Artificial intelligence conversational device, system and method

Abstract

An AI conversational system including a three-dimensional figure representing a character, having an interior pocket accessible through a closure that is selectively opened or closed; and a voice box removably disposed within the interior pocket, wherein the voice box has a housing enclosing a microcontroller unit operationally connected to a wireless antenna, a speaker, a microphone, and a battery; wherein the microcontroller unit is configured to wirelessly access an internet-based artificial intelligence GPT engine and produce interactive and responsive conversation representative of the character represented by the three-dimensional figure. The voice box further includes a near-field sensor enclosed in the housing and operationally connected to the microcontroller unit. The three-dimensional figure further includes a near-field tag disposed in the interior pocket proximate to near-field sensor when the voice box is disposed in the interior pocket, which tag identifies a particular character.

Description

RELATED APPLICATIONS

[0001] This patent application relates to and claims priority from U.S. Provisional Patent Application No. 63 / 517,292 entitled “AI CONVERSATIONAL TOYS” filed Aug. 2, 2023 and is incorporated herein by reference including its specification.FIELD OF THE INVENTION

[0002] The present invention relates generally to devices, systems, and methods for creating, building, and operating conversational toys using artificial intelligence. Specific embodiments relate to particular characters, voices, modes of operation, and interaction with decorative toys or plushies, and other devices.BACKGROUND OF THE INVENTION

[0003] For a very long time, toy manufacturers have sought to create toys and other devices that talk or otherwise allow interactive speech. Most such interactive toys are manufactured and pre-programmed with a limited number of vocabulary words and / or phrases such that the toy is only repeating those fixed phrases, to which the user can respond. True conversation is not possible with such interactive toys. Certain improvements have allowed for removable and replaceable tapes, CDs, and other cartridges by which a user can change the phrases and vocabulary that the interactive toy can produce.

[0004] The ability to change a cartridge allows a user to introduce a new voice, a new set of phrases, and / or a new story with each replacement cartridge. But still, the range of phrases and vocabulary in any particular cartridge is fixed. In addition, the output of any particular cartridge is not interactive. The output of a cartridge either follows the same sequence or random sequence of the same words and phrases, either repeated or not. A user can respond to the output of a cartridge in a device, but such response will not change the output, which is either sequential or random.

[0005] Accordingly, there is a need for an improved system and method used in a conversational toy that creates a truly interactive and responsive conversation. Such need includes a introducing a more diverse range and increased number of vocabulary and phrases, as well as, the ability for the device to respond to the user interaction. The present invention fulfills these needs and provides other related advantages.SUMMARY OF THE INVENTION

[0006] The present invention is directed to an AI conversational system. The system comprises a three-dimensional figure representing a character that has an interior pocket accessible through a closure that is selectively opened or closed. A voice box is removably disposed within the interior pocket, wherein the voice box has a housing enclosing a microcontroller unit operationally connected to a wireless antenna, a speaker, a microphone, and a rechargeable battery. The microcontroller unit is configured to wirelessly access an internet-based artificial intelligence GPT engine so as to produce interactive and responsive conversation representative of the character represented by the three-dimensional figure.

[0007] In the AI conversational system, the three-dimensional figure is selected from the group consisting of a plush toy, a stuffed toy, an action figure, an instrument, and a conversational model. The wireless antenna of the voice box is preferably configured for wireless connectivity through a WLAN protocol or a WPAN protocol. Preferably, the WLAN protocol corresponds to a Wi-Fi connection and the WPAN protocol corresponds to a Bluetooth connection.

[0008] The voice box may further comprise a near-field sensor enclosed in the housing and operationally connected to the microcontroller unit. In addition, a near-field tag may be disposed in the interior pocket of the three-dimensional figure proximate to near-field sensor when the voice box is disposed in the interior pocket. The near-field tag is programmed to identify a particular character and the near-field sensor is programmed to communicate the particular character identified by the near-field tag to the microcontroller unit. The microcontroller unit is then programmed to communicate the particular character identified by the near-field tag to the artificial intelligence GPT engine so as to produce interactive and responsive conversation representative of the particular character identified by the near-field tag.

