Method for analyzing dialogue content

Abstract

An information processing apparatus includes a control unit, an imaging unit, and an input unit. The control unit executes an operation including: acquiring, via the input unit, an agreement of a customer with respect to a recording corresponding to the customer; after the agreement is obtained, shooting by the shooting part is started; and starting recording if a predetermined condition is satisfied, the predetermined condition including a first condition in which the worker is reflected into the image of the imaging unit.

Description

[0001] Cross-reference to related applications

[0002] This application claims priority to Japanese Patent Application No. 2024-189208, filed on October 28, 2024, the entire contents of which are hereby incorporated by reference. Technical Field

[0003] This disclosure relates to methods for analyzing dialogue content. Background Technology

[0004] Currently known techniques for analyzing dialogue content. For example, Patent Document 1 discloses a dialogue analysis system that records dialogue data based on audio data obtained by recording dialogue content, extracts dialogues that match conditions specified by the user from the dialogue data, and displays them at a glance.

[0005] Prior art literature

[0006] Patent documents

[0007] Patent Document 1: Japanese Patent Application Publication No. 2019-28910 Summary of the Invention

[0008] The problem that the invention aims to solve

[0009] Currently, shop staff record their conversations with customers, using the recordings for purposes such as creating customer reports. However, there are instances where staff, focused on interacting with customers, forget to start the recording process.

[0010] The purpose of this disclosure, made in view of the above, is to improve the technology used for analyzing dialogue content.

[0011] Methods for solving problems

[0012] One embodiment of this disclosure relates to a method executed by an information processing apparatus comprising a control unit, an imaging unit, and an input unit.

[0013] The control unit performs actions including the following:

[0014] The input unit obtains the customer's consent to the recording of the response to the customer;

[0015] After obtaining the aforementioned consent, filming begins through the aforementioned camera unit; and

[0016] If the specified conditions are met, recording will begin.

[0017] The specified conditions include a first condition that the staff are reflected in the image of the camera.

[0018] The effects of the invention

[0019] According to one embodiment of this disclosure, the technology for analyzing dialogue content is improved. Attached Figure Description

[0020] Figure 1 This is a block diagram illustrating the general configuration of an information processing apparatus according to one embodiment of the present disclosure.

[0021] Figure 2 This is a flowchart illustrating the operation of an information processing apparatus according to one embodiment of this disclosure. Detailed Implementation

[0022] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings.

[0023] (Summary of this implementation method)

[0024] Reference Figure 1 The following is a summary description of the information processing device 1 according to the embodiments of this disclosure. In this embodiment, the information processing device 1 is a computer such as a laptop computer, tablet, or smartphone. The information processing device 1 is used, for example, by a shop employee. The information processing device 1 is capable of recording the voices of customers and employees.

[0025] First, an overview of this embodiment will be given, with details to follow later. The method described in this embodiment is executed by an information processing device 1 comprising a control unit 10, a camera unit 11, and an input unit 12. The control unit 10 obtains the customer's consent via the input unit 12, relating to recording a response to the customer. After obtaining consent, the control unit 10 begins recording via the camera unit 11. If predetermined conditions are met, the control unit 10 begins recording. The predetermined conditions include a first condition where the staff member appears within the image captured by the camera unit 11.

[0026] According to this embodiment, recording automatically begins if the specified conditions are met. Therefore, recording data can be reliably acquired even if the staff does not initiate the recording.

[0027] (Composition of information processing device 1)

[0028] like Figure 1 As shown, the information processing device 1 includes a control unit 10, a camera unit 11, an input unit 12, a display unit 13, a communication unit 14, and a storage unit 15.

[0029] The control unit 10 includes one or more processors, one or more programmable circuits, one or more special-purpose circuits, or combinations thereof. The processor may be a general-purpose processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or a special-purpose processor designed for specific processing, but is not limited thereto. The programmable circuit may be, for example, a FPGA (Field-Programmable Gate Array), but is not limited thereto. The special-purpose circuit may be, for example, an ASIC (Application Specific Integrated Circuit), but is not limited thereto. The control unit 10 performs various processes related to the operation of the information processing device 1 and controls various parts of the information processing device 1.

