7363 results about "Index term" patented technology

A process is described for assessing the suitability of particular keyword phrases for use in serving contextually relevant content for display on particular web pages. In one embodiment, the process involves determining frequencies of occurrence of particular keyword phrases within a peer group of pages associated with a target URL. Popularity levels of the phrases, as assessed using other sources of information, may also be considered. A process is also disclosed in which selected keyword phrases on a web page are transformed into links that can be selected by a user to view bundled content that is related to such keyword phrases.

When a network resource request having a domain name is received, it is determined whether the network resource can be accessed from the domain name. Rather than displaying an error message or processing a search request in response to determining that a network resource can not be accessed, the domain name can instead be redirected to a registration service for domain names or keyword advertiser registration.

A method and system is provided to monitor speech and detect keywords or phrases in the speech, such as for example, monitored calls in a call center or speakers / presenters using teleprompters, or the like. Upon detection of the keywords of phrases, information associated with the keywords or phrases may be presented to a display device so that a user may dynamically receive new information as context of the speech progresses. This provides dynamic information as the context of the conversation develops. The information may be presented as links, cues, text, or similar formats. The detected keywords or phrases may also be associated with rules that govern the conditions and criteria for processing the detected keyword and presentation of the information.

A method, software and apparatus are provided which enable promotion of products and services in a deterministic manner free of conflicting actions modifying raw ranking data based on merchants interests. For this purpose, an information consolidator is provided to obtain search results for a plurality of sources including directly from merchants. When a shopper enters a set of key words in an entry field in an on-screen form for a web server to obtain a list of items (products and / or services) of interest to the shopper, the documents describing the items can be prioritized by the information provided by the information source based on the web sites owner's priorities. The information consolidator receives ranking information taking the highest ranked products and obtains the product information for the most highly ranked products. The information consolidator then reranks the products using a preferred ranking algorithm to remove information sources biases in this ranking of the products. The information consolidator can add weighting factors such as those covered in the copending applications by the merchant. The weighting factors are combined with the mentioned ranking mechanisms to the documents to increase the probability that certain items come to the top when the search results are presented to the shopper. These pages could be used to promote products or otherwise direct the selection shoppers. The weighting factors are configured so as to not decrease the shoppers confidence in the ranking process.

A system for use on computer servers on a network serving client computers for selecting an advertisement to be presented among a plurality of possible advertisement candidates based on key words. When a client computer requests a document from a server on the network, the system considers words contained within the document and compares them to a set of key words for each possible advertisement of a plurality of possible advertisements. The system selects an advertisement to be presented with the information where a key word associated with the advertisement matches one or more words in the document. If more than one advertisement qualifies, the system considers a price value of each advertisement and a relevance score for each word, which is a function of proximity to the start of the document, to determine which advertisement will be presented.

The invention discloses a Chinese entity relation extraction method based on keyword and verb dependency. Taking large-scale unstructured free text as target text, firstly, the text is segmented and keywords are extracted to form a text keyword thesaurus. Then the text is subjected to sentence segmentation, word segmentation, part-of-speech tagging, named entity recognition, dependency parsing, and entity corpus is constructed by combining named entity thesaurus and keyword thesaurus. According to the characteristics of Chinese sentence structure, syntactic structure and the dependency betweenwords, the entity-relation syntactic rules are constructed from verbs, and then each sentence in the text is matched with the relation syntactic rules. Finally, the relation triple is output and theset of text relation triple is obtained. The invention can make the entity relation extraction of the large-scale Chinese text more effective and more accurate.

A voice platform monitors a conversation between a call center agent and a caller to identify any predetermined keywords or phrases used in the conversation therebetween. These keywords or phrases can then be used to interface into an existing knowledge management system in order to allow information from the system to be pushed to the agent, thus improving agent efficiency. In a preferred embodiment additional processing is provided which generates an information item score based in the detected keywords or phrases, and those information items with the highest scores are then pushed to the agent, by displaying shortcuts to the information to the agent in the form of a shortcut tree.

An intelligent chatting system comprises participle unit for carrying out word property label on input text to obtain terms set with word property label, mapping word bank for storing mapping relation of key word to concept statement, mapping unit for searching said mapping word bank according to said terms set in order to obtain concept statement, conversation word bank for setting up and storing the mapping relation of concept statement to output text, and searching unit for searching said conversation word bank according to concept statement in order to obtain output text by mapping.

