Information processing method

Abstract

Support should be selected as the content of the accumulation of expertise and the transmission itself. An information processing method is provided, which is executed by an information processing device, the information processing method including: acquiring a sound signal including utterances of a plurality of conversationalists of a specific user; and extracting expertise information from text information acquired by recognizing the sound signal, in accordance with a question of the specific user related to a specific object item.

Description

Technical Field

[0001] This disclosure relates to information processing methods. Background Technology

[0002] Previously, technologies related to learning systems for the knowledge and specialized skills of senior experts were known. Patent Document 1 disclosed a method for creating second-level script data based on first-level script data and outputting handouts that included sound of the text data of the second-level script data being aloud and an image of a virtual lecturer.

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent No. 7473270 Summary of the Invention

[0006] However, in previous machine learning-based architectures, there has been no research into supporting the accumulation of knowledge (specialized skills) of senior experts and the selection of content to be passed down.

[0007] The purpose of this disclosure is to support the selection of content that should be used for the accumulation and transmission of specialized skills.

[0008] According to this disclosure, an information processing method is provided, executed by an information processing device, the information processing method comprising:

[0009] Acquire audio signals of speech from multiple conversationalists, including a specific user; and

[0010] Based on the language of a specific user’s question related to a specific object project, specialized skill information is extracted from the text information obtained by recognizing the voice signal.

[0011] According to one embodiment of this disclosure, it is possible to support the selection of content that should be accumulated as specialized skills and passed down. Attached Figure Description

[0012] Figure 1 This is a block diagram illustrating a structural example of an information processing apparatus according to one embodiment.

[0013] Figure 2 This is a flowchart illustrating an example of the operation of an information processing apparatus according to one embodiment. Detailed Implementation

[0014] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings.

[0015] Figure 1 This is a diagram illustrating the structure of the information processing system 1 according to an embodiment of this disclosure. (Refer to...) Figure 1This section describes the structure and overview of the information processing system 1 involved in the embodiments of this disclosure.

[0016] The information processing system 1 includes an information processing device 10 and a terminal device 20. The information processing device 10 and the terminal device 20 are communicatively connected via a network 30.

[0017] The information processing device 10 is, for example, a server device. The information processing device 10 identifies information that should be accumulated as specialized skills from the audio signals of conversations such as those in a multi-participant conference and registers it into a database.

[0018] Terminal device 20 is any device used by the user. Terminal device 20 can be, for example, a general-purpose electronic device such as a smartphone, tablet, wearable device, or PC (Personal Computer), or a dedicated electronic device. In this embodiment, an example is described where multiple speakers use the same terminal device 20 for dialogue; however, different terminal devices 20 can be used for each speaker, or a mixture of multiple speakers' terminal devices 20 and one speaker's terminal device 20 can exist. Even when multiple speakers use the same terminal device 20, the user can use a different microphone (input unit 24) for each speaker to speak, or state their name for each speech, thereby distinguishing the speaker.

[0019] Network 30 is any communication network capable of communication between devices, such as the Internet and mobile communication networks.

[0020] First, an overview of this embodiment will be given, with details to follow. The information processing device 10 extracts specialized skills from conversations among multiple participants. Specialized skills refer to specific or specialized knowledge, techniques, methods, or information. For example, applications of specialized skills include tasks such as screw fixing or assembly, operation of applications or software, or processes for promoting business.

[0021] Information processing device 10 acquires audio signals of speech from multiple conversationalists, including a specific user. The specific user may be, for example, a senior expert with various knowledge and information. Information processing device 10 identifies the audio signals and acquires text information. Information processing device 10 may also display the text information acquired by identifying the user's audio signals on a display unit. Information processing device 10 extracts specialized skill information from the text information based on the specific user's questions related to a specific object item. Information processing device 10 may also register the extracted specialized skill information in a database.

