23 results about "Search ranking" patented technology

The invention relates to the technical field of information retrieval, and provides an intelligent searching and sorting method and system for a library. Obtaining environment parameters of a search terminal and query statements and historical retrieval records input by a user; generating a dynamic environment matrix based on the environment parameters, and generating an intention vector based on a query statement and the historical retrieval record; constructing a knowledge graph based on the metadata of the library, extracting a literature feature vector from the knowledge graph, and performing linear processing on the intention vector and the literature feature vector to generate a literature association graph; generating a comprehensive weight vector based on the statistical parameters extracted from the literature association map and the dynamic environment matrix; and performing comprehensive evaluation based on the comprehensive weight vector and the score of the literature in the preset dimension, and displaying a search result on a user interface according to the retrieval score of the literature. According to the scheme, the search result is highly matched with the user requirement and the scene, and the accuracy and the search efficiency of library intelligent search are remarkably improved.

Artificial intelligence (AI) techniques for connection networking are described. A method comprises generating a first training prompt based on a set of guidelines for a network service of a connection network system, the guidelines defining an objective for the network service, sending the first training prompt and a first set of training datapoints from a first training dataset to a first generative AI model, a training datapoint from the first set of training datapoints comprising a content item, receiving a second set of training datapoints for a second training dataset from the first generative AI model, wherein a training datapoint of the second training dataset comprises a first label for the content item generated by the first generative AI model based on the objective, and training a second generative AI model using the second set of training datapoints based on the objective. Other embodiments are described and claimed.

A method is presented for enhancing search results by segmenting documents into smaller passages and utilizing those passages as the search unit. This method integrates the passage rankings from two search models to produce a new document ranking and arranges the documents accordingly. The ranking of document is also rearranged based on the proportion of passages taken from the same document versus the total number of passages in that document. The final search ranking system combines document-level and passage-level search rankings to rank documents. This method ensures that when conducting a passage search, the search results consider the general relevance of the entire document, which leads to better performance compared to searching only by document-level or passage-level searches.

A method is presented for enhancing search results by segmenting documents into smaller passages and utilizing those passages as the search unit. This method integrates the passage rankings from two search models to produce a new document ranking and arranges the documents accordingly. The ranking of document is also rearranged based on the proportion of passages taken from the same document versus the total number of passages in that document. The final search ranking system combines document-level and passage-level search rankings to rank documents. This method ensures that when conducting a passage search, the search results consider the general relevance of the entire document, which leads to better performance compared to searching only by document-level or passage-level searches.

Embodiments of a method for automatic search engine optimization (SEO) of funnel websites in a tiered software framework comprises: generating at a first tier, a prompt for an artificial intelligence (AI) model to provide recommendations for improving search rankings of a seed website; receiving from the AI model, SEO format recommendations, and SEO content recommendations; generating websites by modifying the seed website according to a unique selection from the SEO format recommendations and the SEO content recommendations; associating each website with a corresponding SEO score based on performance in a web search; ranking and sorting the websites according to the respective SEO scores; generating choices of the ranked websites; providing the choices to a second tier and receiving a selection therefrom for a number of iterations; and deploying, by the funnel website application the final selection at a public universal resource locator.

The present invention provides a system and method for optimizing content to improve search results of a natural language interaction application such as ChatGPT. The method includes processing user data using natural language techniques to identify user intent, sentiment, and other relevant information. The system generates a dynamic response tailored to the specific user and context based on the user's intent, personal profile, and contextual information. The present invention provides a unique approach to optimize content for ChatGPT-based search engines, leading to higher search rankings and increased user engagement. The system also includes local engines that interact with ChatGPT to ensure the accuracy of their classification functions, such as sentiment analysis and tone detection, and machine learning algorithms to improve the system's performance continuously.

A system constructs a topic graph from SERP data on high-ranking keywords. Clusters are formed by measuring either overlap of result links or semantic proximity via keyword embeddings. Each keyword must meet a similarity threshold to its assigned cluster, though not to every peer, producing deliberately loose groupings. Consequently, a single topic gathers keywords that express different facets of one concept, so content covering all facets is more attractive to users and more likely to earn high search rankings for any included term. The system further supplies an interface that lets users browse, filter, and search the topic graph, and view topics prioritized by ROI estimates generated from traffic, competition, and relevance signals.

The present invention provides a server device, a learning assistance method, and a recording medium, which can immediately and easily confirm and effectively learn to what extent a sentence set by oneself as a learning object is searched by other users. When a user attribute of a summary object is set in a communication terminal, a user specifies a sentence and instructs "sentence search", a learning assistance server (10) searches the specified sentence with an encyclopedia, and determines whether the specified sentence is included in the top of a search ranking and whether the specified sentence is included in the top of an average search frequency ranking based on search history data of the summary object. When the specified sentence is included in the top of the search ranking, the server (10) displays a message (M1) notifying of the top of the search ranking in the summary object together with a search result of the specified sentence in the communication terminal (20), and when the specified sentence is included in the top of the average search frequency ranking, a message (M2) notifying of the top of the average search frequency ranking in the summary object is displayed.

