Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

203 results about "Word selection" patented technology

Providing services for an information processing system using an audio interface

A method and system for providing efficient menu services for an information processing system that uses a telephone or other form of audio user interface. In one embodiment, the menu services provide effective support for novice users by providing a full listing of available keywords and rotating house advertisements which inform novice users of potential features and information. For experienced users, cues are rendered so that at any time the user can say a desired keyword to invoke the corresponding application. The menu is flat to facilitate its usage. Full keyword listings are rendered after the user is given a brief cue to say a keyword. Service messages rotate words and word prosody. When listening to receive information from the user, after the user has been cued, soft background music or other audible signals are rendered to inform the user that a response may now be spoken to the service. Other embodiments determine default cities, on which to report information, based on characteristics of the caller or based on cities that were previously selected by the caller. Other embodiments provide speech concatenation processes that have co-articulation and real-time subject-matter-based word selection which generate human sounding speech. Other embodiments reduce the occurrences of falsely triggered barge-ins during content delivery by only allowing interruption for certain special words. Other embodiments offer special services and modes for calls having voice recognition trouble. The special services are entered after predetermined criterion have been met by the call. Other embodiments provide special mechanisms for automatically recovering the address of a caller.
Owner:MICROSOFT TECH LICENSING LLC

Providing menu and other services for an information processing system using a telephone or other audio interface

A method and system for providing efficient menu services for an information processing system that uses a telephone or other form of audio user interface. In one embodiment, the menu services provide effective support for novice users by providing a full listing of available keywords and rotating house advertisements which inform novice users of potential features and information. For experienced users, cues are rendered so that at any time the user can say a desired keyword to invoke the corresponding application. The menu is flat to facilitate its usage. Full keyword listings are rendered after the user is given a brief cue to say a keyword. Service messages rotate words and word prosody. When listening to receive information from the user, after the user has been cued, soft background music or other audible signals are rendered to inform the user that a response may now be spoken to the service. Other embodiments determine default cities, on which to report information, based on characteristics of the caller or based on cities that were previously selected by the caller. Other embodiments provide speech concatenation processes that have co-articulation and real-time subject-matter-based word selection which generate human sounding speech. Other embodiments reduce the occurrences of falsely triggered barge-ins during content delivery by only allowing interruption for certain special words. Other embodiments offer special services and modes for calls having voice recognition trouble. The special services are entered after predetermined criterion have been met by the call. Other embodiments provide special mechanisms for automatically recovering the address of a caller.
Owner:MICROSOFT TECH LICENSING LLC

Keyboard System with Automatic Correction

There is disclosed an enhanced text entry system which uses word-level analysis to automatically correct inaccuracies in user keystroke entries on reduced keyboards such as those implemented on a touch-sensitive panel or display screen, or on mechanical keyboard systems. A method and system are defined which determine one or more alternate textual interpretations of each sequence of inputs detected within a designated auto-correcting keyboard region. The actual contact locations for the keystrokes may occur outside the boundaries of the specific keyboard key regions associated with the actual characters of the word interpretations proposed or offered for selection, where the distance from each contact location to each corresponding intended character may in general increase with the expected frequency of the intended word in the language or in a particular context. Likewise, in a mechanical keyboard system, the keys actuated may differ from the keys actually associated with the letters of the word interpretations. Each such sequence corresponds to a complete word, and the user can easily select the intended word from among the generated interpretations. Additionally, when the system cannot identify a sufficient number of likely word interpretation candidates of the same length as the input sequence, candidates are identified whose initial letters correspond to a likely interpretation of the input sequence. The approach utilizes the information contained in the entire sequence of keystrokes corresponding to a word in order to determine the user's likely intention for each character of the sequence. The system also accommodates punctuation characters such as hyphens or apostrophes that are commonly embedded in words such as hyphenated compounds and contractions in English, and characters with special diacritics such as are commonly found in various European languages, e.g., diacritic accent. Special functions may be applied depending on where the user touches the intended string in a displayed word selection list. Once the user selects the desired string, it is automatically “accepted” for output and the next input detected starts a new input sequence corresponding to the entry of a next word.
Owner:TEGIC COMM +1