[0022] like Figure 1As shown, the information processing device 10 includes a control unit 11, a storage unit 12, and a communication unit 13. The control unit 11 includes at least one processor. The processor is a general-purpose processor such as a CPU (Central Processing Unit) or a dedicated processor for specific processing. The control unit 11 controls each part of the information processing device 10 while performing processing related to the operation of the information processing device 10. The storage unit 12 includes at least one semiconductor memory, magnetic memory, or optical memory. The storage unit 12 functions as, for example, a main storage device or an auxiliary storage device. The storage unit 12 stores data used in the operation of the information processing device 10 and data obtained through the operation of the information processing device 10. The communication unit 13 includes at least one external communication interface. The communication interface can be either a wired communication interface or a wireless communication interface. In the case of wired communication, the communication interface is, for example, a LAN (Local Area Network). In the case of wireless communication, the communication interface is, for example, an interface corresponding to mobile communication standards such as 5G, or an interface corresponding to short-range wireless communication. The communication unit 13 receives data used in the operation of the information processing device 10 and transmits data obtained through the operation of the information processing device 10.

[0023] The functions of the information processing device 10 are implemented by a processor, equivalent to the control unit 11, executing the program described in this embodiment. That is, the functions of the information processing device 10 are implemented through software. The program causes the computer to perform the actions of the information processing device 10, thereby enabling the computer to function as the information processing device 10. In other words, the computer functions as the information processing device 10 by executing the actions of the information processing device 10 according to the program. In this embodiment, the program can be pre-recorded on a computer-readable recording medium. Computer-readable recording media include non-transitory computer-readable media, such as magnetic recording devices, semiconductor memories, etc. The program can be distributed, for example, through the sale, transfer, or rental of portable recording media such as DVDs containing the program. Alternatively, the program can be distributed by storing the program on the storage device of an external server or by sending the program from the external server to other computers. Furthermore, the program can also be provided as a program product. Some or all of the functions of the information processing device 10 can also be implemented through dedicated circuitry equivalent to the control unit 11. That is, some or all of the functions of the information processing device 10 can also be implemented in hardware.

[0024] like Figure 1As shown, the terminal device 20 includes a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, and an output unit 25. The functions and structures of the control unit 21, storage unit 22, and communication unit 23 of the terminal device 20 are the same as those of the control unit 11, storage unit 12, and communication unit 13 of the information processing device 10, so detailed descriptions are omitted. The input unit 24 includes at least one input interface. The input interface can be, for example, a physical key, a touch screen, a sound sensor (microphone) for accepting sound input, or a camera for accepting gesture input. The input unit 24 accepts the input of data used in the operation of the terminal device 20. The output unit 25 includes at least one output interface. The output interface can be, for example, a display unit (monitor) that outputs information as an image, or a speaker that outputs information as sound. The output unit 25 outputs the data obtained through the operation of the terminal device 20. Some or all of the functions of the terminal device 20, like those of the information processing device 10, can be implemented either by software or by hardware.

[0025] (The actions of information processing system 1)

[0026] Reference Figure 2 The flowchart shown illustrates the actions of information processing system 1. (Refer to...) Figure 2 The operation of the information processing system 1 described herein can also be equivalent to an information processing method executed by the information processing device 10. Figure 2 The actions of each step can also be executed according to the control of the control unit 11 of the information processing device 10.

[0027] S1: The control unit 11 acquires the audio signals of the speech of multiple conversationalists, including a specific user. Specifically, the control unit 11 receives the audio signals of the speech of multiple conversationalists from the terminal device 20.

[0028] S2: The control unit 11 identifies the sound signal and obtains the text information. The control unit 11 may also use existing sound recognition technology to identify the sound signal. The control unit 11 may also distinguish the speaker and obtain the text information representing the speech content along with the information distinguishing each speaker. When multiple speakers use the same terminal device 20, the control unit 11 may, for example, distinguish the speaker based on phonemes and characteristic quantities of the sound signal such as MFCC (Mel-Frequency Cepstral Coefficient). When multiple speakers use different terminal devices 20, the control unit 11 may also distinguish the speaker by the terminal device 20 that sends the sound signal. The control unit 11 may also obtain the sound signal for each speaker and be able to determine the speaker. The control unit 11 may also display the text information obtained by identifying the user's speech sound signal on the display unit (output unit 25) in a way that distinguishes the speaker.

[0029] S3: The control unit 11 extracts specialized skill information from the text information obtained by recognizing sound signals based on the language of a specific user's question related to a specific object project.

