321results about "Web data retrieval" patented technology

The technology described herein relates to systems, methods, and computer storage media, among other things, for providing search query intent specificity. Embodiments may include identifying a search query performed using a search engine and generating a query vector for the search query by aggregating search result embeddings (e.g., item listing vectors) of search results from the search query. Further, in some embodiments, similarities (e.g., cosine similarities) between the query vector and the item listing vectors can be determined. As such, an intent specificity of the search query can be determined. Further, in some embodiments, the intent specificity can be used to train an intent specificity machine learning model for generating intent specificity scores for other search queries. Based on the intent specificity scores determined using the one or more trained intent specificity machine learning models, determinations can be made with respect to precision and recall, etc.

Techniques for generating personalized content using generative artificial intelligence (AI) are provided. In an example method, a processing device including a personalization module receives an indication that a user interacted with content displayed on a web page. The personalization module receives a set of attributes, comprising information about the user and information about the content, and information about a segment to which the user belongs. The processing module then determines a tuning parameter, wherein the tuning parameter controls the randomness of the output of the generative AI model. The personalization module next inputs to the generative AI model the tuning parameter and a prompt comprising the set of attributes and the information about the segment and subsequently receives personalized content responsive to the tuning parameter and the prompt. The personalization module can then display the personalized content in a dynamic content field associated with the content.

Methods, systems, and computer program products for managing Internet of Things (IoT) network-connected devices.

In one embodiment, a method includes detecting a change in context of a computing system to a current context, changing a first registration status of a first set of actions with an assistant system associated with the computing system based on the change in context to the current context, where the first application is in a foreground of a user interface of the computing system, changing a second registration status of a second set of actions with the assistant system based on the change in context to the current context, where the second application is in a background of the user interface of the computing system, updating a list of registered actions for the assistant system based on the changed first and second registration statuses, and storing the updated list of registered actions on the computing system.

The technical solutions of the present disclosure are directed to providing validated responses to form specific user queries using machine learning. A system can include a processor to receive, via a user interface, a query corresponding to an entry of a form and identify a data structure. The processor can generate, using the data structure, a prompt to validate the entries and identify, based on the prompt and the data structure input a ML model, an error in an entry of the plurality of entries of the form. The processor can generate, based on the error and the data structure input into the ML model, a response to the query comprising a proposed correction to the error in the form, and provide, for display via the user interface, the response to the query indicating the error and the proposed correction.

A method for use in protecting a first machine learning model that is queryable over an application programming interface, API, against an adversary querying the first machine learning model through the API in order to build up a database of query-response pairs. The method includes identifying a user of the API as a potential adversary. In response to a query from the potential adversary, through the API, method includes providing a response from a second machine learning model instead of the first machine learning model, wherein the first machine learning model has been trained on a first dataset and wherein the second machine learning model has been trained on a second dataset that is different to the first dataset.

Systems, methods and computer readable media comprising a virtual exercise board, which is represented by images on the screen of a pad device; wearable devices configured to attach to each shoe of a user and to collect and transmit touch data to the pad device; cameras for tracking movement and calibrating with the data collected by the wearable devices; and computer programs for collecting user data, processing user data, and generating outputs. In embodiments, features include augmented reality; ratings of performance; automated workouts / protocols; real-time progress bar; multi-location database capabilities; and reports.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for using a large language model (LLM) to generate a specificity labeled query-to-document scored teacher training set for training a teacher model. The teacher model, in turn, in sued to generate a specificity labeled query-to-document scored student training set for training a student model. The student model is ensemble trained, using the student model specificity training set and at least one other student model training set does not quantify the query-to-landing page specificity drift, to predict a performance of a query for a landing page.

The invention provides a document processing method and system based on a multi-modal large model. According to the method, firstly, a target type document is converted into a target picture based on a multi-modal large model according to a preset document segmentation rule, then structured text information is extracted from the target picture based on a preset cue word and by utilizing an advanced optical character recognition technology PaddleOCR technology, the multi-modal large model is guided to generate a text abstract for each target picture, and the text abstract is extracted from the target picture. And the integrated graphic and text information and the condensed picture content are converted into a Markdown document comprising a picture link of the target picture and text summary information. Through the steps of format recognition, image-text separation, content condensation and the like, a target type document is converted into a format which is easy to manage and retrieve, rapid retrieval of information is achieved by means of RAG retrieval enhancement, and documents and information related to user query can be rapidly found to serve as candidate answers. Compared with a traditional OCR technology, the method has the advantages that the missing rate of key information is remarkably reduced, and the accuracy of document processing is improved.

A method for personalizing reviews for a user on a social network, comprising the steps of: receiving from at least two or more users a rating and a recommendation for a reviewable item, wherein the rating is numerical value in a rating scale, and wherein a recommendation is a binary endorsement; receiving a request from a user to view the ratings and recommendations for one or more reviewable items; and determining a combined rating and a combined recommendation for all users of the social network at one or more social degrees for the one or more reviewable items.

