203results about How to "Meet search needs" patented technology

The invention discloses a multi-task layered image retrieval method based on a depth self-coding convolution neural network. The method is characterized by mainly comprising a multi-task end-to-end convolution neural network for deep learning and training recognition, a rapid visual segmentation detection and positioning method of a region-of-interest secondary screening module based on an RPN network, a coarse search of a full-graph sparse hash code, an area sensing semantic feature and matrix h accurate comparison and search based on the maximum response, and a region-of-interest selectivitycomparison algorithm. According to the method, the end-to-end training can be achieved, the interest region with higher quality can be automatically selected, the automation degree and the intelligent level of search by images can be effectively improved, and the image retrieval requirements of the big data age can be met by using little storage space at a high search speed.

The invention discloses a deep convolutional neural network end-to-end based image retrieval method by layered deep searching. The method is characterized by mainly including a convolutional neural network used for deep learning, training and recognition, a rapid visual segmentation algorithm for searching image objects, a quick comparison method used for rough searching with a Hash method and Hamming distance fast images, and a precise comparison method for first k ranked images based on images from a candidate pool P. By the method, automation and intelligence level in searching images with images can be effectively heightened, search results can be acquired accurately, and demand of image retrieval in the big data era is satisfied with less storage space and high retrieval speed.

The invention provides a search method. The search method comprises the following steps of: S1, receiving a query command; S2, performing demand intention analysis on the query command based on a knowledge base, and defining the demand intention of the query command; S3, searching the query command carrying the demand intention in a database to obtain a search result; and S4, outputting the search result. Compared with the prior art, the search method has the advantages that: on the basis of the knowledge base, the query command input by a user is understood better; the intention of the query command is analyzed; the structure of the query command is analyzed to perform semantic content expansion on the query command so as to better guide a search engine to select quality resources to meet the search requirements on the user; therefore, the search efficiency of the user is improved and the network traffic is saved.

The invention discloses a personalized meta search engine based on user interest and a method for processing search results. The search engine comprises a user registration/login unit, a meta search result collecting unit and a personalized processing unit, wherein, the personalized processing unit achieves screening of search results, personalized ordering and establishment and renewal of a user interest model through a search result preprocessing module, a personalized ordering processing module and a user interest renewing module. The method comprises the following steps: establishing and initializing a user interest model and then logging in a server; distributing search words input by users in the format of each search engine required; converting returning results collected into a unified format, removing reprocessing and personalized ordering in sequence, and submitting to the users; and catching search results clicked by users, changing interest types and weight size and renewing the user interest model data. The invention has the advantages that the inquiry coverage and accuracy are high, and the method for processing search results can be used for searching engine in Internet.

The invention provides a method and a system for searching geographic information. The method can comprise: receiving inquiry request information, segmenting the inquiry request information, obtaining an effective address and key words, inquiring a prearranged database, obtaining spatial geometric information of the effective address, determining spatial regions which need searching according to the spatial geometric information, searching according to the key words in the spatial regions which need searching, and outputting a searching result. The invention organically combines spatial index and full-text searching, and can effectively improve the accuracy and the rich degree of geographic information searching.

The invention relates to a vehicle searching method and system based on user-defined features. The method includes the steps of firstly, extracting features of each vehicle in a vehicle image database shot by a monitoring camera and storing the features; secondly, searching for the vehicle, satisfying the user-defined features, in the vehicle image database shot by the monitoring camera and feeding back the searching result. The system comprises a vehicle image data reading device, a vehicle area positioning device, a vehicle feature extracting device, a vehicle feature storage device, a vehicle searching device and a searching result displaying device. According to the vehicle searching method and system, diversified searching methods can be provided, a user can search for the vehicle according to the user-defined features in the practical situation, the number of images which are manually confirmed by personnel who handling cases is greatly lowered, labor and materials are effectively saved, the case handling efficiency is greatly improved, and very good social benefits and economic benefits can be produced.

