Autonomous generative intelligence environment method across operating system, devices and connected networks.

Abstract

A computer-implemented system and method for operating a local cross-application autonomous task routing framework tangibly embodied as a low-level software operational layer designated as 49AGI app via playstore and ios app store. The system architecture intercepts multi-modal input data directly from a plurality of distinct local applications, bypasses visual screen-pixel processing, and manages active task states natively via local processor networks. The 49AGI architecture executes background operations across applications lacking native machine learning models, providing local multi-modal reminder generation, notification scheduling, and native document compilation.

Description

[0001] TITLE: Autonomous generative intelligence environment method across operating system, devices and connected networks.

[0002] TECHNICAL FIELD: The present disclosure relates to computer implemented data processing systems and, more particularly, to autonomous generative intelligence (AGI) systems for multi modal data processing and task execution implemented in electronic devices such as smartphones, tablet computers, desktop computers and servers. The invention concerns hardware and software arrangements in such computing devices, smartphones, operating systems and application programs that enable coordinated processing and inference over text, audio, image, video, sensor and other digital data, and control of user initiated autonomous tasks in local and network connected computing devices environments.

[0003] Background: Electronic devices such as smartphones, tablet computers, laptops, desktop computers, wearables, speakers, vehicles and robots increasingly incorporate artificial intelligence (Al) and machine learning (ML) functionality. Conventional systems typically deploy these capabilities in fragmented forms, such as isolated assistants (e.g., Siri, Google Assistant, Alexa), recommendation engines, or cloud-based services like ChatGPT (OpenAI, 2022) and Gemini (Google, 2023). Each operates with its own data silos, processing pipelines and application-specific interfaces, lacking devicewide coordination across heterogeneous applications. Operating systems provide limited native support for sharing AI / ML resources, model orchestration or multi-modal context (text, audio, image, video, sensors) between apps. Developers resort to bespoke APIs or manual data transfer, leading to duplication, inconsistency and fragmented user experiences.

[0004] Multi-modal Al workloads often run sequentially or ad-hoc in single processes, creating bottlenecks during concurrent tasks across apps. General-purpose OS schedulers are not optimized for parallel inference over diverse data types or structured multi-parallel execution. Privacy concerns drive on-device processing demands (e.g., Ell GDPR, China PIPL), but existing solutions either transmit data to cloud servers or fail to synchronize context across user devices, trading functionality for privacy. These limitations highlight the need for an integrated AGI framework enabling unified multi-modal processing,privacy-preserving operation, cross-device coordination and optimized heterogeneous compute. The present invention addresses these gaps via an on-device, fully multi-modal AGI system with dynamic orchestration across hardware silos and seamless cross-app / device context sharing.

[0005] SUMMARY: A first aspect of the present disclosure provides an autonomous generative intelligence system implemented on one or more electronic devices, smartphones, operating systems and / or application programs. The system comprises: one or more artificial intelligence and / or machine learning models; a multi modal data interface configured to receive input and provide output in one or more of text, voice, image, video, document and sensor formats; vector based memory store(s) for user(s) and system data; and a controller configured to coordinate model execution, memory access and task orchestration across a plurality of applications, devices and networks. The controller is configured to autonomously receive multi modal data from a plurality of local or network connected applications and devices, process the multi modal data using one or more of the models, generate corresponding multi modal output, and route the output to one or more target applications, devices and / or users in accordance with user instructions, predefined rules and / or learned preferences.