This flammability determination device comprises: a first determination unit which determines whether or not there is a prescribed deviation of the frequency of posting to a first SNS by a first user, who has made a certain post to the first SNS, from the average of the frequencies of posting by all users of the first SNS; an estimation unit which, if there is the prescribed deviation, estimates an experience value indicating the first user's level of experience in using the Internet, on the basis of the likelihood that the first user will use a second SNS different from the first SNS; and a second determination unit which, if the experience value is less than a first threshold value, determines whether or not the content of said certain post contains a negative expression, and if the content of the certain post contains the negative expression, adds the content of the certain post to a set of post content that is likely to suffer flaming. Thus the flammability determination device makes it possible to collect post content that is highly likely to suffer flaming due to carelessness.

This disclosure describes methods and systems to externally manage network-to-network interconnect configuration data in conjunction with a centralized database subsystem. An example of the methods includes receiving and storing, in the centralized database subsystem, data indicative of user intent to interconnect at least a first network and a second network. The example method further includes, based at least in part on the data indicative of user intent, determining and storing, in the centralized database subsystem, a network intent that corresponds to the user intent. The example method further includes providing data indicative of the network intent from the centralized database subsystem to a first data plane adaptor, associated with the first network, and a second data plane adaptor, associated with the second network.

A text analytics system may predict whether a policy will be adopted. The system may include at least one processor configured to access information scraped from the Internet to identify text data associated with comments expressed by a plurality of individuals about a proposed policy. The at least one processor may be further configured to analyze the text data in order to determine a sentiment of each comment; apply an influence filter to each comment to determine an influence metric associated with each comment; weight each comment using the influence metric; determine based on an aggregate of the weighted comments, an indicator associated with adoption of the policy; and transmit the indicator to a system user.

The present disclosure includes a system for generating and distributing data records representing quotes for legal services. The data records are generated at a server in response to a request from a client device. The data records are based on parameters received from a plurality of platforms, the parameters representing estimated costs for providing services. The server determines a subset of data records to transmit to the client device based on the parameters, the request, and a rating.

A method for monitoring bills and legal regulations according to one embodiment of the present invention is a method for monitoring bills and legal regulations performed by a computing system including at least one memory and at least one processor, and includes the steps of storing template information including predetermined items, receiving basic information including reasons for proposing the bill and main contents from a user terminal, storing the basic information in an analysis server, forming extracted information from the basic information through text mining based on the predetermined items, generating regulatory impact analysis data based on the extracted information and the template information, and outputting a regulatory impact analysis interface for the bill or legal regulation to the user terminal based on the generated regulatory impact analysis data.

A system and method for analyzing large data sets to determine variances is described. In an example implementation, the system may include an observability platform configured to receive a user request to perform a variance analysis in association with a user-selected dataset on an observability platform. Data representing the user-selected dataset may be retrieved based on the request and may include many dimensions of data on the observability platform. Baseline and outlier representative samples may be generated based on the user-selected dataset. A server may be configured to include a variance analysis engine to perform the request for variance analysis. The observability platform may generate a plurality of data visualizations based on a result data set of the variance analysis. The data visualizations may be ranked using one or more disparity data metrics and may be provided for display in an order based on the ranking on the observability platform.

The invention relates to a webpage data analysis method and device, computer equipment and a readable storage medium. The method comprises the steps of obtaining a to-be-processed target webpage and a first analysis rule matched with the target webpage; determining original collection data of the target webpage, and analyzing the original collection data according to a first analysis rule to obtain an analysis result; if abnormal items exist in the analysis result and the number of the abnormal items is greater than an abnormal threshold value, calling a large language model to analyze the webpage structure of the target webpage, and determining the webpage structure change of the target webpage; updating the first analysis rule according to the webpage structure change to obtain a second analysis rule; and analyzing the original collection data based on a second analysis rule to obtain target analysis data. By the adoption of the method, webpage data analysis can be achieved in a self-adaptive webpage structure change mode, and the reliability of data collection is ensured.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a large language model (LLM) to predict high performing keywords from a set of keywords. The predicted keywords are then used for retrieval processes for digital components.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for using a large language model (LLM) to generate a specificity labeled query-to-document scored teacher training set for training a teacher model. The teacher model, in turn, in sued to generate a specificity labeled query-to-document scored student training set for training a student model. The student model is ensemble trained, using the student model specificity training set and at least one other student model training set does not quantify the query-to-landing page specificity drift, to predict a performance of a query for a landing page.