Metadata for a programming event may be generated by receiving descriptive information and timing information for the programming event and analyzing this information to determine category goodness of fit scores for the programming event corresponding to categories of a classification hierarchy. The information is further analyzed to determine keywords associated with the programming event. The category goodness of fit scores and keywords may be stored along with time data and descriptive data for the programming event as metadata for the programming event. Goodness of fit scores may also be generated for the keywords. Related embodiments may pertain to a device implementing such processing. Keyword metadata may be generated using candidate keywords taken from descriptive data associated with the programming event. The candidate key words may be provided individually as inputs to a classification tool configured to generate goodness of fit scores for categories of a classification hierarchy. Keywords may then be selected from among the candidates based on their individual scores, and stored as part of the metadata for the programming event. The scores of the keywords may be stored in association with the keywords.

A keyword extracting device includes high-frequency term extracting means (30) for extracting high-frequency terms which are index terms having a great weight among the index terms in a document group (E) including a plurality of documents (D), the weight including evaluation on the level of an appearance frequency of each index term, clustering means (50) for clustering the high-frequency terms on the basis of a co-occurrence degree C. which is based on the presence / absence of the co-occurrence of each document with the index terms (w) in the document group (E) in each document, score calculating means (70) for calculating a score key(w) of each index term (w) such that a high score is given to the index term among the index terms (w) that co-occurs with the high-frequency term belonging to more clusters (g) and that co-occurs with the high-frequency term in more documents (D), and keyword extracting means (90) for extracting keywords on the basis of the scores. Accordingly, the keywords indicating a feature of a document group including a plurality of documents can be automatically extracted.

The invention relates to a domain entity disambiguation method for fusing word vectors and a topic model, and belongs to the technical field of natural language processing and deep learning. The method comprises the steps of obtaining candidate entity sets of to-be-disambiguated entities; obtaining vector forms of the to-be-disambiguated entities and candidate entities, obtaining categorical referents of the to-be-disambiguated entities in combination with a hyponymy relation domain knowledge base, and performing context similarity and categorical referent similarity calculation; performing word vector training on documents in different topic classifications by utilizing the LDA topic model and a Skip-gram word vector model, obtaining word vector representations of different meanings of apolysemous word, extracting a topic domain keyword of a text by using a K-Means algorithm, and performing domain topic keyword similarity calculation; and finally, fusing three feature similarities, and taking the candidate entity with the highest similarity as a final target entity. The method is superior to a conventional disambiguation method and can well meet the demands of actual applications.

The invention discloses a text content auditing method based on a sensitive word. The text content auditing method comprises the following steps of: receiving a text to be audited, carrying out parsing and word segmentation on the text to be audited, and obtaining all keywords in the text to be audited; according to all keywords, inquiring a preset sensitive word database, and obtaining the sensitive word in the text to be audited, wherein the sensitive word database comprises sensitive words and the synonyms or the homoionyms of the sensitive words; obtaining the co-occurrence keyword of the sensitive word in a preset text length, calculating the violation weight of the sensitive word and the co-occurrence keyword of the sensitive word, and judging whether the violation weight is greater than a preset violation threshold value or not; and if the violation weight is greater than the preset violation threshold value, proving that the text to be audited is a violation text, and otherwise, proving that the text to be audited is a normal text. By use of the text content auditing method, a misjudgment probability is effectively lowered, auditing accuracy is improved, and the text content auditing method has quick reaction capacity for anagrams and net neologisms.

A method, system and apparatus for selecting, displaying, managing, tracking and transferring access to content of Internet web pages and other sources along with custom text messages has programming permitting a user to create custom selections of selected image, animation, movie and text content items, and other types of content items from web pages or other sources from the same or different network sources containing multiple content items, along with user-supplied text messages, in an independent, resizable, rescalable browser window; permitting the user to transfer access to the custom selection of content items to a recipient; permitting the user or recipient to navigate quickly to a source of a content item in the custom selection; and permitting the user to define search keywords for performing searches related to content items in a custom selection; and other features. A method of tracking viewing and sharing activities of content items and custom selections of content items by users and recipients is also disclosed. A method of assisted content selection provides temporary borders around content items on mouseover.

The system provides early warning intelligence feeds which analyze risks of potential human caused threats and naturally caused hazards. It includes data mining functions that autonomously search and categorize threats / hazards from worldwide open source data on a continuing basis. Data comes from many news feeds, social media feeds, government databases, etc. Key word analyses allow potential threats / hazards to be sorted into categories traditionally used by government agencies. Physical and cybersecurity vulnerabilities are analyzed and measured with threats to disclose potential impacts to people, properties, processes, special events, and related critical infrastructures and industries. Overall risk scores are instantly displayed as color coded icons on a worldwide electronic map / dashboard at any geolocation. Daily Intelligence reports and certain immediate alerts are also produced.