184 results about "Search intent" patented technology

A system and related techniques accepts user search or query terms over of the Internet or other network or connection. In addition to presenting regularly generated search results, according to embodiments of the invention the search engine and related logic may examine the search string for suggested refinements or improvements to the search terms, to attempt to derive improved results or results closer to the user's search intent. According to embodiments of the invention in one regard, the alternative search logic may attempt to extract related or more meaningful search terms from sources including past usage patterns by users, and other data. That alternative search logic may thus examine the user's search terms to determine a substring match to prior searches, for instance stored by the search host for all users. In embodiments, the alternative search logic may likewise present user search extensions or refinement paths selected by prior users running the same search, as an indicator of likely content or source relevance. In further embodiments, the alternative search logic may perform a reverse query lookup to trace queries which resulted in the same Web site or other hit, as the present search and present those other queries as possible alternatives for the user to pursue. These and other search refinements may be performed, taking advantage of usage patterns and other information to improve search quality beyond straightforward spelling-type correction.

In one embodiment, a method includes receiving a search query from a first user and identifying one or more second nodes that match the search query. The method includes determining one or more search intents of the search query. Search intent may be based on one or more topics associated with the identified nodes and one or more node-types of the identified nodes. The method includes generating one or more search results corresponding to the search query, the search-results being generated based on the determined search intents. The method includes sending a search-results page to the client system of the first user for display. The search-results page may include one or more of the generated search results.

A system and related techniques generate alternative search terms derived from a set of search results. A user may input a set of search terms such as keywords or other inputs, and receive a set of search results back, for instance in rank order of estimated relevance to the user's search terms and search intention. In addition to the hyperlink or other results may have associated with them a set of selectable alternative search links, for instance indicating “show me more with titles like this” when for instance a Web page title contains the user's search terms. Other results may present other attributes, depending on the evaluated distinctiveness potential alternative information content of attributes of that Web page or other result, which attributes may further include, for example, the presence of image files, PDF™ files, audio or video files or attachments, Web pages or other hits indicating certain date ranges, or other attributes or characteristics. In embodiments an attribute or attribute of a result may be assessed for inclusion as an alternative search attributes or limiter based on the attribute's deviation in an attribute space from an average of the attributes of the original set of search results, or otherwise. A user may click or otherwise select the alternative search suggestion, for instance indicating “show me more PDFs” and be presented with an updated set of search results containing Web pages or other hits, links or results each of which is, contains or has attached a file or content of that type. Users may thus receive categories of search results more closely aligned with their search intent when characteristic attributes may be a factor in desired content.

Methods and systems for recommending a service based on an electronic social media trust model. A user trust network and a service trust network can be constructed and the two separate trust networks can be combined to form a combined trust network. The combined trust network includes an explicit trust and an implicit trust in order to improve the recommendation coverage and consider a latent service rating without suffering noisy data. A trust-oriented random walk model can be conducted on a user node with respect to the combined trust network based on a user search intent and navigation behavior in order to select and recommend a service candidate. A service rating can then be predicted by considering the user ratings with respect to a target service, a propagated trust and an inferred service rating.

An embodiment of the invention discloses a search engine based search method. The search engine based search method includes that when receiving search keywords input by users and sent from a client side, the search server determines search categories corresponding to search keywords according to corresponding relation between preset keywords and the search categories; and then the search server searches the search keywords according to the determined search categories and returns the search results to the client side. The embodiment of the invention further discloses a search server. By the search engine based search method and the search server, search intension of the users can be identified and judged, corresponding search results can be provided, search efficiency can be increased, and user experience of the users to the search engine can be improved.

The invention provides a voice search method, a voice search device and a voice search system. The voice search method comprises the following steps: receiving a voice search request from a user; performing intent resolution on the voice search request so as to acquire the search intent of the user; acquiring a search result according to the search intent of the user; generating a voice dialogue result of the voice search request according to the search result and the search intent of the user and supplying the voice dialogue result to the user. According to the voice search method provided by the invention, simple voice broadcast for the search result is not performed, but a dialogue form corresponds to the input voice search request, so that the device and the system are more intelligent. Furthermore, the search intent of the user can be analyzed, the corresponding search result is acquired so as to generate the voice dialogue result, user requirements can be met more accurately, and the result is more accurate, individualized and humanized.

