117 results about "Natural language analysis" patented technology

An improved system and method for revising natural language parse trees is provided. A revision dependency parser may learn a set of transformation rules that may be applied to dependency parse trees generated by a base parser for revising the dependency parse trees. A corpus of natural language sentences and a set of correct dependency parse trees may be used to train a revision dependency parser to correct dependency parse trees generated by the base parser. A revision engine may compare the dependency parse trees produced by the base parser with the correct ones present in the training data to produce an observation-rule pair for each dependency. A rule may specify a transformation on the predicted dependency parse tree generated by the base parser to replace an incorrect dependency with a corrected dependency or may change the type of dependency expressed for the grammatical function of the dependent word.

System and methods are disclosed for providing answers to search queries, and for searching using association data without requiring keyword matching. Datasets representing objects and their properties are created from unstructured data sources based on natural language analysis methods, and can be used to answer queries about objects or properties of objects. Implementations include general information search engines and embodiments for searching products, services, people, or other objects without knowing the names of such objects, or searching for information about known objects by using either keyword-based queries or natural language queries such as asking questions. System and methods are also provided for creating a structured or semi-structured representation of various unstructured data, in contrast to the conventional term-vector or term-document matrix representation.

A system for natural language analytics, stored and operating on a network-connected computing device, comprising a natural language application data importer, further comprising a natural language application data importer, a natural language application data augmenter that enriches the data and an analytics component which provides a means of querying structured as well as unstructured data and which also contains a method for providing adaptive natural language analytics.

The invention provides a device for automatically formatting and unionizing medical documents written in natural language. The device comprises medical documents which are based on electric case history systems used in Chinese hospitals and written in the natural language, a Chinese medical standard word library which is classified according to disease type, a natural language analysis based data pick-up system which is used for converting the documents written in the natural language into the standard formatting document, a database which is classified according to the disease type and used for clinical scientific research, a document conversion system used for automatically converting the formatting document into the standard document with consolidation form, and a privilege system used for protecting private information of patients and doctors treating the patients. The device has the advantages of realizing automatization of the medical information management, making the doctors conveniently and quickly look up information related to certain disease, greatly saving time and making the doctors have more energy to be put in the disease research.

The invention relates to a field of instant messaging and provides a customer service method, a customer service system and a customer service device based on the instant messaging. The method includes the following steps: A. a server receives a consultation sentence sent by a user client and applies natural language analysis to the consultation sentence according to stored language experience data; B. the server searches for an answer matched with an analysis result in the stored customer service resource data; and C. the server sends the acquired answer to the user client. The server is utilized to carry out the natural language analysis of the consultation sentence sent by the client available for the user and to feed the found answer corresponding to the analysis result back to the client available for the user in the invention. The method is independent from an artificial mode to automatically reply the consultation, thus lowering workload of personnel for the customer service and enhancing the efficiency, accuracy and timeliness of the customer service.

A system and method delivers marketing messages based on location specific check-ins. This permits highly targeted communications directed at first entities such as persons, organizations, or businesses who are patrons of second entity locations which are typically businesses. Selection of first entities is based on detection of past or potential patronage of second entities through social media or other public digital content check-ins. Check-ins are analyzed to identify any second entity referred to and associating such reference to the author of the content. Second entities, such as a merchant or brand, may be explicitly determined from meta-data of source content, or implicitly through processing such as natural language analysis or association through a third entity. Second entities use such connections to deliver targeted marketing messages through a public social media profile of the first entity. Analytics may be used to track of check-in patterns and effectiveness of marketing campaigns.

The invention discloses a public transportation passenger satisfaction evaluation method and system based on a public opinion knowledge graph, and comprehensively considers a passenger satisfaction analysis method based on questionnaire survey and public transportation network public opinion. A network public opinion analysis technology, a natural language analysis method, a public transport knowledge graph, machine learning and other methods are applied to make a powerful supplement to traditional public transport passenger satisfaction analysis. The method mainly comprises the following steps: implementing text acquisition and processing analysis; completing modeling and storage of the public transport public opinion knowledge graph; acquiring and analyzing satisfaction information of'diving 'passengers; achieving public opinion index mapping, service score research and judgment and construction of a historical event method library. According to the method, text topic classificationand satisfaction index positioning are achieved, and corresponding relations between satisfaction and departments and responsibilities thereof are defined, so that powerful supplements can be providedfor traditional public transport passenger satisfaction analysis, and more scientific reference opinions can be provided for understanding public transport passenger demands and related department service shortages.