Voice Recognition Device and Method, and Program

A speech recognition system in which a user may correct a recognition error resulting from speech recognition more efficiently and easily. Speech recognition means compares a plurality of words inputted from speech input means with a plurality of words stored in dictionary means, respectively, and determines a most-competitive word candidate. Word correction means has a word correction function of correcting the words constituting a word sequence displayed on a screen. Competitive word display commanding means selects one or more competitive words having competitive probabilities close to the competitive probability of the most-competitive word candidate and displays the one or more competitive words adjacent to the most-competitive word candidate. Competitive word selection means selects an appropriate correction word from the one or more competitive words. Word replacement commanding means causes one of the most-competitive word candidate to be replaced with the correction word selected by the competitive word selection means.
Owner:NAT INST OF ADVANCED IND SCI & TECH

Providing menu and other services for an information processing system using a telephone or other audio interface

A method and system for providing efficient menu services for an information processing system that uses a telephone or other form of audio user interface. In one embodiment, the menu services provide effective support for novice users by providing a full listing of available keywords and rotating house advertisements which inform novice users of potential features and information. For experienced users, cues are rendered so that at any time the user can say a desired keyword to invoke the corresponding application. The menu is flat to facilitate its usage. Full keyword listings are rendered after the user is given a brief cue to say a keyword. Service messages rotate words and word prosody. When listening to receive information from the user, after the user has been cued, soft background music or other audible signals are rendered to inform the user that a response may now be spoken to the service. Other embodiments determine default cities, on which to report information, based on characteristics of the caller or based on cities that were previously selected by the caller. Other embodiments provide speech concatenation processes that have co-articulation and real-time subject-matter-based word selection which generate human sounding speech. Other embodiments reduce the occurrences of falsely triggered barge-ins during content delivery by only allowing interruption for certain special words. Other embodiments offer special services and modes for calls having voice recognition trouble. The special services are entered after predetermined criterion have been met by the call. Other embodiments provide special mechanisms for automatically recovering the address of a caller.
Owner:MICROSOFT TECH LICENSING LLC

Text-based query expansion and sort method in image retrieval

InactiveCN101901249AGuaranteed a high degree of commonalityImprove accuracySpecial data processing applicationsData setImage retrieval
The invention belongs to the field of multimedia information retrieval and relates to a method for realizing thesaurus-based query expansion and sort in image retrieval. The method comprises a WordNet-based English word semantic similarity metric algorithm, a HowNet-based Chinese word semantic similarity metric algorithm, an expansion rule-based query expansion word selection and optimization algorithm and a retrieval result evaluation and optimization algorithm. In the method, an image search engine is improved by the relevant text processing method and the relevant semantic network dictionary; and the retrieval result is sorted through semantic expansion, user interaction and improved similarity measurement. Compared with the traditional method, the method has the advantages of high accuracy rate, high integrality and low space-time cost. The method has very important significance for performing high-efficiency image retrieval according to image high-layer semantic information and on the basis of a large-scale image data set, and has wide application value in the field of cross-linguistic and cross-media retrieval.
Owner:FUDAN UNIV

Electrical equipment defect detection and maintenance method

The invention provides an electrical equipment defect detection and maintenance method. The method includes the steps that a configuration file with a preset text format is generated according to attribute parameters, operating environment parameters and equipment state parameters of electrical equipment; text clustering processing including word segmentation, stop word screening, bag-of-words model establishment, feature word selection and feature vector model establishment is carried out on the configuration file, and automatic judgment and classification are carried out according to the similarity between defect information of the electrical equipment under the condition that how many defect types exist specifically is unknown beforehand; then, automatic matching is completed according to defect types having been known beforehand and corresponding keywords so as to obtain the defect type of the electrical equipment; accordingly, defect warning and maintenance can be carried out on the electrical equipment according to the defect type. By means of the method, the efficiency of defect detection and maintenance of the electrical equipment is improved, cost is reduced, and accuracy is improved as well.
Owner:ELECTRIC POWER RES INST OF GUANGDONG POWER GRID +1

Word memory learning system

The invention discloses a word memory learning system, which mainly comprises a word memory practice unit, a word memory challenge first attempt unit, a word memory self challenge unit and a word memory super challenge unit, wherein the word memory practice unit is to practice memorizing words in aspects of listening, reading and speaking by sounding or reading after the word pronunciation of a system; and the word memory challenge first attempt unit, the word memory self challenge unit and the word memory super challenge unit are all the databases of the system, and a word selection module and a timing module with a countdown function are combined to prompt a user of inputting the words in a limited time period for testing if the user memorizes the words and to provide a prompt step to strengthen the word memorizing efficiency when the response is incorrect.
Owner:林汉忠

Korean named entities recognition method based on maximum entropy model and neural network model

