JP-7856370-B2 - A method, computer program, and computer system for communicating between multiple computing devices based on voice commands (execution of voice commands).

JP7856370B2JP 7856370 B2JP7856370 B2JP 7856370B2JP-7856370-B2

Inventors

シャイレンドラ・モヤル
サルバジト・ケイ・ラクシト

Assignees

インターナショナル・ビジネス・マシーンズ・コーポレーション

Dates

Publication Date: 20260511
Application Date: 20210921
Priority Date: 20200930

Claims (12)

A method for communicating between multiple computing devices based on voice commands using computer information processing, Analyzing received voice commands by identifying multiple contextual factors associated with at least one user among multiple users using a natural language processing algorithm, wherein the at least one user is associated with a computing device. Dynamically identify at least one user among the multiple users based on an analysis of the identified contextual factors associated with the received voice command, The received voice command is transmitted to another computing device within a plurality of computing devices associated with another user among the plurality of users, Receiving security factor inputs related to multiple security factors from each of the aforementioned multiple users, By analyzing the received voice commands, the type of communication associated with the received voice commands occurring between the multiple computing devices is identified. Based on the identified type of communication, the security factor inputs received from the multiple users are totaled, In response to the sum of the security factor inputs received meeting or exceeding a predetermined threshold of risk associated with authenticating the identity of each user among the multiple users, a notification is generated requesting authentication from the user associated with the computing device receiving the voice command. A method comprising authenticating the generated notification, or generating communication lines between the plurality of computing devices based on the sum of the received security factor inputs being less than a predetermined threshold .
Dynamically identifying at least one user among the aforementioned multiple users is: Based on the analysis of the received voice command, multiple instruction markers are identified, The method according to claim 1, comprising using natural language programming algorithms and artificial intelligence algorithms to match each of the plurality of instruction markers based on identified contextual factors associated with a voice command received by the user against a database storing instruction markers associated with an additional user identity.
Assigning weighted values to each of the security factors among the multiple security factors based on the received security factor input for each of the multiple security factors, The method according to claim 1, further comprising ranking each of the security factors among the plurality of security factors based on the assigned weighting values, thereby prioritizing each security factor among the plurality of security factors associated with each user associated with each computing device among the plurality of computing devices.
Prioritizing each security factor within the aforementioned multiple security factors is The security factor with the highest weighting value is given the highest priority, The method according to claim 3, further comprising placing the security factor having the lowest weighting value in a lower priority order.
The method according to any one of claims 1 to 4, further comprising generating a notification requesting authentication to a computing device for voice commands that satisfy or exceed predetermined thresholds of the security factors associated with the type of communication associated with the received voice command and the security factors associated with the plurality of security factors.
A computer program comprising program instructions for causing a computer to perform the method described in any one of claims 1 to 5.
A computer-readable storage medium storing program instructions for causing a computer to execute the method described in any one of claims 1 to 5.
A computer system for communicating between multiple computing devices based on voice commands, One or more computer processors, One or more computer-readable storage media, The program includes program instructions stored on one or more computer-readable storage media, which are executed by at least one of the one or more computer processors, and the program instructions are A program instruction for analyzing an received voice command by identifying multiple contextual factors associated with at least one user among multiple users using a natural language processing algorithm, wherein the at least one user is associated with a computing device. A program instruction for dynamically identifying at least one user among the multiple users based on an analysis of the identified contextual factors associated with the received voice command, A program instruction for transmitting the received voice command to another computing device within a plurality of computing devices associated with another user among the plurality of users, A program instruction for receiving security factor inputs related to multiple security factors from each of the aforementioned multiple users, A program instruction for identifying the type of communication associated with the received voice command, occurring between multiple computing devices, by analyzing the received voice command, A program instruction for summing the security factor inputs received from the multiple users based on the identified type of communication, Program instructions for generating a notification requesting authentication from a user associated with a computing device receiving the voice command, in response to the sum of the received security factor inputs meeting or exceeding a predetermined threshold of risk associated with authenticating the identity of each user among the plurality of users, A computer system comprising program instructions for generating communication lines between a plurality of computing devices based on authentication being performed on the generated notification, or the sum of the received security factor inputs being less than a predetermined threshold .
The program instruction for dynamically identifying at least one user among the multiple users is: Based on the analysis of the received voice command, a program instruction for identifying multiple instruction markers is provided, The computer system according to claim 8, comprising a program instruction for matching each of the plurality of instruction markers based on identified contextual factors associated with a voice command received by a user against a database storing instruction markers associated with an additional user identity, using a natural language programming algorithm and an artificial intelligence algorithm.
The program instructions stored on the one or more computer-readable storage media are: A program instruction for assigning weighted values to each of the security factors among the multiple security factors based on the received security factor input for each of the multiple users, The computer system according to claim 8, further comprising: a program instruction for prioritizing each security factor in the plurality of security factors associated with each user associated with each computing device in the plurality of computing devices by ranking each security factor in the plurality of security factors based on the assigned weighting values.
The program instructions for prioritizing each security factor among the plurality of security factors are: A program instruction to place the security factor with the highest weighting value in the highest priority order, The computer system according to claim 10, further comprising a program instruction for placing security factors having the lowest weighting value in a lower priority order.
The program instructions stored on the one or more computer-readable storage media are: The computer system according to any one of claims 8 to 11, further comprising program instructions for generating a notification requesting authentication to a computing device for a voice command that satisfies or exceeds a predetermined threshold of the risk associated with the security factor of the plurality of security factors associated with the type of communication associated with the received voice command.