[0009] The microcontroller unit is preferably wirelessly connected to a persistent long-term memory database whereby a history of past interactive and responsive conversations is stored. The microcontroller unit is preferably wirelessly connected to a persistent contact and entity database whereby a list of contacts and entities associated with the character represented by the three-dimensional figure is stored.

[0010] Other features and advantages of the present invention will become apparent from the following more detailed description, taken in conjunction with the accompanying drawings, which illustrate, by way of example, the principles of the invention.BRIEF DESCRIPTION OF THE FIGURES

[0011] These and other features and advantages of the present invention will become appreciated, as the same becomes better understood with reference to the specification, claims and drawings herein:

[0012] FIG. 1 is a front perspective view of an embodiment of a toy figure according to the present invention.

[0013] FIG. 2 is a back perspective view of the embodiment of the toy figure of FIG. 1.

[0014] FIG. 3 is a cross-sectional view of the embodiment of the toy figure of FIG. 1.

[0015] FIG. 4 is a perspective view of a conversation engine device of the present invention.

[0016] FIG. 5 is a cross-sectional view of an embodiment of the conversation engine device of the present invention.

[0017] FIG. 6 is a cross-sectional view of an alternate embodiment of the conversation engine device of the present invention.

[0018] FIG. 6B is a cross-sectional view of an embodiment of the toy figure including the alternate embodiment of the conversation engine device of FIG. 6.

[0019] FIG. 7 flowchart illustrating a method by which the conversation engine operates the create interactive conversation pursuant to the present invention.DETAILED DESCRIPTION

[0020] The invention now will be described more fully hereinafter with reference to the accompanying drawings, in which embodiments of the invention are shown. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0021] It will be understood that when an element is referred to as being “on” another element, it can be directly on the other element or intervening elements may be present there between. As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed items.

[0022] It will be understood that, although the terms first, second, third etc. may be used herein to describe various elements, components, regions, layers and / or sections, these elements, components, regions, layers and / or sections should not be limited by these terms. These terms are only used to distinguish one element, component, region, layer or section from another element, component, region, layer or section.

[0023] As used herein, the singular forms “a,”“an,” and “the,” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” and / or “comprising,”“includes” and / or “including,” and “have” and / or “having,” when used in this specification, specify the presence of stated features, regions, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, regions, integers, steps, operations, elements, components, and / or groups thereof.

[0024] Furthermore, relative terms, such as “lower” or “bottom,” and “upper” or “top,” and “inner” or “outer,” may be used herein to describe one element's relationship to another elements as illustrated in the Figures. It will be understood that relative terms are intended to encompass different orientations of the device in addition to the orientation depicted in the Figures.

[0025] Unless otherwise defined, all terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0026] Exemplary embodiments of the present invention are described herein with reference to idealized embodiments of the present invention. As such, variations from the shapes and configurations of the illustrations as a result, for example, of manufacturing techniques and / or tolerances, are to be expected. Thus, embodiments of the present invention should not be construed as limited to the particular shapes of regions illustrated herein but are to include deviations in shapes that result, for example, from manufacturing.

[0027] The present invention encompasses a line of innovative AI-conversational toys designed to interact and converse with users. These toys are designed primarily for children but can be used by anyone interested in a conversational companion. The AI-conversational toys bring together a unique blend of plush or solid toy bodies and an AI-based system with the capability to connect to wireless networks, such as wireless personal area networks (WPAN), i.e, Bluetooth, and wireless local area networks (WLAN), i.e., Wi-Fi, for enhanced interactivity. Specifically, a user can talk to the toy and the toy can talk back without having any pre-programmed responses.

[0028] The toys are designed with appealing aesthetic characteristics and feature child-friendly materials that encompass the physical structure. They have an ideal size for children to comfortably carry and interact with.

[0029] The physical structure of the toys conceals a technologically advanced hardware system within. This system is carefully encased within the toys via an invisible zipper closure or otherwise. This invisible zipper closure not only allows for easy maintenance and potential hardware upgrades but also ensures that the technology does not interfere with the toy's aesthetic or tactile appeal.

