but is not limited to this. The dedicated circuit is, for example, an ASIC (Application Specific Integrated Circuit), but is not limited to this. The control unit 11 controls each part of the information processing device 10 and executes processes related to the operation of the information processing device 10.

[0016] The communication unit 12 includes at least one communication interface for connecting to a network. The communication interface may conform to, for example, a mobile communication standard such as 4G (4th generation) or 5G (5th generation), or a wired LAN (Local Area Network) communication standard or a wireless LAN communication standard, but is not limited thereto and may conform to any communication standard.

[0017] The storage unit 13 includes one or more memories. Each memory included in the storage unit 13 may function as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 13 stores any information used for the operation of the information processing device 10. For example, the storage unit 13 may store, for example, a system program, an application program, and embedded software. The storage unit 13 may store a learning model such as an LLM (Large Language Model). The information stored in the storage unit 13 may be updated based on information acquired from a network via the communication unit 12, for example.

[0018] (Configuration of the terminal device 20) As shown in FIG. 1, the terminal device 20 includes a control unit 21, a communication unit 22, an input unit 23, and a display unit 24.

[0019] The control unit 21 includes one or more processors, one or more programmable circuits, one or more dedicated circuits, or a combination thereof. The processor is, for example, a general-purpose processor such as a CPU or GPU, or a dedicated processor specialized for specific processing, but is not limited thereto. The programmable circuit is, for example, an FPGA, but is not limited thereto. The dedicated circuit is, for example, an ASIC, but is not limited thereto. While controlling each part of the terminal device 20, the control unit 21 executes processing related to the operation of the terminal device 20.

[0020] The communication unit 22 includes at least one communication interface for connecting to a network. The communication interface corresponds to, for example, a mobile communication standard such as 4G or 5G, or a wired LAN communication standard or a wireless LAN communication standard, but is not limited thereto and may correspond to any communication standard.

[0021] The input unit 23 includes a microphone for receiving voice input. Instead of being provided in the terminal device 20, the input unit 23 may be connected to the terminal device 20 as an external input device. As a connection method, any method such as USB (Universal Serial Bus), HDMI (registered trademark) (High-Definition Multimedia Interface), or Bluetooth (registered trademark) can be used.

[0022] The display unit 24 includes one or more display interfaces. The display interface is, for example, a display for displaying information as an image. The display is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display. The display unit 24 displays the information obtained by the operation of the terminal device 20. Instead of being provided in the terminal device 20, the display unit 24 may be connected to the terminal device 20 as an external display device. As a connection method, any method such as USB, HDMI, or Bluetooth can be used.

[0023] (Operation flow of the information processing apparatus 10) Referring to FIG. 2, the operation of the information processing apparatus 10 according to the present embodiment will be described. Hereinafter, the communication between the information processing apparatus 10 and the terminal device 20 is performed via the communication units 12 and 22 and the network.

[0024] S1: The control unit 11 of the information processing apparatus 10 acquires voice data related to the dialogue between the salesperson and the customer.

[0025] The control unit 11 may acquire audio data by receiving audio data input to the input unit 23 of the terminal device 20. The audio data may be acquired all at once after the conversation has ended (for example, when the recording stop button on the terminal device 20 is pressed), or it may be acquired in real time during the conversation.

[0026] S2: The control unit 11 extracts customer information from the voice data. The control unit 11 may also perform speech recognition processing on the voice data to obtain dialogue text, and then perform natural language processing on the dialogue text to extract customer information.

[0027] Customer information may include multiple items. Examples of multiple items include the name of the staff member in charge, the customer's name, address, contact information, email address, gender, age group, date and time of visit, number of visits, number of people in the visit, purpose of vehicle use, information on the vehicle to be traded in (manufacturer, model, grade, year of manufacture, and vehicle inspection expiration date, etc.), information on the vehicle to be purchased (manufacturer, model, and grade, etc.), payment method, and information on competing stores (presence or absence of competitors, store name, and staff name). The customer information to be extracted may be pre-stored in the storage unit 13, or it may be newly determined and added by the control unit 11.

[0028] If voice data is acquired in real time during the conversation, the control unit 11 may further display items on the screen that have not been extracted from the voice data among multiple items. For example, the control unit 11 may display the number of extracted items, the number of unextracted items, or the ratio of the number of extracted items to the total number of items on the display unit 24. Alternatively, the control unit 11 may display first support information on the display unit 24 to elicit unextracted items through the conversation. The first support information may be a message such as, "Let's bring up the topic of ○○ and ask about the 'unextracted items'." The control unit 11 may generate the first support information using a conversational AI trained on conversational data from another salesperson in the past (for example, a veteran salesperson). The conversational AI may be trained to output the first support information when an unextracted item is input.

[0029] S3: The control unit 11 generates a report containing the extracted customer information. The control unit 11 may perform natural language processing on the extracted customer information to generate the report. The report may be generated according to a pre-configured format.

[0030] S4: The control unit 11 notifies the customer's referral destination of the report. The referral destination includes, for example, the referral destination's email address.

[0031] The control unit 11 may further display second support information on the display unit 24 of the terminal device 20, indicating potential customer destinations based on a comparison of the extracted customer information with the customer information and purchase history of multiple past customers. The second support information may be, for example, "In past cases with similar customer information, the store with the highest purchase rate is △△ store." The control unit 11 may also receive candidates selected by a salesperson, for example via the input unit 23, and determine the selected candidates as target customers. With this configuration, even a young salesperson with little experience can determine an appropriate customer destination.

[0032] While this disclosure has been described based on the drawings and embodiments, it should be noted that those skilled in the art may make various modifications and alterations based on this disclosure. Therefore, it should be noted that these modifications and alterations are within the scope of this disclosure. For example, the functions included in each component or step can be rearranged in a logically consistent manner, and multiple components or steps can be combined into one or divided. For example, in the embodiments described above, an embodiment is also possible in which the configuration and operation of the information processing device 10 or terminal device 20 are distributed among multiple computers that can communicate with each other. [Explanation of Symbols]

[0033] 1 System, 10 Information Processing Device, 11 Control Unit, 12 Communication Unit, 13 Storage Unit, 20 Terminal Device, 21 Control Unit, 22 Communication Unit, 23 Input Unit, 24 Display Unit, 30 Network

Claims

1. A method executed by an information processing device, To acquire audio data related to conversations between sales staff and customers, Extracting customer information of the customer from the aforementioned audio data, To generate a report containing the extracted customer information, and To notify the customer referred by the aforementioned customer of the aforementioned report, Methods that include...

2. A method according to claim 1, wherein the acquisition includes acquiring the audio data in real time.

3. A method according to claim 2, wherein the customer information includes a plurality of items, The method further includes performing a screen display corresponding to the items among the plurality of items that have not been extracted from the audio data.

4. A method according to claim 1, wherein the acquisition includes acquiring the audio data collectively after the dialogue has ended.

5. A method according to claim 1, further comprising displaying candidates for the customer referral destination based on a comparison of the extracted customer information with the customer information and purchase history of a plurality of past customers.

Images