The invention provides a method and device for carrying out error correction on texts after speech recognition. The method for carrying out error correction on texts after speech recognition comprises the following steps of: preprocessing a text after speech recognition; recognizing a search intention of the preprocessed text; determining to-be-extracted attribute information according to the recognized search intention and extracting attribute information from the preprocessed text; and calculating the similarity between the attribute information and any candidate word in a candidate lexicon, and carrying out error correction on the extracted attribute information according to the similarity. Through the method and device, the free man-machine interaction is realized, the problem that the speech recognition is incorrect in speech search is effectively solved, the speech recognition correctness is improved, the enterprise search demands are satisfied and the user experience is enhanced.

The invention belongs to the technical field of information retrieval, and provides a full-text retrieval system based on two-level semantic analysis. The system comprises a query information receiving module, a sentence summary level semantic processing module, a retrieval module, an index library, an index module, a text level semantic processing module, a result set processing module and a data server. The system performs summary processing and repeat processing for a query statement to repeat the query statement submitted by a user from sentence summary level semanteme, and latent semantic information and thematic information are extracted in the text level to eliminate retrieval result documents not conforming to text level semanteme, so that the full-text retrieval system achieves two-level semantic analysis in the 'sentence summary level' and the 'text level'. By improving semantic processing capacity of query statements and text sets, the full-text retrieval system is more human-friendly and intelligent, and provides more convenient and accurate services for users.

The invention discloses a method and a device for extracting searching value terms based on context search. The method comprises the following steps of: generating a candidate searching term set according to a selected content text; filtering broad terms from the generated candidate searching term set; performing topic relevance calculation and searching value calculation on the candidate searching term set from which the broad terms are filtered respectively; acquiring comprehensive weight measures of candidate searching terms according to a topic relevance calculation result and a searching value calculation result; and obtaining the searching value terms according to the comprehensive weight measures of the candidate searching terms. According to the method and the device, the searching requirements of a user in different places and different fields can be met, searching efficiency can be improved, and the searching experiences of the user can be improved.

The embodiment of the invention discloses a searching method and device based on artificial intelligence. The method comprises the steps of obtaining at least one candidate document related to a searching sentence; determining a searching word vector sequence corresponding to a segmented word sequence of the searching sentence and determining a candidate document word vector sequence corresponding to the segmented word sequence of each candidate document in the at least one candidate document; executing the step of similarity calculation on each candidate document in the at least one candidate document; selecting a preset number of candidate documents as searching results from the at least one candidate document according to the sequence of the similarity with the searching sentence from large to small. According to the searching method and device based on the artificial intelligence, the candidate documents and the searching sentence are represented into a semantic vector through a neural network model, then according to similarities between a candidate document semantic vector and a searching sentence semantic vector, the candidate document is ranked, and the relevance of the searching results which are called back and the searching sentence input by a user is improved.

The invention provides a search content providing method and a search engine. The search content providing method includes that the search engine acquires search data of a user; the search engine acquires a first associated word set and a second associated word set associated with preset keywords according to the search data; the search engine establishes association between first associated words in the first associated word set a nd second associated words in the second associated word set according to the search data and the preset keywords; when receiving a search request including the preset keywords, the search engine provides search content according to the association. By the search content providing method, the search content can be provided according to the association, more systematic and clearer search recommendations can be recommended to the user, convenience is brought to the user for accurately and quickly acquiring needed results, search requirements of the user can be met efficiently and accurately, and search experience of the user is good.

The invention discloses a method and device for sequencing search results, and main contents are as follows: in the embodiment of the invention, not only can the degree of association between the search results and a retrieval word be taken as a sequencing basis, but also amendment conditions are pre-set for each search result, and the degree of association between the search results and the retrieval word and amendment parameters of the search results are combined for sequencing the research results, thereby enabling the final sequencing to be capable of meeting search demands of a user to the maximum extent, improving the efficiency of inquiring the required result from the search results of the user, and reducing system resources occupied by the search process.