[0030] The present invention is directed to a novel artificial intelligence enabled voice box device. Embodiments of the voice box device, generally referred to by reference numeral 10, may be utilized on their own. In a system 12, the voice box 10 may be combined with a stuffed or plush toy 14. The system 12, with voice box 10 and toy 14 are generally shown in FIG. 1. In this system 12, the voice box 10 is preferably disposed within an interior pocket 16 of the plush or stuffed toy 14. FIGS. 2 and 3 generally show the voice box 10 in the interior pocket 16 of the toy 14. The toy 14 preferably is presented in the form of a particular character. The specifics of the character are not important and may vary depending on the features of the character to be portrayed.

[0031] As shown in FIGS. 4 and 5, the voice box 10 is preferably a housing 10a configured for placement in the interior pocket 16. The housing 10a preferably encloses at least a microcontroller unit 18, a wireless antenna 20, a speaker 22, a microphone 22a, and a battery 24. The exterior of the housing 10a preferably includes one or more control buttons 26 and a connection port 28. The battery 24 is connected to at least the microcontroller unit 18 and the speaker 22 so as to provide the necessary power for operation. The control buttons 26 preferably include at least a power (on / off) button, a mode button, and / or volume buttons.

[0032] The connection port 28 may be connected to the microcontroller unit 18 so as to provide communicative control so as enable downloading or uploading software and / or data, as for updates or upgrades. The connection port 28 may also be connected to the battery 24, either directly or through the microcontroller unit 18 so as to allow for recharging the battery 24. In this way, the voice box 10 is enabled for operation without requiring persistent connection to an external power source.

[0033] At the core of the voice box 10 the microcontroller unit 18 hardware is preferably a low-cost, low-power system on a single chip such as an ESP32 microcontroller unit (or another comparable microcontroller or system on a chip). The microcontroller unit 18 in the form of an ESP32 microcontroller unit may include an integrated wireless dual-mode antenna for WLAN (Wi-Fi) and WPAN (Bluetooth) connectivity. Alternatively, the separate wireless antenna 20 may be configured for similar wireless dual-mode operation. The microcontroller unit 18 is responsible for managing the various hardware components of the voice box 10 and forms the foundation for the AI and networking capabilities. For networking, the voice box 10 preferably uses both WLAN and WPAN capabilities, whether integrated into an ESP32 microcontroller unit or separately disposed. These connectivity options allow the voice box 10 to communicate with the internet for updating AI models, downloading new conversational scripts, or syncing with a user's ancillary device for customized interaction.

[0034] The voice box 10 is further preferably enhanced with a dedicated mobile application, compatible with mobile device operating systems, including but not limited to iOS and Android devices. The user can connect the voice box 10 to such mobile applications through the wireless antenna 20, allowing for advanced setup and control of the AI model. The process begins with the user logging into the mobile application on their mobile device. The user can then add a voice box 10 to their account, creating a unique pairing between the user's account and the voice box 10. The mobile application will then attempt to connect to the voice box 10 through the wireless antenna 20 using WLAN, WPAN, or similar connectivity. During this process, if the user's mobile device is unable to connect, i.e., its Bluetooth or similar wireless connection is turned off, the mobile application will display an error message prompting the user to enable such wireless connectivity to proceed. Once a successful connection is established, the mobile application can relay its credentials to the voice box 10. This process includes identifying each voice box 10 with a unique ID to ensure secure and exclusive connectivity.

[0035] The next part of setup involves connecting the voice box 10 to the internet for enhanced functionality. The user is prompted to setup their WLAN wireless connectivity, i.e. input Wi-Fi credentials, within the mobile application. The credentials for WLAN connectivity to the internet are securely transmitted to the voice box 10 via the established WPAN, i.e., Bluetooth, connection. This process ensures the ability of the voice box 10 to independently connect to the internet, paving the way for its AI-based interactive features.

[0036] The voice box 10 is equipped with a high-quality speaker 22 and microphone 22a which are used for the audio input and output functions. The speaker 22 provides clear and loud audio, enabling the voice box 10 to ‘speak’ to its users. The microphone 22a captures the user's voice inputs for interaction and conversation. These two components work in tandem to facilitate interactive conversations with the users. Powering the voice box 10 is a battery 24 that is securely contained within the housing 10a. The battery 24 provides an efficient power source for all the hardware components within the voice box 10, ensuring hours of interactive use.