[0030] The control unit 11 can also extract questions related to the target project and answers related to those questions from textual information based on the content of the speech, as specialized skill information. The control unit 11 can also determine the relevance to the target project based on keywords in the speech. For example, the control unit 11 can also obtain responses to questions related to the target project (e.g., regarding material changes, heat countermeasures are a point of concern) as specialized skill information. The control unit 11 can also obtain statements made during design review meetings regarding questions about the design content as specialized skills. For example, if the control unit 11 asks a question such as "Will heat accumulate?" regarding a design that changes the material from metal to resin, it can also obtain the response to that question as specialized skills.

[0031] Control unit 11 can also prioritize acquiring specialized skills information from question-and-response interactions where a specific user participates as a questioner or responder. When different terminal devices 20 are used for each speaker, control unit 11 can also identify a specific user based on information used to identify the terminal device 20. Control unit 11 can also determine which specific user should accumulate specialized skills by weighting the conversation based on attributes such as the speaker's length of service and job title. Alternatively, control unit 11 can determine which specific user should accumulate specialized skills by considering the context of the conversation.

[0032] The control unit 11 can also acquire audio signals of conversations in meetings that reference materials (such as design review materials). The control unit 11 can also determine the correspondence between the spoken content and the target items by measuring the content of the materials displayed on the screen during the meeting, the mouse pointer displayed in the materials, and the matching of the recorded content of the materials with the speech, thereby acquiring the conversation as a specialized skill extraction.

[0033] The control unit 11 can also store the extracted specialized skill information in the database. The control unit 11 can also compare the extracted specialized skill information with previously stored specialized skill information in the database, and if the same specialized skill information does not exist, store the extracted specialized skill information as new specialized skill information in the database. That is, the control unit 11 can also register only new specialized skill information in the database.

[0034] As described above, in the information processing apparatus 10 according to this embodiment, the control unit 11 acquires the audio of a meeting involving multiple users, including senior experts, and extracts specialized skills from the conversation content based on the language of questions asked by senior experts related to a specific project. That is, the control unit 11 acquires audio signals of the language of multiple participants, including a specific user, and extracts specialized skill information from text information obtained by recognizing the audio signals based on the language of questions asked by a specific user related to a specific project. In this way, the control unit 11 extracts specialized skill information from text information obtained by audio recognition of the meeting audio based on the language of questions asked by a specific user related to a specific project. Therefore, according to the information processing apparatus 10, it is possible to support the selection of content that should be used for the accumulation and transmission of specialized skills.

[0035] This disclosure is not limited to the embodiments described above. For example, multiple blocks described in the block diagram may be merged, or a single block may be divided. Alternatively, instead of executing multiple steps described in the flowchart in the described sequence, the steps may be executed in parallel or in different orders, depending on the processing capability of the device executing each step or as needed. Furthermore, modifications can be made without departing from the spirit of this disclosure.

[0036] For example, some of the processing operations performed in the information processing device 10 in the above embodiments can also be performed in the terminal device 20. Additionally, some of the processing operations performed in the terminal device 20 in the above embodiments can also be performed in the information processing device 10.

[0037] (Symbol Explanation)

[0038] 1: Information processing system; 10: Information processing device; 11: Communication unit; 12: Storage unit; 13: Input unit; 14: Output unit; 15: Control unit; 20: Terminal device; 30: Network.

Claims

1. An information processing method executed by an information processing apparatus, the information processing method comprising: acquiring a sound signal including utterances of a plurality of conversationalists of a specific user; and extracting, from text information acquired by recognizing the sound signal, expert skill information according to an utterance of a question of the specific user related to a specific target item.

2. The information processing method according to claim 1, wherein conversational content in a meeting in which reference to a material is made is acquired as the sound signal.

3. The information processing method according to claim 1, wherein from the content of the utterance, a question related to the target item and an answer related to the question are extracted from the text information as the expert skill information.

4. The information processing method according to claim 1, wherein the extracted expert skill information is compared with expert skill information accumulated in a database in the past, and in the absence of the same expert skill information, the extracted expert skill information is accumulated in the database as new expert skill information.

5. The information processing method according to any one of claims 1 to 4, wherein the sound signal is acquired for each conversationalist.

Images