A computer-implemented method of determining search intent, comprises: receiving a search query; searching content across a plurality of content classes using the search query, so as to obtain a plurality of search results; deriving summary data from the search results; applying the summary data to a trained machine learning model; and determining from the machine learning model a selected one of the content classes corresponding to the search intent of the search query.

The invention discloses a recognition method and device for application search intentions and an application search method and server. The method includes the steps that search terms in query sessions are acquired from a query session log of an application search engine; label systems of the search terms are mined according to the search terms in the query sessions and preset strategies; the application search intentions corresponding to the search terms are recognized according to the label systems of the search terms. In the scheme, by proposing the label method of the recognition method for the user intentions corresponding to the app label systems, the fine-grained user query intentions are flexibly expressed. The label systems of the user intentions are constructed based on the unsupervised machine learning technology, a traditional user intention classification method is abandoned, an automatic user intention mining process is achieved, and a high-accuracy and high-recall-rate user intention label list can be generated; the user intentions and apps are mapped into the same label system, and thus a user can rapidly and accurately acquire apps meeting intentions when searching for apps.

A system and method for generating advertisements based on search intent. The system includes a query engine, and an advertisement engine. The query engine receives a query from the user. The query engine analyzes the query to determine a query intent that is matched to a predetermined domain. A translated query is generated including the domain type. Once a domain is selected, the query may be further analyzed to determine generic domain information. The domain and associated information may then be matched to a list of advertisements. The advertisement may be assigned an ad match score based on a correlation between the query information and various listing information provided in the advertisement.

An information processing apparatus: a pointing device that allows a user to move a cursor to point a position in a display screen of the display device; a monitoring unit that monitors whether or not the pointed position is unmoved for a predetermined time period; a text extraction unit that, when determined that the pointed position is unmoved for the predetermined time period, determines a character displayed on the pointed position and extracts a target text piece having a predetermined length and including the character from the displayed text; a text analysis unit that (1) adjusts text string that exists near the character into a search keyword that is suitable for performing a search by analyzing the target text and (2) outputs a search intention item that indicates a subject to be searched regarding the search keyword based on an attribute of the search keyword; and a display controller that controls the display device to display a search menu that allows the user to select at least one of the search keyword and the search intention item.

A restaurant service system includes a restaurant server adapted to communicate with diner communication devices and restaurant communication devices. The restaurant server builds a food taxonomy including dishes, dish attributes and dish ingredients. The dishes are mapped from menu items. The server also trains dish classifiers and applies the dish classifiers to map menu items to dishes. Dish attributes are derived from search logs and dish ingredients are extracted from menu item descriptions. The server determines the search intent of a diner based on her search terms. Food search is conducted based on the taxonomy and the search intent with consideration of restaurant similarity and dish popularity. The server also provides dish recommendations based on taste similarity between diners.

Computer-storage media, methods, and systems for improving the ability of a user to accomplish a task that is pending during a search session are provided. This pending task can be distilled by identifying a current searching intent associated with a recently submitted query and by determining which candidate tasks are most comparable to the current searching intent of a user. The candidate tasks are mined from a search history of the user by categorizing those navigation events that appear to share a semantically common concept. Upon performing a comparison, the candidate task that captures the user's true current searching intent is designated as the pending task. When a user invokes the pending task, a collection of elements that are associated with the pending task are dynamically organized into a sharable content page, thereby providing a collaborative experience that involves exposing the collection to contacts and accepting feedback therefrom.