The invention discloses a public testing error report priority sorting method based on natural language analysis. The public testing error report priority sorting method based on the natural language analysis is characterized by using the natural language analysis to sort error reports submitted by public testing people. The public testing error report priority sorting method based on the natural language analysis provides a brand-new public testing report sorting technology based on a public testing scene, and the brand-new public testing report sorting technology based on the public testing scene is mainly used for solving the problems that there are too much error reports, and a professional tester cannot examine all the error reports under the public testing scene. The public testing error report priority sorting method based on the natural language analysis has beneficial effects that the dynamic public testing report sorting technology is used, the tester can change a distance matrix in real time while examining the results, and accordingly the examining efficiency is higher; when the tester cannot examine timely, an examiner can guarantee a high examining efficiency in the subsequent examination by means of a static public testing report sorting technology.

The invention relates to the field of natural language processing, and particularly relates to an enterprise industry classification method based on fully-automatic learning. The method of the invention uses a recurrent neural network to carry out fully-automatic feature learning on a business scope of a to-be-classified enterprise and automatically divides the to-be-classified enterprise to a corresponding industry scope. The method breaks domain barriers of the natural language and the neural network technology, and automatic enterprise industry classification based on natural language analysis is realized. The method does not need to manually select features, the defect that manual feature selection in the traditional method deviates from a specific sample is solved, the developer pays more attention to the task itself and data reserve, the working efficiency is enhanced, and as the recurrent neural network is used, longer sequence features can be captured by the model, the industry classification accuracy can be greatly enhanced, and more accurate basic data are provided for business and finance analysis.

A method and a system for natural language processing of digital content objects, such as news stories, which ranks named entities in digital content objects by the impact that digital content objects that mention them are having on social media, is provided. Digital content objects are scored on a per object basis based on social media activity metrics associated with that digital content object. Named entities that appear in each digital content object are also extracted through natural language analysis. The named entities are then scored on a per entity basis to obtain an entity score that the object scores of those digital content objects in which that named entity appears. An entity ranking list can be created based on the entity scores, which can then be used in various different ways. For example, the entity ranking list can be displayed on a graphical user interface.

The invention relates to the field of processing of natural languages, and in particular relates to an information classification prediction system based on full-automatic learning. The system comprises a data storage module, a word segmentation module, a dictionary mapping table module and a recursive neural network module, wherein the data storage module is used for storing basic data; a dictionary mapping table maps words in an information text to be classified into vector data, and then inputs the vector data into a recursive neural network at a corresponding time; and the recursive neural network predicts the classification probability of information to be classified after recursion is ended. According to the system disclosed by the invention, the field barrier between the natural language and the neural network technology is broken; automatic classification of the enterprise industry based on natural language analysis is realized; manual feature selection is unnecessary; the disadvantage that manually selected features deviate from a specific sample in the traditional method can be avoided; the recursive neural network is used; a longer sequence feature can be captured by the model; the industry classification accuracy is improved; and a rapid and reliable industry classification tool is provided for related data analysis.

The invention provides a website information identification method and device and electronic equipment, and the method comprises the steps: obtaining the content of a target website according to the address of the target website, wherein the content comprise text contents, picture files and display effect screenshots; performing accurate matching and/or natural language analysis processing on the text content according to a preset sensitive violation lexicon, and determining a text recognition result of the target website; and performing image classification recognition based on deep learning on the image file and the display effect screenshot according to preset sample images with different types of tags, and determining an image recognition result of the target website. After the content of the target website is obtained, the text content is accurately matched and/or analyzed and processed in a natural language to obtain a text recognition result; and deep learning is carried out on the picture file and the display effect screenshot to obtain a picture recognition result. Whether the website has bad content or not can be effectively judged, and the misjudgment rate is reduced.

An embodiment of the invention discloses a public opinion analysis method, and further provides a corresponding device. The public opinion analysis method comprises the steps that the public opinion analysis device acquires a keyword which is set by a user in advance, news which includes the keyword is acquired according to the keyword, the early warning level of the news is analyzed through a natural language analysis method according to the acquired news, a current public opinion health index of the user is calculated, and a coping strategy corresponding to the public opinion health index is displayed to the user. By the adoption of the public opinion analysis method, current public opinion state analysis can be provided for the user, and the purpose that intuitive decision reference and guidance are provided for the user is achieved.