[0006] In the context of the present disclosure, “autonomous generative intelligence” (AGI) refers to a computer implemented framework in which multiple Al and / or ML models, including but not limited to large language models, visual language models, small language models, object detection models, embedding models and decision-making models, operate together to perform multi modal understanding, reasoning, content generation, decision support and task execution. The AGI framework is not limited to a single application; rather, it is integrated within or alongside the operating system and a plurality of applications such that it may observe, process and act upon data and events arising across different applications, files, devices and networks. The AGI framework may run partially or entirely on device, partially or entirely in cloud infrastructure, or in a hybrid configuration in which tasks are dynamically allocated between on-device and remote resources.Depending on the implementation, the AGI method is able to process individual items of data (for example, a single document, message or image), continuous streams of data (for example, live sensor feeds, chats, news streams or meetings), or combinations of both. In some examples, the AGI method receives multi modal inputs from messaging, email, calendar, maps, journal, notes, social media, travel, payment, browser and other applications, performs analysis, summarization, labeling, comparison and / or recommendation, and then writes multi modal results back into one or more of those applications. In other implementations, the AGI method coordinates long running tasks such as trip planning, project tracking, environment monitoring or autonomous monitoring of financial markets, with periodic or event driven updates to the user. The AGI method system may create, update and or maintain structured, vector based memory store that captures user preferences, historical interactions, labeled content and task state across applications and devices. In some examples, the memory store is shared across multiple AGI agents or components, enabling consistent context and history for the user. The AGI method may apply clustering, categorization and labeling techniques to organize the memory into topics, projects, subjects, single and or connected cluster environments and or other logical groupings. The memory store may be updated both in response to new multi modal data and in response to user feedback, such that the system can refine future outputs and recommendations. In some implementations, the AGI method can autonomously identify duplicate or redundant files across one or more applications and storage locations, consolidate them, and manage retention policies so that non relevant data is deleted after predetermined periods. A second aspect of the present disclosure provides a method of operating an autonomous generative intelligence system integrated into an operating system and / or one or more applications on an electronic device. The method includes receiving, by a multi modal input interface, user requests and data in one or more forms including text, speech, images, video, sensor readings and / or external documents; invoking, by a controller, one or more Al and / or ML models selected according to the subject matter, data modality and device constraints; processing the received data by the selected models to produce multi modal outputs such as summaries, action plans, suggested replies,generated content, configuration changes or control commands; updating, by a memory manager, entries in a vector based memory store to reflect new information, labels, relationships and user preferences; and autonomously executing one or more actions based on the outputs, including updating application content, sending communications, filling forms, triggering device controls and or scheduling follow up tasks.

[0007] In some examples, the method further comprises orchestrating multiple Al and / or ML models in parallel or multi-parallel fashion. For example, a first model may be used to understand and structure a user request, a second model to retrieve relevant information from the vector-based memory, one or more specialized models to handle domain-specific subtasks (for example, travel booking, financial analysis, legal drafting or design generation), and a further model to synthesize a final multi-modal result. The controller may schedule these sub-tasks across available processing resources, such as CPU, GPU and neural engines of the device, and may offload portions of the workload to cloud based services when appropriate.

[0008] A third aspect of the present disclosure provides a system and method for cross application and cross device coordination using autonomous generative intelligence. In one example, the AGI system operates on a user’s primary device (such as a smartphone, tablet, laptop or desktop computer or any other device) and is configured to interface with other devices including smart home appliances, speakers, environmental sensors, wearables, robotics and or vehicles over one or more wired or wireless networks. The AGI system may receive multi-modal sensor data (for example, motion, temperature, light, sound, humidity, air quality, power consumption, security status) from a plurality of devices within an environment such as a home, office, industrial facility or vehicle fleet. The AGI system analyzes and summarizes this data, and generates recommended and or autonomous control actions such as adjusting lighting, air conditioning, heating, blinds, appliances, security systems, EV chargers or other equipment according to user preferences, schedules, environmental conditions and energy saving policies.

[0009] Brief Description of Drawings:Examples of the present disclosure will be explained below with reference to the accompanying drawings, in which:

[0010] FIG. 1 is a block diagram illustrating an exemplary hardware and software environment for an autonomous generative intelligence (AGI) device ecosystem configured for local cross-application data orchestration, vectorbased state synchronization, and multi-device network connectivity.

[0011] FIG. 2 illustrates a method which defines a functional method and system flow wherein distinct incoming data streams — comprising documents, text, vocalizations, and video are simultaneously processed.

[0012] FIG. 3 illustrates a method which defines a centralized control core centered around a user component operating within a native client device framework, wherein the centralized control core establishes direct administrative pathways to a surrounding matrix of a plurality of applications.

[0013] FIG. 4 illustrates an integrated application matrix enclosed within a local device containment boundary, where each distinct application incorporates a dedicated, embedded intelligence engine (AGI Model) interconnected via horizontal, vertical, and diagonal data routing links. This specialized local application matrix is operatively coupled to multi-layer vector storage architecture while simultaneously expanding tasks to a hardware synchronization layer spanning connected companion devices, context synchronization with cross-application data and connected network apps. FIG. 5 is a flowchart illustrating an embodiment of an Autonomous Generative Intelligence (AGI) system configured to create and label a multimodal vector base from diverse inputs (documents, images, voice, chat, video), generate overall summarizations, apply agent-based labeling, and refine clusters with user feedback.

