23 results about "Real-time Search" patented technology

Disclosed is a system and / or a method for near-instant trademark approval and rejection via ai-powered legal reasoning. The platform includes a user-facing interface enabling an applicant to input a proposed trademark comprising a word mark, logo, and slogan with a textual description of associated goods and services, and optionally visual proof of use in commerce. A classification engine powered by a natural language processing model assists in selecting classes of goods and services from standardized taxonomies. A backend examination engine performs real-time searches, analyses across databases of registered, pending, common law marks using a large language model, and design recognition algorithm. An autonomous legal reasoning module powered by the large language model interprets trademark law precedents, disclaimer requirements, registration criteria, and simulating multi-perspective legal analysis. An outcome generation engine delivers within a predefined time frame a preliminary approval with automated registration, preliminary refusal with detailed explanation, and recommended amendments.

Technology is disclosed for dynamically creating and / or validating new URLs based on a user's query and / or contextual data. This enables the discovery of relevant content that may not be pre-existing in the search engine's index. This process enhances the search engine's ability to deliver the most current and relevant results by generating potential content sources in real-time, validating them, and incorporating the discovered content into the index for immediate query execution. Various embodiments are additionally or alternatively directed to a process that involves iteratively discovering, crawling, and indexing new content by following links from seed URLs, which may be either pre-existing or generated. This process deepens the search engine's index by continuously exploring outlinks, fetching new content, and updating the index in real-time.

The invention provides a ship berthing auxiliary decision-making method and device, electronic equipment and a storage medium, and belongs to the technical field of ship berthing route control, and the method comprises the steps: obtaining a multi-modal environment and ship navigation sensing data; the method comprises the following steps: extracting carbon emission factors on the basis of a multi-modal environment and ship navigation sensing data, then constructing a carbon emission scoring model according to a nonlinear collaborative amplification effect among the carbon emission factors, and generating a low-carbon semantic map; a path evaluation function fusing a ship energy efficiency model and carbon emission-berthing time window compliance constraint is utilized, path section carbon emission and berthing time window compliance serve as a search basis, a berthing path enabling the path evaluation function value to be minimum is searched in real time, and the optimal navigational speed and steering angle are generated for each path section; therefore, ship berthing aided decision-making under low-carbon compliance guidance is realized. According to the method, comprehensive optimization of low-carbon property, compliance and performability can be realized, and the port and navigation system is assisted to be upgraded to a green and intelligent direction.

Systems and techniques are provided for processing streaming data. For example, a process can include obtaining, by an edge device, a plurality of data streams corresponding to objects, activities, or events registered in an edge environment associated with the edge device. One or more machine learning networks implemented on the edge device can generate a plurality of features and / or embeddings corresponding to each respective data stream of the plurality of data streams. The edge device can determine a subset of salient content from the plurality of data streams, based on analyzing the plurality of features and / or embeddings generated for each respective data stream. The edge device can generate index information corresponding to the determined subset of salient content. The subset of salient content and the generated index information can be stored locally at the edge device for search and retrieval based on local queries received at the edge device.

The invention provides a formula editor implementation method based on a knowledge graph. According to the method, a formula editor is realized on the basis of the knowledge graph, operation is simplified through a semantic node relationship, a user can configure a formula only through scenario node selection without professional programming knowledge, and a use threshold is reduced by combining double strategies of dynamic sorting (association strength + use frequency) and fixed classification sorting and cooperating with a real-time search function; logic errors are verified in real time, and accuracy and configuration efficiency are improved by means of an AST disassembling formula structure and in combination with a formula library reuse function; business logic is dynamically defined, new functions do not need to modify codes, expansion can be achieved only by updating knowledge graph data, upgrading iteration is simplified, and maintenance cost is reduced; metadata accurately matches an editing scene, a front end displays a domain concept in real time, deep fusion of a business scene and formula editing is realized, logic deviation is avoided, and a reliable data basis is provided for decision making.

This invention belongs to the field of computer technology and discloses a financial information aggregation and recommendation method and system based on unsupervised cross-modal learning. It constructs a multi-channel data collection crawler engine to dynamically acquire heterogeneous data from cross-platform data sources; deploys a heterogeneous dual-engine architecture of semantic and numerical engines to perform semantic parsing and extract transaction features from the acquired heterogeneous data; constructs a cross-modal dynamic alignment matrix to generate a joint representation vector; acquires real-time search keywords and click behaviors to form short-term intent, analyzes historical cross-platform behavior trajectories to form long-term preferences, and constructs a two-layer intent recognition network based on short-term intent and long-term preferences; and outputs dynamic recommendation results integrating business objectives and user satisfaction indicators. This invention, based on unsupervised cross-modal learning technology, achieves cross-platform multi-channel financial information aggregation, deep user intent analysis, and personalized recommendation, thereby solving the problems existing in the prior art.

