4232results about "Program control" patented technology

Systems and methods for integrating generative artificial intelligence (AI) within Software-as-a-Service (SaaS) platforms to automate data operations, synchronize cross-platform workflows, and enable intent-based interactions. A platform displays table structures of items and characteristics linked to a common objective, provides input interfaces, and enrolls AI agents as credentialed users with read / write privileges. The system prompts agents with column types, structural relations, and role profiles to generate and execute editing instructions that progress workflow objectives, detect missing or inconsistent data, and notify users or request information as needed. Hierarchical access schemes permit multiple agent instances with inherited privileges and resource limits managed through an AI center. Agents can operate as autonomous team members, analyze outputs, and support natural-language explanation sessions. Additional embodiments coordinate inter-service updates, maintain deviation detection tools, and construct tailored products and platform elements. These capabilities improve robust automation, decision support, and operational efficiency in complex SaaS environments.

Systems and methods disclosed herein perform privacy-preserving evaluations of artificial intelligence (AI) agents. A first AI agent associated with a first entity obtains a machine-readable data structure defining one or more operative boundaries for a second AI agent associated with a second entity. The system generates a unique fixed reference value representing the machine-readable data structure by applying a first transformation operation set, and transmits the unique fixed reference value to a multi-agent storage to store the value. The system receives, via the multi-agent storage, a verification artifact from the second AI agent that indicates an observed value based on internal operational data of the second AI agent corresponding to the operative boundaries. The first AI agent determines a verification status of the verification artifact by comparing the unique fixed reference value with the observed value, and autonomously generates a verification record including a representation of the verification status.

The systems and methods disclosed herein orchestrate task execution among autonomous (or semi-autonomous) AI agentic models (“agents”) using a gateway router that dynamically coordinates the agents based on prompt characteristics, user context, and / or real-time operational factors. Received inputs (e.g., prompts) are segmented into subcomponents (e.g., sub-queries), which are routed / mapped to candidate agents based on the output parameters of the subcomponent (e.g., performance thresholds, cost thresholds) and operational parameters (e.g., cost, performance metric values, user access restrictions, timing restrictions) of each agent. The gateway router maintains dynamic routing data structures for each agent that are continuously updated based on environmental stimuli (e.g., geo-political stimuli, sensor stimuli, agent stimuli). For example, the gateway router causes agents to dynamically switch between rule engines identified by the routing tables in response to detecting environmental stimuli. Responses from the candidate agents are aggregated into an output that is responsive to the input.

Systems, methods, and devices that relate to routing requests to large language models (LLMs) are disclosed. In one example aspect, the system receives session-specific data elements in response to a request to generate an output using LLMs. The system determines a hierarchy of operational constraints including privacy protocols and performance requirements. Weights for a multi-variable optimization are dynamically updated using the session-specific data elements. The system executes the multi-variable optimization across candidate LLMs that satisfy privacy constraints and optimize performance constraints. Based on the optimization, at least one candidate LLM is selected and the request is routed to it. In response to performance feedback, the system automatically selects a different LLM to improve one constraint, resulting in degradation of another constraint.

Systems for explainable large language model routing with immutable audit trails are disclosed. The system receives a query and determines its characteristics including complexity, domain, regulatory constraints, and performance requirements. It retrieves profiles for multiple LLMs from a model matrix containing performance attributes, resource consumption, and compliance parameters. The system selects a particular LLM by balancing resource consumption with performance requirements, evaluating regulatory compliance, ranking LLMs based on these factors, and prioritizing models with successful processing history. The system generates a human-readable explanation of the selection including decision factors, rationale, and alternatives considered. Finally, it records the selection and explanation in a tamper-evident, immutable audit trail data structure.

Systems and methods for integrating generative artificial intelligence (AI) within Software-as-a-Service (SaaS) platforms to automate data operations, synchronize cross-platform workflows, and enable intent-based interactions. A platform displays table structures of items and characteristics linked to a common objective, provides input interfaces, and enrolls AI agents as credentialed users with read / write privileges. The system prompts agents with column types, structural relations, and role profiles to generate and execute editing instructions that progress workflow objectives, detect missing or inconsistent data, and notify users or request information as needed. Hierarchical access schemes permit multiple agent instances with inherited privileges and resource limits managed through an AI center. Agents can operate as autonomous team members, analyze outputs, and support natural-language explanation sessions. Additional embodiments coordinate inter-service updates, maintain deviation detection tools, and construct tailored products and platform elements. These capabilities improve robust automation, decision support, and operational efficiency in complex SaaS environments.