[0030] The imaging unit 11 includes any imaging module capable of capturing images of the area surrounding the information processing device 1. Each imaging module includes one or more cameras. Each camera is positioned appropriately on the information processing device 1 such that it can capture images of the area surrounding the information processing device 1. In this embodiment, the imaging unit 11 includes a front-facing camera capable of capturing images of a subject (e.g., a staff member) on the user side of the information processing device 1. The imaging unit 11 may also include a rear-facing camera capable of capturing images of a subject (e.g., a customer) located on the opposite side of the user.

[0031] The input unit 12 has one or more input interfaces. Each input interface includes a microphone for receiving voice input from customers and staff. The input interface may include, for example, a physical keyboard, a capacitive keyboard, a pointing device, or a touchscreen integrated with the display of the display unit 13. The input unit 12 receives and inputs information for the operation of the information processing device 1. Alternatively, the input unit 12 may be connected to the information processing device 1 as an external input device, instead of being installed within the information processing device 1. As a connection method, any method such as USB (Universal Serial Bus), HDMI (High-Definition Multimedia Interface), or Bluetooth (registered trademark) can be used.

[0032] Display unit 13 includes one or more display interfaces. The display interface is, for example, a display that shows information as an image. The display is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electroluminescence) display. Display unit 13 displays information obtained through the operation of information processing device 1. Alternatively, display unit 13 may be connected to information processing device 1 as an external display device, instead of being installed on information processing device 1. As a connection method, any method such as USB, HDMI (registered trademark), or Bluetooth (registered trademark) can be used.

[0033] The communication unit 14 includes at least one communication interface for connecting to a network. The communication interface may correspond to mobile communication standards such as 4G (4th generation) or 5G (5th generation), or wired LAN (Local Area Network) communication standards or wireless LAN communication standards, but is not limited to these, and may correspond to any communication standard.

[0034] Storage unit 15 includes one or more memories. Each memory included in storage unit 15 can function as a main storage device, an auxiliary storage device, or a buffer memory, for example. Storage unit 15 stores any information for the operation of information processing device 1. Storage unit 15 can also store system programs, application programs, and embedded software, for example. In this embodiment, storage unit 15 can also store any data related to customer interactions, such as negotiation data. The information stored in storage unit 15 can also be updated based on information obtained from the network via communication unit 14, for example.

[0035] (Operation flow of information processing device 1)

[0036] Reference Figure 2 The operation of the information processing apparatus 1 according to this embodiment will be described below. Communication between the various parts of the information processing apparatus will be performed via the communication unit 14.

[0037] S101: The control unit 10 of the information processing device 1 obtains the consent of the customer related to the recording of the customer's response via the input unit 12.

[0038] In this embodiment, the control unit 10 obtains consent by detecting consent phrases that imply customer agreement related to recording from the speech input to the input unit 12 (e.g., a microphone). The control unit 10 may also detect consent phrases by comparing the phrases stored in the storage unit 15 with the speech content. In the comparison, natural language processing techniques such as morpheme analysis, syntactic analysis, semantic analysis, contextual analysis, and attribution analysis, as well as learning models pre-trained using machine learning, may be employed. For example, the learning model may be trained by taking the speech content as input and the comparison result between the phrases stored in the storage unit 15 and the speech content as output. The features of the learning model may also be specific words or phrases, such as "record" or "agree."

[0039] A consent phrase can also include, for example, a phrase indicating consent to recording of customers, such as "I consent to recording of customers." A consent phrase can also include a question from the staff related to consent and the customer's answer to that question, such as "Do you consent to recording of customers?" or "Yes." Consent phrases are not limited to the examples above and can include any phrase.

[0040] The control unit 10 can also cause the display unit 13 to display the question in order to prompt the staff to speak on the question. Therefore, even if the staff forgets to ask the question or forgets the content of the question, the staff can reliably ask questions related to consent and reliably obtain consent.

[0041] The control unit 10 may also obtain consent by acquiring the customer's signature input into the input unit 12 (e.g., a touchscreen). Alternatively, the control unit 10 may obtain consent by displaying a consent request screen on the display unit 13 of the information processing device 1 and accepting the customer's consent selection via the input unit 12 (e.g., selecting a button indicating consent).