The invention discloses a mail system advanced threat traceability and detection method and system based on a dynamic attribute graph, and relates to the technical field of network security, and the technical scheme is characterized in that the method comprises the steps: collecting an operation log of a mail server in real time, and extracting a standardized field; based on a predefined graph ontology, mapping a log entity into nodes such as a user, a network address, a session, a resource and the like, mapping an operation behavior into a directed edge with a timestamp and a weight, and constructing a dynamic traceability graph; defining a malicious sub-graph topology template for a specific attack mode; searching matched connected sub-graphs in real time in the traceability graph by using a sub-graph isomorphic matching algorithm; and when matching succeeds, generating an alarm and extracting a sub-graph as a traceability evidence. According to the method, discrete log behaviors are correlated through a graph theory method, complex attack behaviors such as silence rule thunder burying, parasitic account aggregation and geographical kinetic energy abnormity can be effectively recognized, and the initiative and accuracy of mail security defense are remarkably improved.

The invention relates to the technical field of intelligent recruitment, in particular to a multi-platform candidate information intelligent synchronous search method and system. Comprising the steps that a candidate search request input by a user is obtained, and the search request comprises at least one search keyword; based on a preset multi-platform feature database, the real-time search weight of each recruitment platform is dynamically determined, and the multi-platform feature database collects and updates the candidate activeness of each recruitment platform, the platform attribute features and the historical search click rate of a user to each platform in real time; according to the real-time search weight, distributing the search request to a corresponding recruitment platform for synchronous search, and obtaining candidate information returned by each platform; performing multi-dimensional deduplication processing on candidate information returned by each platform, wherein the multi-dimensional deduplication processing comprises dominant feature matching and implicit feature semantic similarity calculation; according to the method, the candidate information acquisition quality and speed can be remarkably improved, and more reliable support is provided for enterprise recruitment decision making.

The application discloses an intelligent information interaction method and device, and relates to the technical field of Internet, and comprises the following steps: extracting preset content in voice or video recording information, adding a plurality of first label information after processing; performing intrasite real-time search on the first label information, and delivering feedback results to a digital person to perform information interaction; obtaining user information and real-time position information of a login user to continue adding a plurality of second label information, obtaining updated voice or video, and importing the updated voice or video into a content candidate pool; obtaining third label information of other login users, and judging whether the third label information is consistent with the first label information and the second label information; when the third label information is consistent with the first label information and the second label information, judging whether the updated voice or video in the content candidate pool is automatically pushed, if yes, pushing the updated voice or video in the content candidate pool to matched login users, if not, jumping to the first step when there is an input requirement; when the third label information is inconsistent with the first label information and the second label information, performing extracorporal real-time search.

The invention discloses a dynamic commodity recommendation method and system based on model multiplexing, and the method comprises the steps: obtaining behavior sequence data of a user in a preset event window, and extracting a feature code of the recent commodity preference of the user; and injecting a task specific adapter library based on the basic recommendation model, training the basic recommendation model by using the feature codes of the recent commodity preferences of the user, generating a new adapter, and storing the new adapter in the task specific adapter library. And selecting the adapter with the highest similarity as a historical adapter and storing the historical adapter into the task specific adapter library by utilizing the interest label vectors of the adapters in the task specific adapter library and the real-time search query word. And fusing the historical adapters and the new adapters to obtain recommended adapters, and loading the recommended adapters into the basic recommendation model to obtain a unified recommendation model. And using the unified recommendation model to predict and sort interested commodities of the user to generate a recommendation list. According to the method, recent data are quickly and finely adjusted through the lightweight adapter library, the short-term interest change of the user is sensitively captured and responded, and the recommendation result is more accurate.

This invention discloses an adaptive reinforcement learning-driven multi-objective optimization method for accelerators, belonging to the technical field of accelerator optimization design. First, it analyzes the mechanism of action of key design variables such as convolution loop unrolling factor, quantization accuracy, and cache partitioning, establishes a system-level state modeling method, and designs the DDPG framework suitable for continuous action space optimization as a learner for the configuration strategy. Simultaneously, a lightweight searcher is implemented by running Python scripts on the CPU to search and allocate the block parameters of Loop-3 and Loop-4 in real time, thereby reducing the computational burden on the reinforcement learning agent. Finally, an adaptive configuration method driven by reinforcement learning and a corresponding search process are proposed to achieve joint optimization of unrolling scale, quantization accuracy, and block parameters.