The embodiment of the invention discloses a method and device for generating a picture search library and a method and device for searching for a picture. The method for generating the picture search library comprises the steps that image data of a currently shot object are obtained; a search recognition picture is generated according to the image data and the search recognition information of the image data; the search recognition picture is provided for the picture search library; the search recognition information comprises the shooting time and shooting spot of the image data. The method for searching for the picture comprises the steps that a target search recognition picture matched with a target picture is searched for in the picture search library; the target search recognition picture is provided for a user, and the target search recognition picture comprises the image data and the search recognition information; the search recognition information comprises the shooting time and shooting spot of the image data. An existing picture search technology is optimized, data sources and data types in the picture search library are enriched, and the growing individualized and convenient picture search needs of people are met.

The invention discloses a text modal and image modal crossing type data retrieval method. The method comprises the following steps: dividing all text and image modal data into multiple samples, and carrying out co-clustering; carrying out main affinity calculation on all data according to a co-clustering center; taking sense vectors of the text modal data and the image modal data as an output expression of a Logistic regression classifier, centralizing a main affinity non-linear expression, and training the main affinity non-linear expression as an input expression, so as to obtain multiple classification functions; when a user needs to retrieve the text or image modal data sample, respectively calculating main affinities, inputting the main affinities into the classification functions to obtain a semantic layer expression of the text or image modal data sample, and carrying out normalization to generate a final expression; and calculating a retrieval result by virtue of an inner product calculation formula. According to the text modal and image modal crossing type data retrieval method, the modal crossing retrieval can be rapidly and effectively realized, and the modal crossing retrieval time can be remarkably shortened.

The invention discloses a search method and device. The search method includes that receiving a first search term; acquiring a first search result according to the first search term and a plurality of first level of knowledge categories corresponding to the first search term, wherein each first level of knowledge category comprises at least one first level of knowledge label; providing a display interface and providing the first search result, a plurality of first level of knowledge categories and at least one first level of knowledge label of each first level of knowledge category on the display interface. By means of the search method, a user can comprehensively understand the global knowledge of the search term according to the knowledge categories and knowledge labels; the search method arouses the search interest of the user, meets the search requirements of the user in a wide range and greatly improves the user experiment.

The invention provides a method and a device for establishing an example sentence index and a method and a device for indexing example sentences. A special index is established for the example sentences by performing text analysis on the example sentences in an example sentence library; when a user inputs a grammar-based advanced search requirement, the search requirement input by the user is resolved; search results of respective inquiry items are acquired according to resolved inquiry items; and the search results of the respective inquiry items are integrated and processed according to a logic relation of the resolved inquiry items. The established index and the inquiry items are at least one of the following combinations: a combination of terms in the example sentences and parts of speech corresponding to the terms, a combination of terms in the example sentences and types of named entities corresponding to the terms, a combination of terms in the example sentences and syntactic roles corresponding to the terms, and a combination of terms in the example sentences. According to the methods and the devices, the grammar-based advanced search can be realized, so that the search effect can be improved.

The invention discloses a video GIS data retrieval method based on deep learning. The video GIS data retrieval method comprises the steps of firstly, calculating Euclidean distance of a video GIS frame-frame difference under space and time sampling of video GIS data and conducting key frame extracting on a video lens; then building a deep convolutional neural network model alternatively constituted by a convolutional layer, an activating layer and a pooling layer, conducting layer-layer mapping on input video GIS frame images and achieving deep characteristic representing of the video GIS frame images; finally, conducting layered retrieval, wherein in the first layer, a Hash method and Hamming distance are subjected to coarse retrieval, in the second layer, the result of the coarse retrieval in the first layer is filtered, and the first m video GIS frame images are subjected to fine retrieval from a candidate pool. The frame difference Euclidean distance is adopted to extract key frames, so that the retrieval efficiency is greatly improved, the deep convolutional neural network model is adopted for training, characteristic representing of a higher layer is extracted, so that the retrieval time is shortened by a large margin, and storage expenditure is reduced by a large margin.