[0042] S102: After obtaining the customer's consent to the recording, the control unit 10 begins recording via the recording unit 11.

[0043] S103: Control unit 10 determines whether the specified conditions are met. If the specified conditions are met (S103: Yes), the process proceeds to S104. If the specified conditions are not met (S103: No), the process ends.

[0044] In this embodiment, the specified condition includes a first condition that the staff member appears in the image of the imaging unit 11. The image can be captured, for example, by the front-facing camera of the imaging unit 11. The control unit 10 can also use any object detection technology such as YOLO (You Only Look Once) and CNN (Convolutional Neural Network) to determine the first condition. Alternatively, the first condition can also be that the customer appears in the image of the imaging unit 11. The image can also be captured, for example, by the rear-facing camera of the imaging unit 11.

[0045] The specified conditions may also include a second condition: the input unit 12 is able to acquire sound from the background and detect a starting phrase that implies the start of a response to the customer from the speech input to the input unit 12. Processing can proceed to S104 if both the first and second conditions are met.

[0046] During the acquisition of sound through the background, the control unit 10 does not record audio. The starting phrase can be pre-stored in the storage unit 15. The control unit 10 can also detect the starting phrase by comparing the phrase stored in the storage unit 15 with the speech content. In the comparison, natural language processing techniques such as morpheme analysis, syntactic analysis, semantic analysis, context analysis, and reference analysis, as well as a learning model pre-trained using machine learning, can be utilized. The learning model can, for example, be trained by taking the speech content as input and the comparison result between the phrase stored in the storage unit 15 and the speech content as output. The features of the learning model can also be specific words or phrases, such as the name of a staff member used in greetings or self-introductions like "Please take care of me."

[0047] The opening phrase can also include phrases that staff are likely to say at the beginning of a customer interaction, such as a greeting like "Nice to meet you" or a self-introduction like "Let me, [your name], take care of you." By setting such phrases as the opening phrase, recording can be reliably performed even if the staff forgets to record. The opening phrase can also include any phrase that a customer might say. The opening phrase is not limited to the examples above and can include any phrase.

[0048] The control unit 10 can also cause the display unit 13 to display the start phrase in order to prompt the staff to say the start phrase. Thus, even if the staff forgets to say the start phrase or forgets the content of the start phrase, the staff can reliably say the start phrase and reliably perform the interruption operation.

[0049] S104: Control unit 10 begins recording. Afterwards, processing ends.

[0050] Specifically, the control unit 10 records the voices of staff and customers input to the microphone of the input unit 12.

[0051] While this disclosure has been described with reference to the accompanying drawings and embodiments, it should be noted that those skilled in the art can make various modifications and alterations based on this disclosure. Therefore, it should be understood that these modifications and alterations are all included within the scope of this disclosure. For example, the functions included in each component or step can be reconfigured in a logically consistent manner, multiple components or steps can be combined into one, or individual components or steps can be separated.

[0052] For example, in the above-described embodiments, the configuration and operation of the information processing device 1 may be distributed among multiple computers capable of communicating with each other. For example, the configuration and operation of the information processing device 1 may be distributed among a server device and one or more terminal devices.

Claims

1. A method performed by an information processing device comprising a control unit, a camera unit, and an input unit. The control unit performs actions including the following: The input unit obtains the customer's consent to the recording of the response to the customer; After obtaining the aforementioned consent, filming begins through the aforementioned camera unit; and If the specified conditions are met, recording will begin. The specified conditions include a first condition that the staff are reflected in the image of the camera.

2. The method according to claim 1, wherein, The specified conditions include a second condition, which is that the control unit is able to acquire sound from the input unit through the background and detect an initiation phrase that suggests the start of a response to the customer from the speech input to the input unit.

3. The method according to claim 2, wherein, The opening phrase includes a greeting to the customer or a phrase indicating self-introduction.

4. The method according to claim 2, wherein, The information processing device also includes a display unit. The action also includes: causing the display to show the start phrase.

5. The method according to claim 1, wherein, The conditions for obtaining the consent include detecting a consent phrase implying consent from the speech input to the input unit.

Images