Systems, methods, and devices that relate to intelligent query decomposition and parallel routing for specialized model processing are disclosed. In one example aspect, the system receives a query from a user comprising a request relating to a particular domain. The system determines, using a decomposition model, a set of sub-queries based on semantic boundaries, syntactics, tasks, relationships, and rules relating to particular domains. The system inputs the set of sub-queries into a routing model to determine a set of specialized models. For each sub-query, the system routes the sub-query to a respective specialized model, generates an output, and assigns a confidence score. The system detects conflicts among outputs using a conflict detection model configured to identify discrepancies. The system generates an aggregated output by combining outputs according to a weighted aggregation algorithm prioritizing higher confidence scores and conflict resolution rules, then displays the aggregated output.

Systems and methods disclosed herein automatically authorize, audit, and manage usage of protected digital content via agentic artificial intelligence (AI) models. A data access / usage request is received (e.g., from a graphical user interface) that is associated with digital assets licensed from third parties. The system uses a first AI agent set to identify the digital content and retrieve corresponding access policies from a distributed database. The system uses a second AI agent set (same as or different from the first AI agent set) to evaluate the request against the retrieved policy to generate a permission set and / or settlement instructions. The system uses a third AI agent set (same as or different from the first and / or second AI agent sets) to embed digital watermarks and / or cryptographic signatures into the accessed content, and to record an audit trail of access, authorization, and / or settlement events in a distributed ledger or database.

A system for automated code modification improves application performance in cloud environments by integrating telemetry analysis with large language model (LLM)-driven reasoning. The system collects contextual information about a target application, including metadata, source code, and configuration files, and correlates it with real-time telemetry data related to application performance. Based on this data, the system constructs a structured LLM prompt using a predefined schema, which is transmitted to an LLM. The prompt instructs the LLM to recommend modifications to source or configuration files that may enhance performance, along with natural language explanations for those recommendations. In response to receiving the LLM's response, the system extracts the proposed code or configuration changes and associated rationale, and presents them to a user via a client device interface.

The present disclosure relates to a data processing method, a processor, a chip, and an electronic device. The method comprises: on the basis of an obtained control instruction, a control logic unit sequentially reads, from a memory to a dot product unit array, loop tiling data of data to be processed; the dot product unit array performs multiply-accumulate operation on the loop tiling data of the data to be processed that is received each time, and determines a loop tiling result of the data to be processed that is received each time; and on the basis of a plurality of loop tiling results obtained from the dot product unit array, the control logic unit determines a logic operation result of the data to be processed. The embodiments of the present disclosure can convert, into the reading and logic operation of multiple pieces of loop tiling data of the data to be processed, the reading and logic operation of the data to be processed, so that data with larger size can be processed under the condition that the hardware resources of the processor are not changed, and the pressure on the storage bandwidth is reduced.

Systems and methods disclosed herein automatically detect, analyze, and mitigate anomalous resource distribution among artificial intelligence (AI)-based agents within a distributed computational network. The system receives a resource allocation request specifying computational resources, agent parameters, and performance objectives for a network of agents. A first AI model set monitors agent activity by tracking resource consumption and behavioral deviations from baseline profiles. The system compares resource usage of agents with historical norms and / or predetermined thresholds to generate an anomaly score for each agent. A second AI model set aggregates scores to construct a multi-dimensional data structure that indicates the comparison and anomaly score. The system ranks agents by anomaly severity to isolate agents with high scores (e.g., misaligned agents), and reallocates resources and updates access privileges for the misaligned agents.

Systems and methods disclosed herein perform privacy-preserving evaluations of artificial intelligence (AI) agents. The system identifies an auditing AI agent from a set of auditing AI agents for assessing target AI agent sets. The system obtains a data structure that defines operative boundaries for a target AI agent set and generates a reference value by applying a first transformation operation set on the data structure. The system transmits the reference value to a multi-agent storage and receives, via the multi-agent storage, a verification artifact from the target AI agent set that indicates an observed value generated by applying a second transformation operation set on an artifact set generated by the target AI agent set. The system determines, via the auditing AI agent, a verification status and responsive to a particular artifact failing to satisfy one or more assessment metrics, generates an action set to modify the target AI agent set.

Implementations of this specification provide key-value cache management, model reasoning, and data processing methods and apparatuses for large language models. In an implementation, a method comprises allocating a virtual memory block in a virtual address slot to newly-added token key-value data of a model reasoning request, in response to determining that a scheduling result of the model reasoning request indicates the model reasoning request is scheduled for execution, maintaining a mapping relationship between an occupied virtual address slot and a physical graphics memory block allocated to the model reasoning request, and copying the newly-added token key-value data to the physical graphics memory block.

Systems, methods, and non-transitory computer readable media including instructions for providing private answers to silent questions are described. Providing private answers to silent questions includes receiving signals indicative of particular facial micromovements in an absence of perceptible vocalization; accessing a data structure correlating facial micromovements with words; using the received signals to perform a lookup in the data structure of particular words associated with the particular facial micromovements; determining a query from the particular words; accessing at least one data structure to perform a look up for an answer to the query; and generating a discreet output that includes the answer to the query.