A search request received at a computer of a search support system is processed by analyzing the received search request to identify request parameters and connecting to a system index of the search support system that is referenced in the request parameters. An external result provider (ERP) process is initiated that establishes communication between the search support system and a data source external to the search support system, for a virtual index referenced in the request parameters. Thus, the ERP process provides an interface between the search support system and external data sources, such as by third parties. The ERP process can operate in a streaming mode (providing realtime search results with minimal processing) and / or a reporting mode (providing results with a greater delay and processing extent) and can switch between modes. The search request results are received from the connected system indexes and the referenced virtual indexes.

A system for real-time indexing and synchronization of relational databases with a search engine cluster. The system can retrieve datasets using NTILE queries, serialize the data, and load the data into the search engine index via a bulk API. Changes in the relational database can be captured using triggers and stored in a delta metadata table with table identifier, record identifier and type of change. Periodic scans of the delta metadata table can identify the changed records, which can then be retrieved and used to update the search engine index. The system can support parallel processing of data chunks and dynamic adaptation to new database fields without code changes. Users can search the indexed data through an interface that allows attribute-based filtering and hierarchical display of search results.

1. The name of the design product: Loran time signal monitoring receiver (enhanced). 2. The use of the design product: for real-time search, capture, tracking and locking of all-view multi-chain eLORAN signals, and real-time output of monitoring data. 3. The design points of the design product: in the shape of the product. 4. The picture or photo that best indicates the design points: front view.

The application discloses an underwater target searching path planning method and system based on an ant colony algorithm, belongs to the technical field of ship and ocean engineering, and is used for planning an underwater target searching path and comprises the following steps: a heterogeneous grid graph is constructed by fusing target probability, water depth, obstacles and ocean currents; an independent ant colony is allocated to each underwater equipment, path pheromone and allocation pheromone are maintained, and the joint solution of regional segmentation, equipment allocation and path planning is realized through coupled state transition probability; an equipment task depth adaptation constraint is introduced to ensure that professional equipment is used for professional water depth; a meeting type bidirectional path construction strategy is adopted to accelerate convergence; a probability graph is updated through Bayes posterior according to real-time search feedback, and local re-planning is triggered. The application greatly improves cumulative discovery probability, convergence speed and resource adaptability, has the beneficial effects of strong dynamic response capability, zero deep violation of equipment, high coverage rate of high-probability areas and the like, and can be widely applied to underwater searching emergency tasks.

Technology is disclosed for dynamically creating and / or validating new URLs based on a user's query and / or contextual data. This enables the discovery of relevant content that may not be pre-existing in the search engine's index. This process enhances the search engine's ability to deliver the most current and relevant results by generating potential content sources in real-time, validating them, and incorporating the discovered content into the index for immediate query execution. Various embodiments are additionally or alternatively directed to a process that involves iteratively discovering, crawling, and indexing new content by following links from seed URLs, which may be either pre-existing or generated. This process deepens the search engine's index by continuously exploring outlinks, fetching new content, and updating the index in real-time.

The application provides a cargo source recommendation method and device and electronic equipment, and belongs to the technical field of logistics transportation. In the method, the real-time search request of a target driver is received, and a first preset number of first historical click behavior data corresponding to the target driver is obtained. Each first historical click behavior data and the real-time search request are subjected to generalization processing to calculate a total generalization score, and the first historical click behavior data is filtered according to a preset generalization score to obtain second historical click behavior data with higher relevance to the real-time search request and determine a second behavior sequence. Finally, the second behavior sequence is input into a target recommendation model to generate a recommendation result sorted according to the relevance. The method provided by the application can effectively utilize the second historical click behavior data with a longer coverage range and higher relevance to the real-time search request to model the long-term interest and periodicity of the driver under the condition that the online inference performance is limited, thereby effectively improving the accuracy of the cargo source recommendation result.

The invention provides a real-time search engine method based on multi-mode joint embedding and incremental learning. The method comprises the following steps: S1, judging data information shot by a camera module of an intelligent mobile terminal; s2, performing image recognition according to the frame image data in the step S1 to obtain image recognition information; s3, judging that the intelligent mobile terminal obtains character data information; and S4, according to the article graph in the image identification information in the step S2 and the description of the article graph in the statement data in the step S3, carrying out final coincidence degree calculation so as to realize the display of article search. The video or image data shot by the camera module of the intelligent mobile terminal and the audio data obtained by the audio input module can be quickly processed, instant search and feedback are realized, and the user experience is enhanced.

