21 results about "Application domain" patented technology

Systems and methods for constructing layered prompts to operate as input into a pre-trained large language model (LLM). The method involves obtaining a set of application domains in which the LLM will be used. Using these application domains, a set of guidelines is determined, defining operation boundaries for the LLM. A set of layers is determined, each associated with the guidelines and including variables representing attributes identified within those guidelines. Using these layers, a first layered prompt is constructed to test the initial operation boundaries of the guidelines and is supplied to the LLM to generate a set of responses. Based on the responses, a second layered prompt is dynamically constructed to test additional operation boundaries, ensuring iterative refinement and contextual relevance.

The invention provides a hot updating method, system and equipment for an automation program of semiconductor equipment and a medium. The method comprises the following steps: dynamically loading a new version script code into an isolated runtime environment created by an application domain or a class loader through a reflective API (Application Program Interface) so as to isolate new and old codes. And performing preheating initialization on the new code in an isolated environment, wherein the preheating initialization comprises execution of an initialization function and simulation of a production request test. After preheating is completed, a new request of the production environment is routed to the new version to be processed through atomic switching operation, and meanwhile, the current running version continues to complete existing in-process affairs. According to the method, shutdown is avoided through dynamic loading and isolation, stability is improved through preheating initialization, new requests and in-process transactions are considered in atomic switching, non-shutdown updating of the automatic program of the semiconductor equipment is achieved, production interruption is effectively eliminated, and the equipment utilization rate and operation and maintenance flexibility are improved.

Systems and methods for constructing layered prompts to operate as input into a pre-trained large language model (LLM). The method involves obtaining a set of application domains in which the LLM will be used. Using these application domains, a set of guidelines is determined, defining operation boundaries for the LLM. A set of layers is determined, each associated with the guidelines and including variables representing attributes identified within those guidelines. Using these layers, a first layered prompt is constructed to test the initial operation boundaries of the guidelines and is supplied to the LLM to generate a set of responses. Based on the responses, a second layered prompt is dynamically constructed to test additional operation boundaries, ensuring iterative refinement and contextual relevance.

The invention relates to a computer architecture for verifying image frame and image line data in a single pass. Aspects of this technical solution may increase the processing speed of low latency applications while maintaining the integrity of error correction detection at these higher speeds. For example, in an image processing environment associated with autonomous navigation (e.g., driving), a large amount of image data is to be quickly and accurately processed to maintain a reliable and latest model of the physical environment. Accordingly, embodiments according to the present disclosure may provide high-speed and accurate error correction of input frame data beyond the ability to be implemented by CPU processing or general GPU processing.

Embodiments herein describe a configurable engine integrated into a processor's cache hierarchy. The configurable engine can enable efficient data sharing between main memory, cache memory, and cores. The configurable engine can perform more efficient operations within the cache hierarchy. In one embodiment, the configurable engine is controlled (or configured) by software (e.g., an operating system (OS)) and is tailored to each application domain. That is, the OS can configure the engine according to the data flow profile of a particular application being executed by the processor.

Systems and methods for evaluating a pre-trained artificial intelligence (AI) model using layered inputs. The system obtains a set of application domains in which the AI model will be used, and a set of guidelines that define one or more operational boundaries of the AI model. The system determines a set of layers, where each layer is associated with corresponding guidelines and mapped to a set of variables and benchmarks. Each variable represents an attribute within the guidelines and each benchmark indicates the degree of satisfaction of the AI model with the guidelines. The AI model is dynamically evaluated against these benchmarks using a series of assessments. Subsequent assessments are dynamically constructed based on the outcomes of previous assessments. Scores are assigned to the AI model for each layer by comparing the expected and actual responses. The results are then displayed in a graphical user interface (GUI).

Provided in the present disclosure are an intelligent multi-domain efficient collaborative information transmission method and apparatus, and a storage medium. The method comprises: acquiring N data packets generated by an application domain; determining configuration information of the N data packets in a control domain on the basis of an artificial intelligence technique and a multi-domain joint optimization indicator, wherein the multi-domain joint optimization indicator includes at least one of the following: a throughput, a transmission delay, a weighted transmission delay and a quality of service; and transmitting the configuration information of the N data packets to at least one communication node, such that the at least one communication node determines a transmission resource on the basis of the configuration information of the N data packets, wherein the transmission resource is configured to transmit the N data packets.