[0037] As briefly described above, the inventive system 12 preferably includes a toy 14 having an interior pocket 16 within which the voice box 10 is disposed. The interior pocket 16 includes a closure 16a in the form of a zipper, hook and loop, or similar mechanism configured so as to make the closure 16a substantially invisible when closed. For convenience, when the closure 16a is open, the voice box 10 may be completely removed from the interior pocket 16. Alternatively, the voice box 10 may remain in the interior pocket, with the control buttons 26 and port 28 configured so as to be accessible through the open closure 16a.

[0038] The toy 14 usable with the voice box 10 is not limited to plush or stuffed toys as mentioned above. The toy 14 may correspond to various types of characters, including but not limited to action figures, instruments, and conversational model or other types of companions. Such toys 14 may be designed for a wider demographic including children, adults, older individuals, or any age in between. The characters embodied in such toys 14 may be original creations or derived from licensing IP from third parties to create different versions that fit within various creative universes.

[0039] Additionally, in the context of the system 12, the voice box 10 utilizes a novel methodology to determine how the AI model of the voice box 10 reacts to stimuli and makes decisions. As shown in FIG. 7, a flowchart of the inventive method 30 illustrating this methodology centered around a dialog coordinator 32. This dialog coordinator 32 acts as a “brain” for the AI model interacting with all of its other components. In one aspect, the dialog coordinator 32 interacts with the system 12 and the user 34 through a series of HTTP, TCP, UDP, or WebSocket network requests 36—whether text or audio. The dialog coordinator 32 further as operational connectivity to a series of databases, for example a current state DB 38a, a short-term memory DB 36b, a long-term memory DB 38c, a contact / entity DB 38d, and a reflexive response DB 38e. Such operational connectivity to the databases may be direct from the dialog coordinator 32 or processed through one or more of a sentiment interface 40, an intent classifier 42, a strategy engine 44, and a reflexive response engine 46. In addition, the inventive method flowchart 30 also depicts a text-and-speech input monitor 48, a text-and-speech output monitor 50, and optional text-to-speech 52 or speech-to-text 54 routines.

[0040] The inventive method 30 for the voice box 10 also includes accessibility through the dialog coordinator 32 to a series of games, apps, skill tests, sequence test, and similar functions 56. The voice box 10 is preferably programmed to allow the AI model to present these functions 56 to the user for interactive play. Further, the dialog coordinator 32 has connectivity to a prompt engine 58 with access to a generative pre-trained transformer (GPT) 60 containing a large language model for generating appropriate and responsive conversation.

[0041] In a particular embodiment, shown in FIGS. 6 and 6bB, the voice box 10 may include a near-field sensor 62 contained within the housing 10a. This near-field sensor 62 is electronically connected to the microcontroller unit 18. When paired with a near-field tag 64 disposed in the toy 14 proximate to the interior pocket 16, the near-field sensor 62 is programmed to instruct the microcontroller unit 18 which of multiple AI characters and / or voices should be accessed through the GPT 60 via internet. In this way, a single manufactured voice box 10 can be used for production of multiple toys 14 and / or systems 12, or interchangeably by a user with various toys 14 and / or systems 12.

[0042] Although several embodiments have been described in detail for purposes of illustration, various modifications may be made without departing from the scope and spirit of the invention.

Examples

Embodiment Construction

[0020]The invention now will be described more fully hereinafter with reference to the accompanying drawings, in which embodiments of the invention are shown. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0021]It will be understood that when an element is referred to as being “on” another element, it can be directly on the other element or intervening elements may be present there between. As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed items.

[0022]It will be understood that, although the terms first, second, third etc. may be used herein to describe various elements, components, regions, layers and / or sections, these elements, components, regions, layers and / or...

RELATED APPLICATIONS

[0001] This patent application relates to and claims priority from U.S. Provisional Patent Application No. 63 / 517,292 entitled “AI CONVERSATIONAL TOYS” filed Aug. 2, 2023 and is incorporated herein by reference including its specification.FIELD OF THE INVENTION

[0002] The present invention relates generally to devices, systems, and methods for creating, building, and operating conversational toys using artificial intelligence. Specific embodiments relate to particular characters, voices, modes of operation, and interaction with decorative toys or plushies, and other devices.BACKGROUND OF THE INVENTION

[0003] For a very long time, toy manufacturers have sought to create toys and other devices that talk or otherwise allow interactive speech. Most such interactive toys are manufactured and pre-programmed with a limited number of vocabulary words and / or phrases such that the toy is only repeating those fixed phrases, to which the user can respond. True conversation is not possible with such interactive toys. Certain improvements have allowed for removable and replaceable tapes, CDs, and other cartridges by which a user can change the phrases and vocabulary that the interactive toy can produce.