The invention belongs to the technical field of named entities recognition, and discloses a Korean named entities recognition method based on a maximum entropy model and a neural network model. The method comprises the steps that a prefix tree dictionary is built, when any one combined noun template or any one proper noun template is matched in an input sentence, the combined noun template or the proper noun template are recognized into a target word; the target word is obtained in a target word selection module, the target word is searched in an entity dictionary, and when only one subclass is matched, the subclass serves as a tag of the target word; the maximum entropy model is adopted, and various linguistics information is utilized; a feedforward neural network model is constructed; adjacency words form an entity tag through a template selection rule. All data used in the method is extracted in a training corpus with tags and a field-independent entity dictionary, the data is very easily migrated to other application fields, and the performance cannot be reduced obviously.
Owner:GLOBAL TONE COMM TECH

Method, device and system for providing search prompt message based on conversation

The invention discloses a method for providing a search prompt message based on conversation. The method comprises the steps of acquiring a word list of hot words; acquiring conversation messages, selecting a word from the acquired conversation messages according to the preset word selection strategy, and matching the word with the word list of the hot words; setting up a search interlinking message of the selected word successfully matched with the word list of the hot words, and labeling the selected word. According to the application of the method, a device and a system which are disclosed by the invention, a user is helped to search, the search requirements of the user can be known at any time, the operation complexity brought to the user making a search is reduced and the user experience is enhanced.
Owner:TENCENT TECH (SHENZHEN) CO LTD

Searching for a Directory in a File System

Methods, apparatus, and products for searching for a directory in a file system are disclosed that include selecting, by a word selection module for inclusion in a word list, a word of text whose frequency of occurrence meets a predefined criterion; inserting, by the word selection module into the word list, the selected word; inserting, by an indexing module into a search index, the selected word in association with the directory name; receiving, by a search module from a user, a search request that includes the selected word; and returning, by the search module to the user in dependence upon the search request and the search index, a search result that includes the directory name. The directory is characterized by a directory name and includes computer storage resources, the computer storage resources including words of text, each word of text characterized by a frequency of occurrence among the computer storage resources.
Owner:DOORDASH INC

Unsupervised automatic extraction method of microblog new words based on repeated word strings

The invention discloses an unsuspervised automatic extraction method of microblog new words based on repeated word strings. The method includes the steps that firstly, text segmentation is conducted on microblog documents to be processed, texts are segmented through a dynamic programming word segmentation method, the word strings to be recognized are segmented, and word segmentation fragments in the word strings to be recognized are combined into the new words to be recognized; candidate new words are extracted from the word strings to be recognized according to a statistic word selection model, and then the candidate words are filtered through a rule filtering model, and eventually the final new words are acquired. The method has the advantages that the high accuracy rate is effectively guaranteed, the method does not depend on a rule word stock too much, and the extraction speed of the new words is guaranteed.
Owner:HEFEI UNIV OF TECH

Text display apparatus and recording medium recording text display program

Disclosed is a text display apparatus including: a display section; a dictionary storage section to store dictionary information composed of a headword of a first language corresponded to description information of a second language; a text storage section to store text data of the first language; a text / translation display control section to display text data and to display a portion of the description information as an initial translated word in the second language; a selection section to select a word; a description information display control section to display the description information; and a translated word selection section to select a portion of the description information as a selected translated word, wherein the text / translation display control section includes a selected translated word discrimination display section to replace the initial translated word to display the selected translated word with a display form different from the initial translated word.
Owner:CASIO COMPUTER CO LTD

Method and apparatus for generating a keyword list from tables to facilitate searching an electronic catalog

A computer-implemented method is described, for searching for items in an electronic catalog, e.g. an on-line catalog accessible over the Internet. A hierarchy of category names is defined, each item in the electronic catalog being associated with one of those category names. When a search page is accessed, the category names are scanned, to generate a list of words that appear in the category names at any level of the hierarchy. The list of words is displayed in the search page, allowing a user to select one. When the user selects a word from the list, a list of items whose category names contain the selected word is displayed.
Owner:FUJITSU SERVICES

Method and device for showing candidate items based on input method

The embodiment of the invention provides a method and device for showing candidate items based on an input method. The method comprises the steps of determining target character strings of currently unselected candidate items, wherein the candidate items comprise candidate phrases or candidate words; searching candidate phrases matched with part or all of the target character strings; searching candidate words matched with first characters in the target character strings; and showing at least part of candidate phrases and at least part of candidate words in a candidate column. According to the method and device for showing the candidate items based on the input method, on the conditions of no correct result and the like, users can direct perform single word selection in the candidate column, reduce operations of page turning and sliding and improve input speed and user experience; the input method does not needs to repeatedly respond to the operations of page turning and sliding, and resource consumption is reduced.
Owner:北京鸿享技术服务有限公司