A permissive search intent registry allowing intending purchasers to receive special offers and incentives from participating merchants wherein merchants may thereby more effectively target advertising campaigns by gaining access to a pool of intending purchasers, allowing merchants to differentiate between intending purchasers and mere “click-thrus”. An intending purchaser may tag a search, product, or category of products as being related to a purchase intention and thereby automatically be linked to participating merchants via the present invention. Intending purchasers are rewarded for the disclosure regarding their purchase intent and their estimated purchase timeline by receiving special offers, rewards, and / or incentives from the participating merchants that are not readily available to the general public. In this manner, both the purchasers and the merchants receive a benefit through their automatic relationship via the present invention; purchasers receive rewards towards the desired goods or services and merchants may directly market to intending purchasers.

The invention provides a search recommendation method and device. The method includes the first step of receiving search terms, the second step of obtaining a plurality of search results related to the search terms and obtaining at least one content item related to the search terms in a knowledge base, the third step of obtaining at least one recommended result according to the search terms and at least one content item, and the fourth step of providing a search page, wherein the search page includes a first display portion and a second display portion, the search results are displayed on the first display portion of the search page, at least one recommended result is displayed on the second display portion of the search page. The search recommendation method can provide search results for the user and can help the user to know summarized information related to the type of the search terms and provide information more in line with search intentions for the user, and consequently demands of the user are met and user experience is promoted.

The invention provides a search method, a search device and a search engine system to solve the problems that the prior art is not accurate when recognizes a search intention of a user, and search accuracy is affected. The method comprises the steps: receiving a real-time search character string; carrying out matching on the real-time search character string and a pre-generated dictionary, wherein the dictionary is a gather of a first kind of words and a second kind of words; if a certain part in the real-time search character string is matched with the second kind of words of a certain category in the dictionary, replacing the part by a label of the category, wherein the second kind of words belongs to the category, and real-time search character string which finishes being matched comprises the label of the category to which the first kind of words and / or the second kind of words belong and / or a part which is not matched; confirming a specific search intention of the matching-finished real-time search character string according to a pre-generated model, and returning data of a search result according to the specific search intention. According to the search method, the search device and the search engine system, the search accuracy can be remarkably improved, and the accurate data of the searching result can be provided.

The invention provides an image search method and a search engine. The image search method includes the steps of receiving search terms inputted by a user, analyzing the search terms, obtaining demand option information and an image search result related to the search terms, sending the demand option information and the image search result to a client side, receiving current demand options selected by a user when the current image search result is determined not to meet the requirement of the user, analyzing the current demand options, obtaining new demand option information and a new image search result, sending the new demand option information and the new image search result to the client side, continuously repeating the steps until the current image search result meets the requirement of the user. By means of the image search method, by displaying new demand option information and new image search results for the user multiple times, interacting with the user and thoroughly and continuously understanding the search intention of the user, the search result which meets the search intention of the user can be accurately provided for the user, the accuracy of the search result is improved, and the search experience and satisfaction degree of the user are improved.

The invention provides a voice control method and a display device. The voice control method comprises the following steps: receiving voice input from an audio receiving element, and generating a voice search instruction according to the voice; sending a voice search instruction input by a user to the server, wherein the voice search instruction carries a target search term, and the target searchterm is used for adjusting the display sequence of the labels when the service types are not less than two; receiving a first display instruction returned by the server based on the voice search instruction, wherein the first display instruction is generated according to the display sequence of the tags; and in response to the first display instruction, sequentially displaying the labels in the label display area in the resource display interface according to the adjusted display sequence. By means of the mode, the resource information of the service type with the higher association degree with the target search term can be displayed preferentially, so that the possibility that the display sequence of the resource information does not meet the search intention of the user is reduced, and the user can find the target resource information conveniently.

The disclosed embodiment discloses a search method, a search set generation method, an apparatus, a medium, a terminal and a server. The method comprises the following steps of: acquiring search information corresponding to a user search request; Determining a user search intent according to the search information, and determining a search set corresponding to the user search intent, wherein the search set is a set of stored data records associated with data items matching a set field, and data records in different search sets correspond to different user search intent; A search result corresponding to the user search request is determined based on the search set. The technical proposal of the disclosed embodiment can realize the high matching between the search results and the user searchrequest, avoid the situation that the search results contain more interference items or miss detection, and improve the accuracy of the information search.