[0004] The ability to change a cartridge allows a user to introduce a new voice, a new set of phrases, and / or a new story with each replacement cartridge. But still, the range of phrases and vocabulary in any particular cartridge is fixed. In addition, the output of any particular cartridge is not interactive. The output of a cartridge either follows the same sequence or random sequence of the same words and phrases, either repeated or not. A user can respond to the output of a cartridge in a device, but such response will not change the output, which is either sequential or random.

[0005] Accordingly, there is a need for an improved system and method used in a conversational toy that creates a truly interactive and responsive conversation. Such need includes a introducing a more diverse range and increased number of vocabulary and phrases, as well as, the ability for the device to respond to the user interaction. The present invention fulfills these needs and provides other related advantages.SUMMARY OF THE INVENTION

[0006] The present invention is directed to an AI conversational system. The system comprises a three-dimensional figure representing a character that has an interior pocket accessible through a closure that is selectively opened or closed. A voice box is removably disposed within the interior pocket, wherein the voice box has a housing enclosing a microcontroller unit operationally connected to a wireless antenna, a speaker, a microphone, and a rechargeable battery. The microcontroller unit is configured to wirelessly access an internet-based artificial intelligence GPT engine so as to produce interactive and responsive conversation representative of the character represented by the three-dimensional figure.

[0007] In the AI conversational system, the three-dimensional figure is selected from the group consisting of a plush toy, a stuffed toy, an action figure, an instrument, and a conversational model. The wireless antenna of the voice box is preferably configured for wireless connectivity through a WLAN protocol or a WPAN protocol. Preferably, the WLAN protocol corresponds to a Wi-Fi connection and the WPAN protocol corresponds to a Bluetooth connection.

[0008] The voice box may further comprise a near-field sensor enclosed in the housing and operationally connected to the microcontroller unit. In addition, a near-field tag may be disposed in the interior pocket of the three-dimensional figure proximate to near-field sensor when the voice box is disposed in the interior pocket. The near-field tag is programmed to identify a particular character and the near-field sensor is programmed to communicate the particular character identified by the near-field tag to the microcontroller unit. The microcontroller unit is then programmed to communicate the particular character identified by the near-field tag to the artificial intelligence GPT engine so as to produce interactive and responsive conversation representative of the particular character identified by the near-field tag.

[0009] The microcontroller unit is preferably wirelessly connected to a persistent long-term memory database whereby a history of past interactive and responsive conversations is stored. The microcontroller unit is preferably wirelessly connected to a persistent contact and entity database whereby a list of contacts and entities associated with the character represented by the three-dimensional figure is stored.

[0010] Other features and advantages of the present invention will become apparent from the following more detailed description, taken in conjunction with the accompanying drawings, which illustrate, by way of example, the principles of the invention.BRIEF DESCRIPTION OF THE FIGURES

[0011] These and other features and advantages of the present invention will become appreciated, as the same becomes better understood with reference to the specification, claims and drawings herein:

[0012] FIG. 1 is a front perspective view of an embodiment of a toy figure according to the present invention.

[0013] FIG. 2 is a back perspective view of the embodiment of the toy figure of FIG. 1.

[0014] FIG. 3 is a cross-sectional view of the embodiment of the toy figure of FIG. 1.

[0015] FIG. 4 is a perspective view of a conversation engine device of the present invention.

[0016] FIG. 5 is a cross-sectional view of an embodiment of the conversation engine device of the present invention.

[0017] FIG. 6 is a cross-sectional view of an alternate embodiment of the conversation engine device of the present invention.

[0018] FIG. 6B is a cross-sectional view of an embodiment of the toy figure including the alternate embodiment of the conversation engine device of FIG. 6.