[0014] Detailed Description of the preferred Embodiment: Various examples of the invention are described below. It should be understood that these examples are provided for purposes of illustration only, and that other configurations, components and embodiments may be used without departing from the scope of the invention as defined by the appended claims, drawings or explanations. According to an aspect, the autonomous generative intelligence (AGI) method provides a number of technical advantages overconventional approaches. The method delivers seamless intelligent assistance across all applications on a user's device without requiring per application configuration or manual data transfer between applications. User data privacy is maintained through primary on-device processing, while selective synchronization with cloud services is available when explicitly authorized by the user. If needed Computational efficiency is achieved through parallel processing architectures that optimize resource utilization across heterogeneous processor types including CPU, GPU, neural engines and emerging architectures. Complex multi step tasks are completed autonomously by multi agent coordination, with appropriate checkpoints for user confirmation and refinement. An unified vector based database provides consistent context and intelligence across the user's entire device ecosystem. The methodology demonstrates broad industrial applicability through embodiments in everyday smartphones, speakers, vehicles or with other smart devices in any environment. In various embodiments, the AGI method can be embedded directly into devices and or systems, enabling seamless inter-device communication and coordination. Embedded implementations support real-time status reporting, updates, scheduling notifications, task completion monitoring and multi-modal user interaction workflows across connected environments. For example, household appliances, environmental sensors, security systems, lighting, climate controls and other networked equipment can operate under unified AGI coordination, with users receiving multi-modal updates and exercising control through speech, text, gestures or graphical interfaces.

[0015] FIG. 1, an exemplary embodiment of the autonomous generative intelligence environment comprises a centralized digital assistance framework embedded directly within a core device operating system layer — such as Android, iOS, or Windows — to orchestrate localized computing tasks on behalf of a user. As illustrated, a plurality of distinct local applications including communication tools, media repositories, productivity journals, and transaction mechanisms are programmatically unified by the central operating system service, wherein each application component includes specific functional capabilities to interoperate and exchange data matrices directly with other local applications. By operating natively at the underlying operating system layer, the methodframework eliminates computationally expensive visual screen-pixel processing or raw accessibility overlay reliance, intercepting multi-modal application payloads directly from source apps and routing automated background control instructions to separate target applications lacking native machine learning models. Furthermore, the illustrated device boundaries extend horizontally to form a distributed network architecture with external connected computing hardware — comprising a tablet, a desktop, a laptop — wherein active task states, user contextual preferences, and continuously updating vector-base memories are synchronized dynamically across the multi-device matrix, thereby securing an integrated, low-latency, and privacy-first ambient computing environment.

[0016] FIG. 2, the autonomous generative intelligence environment provides a localized method and system for multi-modal data transformation, validation, and storage. The execution architecture comprises a first generative pathway configured to ingest textual and document components (Doc(s), Text(s)) for local AGI summary and text generation, and a second concurrent pathway configured to process visual and audio vectors (Video(s), Voice(s)) to output a unified multi-modal summary matrix (Summary (multi-modal)). Operational progression through the pipeline is gate-controlled via an explicit verification interface layer requiring a user confirmation protocol (User Confirmation) corresponding to an active user task assignment (User (AGI Task)).

[0017] FIG. 3 illustrates a schematic representation of an Autonomous Generative Intelligence device configured to provide multimodal, cross-domain assistance in accordance with the present disclosure. At the center of the figure, a user (administrative) node is depicted, representing the operating system environment and user interface through which autonomous tasks are initiated and managed. The user node is communicatively coupled to a plurality of applications, including but not limited to: bars, food, coffee, mall maps, services, shops, restaurants, leisure, library, vehicles, travel, movies, and malls.FIG. 4 illustrates a schematic representation of an Autonomous Generative Intelligence device ecosystem configured to operate across a plurality of applications and devices in accordance with the present disclosure.

[0018] Application modules is depicted, including but not limited to maps, restaurants, chat, video, data, photos, transport, journal, shop, calendar, video tube, meets, travel, contacts, news, browser, payment, and social media wherein it’s data are always connected and updated with multi-modal information crossing applications which are relevant to the data. Electronic devices working autonomously with applications illustrating the cross-device synchronization.

[0019] In further embodiment, the AGI method incorporates integrated data with smart devices from all environments from smartphones, home operating systems, office systems, and when traveling anywhere type of devices including any relevant applications which are working inter-connection autonomously generative intelligence with devices utilizing the benefits AGI Method deployed across networks and devices simultaneously.