The invention discloses an artificial intelligence module operation parameter adaptive control method, and relates to the technical field of parameter control, and the method comprises the steps: predicting future operation index values of an artificial intelligence module under different operation parameter adjustment variables based on a state representation vector and a preliminary control vector, and taking the preliminary control vector as an initial point, the method comprises the following steps of: constructing a multi-objective optimization problem by using a multi-objective optimization algorithm and using a Pareto solution set of the multi-objective optimization problem to perform real-time search and obtain a final control vector, and issuing the final control vector to an execution mechanism of an artificial intelligence module to perform physical adjustment; according to the method, collaborative optimization of energy efficiency and performance is realized by searching the optimal tradeoff control scheme, and the core problem that safety and efficiency are difficult to consider under multi-target conflicts, working condition switching and abnormal working conditions is solved.

The invention belongs to the technical field of computers, and discloses a financial information aggregation recommendation method and system based on unsupervised cross-modal learning, and the method comprises the steps: employing a dynamic crawler to obtain heterogeneous data of a cross-platform data source through constructing a crawler engine for multi-channel data collection; deploying a heterogeneous double-engine architecture of a semantic engine and a numerical engine, performing semantic analysis on the obtained heterogeneous data, and extracting transaction features; constructing a cross-modal dynamic alignment matrix to generate a joint representation vector; acquiring a real-time search keyword and a click behavior to form a short-term intention, analyzing a historical cross-platform behavior track to form a long-term preference, and constructing a double-layer intention recognition network according to the short-term intention and the long-term preference; and outputting a dynamic recommendation result of the integrated service target and the user satisfaction index. According to the method, on the basis of an unsupervised cross-modal learning technology, cross-platform multi-channel financial information aggregation, user intention deep analysis and personalized recommendation are realized, so that the problems in the prior art are solved.

This invention discloses an underwater target search path planning method and system based on ant colony optimization, belonging to the field of marine engineering technology. It is used for planning underwater target search paths, including constructing a heterogeneous grid map integrating target probability, water depth, obstacles, and ocean currents; assigning an independent ant colony to each underwater device, maintaining path pheromones and allocation pheromones, and achieving joint solution of region segmentation, equipment allocation, and path planning through coupled state transition probabilities; introducing equipment task depth adaptation constraints to ensure specialized equipment is used in specialized water depths; employing a meeting-based bidirectional path construction strategy to accelerate convergence; updating the probability map based on real-time search feedback using Bayesian posterior regression, and triggering local replanning. This invention significantly improves cumulative discovery probability, convergence speed, and resource adaptability, possessing beneficial effects such as strong dynamic response capability, zero equipment violations at excessive depths, and high coverage of high-probability areas, and can be widely applied to underwater search emergency missions.

The invention relates to a relative navigation sensor target automatic search method, which uses a relative navigation sensor to carry out target search, and executes target automatic search attitude control operation if a target is not recognized in a view field range. Determining the motion speed of the target search view field, the amplitude of the motion range of the target search track and the initial phase angle; then, the initial position of the search trajectory, the attitude pointing quaternion at the initial position, the attitude pointing quaternion during operation along the search trajectory and the angular velocity are calculated respectively; and finally, the tracking aircraft performs attitude control according to the parameters, performs real-time search relative to the navigation sensor in the flight process, and determines whether the target automatic search attitude control operation is ended or not according to the search result and time. According to the method, the relative navigation sensor is assisted in target search through the target automatic search attitude control operation, so that the probability that the relative navigation sensor searches the target is improved, and the target recognition precision is improved.

The application relates to the technical field of information retrieval, in particular to an SEO keyword intelligent analysis system based on an edge AI chip, which comprises three core modules: a data acquisition module that acquires user behaviors, webpage contents and device environment data in real time; an edge computing module that is internally provided with an AI chip, processes data in a local device, generates user preference features, and generates optimized queries in combination with search keywords; and a search result processing module that sends the optimized queries to a search engine and processes the results individually, wherein the application sinks AI computing power to terminal devices, constructs a closed loop system of real-time acquisition, local intelligent processing and personalized result enhancement, and solves the long-term contradiction between personalized service and user privacy protection. Sensitive data is processed locally without being uploaded to the cloud, thereby eliminating the risk of privacy leakage from the source; the edge AI chip realizes real-time search individualization with extremely low delay and high precision, and significantly improves the intelligent level of the search engine and the user satisfaction.