The invention discloses a search intention recognition method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining search scene information associated with a search request in response to the search request; generating a composite feature for identifying a search intention according to the search scene information and the search request; and inputtingthe composite feature into a search intention recognition model, and obtaining a search intention recognition result output by the search intention recognition model. The technical scheme has the beneficial effects that the structure is simple; not only search request of interest, searching scene information associated with the searching request, such as weather, position, user behavior and the like, is concerned; the search intention recognition model based on composite modeling is utilized, the real demands of the user are predicted by referring to multiple factors, the problem that the search intention cannot be accurately recognized only according to the search request is solved, and the method is particularly suitable for life service and LBS search scenes.

The invention discloses a method and apparatus for pushing search advertisement, and relates to the technical field of internet searching, aiming at achieving refined pushing of search advertisements. According to the invention, the technical solution includes the following steps: on the basis of query words which a user searches, conducting searching, acquiring a candidate advertisement set relevant to the query words; on the basis of the characteristic information of the user, acquiring the classification of the user; based on the classification of the user, the search intent of the query words, the content of each advertisement in the candidate advertisement set and historical data of how the user clicks on different advertisements, selecting, from the candidate advertisement set, an advertisement set which meets predetermined conditions, the advertisement set serving as a search advertisement set presented in the page of results from the user's search; and pushing the advertisements in the search advertisement set to the user so as to be presented in the page of the results from the user's search. According to the invention, the method and the apparatus are applied to the pushing of search advertisements.

A method for processing structured search queries received at an internet search includes receiving at the internet search site a structured search query containing a user's search intent and other pertinent information about the user and the site. The structured search query is constructed as a conforming structured search string. The method further includes parsing the structured search query based on a grammar published for affiliates or partners to construct the structured search query. Still further, the method includes extracting individual breadcrumbs from the structured search query that were used to build the structured search query. This includes decoding the position and meaning of each respective breadcrumb in the structured search query. The method further includes forming match tokens from the identified individual breadcrumbs and combinations of breadcrumbs. Still further the method includes matching listings stored in a search listing database with the formed match token strings, forming a search result list, and ranking elements of the search result list according to strength of match tokens to the original user search intent.

The invention relates to the technical field of knowledge graphs, and provides a search method and device, computer equipment and a storage medium. The method comprises the following steps: receivinga search request carrying input information sent by a terminal, carrying out word segmentation on the input information, and carrying out intention identification according to a word segmentation result to obtain a search intention; traversing a pre-constructed knowledge graph, matching the search intention with nodes in the knowledge graph, and determining a target content label according to thematching degree; querying a target identifier corresponding to the target content label from the knowledge graph, and obtaining an interface parameter corresponding to the target identifier from the knowledge graph; matching the word segmentation result with an interface parameter corresponding to the target identifier, determining a target interface parameter according to a matching result, and sending the target interface parameter and the search intention to a target data source server; and receiving target data returned by the target data source server, obtaining a search result accordingto the target data, and returning the search result to the terminal. The comprehensiveness of the search data can be improved.

The embodiment of the invention discloses a pushing method and device based on user intention, electronic equipment and a computer readable medium, and relates to the technical field of computer application. The method comprises the steps of obtaining a search term input by a user and a to-be-pushed content mapping relationship set, wherein the to-be-pushed content mapping relationship set comprises a mapping relationship between to-be-pushed content and a keyword; respectively obtaining a search semantic vector corresponding to the search term and a content semantic vector corresponding to the keyword based on a pre-trained semantic understanding model; calculating the similarity between the search semantic vector and the content semantic vector, and determining a target content semanticvector from the content semantic vector according to the similarity; and obtaining to-be-pushed content corresponding to the target content semantic vector according to the target content semantic vector, and pushing the to-be-pushed content. Therefore, the search intention of the user can be mined according to the search term of the user so that the content is effectively pushed.