A social media platform provides a map-based graphical user interface (GUI) for accessing social media content submitted for public accessibility via the social media platform supported by the map-based GUI. The GUI includes a map providing interactive location-based searching functionality in that selection of a target location by the user in the GUI, such as by tapping or clicking at the target location, triggers a search for social media content having geo-tag data indicating geographic locations within a geographical search area centered on the target location. A search period for which content is returned is dynamically variable based on the duration for which the tap or click is held.

An AI-based energy edge platform is provided herein with a wide range of features, components and capabilities for management and improvement of legacy infrastructure and coordination with distributed systems to support important use cases for a range of enterprises. The platform may incorporate emerging technologies to enable ecosystem and individual energy edge node efficiencies, agility, engagement, and profitability. Embodiments may forecast, plan for, and manage the demand and utilization of energy in greater distributed environments. Embodiments may use AI, IoT, and technologies that filter, process, and move data more effectively across communication networks. Embodiments of the platform may leverage energy market connection, communication, and transaction enablement platforms. Embodiments may employ intelligent provisioning, data aggregation, and analytics.

Data from manufacturing is highly uncontextualized and siloed, requiring expert knowledge of context and substantial data pre-processing to support meaningful queries and visualizations. To address this problem, data for a number of sources in a manufacturing context can be retrieved and converted into an intermediate representation in a natural language or near-natural language form, which can in turn be ingested by a generative AI engine, along with suitable prompts by the user to summarize, analyze, and make recommendations based on the data.

A method of operating a device that interacts with a physical environment includes determining to take an action on the physical environment wherein the action is based on an output of a computing task, generating a risk level that estimates a risk of physical harm associated with taking the action within the physical environment, obtaining a performance indicator of a communication network between the device and a remote computing device, and determining, based on the risk level and the performance indicator, whether to offload the computing task to the remote computing device or to perform the computing task locally. Related devices are also disclosed.

Systems and methods disclosed herein perform privacy-preserving evaluations of artificial intelligence (AI) agents. A first AI agent associated with a first entity obtains a machine-readable data structure defining one or more operative boundaries for a second AI agent associated with a second entity. The system generates a unique fixed reference value representing the machine-readable data structure by applying a first transformation operation set, and transmits the unique fixed reference value to a multi-agent storage to store the value. The system receives, via the multi-agent storage, a verification artifact from the second AI agent that indicates an observed value based on internal operational data of the second AI agent corresponding to the operative boundaries. The first AI agent determines a verification status of the verification artifact by comparing the unique fixed reference value with the observed value, and autonomously generates a verification record including a representation of the verification status.

The server, initializes, for a third-party application executing on the server, an entirety of available GPU memory of a client device, including pre-allocating a plurality of blocks of GPU memory. During execution of the third-party application, the server receives a first request from the third-party application to store first data in the GPU memory of the client device, and, in response to the first request, frees a portion of a respective pre-allocated block of the plurality of pre-allocated blocks of GPU memory and stores the first data in the portion of the respective pre-allocated block. The server pre-allocates a new block of GPU memory of the client device, the new block comprising a complementary portion of the respective pre-allocated block such that, after pre-allocating the new block of GPU memory, the entirety of available GPU memory of the client device remains allocated.

A device to process data associated with a surgical event of a surgery may include a processor. The processor may be configured to receive multiple data streams during the surgical event. The processor may be configured to select a primary data stream based on a surgical data interface via which the primary data stream is received. The processor may be configured to select a secondary data stream based on a surgical data interface via which the second data stream is received. The processor may be configured to identify the surgical data interfaces. The processor may be configured to generate situational data associated with the primary data stream based on the secondary data stream. The situational data may indicate a medical decision-making factor of the surgical event. The primary data stream and the situational data may be sent during the surgical event.

Protection for a secure boot procedure can be provided in addition to cryptographic verification of boot firmware associated with the boot procedure. While the boot firmware is being verified and executed at a secure sub-system, an open sub-system can be put into a halt state, during which the open sub-system is prevented from performing the boot procedure. The open sub-system is still prevented from performing the boot procedure even if the boot firmware is verified and / or executed unless the open sub-system is put into the resume state again.