[0020] AGI SYSTEM INTEGRATION, APP EMBODIMENT & HARDWARE

[0021] The autonomous generative intelligence method, user experience, and background routing layers described herein are tangibly embodied, commercially deployed, and executed via a native software application architecture designated as 49AGI. The 49AGI architecture is compiled to operate natively as an embedded, low-level operational layer application within the host device operating system, bypassing standard cloud API loops.

[0022] To establish immediate industrial applicability and functional execution metrics across active consumer device matrices, the 49AGI application is optimized to function within strict, restricted system memory parameters available for smartphone device generations including iPhone 16, iPhone 16 Pro, iPhone 17, and higher-end 2024-2026 Android smartphone hardware iterations. In practical execution, the 49AGI application explicitly eliminates redundant matrix math operations associated with processing visual screen pixels or raw accessibility overlays. Instead, the 49AGI application performs the disclosed claims in real-world physical environments to output multi-modal notifications,

Claims

handle cross-application data transfers, and generate real-time user reminders directly on the device operating system layer, including natively reading, parsing, and creating structured PDF file formats.CLAIMS1. A computer-implemented method of operating a cross-application autonomous generative intelligence framework integrated across a plurality of distinct local applications and an operating system of one or more electronic devices, the method comprising:receiving, by a distributed hardware-based processor architecture, multimodal input data originating from a plurality of distinct local applications, the multi-modal input data comprising a combination of at least two of text data, voice data, image data, video data, and physical sensor data;querying, by the distributed hardware-based processor architecture, a vectorbased memory store using the multi-modal input data to retrieve a user context, a user preference profile, and an active task state history, wherein the vector-based memory store is synchronized across a plurality of distinct storage nodes distributed within a single device, across local networks, or remote cloud nodes;processing, by the distributed hardware-based processor architecture executing one or more machine learning models, the multi-modal input data in combination with the retrieved user context to generate multi-modal output data, wherein the generated multi-modal output data comprises crossapplication autonomous instructions and contextual system feedback;creating or updating, by the distributed hardware-based processor architecture, the vector-based memory store with the generated multi-modal output data to maintain real-time task state synchronization across a plurality of distinct storage nodes distributed within a single device, across local networks, or remote cloud nodes; androuting, by the distributed hardware-based processor architecture, the crossapplication autonomous instructions directly to a target application of the singular or plurality of applications to execute a parallel background task on the one or more electronic devices.

2. The method of claim 1 , wherein the distributed hardware-based processor architecture is further configured to execute the querying, processing, updating, and routing steps when the input data originating from the plurality of distinct local applications comprises a single data modality selected from the group consisting of text data, voice data, image data, video data, and physical sensor data.

3. The method of claim 1 , wherein the distributed hardware-based processor architecture executes the querying and processing steps within a secure local hardware enclave embedded directly on a local system-on-chip (SoC) of the one or more electronic devices, and wherein the real-time task state synchronization with the network cloud environment is executed via end-to-end encrypted cryptographic handshakes with a verified remote secure cloud compute node.

4. The method of claim 1 , wherein the one or more machine learning models comprise any combination of one or more of large language models, visual language models, small language models, object detection models, vision models, embedding models, decision making models, and decision tree structures.

5. The method of claim 1 , wherein the one or more electronic devices comprise one or more of a smartphone, a tablet computer, a desktop computer, a laptop computer, a wearable electronic device, a robotic system, a smart household appliance, and an integrated vehicle computing system.

6. The method of claim 1 , wherein the distributed hardware-based processor architecture is configured to receive a user selection assigning distinct machine learning models to distinct automated computing processes, allocatethe selected machine learning models to run within a plurality of local applications or device operating systems, and execute the assigned machine learning models in parallel to process a plurality of concurrently running user tasks.

7. The method of claim 1 , wherein at least one application of the plurality of distinct local applications lacks an integrated native machine learning model, and wherein the cross-application autonomous generative intelligence framework provides artificial intelligence functionalities directly to the at least one application lacking an integrated native model via a centralized system service, an external system application, or an operating system digital assistant that houses the one or more machine learning models.

8. The method of claim 1 , wherein a designated subset of applications, application programming interfaces (APIs), system utilities, and local data files are classified as restricted resources within the operating system, and wherein the cross-application autonomous generative intelligence framework maintains strict cryptographic access control rules restricting interaction with the restricted resources exclusively to authorized digital assistants, verified local applications, and authenticated network platforms.