Speech recognition device and speech recognition method and recording medium utilizing preliminary word selection

A speech recognition apparatus in which the accuracy in speech recognition is improved as the resource is prevented from increasing. Such a word which is probable as the result of the speech recognition is selected on the basis of an acoustic score and a linguistic score, while word selection is also performed on the basis of a measure different from the acoustic score, such as the number of phonemes being small, a part of speech being a pre-set one, inclusion in the past results of speech recognition or the linguistic score being not less than a pre-set value. The words so selected are subjected to matching processing.
Owner:SONY CORP

Deep learning-based natural language generation method

The invention discloses a deep learning-based natural language generation method. The method comprises the steps of training a comment generation apparatus by using existing news and comments. The training stage comprises the following steps of S1, performing vectorization processing on words in the existing news and comments to obtain word vectors corresponding to the words in the news and word vectors corresponding to the words in the comments; S2, obtaining hidden state vectors of the words in the news; S3, obtaining hidden state vectors of the words in the comments; S4, processing the words in the comments to obtain new hidden state vectors of the words; and S5, according to the obtained new hidden state vectors of the words in the comments in the step S4, predicting the next word corresponding to each word: according to the hidden state vector of the current word, obtaining a probability of selecting each word in a word table, and selecting the word with the maximum probability asthe next word of the current word in the generated comments. According to the method, the corresponding news comments can be generated for the given news, and the accuracy of word selection in the comments is relatively high.
Owner:SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV

Method and device for intelligently selecting words

An intelligent word selection method and device, the method comprising: detecting a first area touched in a word selection state; expanding the first area into a second area according to a preset pixel value; identifying the text in the second area; according to the identified text, conducting word segmentation calculation on the text to obtain a word segmentation result; and displaying the word segmentation result for a user to select words. The device comprises a detection module, an expansion module, an identification module, a word segmentation module and a display module. The present invention does not require a user to utilize an adjusting bar for manual adjustment, thus reducing selection errors, and automatically provides corresponding words for a user to directly choose from, thus realizing intelligent word selection, improving word selection precision, and facilitates subsequent operations.
Owner:TENCENT TECH (SHENZHEN) CO LTD

Association dictionary creation apparatus

An association dictionary creation apparatus is provided that is capable of easily and efficiently creating an association dictionary suiting the user's taste. The association dictionary creation unit includes: a profile storage unit that stores a profile which is information regarding the user's taste; a word selection unit that determines, every predetermined time, a word from the profile stored in the profile storage unit as an associated word search word, and further, selects words, other than the associated word search word, included in the profile as the associated word candidates; and an association degree calculation unit that calculates the degree of association between the associated word search word and each associated word candidate word selected by the word selection unit with reference to the contents stored in the contents storage unit, and when the association degree is higher than a predetermined threshold value, sets the associated word search word and the associated word candidate word as the associated word pair and stores the associated word pair and the association degree in the association dictionary storage unit in association with each other.
Owner:GK BRIDGE 1

Internet image search based Web verification code generation method

The invention discloses an Internet image search based Web verification code generation method. The method comprises the steps of key word selection, picture searching and caching, picture preprocessing, user operation, verification and the like. Nouns are randomly selected from a word bank, and picture resources corresponding to the nouns are obtained by utilizing a search engine, so that corresponding relationships between certain nouns and pictures are generated; the relationships are real and can be conveniently identified by users, but difficultly distinguished by computer programs, so that the Web phenomenon that certain malicious programs masquerade as users to perform unreasonable operations can be avoided, and the security and reliability of a network can be improved. The method solves the technical problems such as poor user experience and high possibility of automatically identifying and cracking the content of verification codes by programs in a verification process for an existing verification code technology. The method has the advantages of being large in verification code space, high in reliability, simple in verification process, quick in user identification, good in user experience and the like.
Owner:NANJING UNIV OF SCI & TECH

Text categorization method based on probability word selection and supervision subject model