A system and method for facilitating natural language conversations between customers and vendors for product purchases is provided. The system ingests product catalogs from vendors, normalizes the data, and provides a conversational interface for customers to query the catalogs. In some examples, a chatbot system receives a natural language query from a customer about a product in a chat interface, identifies vendors offering that product by searching uploaded product catalogs, determines available inventory for the product by querying the catalogs, and generates a natural language response to the customer using the vendor and inventory information. The system can extract product details from the query, search based on those details, rank and recommend vendors and products, update user profiles, offer purchase incentives, and complete transactions within the conversation. The system handles the conversational and technical aspects to enable natural dialog between businesses and customers regarding products.

The present application discloses a method for interacting with hot search terms and its apparatus, device, and medium. The method includes: responding to a face presence event acting on a camera view frame, identifying eye features in the camera view frame, and locating the gaze point where the eye features act on a current graphical user interface; responding to a gaze event where the gaze point acts on a hot search term control in a hot search ranking window, displaying the term-specific animation effects corresponding to the hot search term control in the current graphical user interface, and the hot search ranking window is displayed in the current graphical user interface; responding to a sustained gaze event where the gaze point acts on the hot search term control, displaying the term interaction window corresponding to the hot search term control in the current graphical user interface. The present application tracks the gaze point of a user when browsing a hot search page to interact with controls, so as to display relevant content of the hot search, enhance the interactivity of the hot search page, and improve the effectiveness of user browsing and reading information.

Embodiments of a method for automatic search engine optimization (SEO) of funnel websites in a tiered software framework comprises: generating at a first tier, a prompt for an artificial intelligence (AI) model to provide recommendations for improving search rankings of a seed website; receiving from the AI model, SEO format recommendations, and SEO content recommendations; generating websites by modifying the seed website according to a unique selection from the SEO format recommendations and the SEO content recommendations; associating each website with a corresponding SEO score based on performance in a web search; ranking and sorting the websites according to the respective SEO scores; generating choices of the ranked websites; providing the choices to a second tier and receiving a selection therefrom for a number of iterations; and deploying, by the funnel website application the final selection at a public universal resource locator.

The invention provides a hierarchical video search ranking optimization method and device, and the method comprises the steps: generating an initial similarity ranking based on a descending order of similarity scores of a query statement and candidate video clips; performing semantic annotation on a preset number of candidate video clips before the initial similarity ranking by using a multi-modal large language model, and screening based on an annotation result to obtain the most difficult semantics and the most easy semantics; and updating the initial similarity score by using the most difficult semantics and the most easy semantics to strengthen the recognition capability of the most difficult semantics and suppress the interference of the most easy semantics, and generating a search result of the video clip based on the updated initial similarity score. According to the method, the candidate video clips are subjected to semantic annotation through the multi-modal large language model, and the most easy semantics and the most difficult semantics are obtained by screening the accuracy of each basic semantics of the query statements, so that the correct semantic information implied in the negative sample is effectively mined, and a fine-grained supervision signal is provided for video ranking optimization.

This invention discloses a search ranking model generation method, ranking display method, apparatus, and device. The method includes: acquiring multiple historical input items entered by a user in a search box, a list of historical suggestion words corresponding to each historical input item, and historical search items determined by the user in the historical suggestion word list; forming positional bias-eliminating sample data based on the historical input items, the historical suggestion word list, and the historical search items; and training a deep learning model based on the positional bias-eliminating sample data, using a ranking loss function as the optimization objective, to obtain a search ranking model. This method, by focusing on positional bias information in the sample data, can generate a search ranking model that better conforms to relevance ranking, thereby facilitating the obtaining of suggestion word ranking results that better meet user needs through this search ranking model.

A technique for search ranking media content items is described. In accordance with the described techniques a media content item previously absent from a media content library is received. A popularity value of the media content item is estimated based on the artist popularity value and one or more album popularity values for one or more albums of the artist released prior to the media content item and based on an elapsed duration after receiving the media content item satisfying a threshold duration. A search request for a media content item is received. One or more search results are populated in response to the search request. The one or more search results include the media content item and one or more additional media content items ranked based on the estimated popularity value of the media content item and respective popularity values of the one or more additional media content items.

The application relates to the field of artificial intelligence, and provides a search sorting method and device, a server and a storage medium, the method comprising the following steps: when a content search request is acquired, acquiring a plurality of target network resources; acquiring a respective heat feature vector corresponding to each target network resource; running a preset click probability prediction model to process the respective heat feature vector corresponding to each target network resource, so as to obtain a prediction probability of user clicks on each target network resource; sorting the target network resources according to the prediction probability of user clicks on each target network resource, obtaining a search sorting result, and outputting the search sorting result. The application also relates to the field of blockchains, and the storage medium can store data created according to the use of a blockchain node. The method improves the accuracy of the search sorting result.