9. The method of claim 1 , wherein the one or more electronic devices comprise a robotic system, the method further comprising: autonomously collecting, by the distributed hardware-based processor architecture via a plurality of robotic sensors, physical environment data, wherein the plurality of robotic sensors includes at least one of a camera, a depth sensor, a LiDAR sensor, a touch sensor, an inertial sensor, and a microphone;analyzing and summarizing, by the distributed hardware-based processor architecture executing the one or more machine learning models, the collected physical environment data;generating, by the distributed hardware-based processor architecture, a set of generatively intelligent suggested courses of action for the robotic system; and commanding, by the distributed hardware-based processor architecture,the robotic system to execute a physical operational task based on the set of suggested courses of action upon detecting either a manual user confirmation or an autonomous trigger matching a set of pre-defined safety criteria.

10. The method of claim 9, wherein the robotic system comprises a plurality of distinct sensor types distributed across a physical body structure of the robotic system, and wherein the distributed hardware-based processor architecture is configured to execute multi-modal training and model re-training cycles using parallel, simultaneous input streams of physical movement data, voice data, and imaging sensor data corresponding to specific human tasks.

11. The method of claim 9, wherein the distributed hardware-based processor architecture is communicatively coupled to a set of wearable multi-modal input sensors worn by a human operator in parallel with the robotic system, the wearable multi-modal input sensors including at least one of a LiDAR sensor, a camera, and a tactile sensor, and wherein the distributed hardware-based processor architecture is further configured to:receive step-by-step task instructions and manual correction feedback from the human operator;apply semantic labels to the physical environment data corresponding directly to the received step-by-step task instructions; andupdate internal training parameters of the one or more machine learning models controlling the robotic system based on the applied semantic labels and the manual correction feedback.

12. The method of claim 1, wherein the one or more electronic devices are integrated within an aircraft computing architecture, the method further comprising:operating, by the distributed hardware-based processor architecture, in a cooperative-pilot configuration with a human flight pilot during taxi, take-off, inflight operation, landing, and emergency flight situations;rendering, via an avionics interface, multi-modal notifications, flight recommendations, and flight profile updates to the human flight pilot; andinitiating, by the distributed hardware-based processor architecture, an emergency operational takeover to assert autonomous flight control assistance upon verifying that a set of flight safety thresholds has been violated.

13. The method of claim 12, wherein the distributed hardware-based processor architecture is further configured to:maintain a continuous, multi-modal communication uplink with an external air traffic control system via a dedicated system application; andsynchronize live flight status data, active navigation vectors, and safety-critical telemetry data between the aircraft computing architecture and the external air traffic control system.

14. The method of claim 12, wherein the aircraft computing architecture further comprises a plurality of networked avionics modules, and wherein the distributed hardware-based processor architecture executes real-time multimodal data synchronization across applications, utility programs, system subsystems, and the plurality of networked avionics modules within the aircraft computing architecture.

15. The method of claim 1, wherein the one or more electronic devices are integrated within an automotive vehicle system, the method further comprising: autonomously gathering, by the distributed hardware-based processor architecture via a vehicle sensor array, multi-modal spatial data, wherein the vehicle sensor array includes at least one of a camera, a radar system, a LiDAR system, an ultrasonic sensor, and an inertial measurement unit; generating, by the distributed hardware-based processor architecture executing the one or more machine learning models, real-time multi-modal estimations of relative distance, relative velocity, and trajectory vectors between the automotive vehicle system and external objects; and calculating, by the distributed hardware-based processor architecture, an optimized velocity and distance profile to maximize physical safety margins for human occupants situated inside the automotive vehicle system.

16. The method of claim 15, wherein the distributed hardware-based processor architecture is further configured to:simultaneously capture and summarize the multi-modal spatial data in realtime to generate localized traffic condition profiles;output the localized traffic condition profiles as multi-modal notifications comprising text, video, and synthetic voice alerts through at least one internal cabin display and audio speaker; andinitiate automated adjustments to a vehicle speed parameter and a vehicle steering vector when the vehicle sensor array detects an imminent obstacle collision path.

17. The method of claim 15, wherein upon detecting a critical collision hazard, the distributed hardware-based processor architecture generates and mathematically evaluates a plurality of distinct evasive maneuvers, determines an optimized distribution of acceleration, steering torque, and braking forces to minimize physical impact force vectors based on real-time biometric positions of human occupants within a vehicle cabin, and transmits a control command to a vehicle drive-by-wire system to execute the optimized evasive maneuver.