Description

This invention generally relates to the field of voice command system technology, and more specifically to artificial intelligence voice assistance system technology. A microphone is a device that converts sound into electrical signals. Microphones are used in many applications, including telephones, hearing aids, broadcasting equipment for concert halls and public events, film production, live and recorded acoustic engineering, recording, two-way radio, megaphones, and radio and television broadcasting. They are also used for non-acoustic purposes such as recording voice in computers, speech recognition, and ultrasonic or knock sensors. Several types of microphones are used today, employing different methods to convert variations in air pressure of sound waves into electrical signals. The most common are dynamic microphones, which use wire coils suspended in a magnetic field; condenser microphones, which use a vibrating diaphragm as a condenser plate; and contact microphones, which use crystals of piezoelectric material. Microphones typically need to be connected to a preamplifier before the signal can be recorded or reproduced. A loudspeaker is an electroacoustic transducer, a device that converts electrical audio signals into corresponding sound. The most widely used type of speaker is the dynamic speaker. The sound source (e.g., recording or microphone) needs to be amplified or enhanced by an audio power amplifier before the signal is sent to the speaker. A dynamic speaker operates on the same basic principle as a dynamic microphone, but in reverse, it generates sound from an electrical signal. When an alternating electrical audio signal is applied to an audio coil, which is a coil of wire suspended in a circular gap between the poles of a permanent magnet, the coil is forced to move rapidly back and forth by Faraday's law of induction, causing a diaphragm (usually conical) attached to the coil to move back and forth, pushing air and generating sound waves. In addition to this most common method, there are several alternative techniques that can be used to convert electrical signals into sound. Speakers are typically housed in a speaker enclosure, and the material and design of this enclosure play a crucial role in sound quality. The enclosure should generally be as rigid and non-resonant as possible. Small loudspeakers are found in devices such as radios, televisions, portable audio players, computers, and electronic musical instruments. Larger loudspeaker systems are used in music, theater, and concert hall sound reinforcement and broadcasting equipment. This is a functional block diagram showing an environment comprising a computing device connected to or communicating with another computing device, according to at least one embodiment of the present invention.This is a flowchart showing the operational steps for dynamically authenticating voice commands from multiple users according to at least one embodiment of the present invention.This is a flowchart showing the operational steps for establishing communication between multiple artificial intelligence devices according to at least one embodiment of the present invention.A block diagram of the components of a computing system in the computing display environment of Figure 1, according to one embodiment of the present invention, is shown. Embodiments of the present invention recognize the need to improve current speech recognition technology systems, which are initiated by a wake-up command and authenticated by a single user associated with a speech recognition device. Currently, speech recognition technology systems require a user known to the device to submit a voice command following an initiation command, where the voice command can be the execution of a task or a retrieval request. Generally, a speech recognition technology system does not communicate with other speech recognition technology systems associated with unknown users. Furthermore, current speech recognition technology systems authenticate the identity of a single user based on voice identification at a given time. Embodiments of the present invention improve these speech recognition technology systems by enabling users to transmit voice commands without requiring a wake-up command, dynamically authenticating the identities of multiple users based on the voice identifications of known and unknown users by storing the voice identifications of known users and querying the voices of unknown users in a database of possible user voices, transmitting information between multiple speech recognition devices associated with multiple users without requiring multiple authentication steps, and enabling multiple artificial intelligence devices to communicate with each other without requiring user input. Embodiments of the present invention bring an improvement to a voice recognition technology system by enabling multiple artificial intelligence devices to communicate with each other without requi