A computing system is provided including processing circuitry configured to implement a ranker module configured to jointly compute relevance scores of a set of candidate keywords to a query, and to generate a ranked list of candidate keywords based on the relevance scores. The ranker module includes a cross attention encoder configured to jointly compute the relevance scores by obtaining contextual embeddings for query tokens in the query and union of keyword tokens in the set of keywords, selectively pooling the contextual embeddings for the query tokens and the union of keyword tokens, inputting the selectively pooled contextual embeddings into a classifier that has been trained to predict a relevance score of the plurality of keywords to the query based on the contextual embeddings to output a relevance score for each query-keyword pair for the keywords in the set of candidate keywords, and outputting the ranked list of candidate keywords.

The present disclosure relates to systems and methods for improved searching. In some implementations, the approaches herein can be used to rank search results to provide more relevant results to users, for example by monitoring the interactions of one or more users with pages or other items. In some implementations, the approaches herein can be used to refine and improve the performance of a search result ranking model over time.

The present application provides a search ranking method, device, and question-answering system. The search ranking method includes: obtaining search results based on a user query text; determining whether the user query text is a time-sensitive query text; if the user query text is a time-sensitive query text, ranking the search results based on their relevance scores and timeliness scores to obtain a ranking result; if the user query text is not a time-sensitive query text, ranking the search results based on their relevance scores to obtain a ranking result; wherein the ranking result is used to assist a large model in generating a reply text corresponding to the user query text. The present application can improve the accuracy of reply text generation by the large model.

The present application discloses an e-commerce site promotion configuration method and its device, equipment, medium, and product, the method comprising: constructing a search text according to the product words and attribute words of the product title in the product display page; obtaining statistical data matching the search text, the statistical data comprising a plurality of candidate long-tail words and their historical search statistical indicators; determining the only candidate long-tail word semantically matching the product title as the target long-tail word according to the statistical indicators; configuring the target long-tail word to the page title of the product display page. The present application can determine the long-tail keyword based on the product title corresponding to the product display page, automatically configure it as the page title of the product display page, realize search engine keyword optimization, utilize the long-tail effect, and exert the effect of high search ranking through the long-tail keywords of a large number of single product display pages, so as to achieve the effect of improving the search engine drainage ability of the entire independent site of the e-commerce platform.

The application provides a search ranking method based on knowledge community discovery, which comprises the following steps: forming a knowledge community based on a domain knowledge graph in a domain to be searched; generating a topic and a description text for each knowledge community by using a large model; generating a semantic space vector according to the topic and the description text of each knowledge community; generating a semantic vector of a query word according to a user input query word, and recalling a candidate data set; retrieving n knowledge communities most similar to the query word as relevant knowledge communities from the candidate data set according to the semantic vector of the query word; selecting m nodes from the n relevant knowledge communities to obtain a node set; obtaining a knowledge-enhanced candidate document set by taking an intersection of the retrieved content and the node set; calculating the scores of the documents in the knowledge-enhanced candidate document set by using a knowledge-enhanced ranking method, and ranking the documents to complete the search ranking based on the knowledge community discovery.

The application discloses a data-communicative-based cyber search sorting method and system, which comprises the following steps: determining a search result data set matched with a search text used for describing a target digital object to be searched from a registration table of a cyber network distributed in multiple scattered data spaces; determining the query similarity of the metadata of each digital object in the search result data set to the search text, and determining the pragmatic weight value of each digital object in the search result data set; determining the search result evaluation value of each digital object in the search result data set according to the query similarity and the pragmatic weight value of each digital object in the search result data set, so as to obtain the sorting result of the digital objects in the search result data set. The application is based on the premise that the data in the data space is not out of the domain, so that the data sorting in the cyber search process is matched with the actual data use relationship, and the precision rate of the cyber search and the user satisfaction are improved.

Methods and systems for client side search ranking improvements are disclosed. In one example, a search query is received from a user on a client device. The local search results are filtered based on the received search query and one or more local ranking rules. Features for each filtered local search result are computed. The computed features of each filtered local search result are input to one or more machine learning (ML) models. Each ML model can generate a score for each filtered local search result. The filtered local search results are ranked based on the generated score within a category. In one example, local search results and remote server search results are obtained. The local search results and remote server search results are ranked using at least one machine learning (ML) ranking model. The ranked local search results and remote server search results are displayed on the client device by category.

The present application provides a search ranking method and device that can be used in the financial field or other fields. The method includes: receiving a target search statement; obtaining multiple recall statements from a preset operation and maintenance knowledge base based on the target search statement; determining the operation and maintenance knowledge words corresponding to the target search statement and each recall statement, as well as the word weight and word vector of each operation and maintenance knowledge word based on a pre-stored operation and maintenance knowledge graph, a word vector set, the target search statement, and each recall statement; and determining and outputting the ranking results of the multiple recall statements based on the word weight and word vector of each operation and maintenance knowledge word. The present application can improve the efficiency and accuracy of search ranking, thereby improving the reliability of data center operation and maintenance.