18. An autonomous generative intelligence processing apparatus comprising: a central processing unit;a graphics processing unit;one or more neural processing engines; anda unified memory architecture comprising a cache memory layer and a dynamic random access memory layer;wherein the central processing unit, the graphics processing unit, the one or more neural processing engines, the cache memory layer, and the dynamic random access memory layer are interconnected via a multi-layered parallel processing fabric; andwherein the central processing unit, the graphics processing unit, and the one or more neural processing engines share access to at least a portion of the cache memory layer to distribute autonomous generative intelligence processing workloads across a unified hardware processor network.

19. The apparatus of claim 18, wherein the central processing unit shares an identical physical cache space with the graphics processing unit and the one or more neural processing engines, the apparatus further comprising task scheduling logic configured to partition and allocate sub-tasks of the autonomous generative intelligence processing workloads across the central processing unit, the graphics processing unit, and the one or more neural processing engines based on an executing model type, an incoming data type, and real-time hardware resource availability.

20. The apparatus of claim 18, wherein the multi-layered parallel processing fabric and the shared access to the cache memory layer are integrated with a quantum processing architecture comprising a plurality of qubits, wherein one or more quantum processing layers operate in a parallel processing configuration to execute the autonomous generative intelligence processing workloads.

21. The apparatus of claim 18, wherein the graphics processing unit comprises a plurality of arithmetic logic units configured in a multi-layered parallel matrix optimized to execute vector and tensor mathematical operations for an active autonomous generative intelligence model.

22. The apparatus of chain 18, further comprising a plurality of tensor processing cores and a plurality of multi-dimensionally stacked memory chips, wherein the central processing unit, the graphics processing unit, the plurality of tensor processing cores, the dynamic random access memory layer, and the cache memory layer are structured in a multi-dimensional stacked chip configuration to maximize processing density and interconnect bandwidth for the autonomous generative intelligence processing workloads.

23. A computer-implemented method of securing access to restricted digital resources using an autonomous generative intelligence framework, the method comprising:receiving, by a distributed hardware-based processor architecture via a plurality of device sensors, multi-modal authentication input from a user, the multi-modal authentication input comprising a combination of at least two of biometric facial data, voice data, physical gesture data, typed input patterns, device kinetic movement patterns, and contextual environmental signals; generating, by the distributed hardware-based processor architecture executing one or more machine learning models, a dynamic autonomous generative intelligence cryptographic passcode derived from the multi-modal authentication input; andtransmitting, by the distributed hardware-based processor architecture, an access control command utilizing the dynamic autonomous generative intelligence cryptographic passcode to lock or unlock an operating system resource selected from the group consisting of a local file, a system application, a connected device, and an external network domain; wherein the distributed hardware-based processor architecture requires a synchronized temporal combination of the multi-modal authentication inputs within a pre-defined time interval to validate the passcode, and autonomously modifies the required combination of inputs or the pre-defined time interval based on a real-time calculated threat risk level.

24. The method of claim 23, wherein the dynamic autonomous generative intelligence cryptographic passcode is configured as a time-limited session password valid exclusively for a restricted temporal window to log into a targeted computing environment, and wherein the distributed hardware-based processor architecture maintains a structured administrative authorization tree defining a plurality of distinct multi-modal input verification combinations required to grant distinct access permissions to distinct protected system resources.

25. The method of claims 1 to 24; where in the autonomous generative intelligence method can be used for creating large language models or when fine tuning models for user own preferences or when in use for user queries.

26. The method of claims 1 to 24; where in users can use one device to access device bio metrics to register other devices users own into a synced devices network and access data and input commands to user’s device(s).

27. The method of claims 1 to 24; where in devices users own it’s processes can also be autonomous and output data to other user’s relevant device(s).

28. The method of claims 1 to 24; where in devices users own can autonomously connect with each other to update data in relevant apps, operating system autonomous background processes between cross applications, relevant device(s) or connected networks.

29. The method of claims 1 to 24; where in devices users own can autonomously be authenticating user passwords and or bio metrics for user tasks.

30. The method of claims 1 to 24; where in devices users own can operate any type of singular input or simultaneous input comprises a single data modality selected from the group consisting of text data, voice data, image data, video data, face data, physical sensor data or any other type of data.

31. The method of claims 1 to 24; where in devices users own can operate control points where user relevant device(s) require user’s approval comprising a single or multiple data or multiple sequenced data selected from the group consisting of text data, voice data, image data, video data, physical sensor data, face data, fingerprint data or any other type of data.

32. The method of claims 1 to 31 ; wherein the processing, querying, updating and routing steps are executed in any operation combination across plurality of local applications, the operation system, device(s) or connected networks.

Images