The present application relates to the technical field of data storage, and specifically discloses a data transmission method and device, a heterogeneous system, and a coherent interconnect processing component. The coherent interconnect processing component installed on a device enables corresponding coherent interconnect interfaces on the basis of the number of other devices to be interconnected in a heterogeneous system where said device is located, initializes physical communication links to obtain memory interconnect parameters, establishes memory coherent interconnect communication links between the devices on the basis of the memory interconnect parameters, allocates corresponding cache spaces from said device, and on the basis of the memory coherent interconnect communication links and the cache spaces, performs cache coherent transaction processing of said device and the other devices, so as to implement memory coherent interconnect transmission requests between said device and the other devices. Therefore, topologies can be dynamically sensed, and memory coherent interconnect communication links between devices in a heterogeneous system can be automatically established, thereby mitigating the problem that different device interconnect protocols need to be managed in the heterogeneous system, achieving inter-device cache coherence, and further improving the access performance.

The systems and methods disclosed herein orchestrate task execution among autonomous (or semi-autonomous) AI agentic models (“agents”) responsive to a received query by using a hierarchical semantic fingerprinting framework to generate semantic-aware fingerprints for the query and agents. Queries and descriptions of agent capabilities are processed by a series of hierarchical levels using locality-sensitive hash (LSH) functions, where subsequent layers encode more complex semantic information and generate longer hash values. The hash values are aggregated into a semantic fingerprint. A bloom filter cascade uses a series of increasingly accurate hierarchical bloom filters to reject agent fingerprints that differ from the query fingerprint. The remaining agent fingerprints are compared bitwise to the query fingerprint, and those closest to the query fingerprint are selected to generate a routing path for the query. Responses from the selected agents are aggregated into an output that is responsive to the input.

To improve user convenience.SOLUTION: A work support system (1) provided herein is capable of supporting work of users. A user input information acquisition unit (201) acquires user input information regarding input by a user. An API request generation unit (203) generates an API request for a destination API from among multiple APIs related to work support based on the user input information and AI. An API request transmission unit (204) sends the API request to the destination API.SELECTED DRAWING: Figure 4

A system and method are provided for placing network functions among respective locations in a network. The locations at which the network functions are placed can be nodes and network devices within the network. These nodes can be selected, e.g., based on which network devices have available capacity and or specialized hardware (e.g., accelerator sin a data processing units (DPUs)) that is optimized for particular network functions. The network functions can include an inline network function that is provisioned directly in a data plane of one of the network devices (e.g., in-lined directly in a hardware offload device without a virtual machine and without a container). The decision of where to place the network functions can be based on a performance metric (e.g., representing available computational / memory resources at the network nodes) and / or a network-function metric (e.g., representing consumed computational / memory resources by the network functions) to improve system performance.

Systems, methods, and computer readable media for routing inputs on a extended reality (XR) wearable device where the methods performed on an apparatus of a system include receiving, at an input framework service, an input data registration request from a client component, the input data registration request comprising an indication of a callback component and an indication of input data having a type, and verifying, at the input framework service, the client component is authorized to access the input data having the type. The method may further include registering, at the input framework service, the callback component with an input service associated with the input data having the type, receiving, at the input service, input data having the type, and invoking, at the input service, the callback component.

Systems and methods for orchestrating interaction with an artificial intelligence (AI) application in a contact center environment receive, via an AI agent, a voice message from a user; convert the message from voice to text; generate an initial computational inference process based on the text message; determine whether or not all information required to execute the initial computational inference process is available to the processor; when a determination is made that all information required is available: execute the initial computational inference process; generate a text reply based on the initial computational inference process; convert the text reply to a voice reply; and send the voice reply to the user via the AI agent; when a determination is made that information is unavailable: generate a text query requesting the information; convert the text query to a voice query; and send the voice query to the user via the AI agent.

This application discloses a model training method and apparatus based on a hybrid parallelism manner. In this method, a neural network model is divided into a plurality of pipeline stages, and each pipeline stage includes a plurality of sub-stages of the neural network model. Computing nodes corresponding to the plurality of pipeline stages are invoked in a hybrid parallelism manner according to a sequence of sub-stages in the neural network model. When iterative training is performed on a network layer in a corresponding pipeline stage, because sub-stages at same locations in adjacent pipeline stages are consecutive in the neural network model, the computing node does not need to wait for completion of forward propagation of a previous pipeline stage, and can perform forward propagation on the corresponding pipeline stage only after forward propagation of the 1st sub-stage in the previous pipeline stage is completed.

A direct memory access controller (DMAC) includes a virtual channel, a physical channel, and a context manager. The virtual channel is configured to generate a flow control signal for executing a direct memory access (DMA) command. The physical channel includes read and write control logic to initiate data transmission from the source device to the destination device in accordance with the DMA command in response to the flow control signal. In one embodiment, a context manager includes: allocation logic configured to arbitrate between allocation requests from virtual channels and to allocate physical channels to selected virtual channels; and routing logic configured to route a flow control signal from the selected virtual channel to the allocated physical channel, and to route a status signal between the allocated physical channel and the selected virtual channel.