A data processing device (1901) for end-to-end user query correction and slot filling is described, the device having one or more processors for: receiving (1801) a user query (301); processing (1802) the user query to determine whether the user query is correct for an application domain language or a natural language; forming (1803) a corrected query (350) based on the processing of the user query; performing (1804) a slot fill operation on the corrected user query to identify one or more slots (306) of the corrected query, where each identified slot corresponds to a portion of the corrected user query; each identified slot of the corrected query is classified (1805) as one of a plurality of categories. In addition to the slot filling task, this approach can handle incorrect input variants in multi-language settings and can handle application domain languages in addition to different natural languages.

The application discloses a program processing method of a domain controller. The method is applied to the domain controller, the domain controller comprises at least two M cores, at least one A core, a first storage medium and a second storage medium, the first storage medium comprises a boot program of the domain controller, the second storage medium comprises M core application programs, a configuration file of the domain controller and A core related programs, and the method comprises the following steps: the A core checks whether each program in the second storage medium can be read and written; if each program in the second storage medium can be read and written, the A core updates to-be-updated programs in the second storage medium based on the configuration file and a downloaded update file; and if at least one program cannot be read and written, a first M core in the at least two M cores executes the boot program of the domain controller, formats the damaged program through the boot program of the domain controller, and updates the to-be-updated programs based on the configuration file and the downloaded update file.

The present disclosure relates to the field of network technologies and discloses an application access control method and system, and a device, a medium and a program product thereof. The present disclosure provides an application access control method. The method includes: generating, by a security management application client, an access request after detecting access to a target application, and sending the access request to a central domain name system; performing, by the central domain name system, domain name resolution on the access request to obtain a target application domain name of the target application, and sending the target application domain name to an application gateway; and determining, by the application gateway, a target access policy for the target application based on a matching result of the target application domain name in a first configuration file, and controlling, based on the target access policy, a terminal device.

The invention relates to the field of data processing, and particularly discloses a category activation method and device, electronic equipment and a storage medium. In response to a category activation request submitted by a user, a user domain module is called to obtain user information; in response to a first selection instruction for selecting at least one candidate account, calling an account domain module to obtain a category list corresponding to the selected target account; in response to a second selection instruction for at least one target category in the non-activated category list, calling the application field submitting module to perform preposition check on the at least one target category corresponding to the second selection instruction, and performing preposition operation when the at least one target category needs preposition operation; in response to submission information fed back by the application domain submission module, calling the user application domain module to activate and check at least one target category corresponding to the second selection instruction; and when the target category is activated and audited successfully, the activation result of the target category is fed back, so that the maintenance cost of the category activation function is reduced.

This invention discloses a neural network reconfigurable configuration mapping method for FPGA resources, relating to the field of embedded artificial intelligence systems. The method includes the following steps: adjusting the FPGA platform according to different task requirements to construct multiple mapping schemes oriented towards resource constraints; establishing a mapping evaluation model by analyzing the resource characteristics of different FPGA platforms, evaluating multiple mapping schemes, and analyzing the differences between different mapping schemes and their performance differences on different FPGA platforms; and constructing a partially reconfigurable mapping adjustment scheme based on the deployment of different neural network algorithms according to the application domain. This invention analyzes the resource characteristics of the FPGA platform and effectively reduces the mapping space by imposing resource constraints. When a certain resource is limited, the accelerator performance boundary is further explored through the replacement of different resources with the same logic. It supports configuration mapping methods under the partially reconfigurable FPGA approach, and by analyzing the resource changes and parameter adjustments after partial reconfiguration of the target platform, a new mapping scheme can be quickly completed.

Embodiments of the present disclosure provide an intelligent multi-domain efficient collaborative information processing method, an apparatus, and a storage medium. The method comprises: acquiring N data packets generated by an application domain; on the basis of the N data packets, determining M feature sets corresponding to the N data packets, each feature set comprising at least one of the following features: a spectrum efficiency requirement, a transmission delay requirement, a reliability requirement, a capacity requirement, an energy efficiency requirement, and a quality of service requirement; in a control domain, on the basis of the M feature sets corresponding to the N data packets, determining M pieces of configuration information for the N data packets, each piece of configuration information comprising signal domain configuration information and resource domain configuration information; and, processing the N data packets on the basis of the M pieces of configuration information for the N data packets and intelligent technologies, N and M being positive integers.

An apparatus comprising a plurality of refinement nodes implemented on processors and memory, each arranged as a vertex in a graph topology. Each refinement node obtains inputs, performs refinement operations, and contributes enhanced outputs into a structured interchange maintained in memory accessible across the graph. The structured interchange is realized through embodiments including network-connected data containers, in-memory caches, or distributed key-value stores. Notification mechanisms signal availability of new or modified artifacts through publish-subscribe messaging, polling, processor interrupts, or equivalent signaling techniques. Refinement nodes opportunistically detect and act upon artifacts without centralized orchestration and without requiring synchronization of identical data copies. Refinement operations are cumulative and domain-specific, ensuring no node negates refinements of another. The apparatus operates as a computer-implemented collective system where successive outputs are progressively refined through iterative graph traversal, producing stable, convergent artifacts across diverse application domains.