The invention relates to an industry knowledge question-answering method and system based on self-adaption and retrieval enhancement generation, and the method comprises the steps: obtaining input questions, employing a question classifier to judge the types of the input questions, and enabling the types of the input questions to comprise viewpoint type questions, data type questions, and other types of questions; respectively adopting different retrieval strategies for viewpoint questions, data questions and other questions, and outputting question answers based on a large model; and a scoring and rewriting mechanism is introduced to score and rewrite the answers to the questions based on the large model, and final answers to the questions are output. According to the method, the user questions are classified, different retrieval methods are used for each class of questions, and scoring and rewriting mechanisms are introduced, so that the knowledge retrieval efficiency is improved, the computing resources required by retrieval are reduced, and the question and answer accuracy is improved; the problems that knowledge base information is accurate but incomplete, the accuracy of internet information is insufficient, and knowledge conflicts possibly exist between the knowledge base and the internet information in an industry knowledge question and answer scene can be solved.

The invention provides a community evolution mode mining system of a dynamic network and a mining method thereof, and relates to the technical field of data mining. According to the method, a community evolution network is constructed based on a community division result and a community evolution matching method, a meta-community concept is proposed on this basis, and an evolution cluster recognition method with a strong evolution relationship is provided for representing a complex community evolution path. And finally, an evolution sequence frequent pattern mining module processes the evolution event sequence by adopting a frequent pattern mining method so as to identify the student social network community evolution pattern. Through the technical scheme provided by the invention, a community evolution mode recognition problem can be converted into a frequent mode mining problem of an event sequence, a corresponding evolution event sequence is extracted from a complex meta-community structure, and important evolution events and sequential relationships in an evolution relationship are reserved by reducing the complexity of an evolution structure; and an analyst is helped to identify the community evolution mode in the dynamic network.

A method and system for providing web resources having long identifiers through a zero trust network environment. The method comprises receiving a request from a client device to access a web resource through a zero trust network environment, wherein the web resource is external to the zero trust network environment, the request including a first uniform resource locator (URL), and the resource further including a second URL having a first length; fetching the web resource based on the first URL; generating a shortened alternate URL based on at least a portion of the second URL, in response to determining that the first length exceeds a predetermined threshold; generating an alternate resource, the alternate resource including the shortened alternate URL replacing the second URL; and providing the alternate resource to the client device.

Methods for product recommendation are provided. This includes collecting personal user data including profession, gender, size, preferences, user's apparel size, user's address, who the user's friend are, user's friends' information, users' medical records including eyeglass and contact lens prescription information; collecting vendor data including product size, product description, product location, price; and recommending vendor products that best match the users' personal data.

An improved technique for identifying a user's mobile device is discussed. A persistent and unified identifier that bridges mobile app to mobile web and to other web browser-compatible mediums is utilized. Using a unique verification identifier, the unified identifier is consistently verified, revived and distributed across application and browser mediums.

A method for enabling collaboration between individuals to design, construct and maintain a building. The method comprises providing a network based computer system including at least one server and multiple clients. The multiple clients allow respective individuals to interact with the server. The server includes a machine-readable storage, which is encoded with software for execution by a CPU for allowing individuals at the respective clients to create, execute and manage projects associated with at least one of a design phase, construction phase and maintenance phase of the building. Each project comprises one or more events that are related to time. The method also comprises storing in the machine-readable storage events as they occur during execution of each project to create a building project database spanning at least the design phase and the construction phase and optionally the maintenance phase of the building.

Systems and methods for generating analytical data based on captured audit trails are described. An exemplary method includes generating a natural language preference for the natural language of a document based on an opening action performed by an end user using a client device associated with the end user during a user session; generating a unique transaction key in response to the opening action; correlating subsequent actions relative to the document via the unique transaction key; generating content rich analytical data from an audit trail generated during the user session; obtaining informational content for the end user from informational content stored in a database; translating the obtained informational content; reformatting a native extensible markup language format of the obtained informational content obtained from the database; and providing the translated and formatted informational content to the end user.

Systems and methods are disclosed for processing a search request received from a user. A method includes providing access to content items associated with metadata. The method includes providing information about at least one search previously performed for a user, and providing access to information describing relationships between at least one of the content items and the metadata. The method includes receiving a present input from the user intended to identify a desired content item. Upon determining that results from the previous search did not satisfy the search request from the user, the method includes determining an intent shared by the previous search and the present input based on comparing (i) the relationship information, (ii) the previous search, and (iii) the present input. The method also includes selecting and presenting a subset of content items based on comparing the shared intent and the metadata.

The invention relates to a method for operating a navigation system (1) wherein, after entering a navigation destination (2), information (6) about business opportunities located in the vicinity of the navigation destination (2) is output to a user.The method according to the invention is characterized in that the navigation system (1) transmits at least one piece of information (5) characterizing the navigation destination (2) to an AI model (3) and the AI ​​model (3) determines the information (6) relating to the business opportunities from the Internet depending on the information (5) characterizing the navigation destination (2) and transmits it back to the navigation system (1) for output, wherein the AI ​​model (3) is at least trained to receive and interpret the information (5) characterizing the navigation destination (2) and, depending on the interpretation result, to carry out an Internet search and provide the results found as a response.