[0019] FIG. 7 flowchart illustrating a method by which the conversation engine operates the create interactive conversation pursuant to the present invention.DETAILED DESCRIPTION

[0020] The invention now will be described more fully hereinafter with reference to the accompanying drawings, in which embodiments of the invention are shown. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0021] It will be understood that when an element is referred to as being “on” another element, it can be directly on the other element or intervening elements may be present there between. As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed items.

[0022] It will be understood that, although the terms first, second, third etc. may be used herein to describe various elements, components, regions, layers and / or sections, these elements, components, regions, layers and / or sections should not be limited by these terms. These terms are only used to distinguish one element, component, region, layer or section from another element, component, region, layer or section.

[0023] As used herein, the singular forms “a,”“an,” and “the,” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” and / or “comprising,”“includes” and / or “including,” and “have” and / or “having,” when used in this specification, specify the presence of stated features, regions, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, regions, integers, steps, operations, elements, components, and / or groups thereof.

[0024] Furthermore, relative terms, such as “lower” or “bottom,” and “upper” or “top,” and “inner” or “outer,” may be used herein to describe one element's relationship to another elements as illustrated in the Figures. It will be understood that relative terms are intended to encompass different orientations of the device in addition to the orientation depicted in the Figures.

[0025] Unless otherwise defined, all terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0026] Exemplary embodiments of the present invention are described herein with reference to idealized embodiments of the present invention. As such, variations from the shapes and configurations of the illustrations as a result, for example, of manufacturing techniques and / or tolerances, are to be expected. Thus, embodiments of the present invention should not be construed as limited to the particular shapes of regions illustrated herein but are to include deviations in shapes that result, for example, from manufacturing.

[0027] The present invention encompasses a line of innovative AI-conversational toys designed to interact and converse with users. These toys are designed primarily for children but can be used by anyone interested in a conversational companion. The AI-conversational toys bring together a unique blend of plush or solid toy bodies and an AI-based system with the capability to connect to wireless networks, such as wireless personal area networks (WPAN), i.e, Bluetooth, and wireless local area networks (WLAN), i.e., Wi-Fi, for enhanced interactivity. Specifically, a user can talk to the toy and the toy can talk back without having any pre-programmed responses.

[0028] The toys are designed with appealing aesthetic characteristics and feature child-friendly materials that encompass the physical structure. They have an ideal size for children to comfortably carry and interact with.

[0029] The physical structure of the toys conceals a technologically advanced hardware system within. This system is carefully encased within the toys via an invisible zipper closure or otherwise. This invisible zipper closure not only allows for easy maintenance and potential hardware upgrades but also ensures that the technology does not interfere with the toy's aesthetic or tactile appeal.

[0030] The present invention is directed to a novel artificial intelligence enabled voice box device. Embodiments of the voice box device, generally referred to by reference numeral 10, may be utilized on their own. In a system 12, the voice box 10 may be combined with a stuffed or plush toy 14. The system 12, with voice box 10 and toy 14 are generally shown in FIG. 1. In this system 12, the voice box 10 is preferably disposed within an interior pocket 16 of the plush or stuffed toy 14. FIGS. 2 and 3 generally show the voice box 10 in the interior pocket 16 of the toy 14. The toy 14 preferably is presented in the form of a particular character. The specifics of the character are not important and may vary depending on the features of the character to be portrayed.

[0031] As shown in FIGS. 4 and 5, the voice box 10 is preferably a housing 10a configured for placement in the interior pocket 16. The housing 10a preferably encloses at least a microcontroller unit 18, a wireless antenna 20, a speaker 22, a microphone 22a, and a battery 24. The exterior of the housing 10a preferably includes one or more control buttons 26 and a connection port 28. The battery 24 is connected to at least the microcontroller unit 18 and the speaker 22 so as to provide the necessary power for operation. The control buttons 26 preferably include at least a power (on / off) button, a mode button, and / or volume buttons.

[0032] The connection port 28 may be connected to the microcontroller unit 18 so as to provide communicative control so as enable downloading or uploading software and / or data, as for updates or upgrades. The connection port 28 may also be connected to the battery 24, either directly or through the microcontroller unit 18 so as to allow for recharging the battery 24. In this way, the voice box 10 is enabled for operation without requiring persistent connection to an external power source.