Embodiments herein describe a configurable engine that is embedded into the cache hierarchy of a processor. The configurable engine can enable efficient data sharing between the main memory, cache memories, and the core. The configurable engine can perform operations that are more efficient to be done in the cache hierarchy. In one embodiment, the configurable engine is controlled (or configured) by software (e.g., the operating system (OS)), adapting to each application domain. That is, the OS can configure the engine according to a data flow profile of a particular application being executed by the processor.

The application relates to the computer technical field and provides an application filing result identification method and device, equipment and a storage medium. The method comprises the following steps: extracting application description information of a to-be-identified application and a plurality of access domain names involved in a running process from an installation package of the to-be-identified application; matching the plurality of access domain names with a preset third-party service domain name set, screening out each access domain name which does not hit any third-party service domain name as a candidate domain name; selecting a candidate domain name which meets a preset screening condition in the degree of association between the application description information of the to-be-identified application and each candidate domain name as an application domain name of the to-be-identified application; and matching the application domain name with prestored filed application data to obtain a filing result of the to-be-identified application. The above method can solve the problem that a server cannot accurately determine whether an application program has been filed.

This disclosure relates to a training dataset generation, dialogue processing method, device, medium, and product. The method includes: acquiring multiple first dialogue data samples from a target application domain; each first dialogue data sample includes input content and its corresponding response content; inputting the first dialogue data samples into a target generative model to obtain corresponding inference steps; the inference steps characterize the inference process of generating response content from the input content; integrating the first dialogue data samples and their corresponding inference steps to obtain a thought chain data sample corresponding to the first dialogue data sample; the thought chain data sample is data with a triple structure including sequentially arranged input content, inference steps, and response content; and constructing a training dataset corresponding to the target application domain based on each first dialogue data sample and each thought chain data sample. This improves the efficiency of acquiring thought chain data samples for the target application domain.

Disclosed in the present invention are a cloud-native train control system based on domain-driven design, and an implementation method therefor. The train control system comprises: a communication interface service layer; an application domain, which is connected to the communication interface service layer, wherein the application domain comprises several functional modules corresponding to specific entities in the train control system, and the application domain is used for preliminary logic processing in the train control system, and for information interaction with the communication interface service layer; a field domain, which is connected to the application domain, wherein the field domain receives information of the application domain, and on the basis of different requests in the information of the application domain, the field domain calculates and / or verifies state information of a corresponding train; and an infrastructure layer. By means of the present invention, a traditional monolithic train control system is decoupled, and split into a multi-module train control system, such that the coupling between modules is reduced, so as to facilitate upgrades and iterations and control a failure range, thereby providing technical references for the design of a cloud-native train control system.

The application relates to the technical field of cloud computing, and discloses a service request processing method and device based on a large-scale cluster, equipment and a medium. The method comprises the following steps: receiving and analyzing a service request of a client to obtain a service request identifier, request end information and target end information; determining a request path corresponding to the service request; if the service request is determined to be an intra-cluster service request, injecting the request end information and the target end information into header information to obtain a target application domain and a target service corresponding to the service request in a service registration center, calling the target service in the target application domain, and processing the service request through the target service; and if the service request is determined to be a cross-cluster service request, injecting the request end information and the target end information into the header information, injecting the header information into cluster relationship information through a service gateway, and obtaining a target service to process the service request. The application reduces the management difficulty of services in the cluster and is beneficial to improving the efficiency of service request processing.

The invention applies to the context of an electric machine system where the digital control is handled with a FPCU component. This applies to application domains like but not limited to the automotive domain. The invention enables fast and safe time sliced context switching for application tasks mapped in FLU e FPGA matrix, similar as for the task context switching in a microprocessor, with the goal to maximize the usage of all computation resources of the FLU over time.

The invention provides a multi-core SOC safe starting method. The multi-core SOC safe starting method comprises two core stages of safe starting import and safe starting processing. The application domain initiates an import request, the HSM responds to the request, and personalized configuration of secure startup is completed through pre-verification and parameter storage; and safe starting processing: when the system is subsequently powered on, the HSM actively carries out processing, and efficient and credible safe starting is completed through acceleration verification and starting processing. According to the method, the starting speed is greatly improved through an innovative starting acceleration verification processing scheme. Meanwhile, the method has high flexibility and supports abundant configurable parameters so as to adapt to different application scenes.