The invention provides a search method and device, electronic equipment and a storage medium, and the method comprises the steps: receiving a ubiquitous query search request; wherein the ubiquitous query search request carries ubiquitous query words; obtaining at least one multimedia content card corresponding to the generic query word; wherein each multimedia content card corresponds to one extension tag corresponding to the extensive query search request, each multimedia content card comprises information of a plurality of multimedia content sets, and each multimedia content set correspondsto one extension sub-tag corresponding to the extension tag; and displaying the information of the plurality of multimedia content sets included in each multimedia content card in the at least one multimedia content card. By the adoption of the scheme, the search results related to the generic query words can be displayed in a clustering mode from various dimensions, a user can directly find content related to the search intention of the user, search efficiency is improved, and a search path is shortened.

The invention discloses an implementation method for associational word search based on a redis technology. The method mainly comprises search keyword pre-processing, index establishment, setting of a search intent weight, and display of associational word results. The index establishment mainly comprises that a solrJ is used to establish an index of which a keyword orients to a search intent and establish an index of which a keyword prefix orients to the keyword. According to the embodiment of the invention, when a user conducts search, the user can find the needed keyword more quickly through analysis of character strings input by the user and dynamic keyword recommendation. In this way, the user's experience is improved.

The invention discloses a training method of a search intention recognition model, a search intention recognition method, a search intention-based content recommendation method and device, equipment, a medium and a product, and relates to the fields of deep learning, natural language processing, intelligent recommendation and the like. The training method of the search intention recognition model comprises the steps of obtaining a plurality of search texts, wherein each search text has a plurality of tags representing a search intention; each search text is input into a search intention recognition model, and the search intention recognition model comprises a feature extraction network and a plurality of recognition networks; extracting feature data of the search text by using a feature extraction network; processing the feature data by using a plurality of recognition networks to obtain a plurality of recognition results in one-to-one correspondence with the plurality of tags; and adjusting model parameters of the search intention recognition model based on the plurality of recognition results and the tag corresponding to each recognition result to obtain a trained search intention recognition model.

The invention provides a method and a device for recommending an App to a mobile terminal during search. The method comprises that a first terminal receives a searched word from a user, and acquires at least one to-be-recommended App which is related to the searched word according to the searched word; a recommendation identifier is generated for each to-be-recommended App according to a client side environment in the first terminal; and each to-be-recommended App is pushed to the mobile terminal related to the first terminal by the recommendation identifier. The technical scheme provided by the invention realizes the objective of recommending the App to the mobile terminal during the search. The searched word can directly reflect a search intent of the user, so the user can be provided with more abundant search results by recommending the to-be-recommended App which is related to the user's searched word to the user, extra help can be provided to the user, and the user can also get rid of being bothered by App recommendation manners such as window popup or suspended advertisements.

The invention provides an input association recommendation method and apparatus for optimizing commercial word promotion. The method comprises the steps of mining a search behavior log of a user, andextracting candidate words from the search behavior log of the user based on a preset extraction model to generate an input association candidate word library; matching the input association candidateword library with a high-quotient word library of a search advertisement release system, and according to a matching result, adjusting the input association candidate word library; receiving a searchquery input by the user, and sorting the adjusted input association candidate word library in combination with the search query; and recommending the sorted input association candidate word library as an input association recommendation result of the search query. The correlation between high-quotient words in the high-quotient word library and input association can be reasonably utilized; the candidate words can be accurately recommended to express a search intention of the user and improve the search experience; and the business revenue obtained by quotation through the high-quotient wordscan be increased, so that the cashability and the correlation search of the whole input association can be improved.

A computer-implemented method of determining search intent, comprises: receiving a search query; searching content across a plurality of content classes using the search query, so as to obtain a plurality of search results; deriving summary data from the search results; applying the summary data to a trained machine learning model; and determining from the machine learning model a selected one of the content classes corresponding to the search intent of the search query.