[0033] At the core of the voice box 10 the microcontroller unit 18 hardware is preferably a low-cost, low-power system on a single chip such as an ESP32 microcontroller unit (or another comparable microcontroller or system on a chip). The microcontroller unit 18 in the form of an ESP32 microcontroller unit may include an integrated wireless dual-mode antenna for WLAN (Wi-Fi) and WPAN (Bluetooth) connectivity. Alternatively, the separate wireless antenna 20 may be configured for similar wireless dual-mode operation. The microcontroller unit 18 is responsible for managing the various hardware components of the voice box 10 and forms the foundation for the AI and networking capabilities. For networking, the voice box 10 preferably uses both WLAN and WPAN capabilities, whether integrated into an ESP32 microcontroller unit or separately disposed. These connectivity options allow the voice box 10 to communicate with the internet for updating AI models, downloading new conversational scripts, or syncing with a user's ancillary device for customized interaction.

[0034] The voice box 10 is further preferably enhanced with a dedicated mobile application, compatible with mobile device operating systems, including but not limited to iOS and Android devices. The user can connect the voice box 10 to such mobile applications through the wireless antenna 20, allowing for advanced setup and control of the AI model. The process begins with the user logging into the mobile application on their mobile device. The user can then add a voice box 10 to their account, creating a unique pairing between the user's account and the voice box 10. The mobile application will then attempt to connect to the voice box 10 through the wireless antenna 20 using WLAN, WPAN, or similar connectivity. During this process, if the user's mobile device is unable to connect, i.e., its Bluetooth or similar wireless connection is turned off, the mobile application will display an error message prompting the user to enable such wireless connectivity to proceed. Once a successful connection is established, the mobile application can relay its credentials to the voice box 10. This process includes identifying each voice box 10 with a unique ID to ensure secure and exclusive connectivity.

[0035] The next part of setup involves connecting the voice box 10 to the internet for enhanced functionality. The user is prompted to setup their WLAN wireless connectivity, i.e. input Wi-Fi credentials, within the mobile application. The credentials for WLAN connectivity to the internet are securely transmitted to the voice box 10 via the established WPAN, i.e., Bluetooth, connection. This process ensures the ability of the voice box 10 to independently connect to the internet, paving the way for its AI-based interactive features.

[0036] The voice box 10 is equipped with a high-quality speaker 22 and microphone 22a which are used for the audio input and output functions. The speaker 22 provides clear and loud audio, enabling the voice box 10 to ‘speak’ to its users. The microphone 22a captures the user's voice inputs for interaction and conversation. These two components work in tandem to facilitate interactive conversations with the users. Powering the voice box 10 is a battery 24 that is securely contained within the housing 10a. The battery 24 provides an efficient power source for all the hardware components within the voice box 10, ensuring hours of interactive use.

[0037] As briefly described above, the inventive system 12 preferably includes a toy 14 having an interior pocket 16 within which the voice box 10 is disposed. The interior pocket 16 includes a closure 16a in the form of a zipper, hook and loop, or similar mechanism configured so as to make the closure 16a substantially invisible when closed. For convenience, when the closure 16a is open, the voice box 10 may be completely removed from the interior pocket 16. Alternatively, the voice box 10 may remain in the interior pocket, with the control buttons 26 and port 28 configured so as to be accessible through the open closure 16a.

[0038] The toy 14 usable with the voice box 10 is not limited to plush or stuffed toys as mentioned above. The toy 14 may correspond to various types of characters, including but not limited to action figures, instruments, and conversational model or other types of companions. Such toys 14 may be designed for a wider demographic including children, adults, older individuals, or any age in between. The characters embodied in such toys 14 may be original creations or derived from licensing IP from third parties to create different versions that fit within various creative universes.

[0039] Additionally, in the context of the system 12, the voice box 10 utilizes a novel methodology to determine how the AI model of the voice box 10 reacts to stimuli and makes decisions. As shown in FIG. 7, a flowchart of the inventive method 30 illustrating this methodology centered around a dialog coordinator 32. This dialog coordinator 32 acts as a “brain” for the AI model interacting with all of its other components. In one aspect, the dialog coordinator 32 interacts with the system 12 and the user 34 through a series of HTTP, TCP, UDP, or WebSocket network requests 36—whether text or audio. The dialog coordinator 32 further as operational connectivity to a series of databases, for example a current state DB 38a, a short-term memory DB 36b, a long-term memory DB 38c, a contact / entity DB 38d, and a reflexive response DB 38e. Such operational connectivity to the databases may be direct from the dialog coordinator 32 or processed through one or more of a sentiment interface 40, an intent classifier 42, a strategy engine 44, and a reflexive response engine 46. In addition, the inventive method flowchart 30 also depicts a text-and-speech input monitor 48, a text-and-speech output monitor 50, and optional text-to-speech 52 or speech-to-text 54 routines.