Aiming at the problems in the prior art that when searching image data in a PACS system having a plurality of data, especially searching simultaneously in a plurality of image workstation, workload of a database server is sharply raised, system speed is declined, and the overall cost is added, the invention provides a caching technology based medical image database searching method, which comprises: after receiving an initial searching request, searching firstly in a local caching list; sending final searching request to the database server if not searching it, transmitting it to a local image workstation if the database server searches it, reporting the searching result to the local image workstation if not searching it in the database server. By using the method, the image data searching speed is quickened, the workload of the database server is lightened, and the working efficiency of the PACS system is improved. The invention also provides a a caching technology based medical image database searching system, which is used for guaranteeing implementation and application of the method in actual system.

The embodiment of the application discloses a data query method and device of a time interval and an index construction method and device of a time interval. The data query method includes: acquiring a to-be-queried time interval; using the to-be-queried time interval to obtain a first result set of index interval objects in intersection and containing association relationships with the to-be-queried time interval by querying in a first sorted index constructed on the basis of key value pairs of the index interval objects; using the to-be-queried time interval to obtain a second result set of index interval objects in an overlaying association relationship with the to-be-queried time interval by querying in a second segment tree index constructed on the basis of key value pairs of the index interval objects; and combining the first result set of the index interval objects and the second result set of the index interval objects obtained by querying, and then using the combined index interval objects as a query result of the to-be-queried time interval. According to the embodiment of the application, a reverse indexing manner and a segment-tree-type indexing manner are combined, retrieval requirements of the high expansibility and the high concurrency of big data based on a cloud platform can be met, and the retrieval efficiency can also be greatly improved.

The invention provides a map searching method and system. The map searching method includes searching nationwide according to query inputted by users when the query inputted by the users fails to call back search results in current cities or the callback search results are dissatisfied with the preset conditions; when the search results are judged to be dissatisfied with the condition of uniformity in nationwide distribution, judging whether the cities corresponding to the search results is met with the preset skip condition or not according to matching degree of POI data of the search results and the pre-generated query; if yes, switching the current city to the city meeting the skip condition, and providing the search results of the query of the cities meeting the skip condition. According to the technical scheme, searching cost of map searching applications is reduced while searching efficiency is improved.

Embodiments of the present invention provide an information search method and apparatus, and a timeliness query word recognition method and apparatus. The information search method comprises: searching information according to a query word input by a user; determining whether the query word is a target query word, wherein the target query word is a query word with the timeliness requirement, corresponding to an information search result; and if so, raising the weight of the timeliness factor to a preset value, ranking the searched information based on the preset value and outputting the searched information, wherein the target query word has the corresponding timeliness factor which is used to calculate the score of the searched information. In the embodiments of the present invention, in the manner of determining whether the query word is the target query word, the weight of the timeliness factor is raised, and the searched information is ranked based on the preset value and then is output, so that the search requirement of the user for the timeliness information is improved.

The invention provides a broad application requirement retrieval method and a system. The method comprises the following steps: analyzing a query word of the broad application requirement retrieval so as to obtain a concept label or an attribute label of the query word, wherein the concept label and the attribute label respectively describe the category and attribute of the application; matching in a pre-arranged application label system according to the concept label or the attribute label of the query word, so as to obtain the applications containing the concept label or the attribute label; obtaining relativity marks of the applications according to the concept label or the attribute label of the query word, ordering the applications according to the marks, and offering the ordered applications, as the result of the query word, to the user. The technical scheme adopted by the invention can improve the diversity and relativity of the retrieval result in broad requirement retrieval scenes.

The invention relates to a method for big data retrieval based on time characteristics and supporting complicated conditions. According to timestamps generated during data storage or according to user defined time characteristics, data information is segmented according to the time characteristics, indexes are established on different collections on a full-text retrieval engine Solr; on the conditions that users already know the time of queried information generation, quick positioning can be performed on an index database of a collection of the same month to perform retrieval, the retrieval range can be greatly reduced, and the efficiency is improved. On the conditions that users cannot determine information generation time, results conforming to user query are provided for users for reference and selection. According to the method, not only is the shortcoming that a distributed database HBase has no secondary index overcome, but also the index establishment is more flexible, the retrieval on different demand conditions is met, and the retrieval efficiency can be guaranteed.