ActiveCN103473309AAccurate classificationReduce the cumbersome preprocessing processSpecial data processing applicationsWord selectionWord list
The invention discloses a text categorization method based on probability word selection and a supervision subject model. The method includes the following steps that (1) punctuation marks in a training text are removed, word frequency information and category information are collected, and a word list and a category list are formed; (2) a subject proportion vector, a subject word matrix, a subject word distinguishing degree matrix and a regression coefficient matrix are initialized; (3) the subject proportion vector, the subject word matrix, the subject word distinguishing degree matrix and the regression coefficient matrix are updated according to the word list of the training text and category iteration of the word list; (4) for a testing text, the word frequency information is collected, and categorization is conducted by using the subject proportion vector, the subject word matrix, the subject word distinguishing degree matrix and the regression coefficient matrix. By means of the method, a complex pre-processing process during text categorization can be reduced to the maximum degree, and the testing text can be categorized more accurately. By means of the method, the distinguishing degree of words in a subject can be excavated, and the significance of the words in the text can be displayed visually.
Owner:ZHEJIANG UNIV

Text classification method for different subject topics

The invention is suitable for the technical field of data pre-processing, and provides a text classification method for different subject topics. The method comprises the following steps of: A, performing word selection on each subject by using a chi-square test to form a feature vocabulary of the subject; B, performing subject classification on the selected feature words by using a Naive Bayes model; and C, performing secondary classification on first two structures with maximum probabilities given in the Naive Bayes model classification by using a support vector machine to obtain a first result. Through two-time classification, the average accuracy of classification is improved. The text classification method for different subject topics is simple to realize and operate, convenient and accurate to use and more accurate in classification between the subjects, and effectively improves the accuracy of classification between the adjacent subjects.
Owner:深圳市点通数据有限公司

Machine translation apparatus, method and program

The invention provides a machine translation apparatus, a method and a program. The machine translation apparatus includes a translation unit for translating an original text of a first language into a translated text of a second language; a translated word candidate acquisition unit for acquiring more than one second translated word different from the first translated word for an original word in the original text corresponding to the first translated word in the translated text, and taking the first translated word and the second translated word as translated word candidates; a fluency calculating unit for calculating the fluency of the translated word candidates, wherein the fluency represents the suitability of the translated word candidates when the candidates are inserted into the insertion position of the first translated word in the translated text to generate a natural translated text; a reverse translation unit for obtaining more than one reverse-translated word for each of the translated word candidates by reverse-translating each translated word candidate into the first language; a similarity calculating unit for calculating the semantic similarity of the reverse-translated words to the original words in the first language; and a translated word selection unit for selecting a corrected translated word to be replaced with the first translated word from among the translated word candidates based on the similarity and fluency.
Owner:KK TOSHIBA

Iteration-based three-step unsupervised Chinese word segmentation method

The invention discloses an iteration-based three-step unsupervised Chinese word segmentation method and belongs to the field of natural language processing technology. According to the basic thought,the method is an unsupervised word segmentation framework including local segmentation, global word selection and corpus reduction iteration execution; and in each iteration, a word formation probability model based on segmentation-context mutual independency is utilized to perform locally optimal unsupervised segmentation on text corpus, and the form is simple and effective; a document-level pulse weighting method is adopted according to the long-tail phenomenon; according to a global support degree, new words are screened, and a dictionary is incrementally generated; and last, a text is divided based on the longest matching and maximum probability principle of the dictionary, formed segmented words are filtered out, continuous non-segmented words are stitched, the words are reconstructedinto a scale-reduced training corpus, and similar iteration processing is performed on the remaining corpus till no new word is generated. The method is superior to an existing Chinese unsupervised word segmentation algorithm with best performance.
Owner:北京时空迅致科技有限公司

Equipment maintenance method in 10kV voltage substation operation

The invention discloses an equipment maintenance method in 10kV voltage substation operation. The method comprises steps: attribute parameters, operation environment parameters and state parameters of the equipment are firstly generated into a configuration file with a predetermined text format; technical means such as text clustering and text classification are then used for carrying out numerical value and text data source-based association, clustering and classification on massive equipment information, that is, test clustering processing of word segmentation, stop word screening, word bag model building, feature word selection and feature vector model building are carried out on the configuration file, and automatic judgment and classification are carried out on similarities between equipment fault information; according to a fault type cleared in advance and corresponding key words, automatic matching is completed, and the equipment fault type can be accurately obtained. An equipment state development and change law is obtained, the equipment is maintained according to the law, the equipment fault detection efficiency and the maintenance efficiency are improved, the cost is reduced, and accuracy is improved.
Owner:STATE GRID CORP OF CHINA +1
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products