[0040] The inventive method 30 for the voice box 10 also includes accessibility through the dialog coordinator 32 to a series of games, apps, skill tests, sequence test, and similar functions 56. The voice box 10 is preferably programmed to allow the AI model to present these functions 56 to the user for interactive play. Further, the dialog coordinator 32 has connectivity to a prompt engine 58 with access to a generative pre-trained transformer (GPT) 60 containing a large language model for generating appropriate and responsive conversation.

[0041] In a particular embodiment, shown in FIGS. 6 and 6bB, the voice box 10 may include a near-field sensor 62 contained within the housing 10a. This near-field sensor 62 is electronically connected to the microcontroller unit 18. When paired with a near-field tag 64 disposed in the toy 14 proximate to the interior pocket 16, the near-field sensor 62 is programmed to instruct the microcontroller unit 18 which of multiple AI characters and / or voices should be accessed through the GPT 60 via internet. In this way, a single manufactured voice box 10 can be used for production of multiple toys 14 and / or systems 12, or interchangeably by a user with various toys 14 and / or systems 12.

[0042] Although several embodiments have been described in detail for purposes of illustration, various modifications may be made without departing from the scope and spirit of the invention.

Examples

Embodiment Construction

[0020]The invention now will be described more fully hereinafter with reference to the accompanying drawings, in which embodiments of the invention are shown. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0021]It will be understood that when an element is referred to as being “on” another element, it can be directly on the other element or intervening elements may be present there between. As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed items.

[0022]It will be understood that, although the terms first, second, third etc. may be used herein to describe various elements, components, regions, layers and / or sections, these elements, components, regions, layers and / or...

Claims

1. An AI conversational system, comprising:a three-dimensional figure representing a character, having an interior pocket accessible through a closure that is selectively opened or closed;a voice box removably disposed within the interior pocket, wherein the voice box has a housing enclosing a microcontroller unit operationally connected to a wireless antenna, a speaker, a microphone, and a battery;wherein the microcontroller unit is configured to wirelessly access an internet-based artificial intelligence GPT engine and produce interactive and responsive conversation representative of the character represented by the three-dimensional figure.

2. The AI conversational system of claim 1, wherein the three-dimensional figure is selected from the group consisting of a plush toy, a stuffed toy, an action figure, an instrument, and a conversational model.

3. The AI conversational system of claim 1, wherein the wireless antenna of the voice box is configured for wireless connectivity through a WLAN protocol or a WPAN protocol.

4. The AI conversational system of claim 3, wherein the WLAN protocol corresponds to a Wi-Fi connection and the WPAN protocol corresponds to a Bluetooth connection.

5. The AI conversational system of claim 1, wherein the voice box further comprises a near-field sensor enclosed in the housing and operationally connected to the microcontroller unit.

6. The AI conversational system of claim 5, further comprising a near-field tag disposed in the interior pocket of the three-dimensional figure proximate to near-field sensor when the voice box is disposed in the interior pocket.

7. The AI conversational system of claim 6, wherein the near-field tag is programmed to identify a particular character and the near-field sensor is programmed to communicate the particular character identified by the near-field tag to the microcontroller unit.

8. The AI conversational system of claim 7, wherein the microcontroller unit is programmed to communicate the particular character identified by the near-field tag to the artificial intelligence GPT engine so as to produce interactive and responsive conversation representative of the particular character identified by the near-field tag.

9. The AI conversational system of claim 1, wherein the microcontroller unit is wirelessly connected to a persistent long-term memory database whereby a history of past interactive and responsive conversations is stored.

10. The AI conversational system of claim 1, wherein the microcontroller unit is wirelessly connected to a persistent contact and entity database whereby a list of contacts and entities associated with the character represented by the three-dimensional figure is stored.

Images