The present invention provides a natural language processing method, an apparatus and a device thereof. The natural language processing method comprises the following steps of: acquiring information input by a user at present, detecting whether the information has a missing intent object, and/or a missing intent purpose; if it is detected that the information has the missing intent object, and/orthe missing intent purpose, then calling an exclusive corpus corresponding to the user so as to acquire historical corpus information of the user; performing natural language analysis for the historical corpus information of the user, and extracting a filling information matched with the missing intent object, and/or the missing intent purpose; combining the filling information and the informationinput at present into a complete target information, and performing corresponding processing according to an intent object and an intent purpose in the target information. Therefore, the integrationof an ambiguous speech data is realized, then the response efficiency of man-machine interaction can be improved, and the user experience of the man-machine interaction is improved.

The invention discloses an intelligent interactive method and device of natural language analysis. The intelligent interactive method comprises the following steps: collecting a work order record, carrying out data analysis on information in the collected work order record, and trimming common problems of common knowledge points with high click rates; collecting and compiling related knowledge points for the trimmed knowledge titles, compiling corresponding linguistic data of the corresponding knowledge points, and creating a knowledge base; carrying out reverse index with semantic retrieval on the linguistic data input by a user, and carrying out primary screening index in the knowledge base according to keywords of the linguistic data; recalling the knowledge points of the keywords contained in the current problem in combination with a context scene of the user, and processing on thesaurus and correction word level; merging and combining the recalled knowledge points according to semantic, and establishing a semantic relation; and carrying out semantic analysis on an input content of the user, matching the input content with the established semantic relation, and deleting unmatched knowledge points in a continuous interaction process with the user.

The invention refers the conventional natural language analysis technology, and discloses a language analysis and instruction analysis algorithm based on large logistics management software. In one aspect, instruction information of an instruction of a natural language input by a user can be extracted through a semantic analysis engine, wherein the instruction information includes key information such as an instruction operation target, an operation command and parameters; in the other aspect, an execution demand of the user and an actual resource condition of a system is combined through an instruction analysis engine, and an executable scheme including an AJAX format command and description information is fed back to the user; and a semantic analysis intelligent instruction robot applied to logistics management software is established by combination of the two aspects, the user can directly input a natural language type instruction to directly operate the logistics management software, and the fuzziness and ambiguity of the natural language can be supported to some extent; the problem that the conventional management software is complex in interface, and an operator is difficult to operate the conventional management software can be solved; man-machine interaction is humanized and simple; and the operation efficiency is high.

The invention relates to a natural language analysis technology, and aims to provide a text sentiment analysis method based on a hybrid supervision model. The method comprises the following steps: performing strong supervision qualitative analysis by using a qualitative sentiment analysis model based on a composite neural network, constructing the composite neural network by combining LSTM and CNN, and extracting sequence features and multi-dimensional features of a text at the same time to more accurately predict the sentiment polarity credibility of the text; achieving weak supervision quantitative analysis based on a syntactic analysis tree, and obtaining the hierarchical modification relation of sentences by conducting word segmentation on the sentences and constructing the syntactic analysis tree; performing recursive upward labeling and calculation according to the sentiment dictionary, and calculating the sentiment intensity value of each sentence; multiplying the credibility bythe emotion intensity to obtain the final emotion intensity of the text. According to the hybrid supervision model provided by the invention, the advantages of two calculation modes in the prior artcan be taken, and an analysis result with credibility and fineness can be given.

An operating device for natural language input is disclosed. A user can express its own request to the operating device by inputting natural language, then a processor determines format of natural language, if the natural language is voice format, a voice identification cell transforms it into word data and transmits to a natural language analysis unit; if the natural language is word or character identification format, the natural language analysis unit directly analyzes sentence type and issues a instruction accordingly, and then, an executive interface is to find out a matched equipment end to transmit the instruction for operating in real time, such design can respond to equipment end as required by the user so as to achieve a best man-machine communicating channel.

The invention discloses a net-based survey voting system, which comprises a voting information statistic unit for receiving the voting information in the natural language from the user, analyzing the natural language and comprehending to obtain the comprehended result, conducting statistics to obtain a result of the survey being conducted. The invention also discloses a method, by using the provided system and method, a flexible survey will be implemented.

Techniques are disclosed herein for resolving a natural language query. Input (e.g., text input, audio input) corresponding to a query requesting data is received. A type of the query is determined based on a natural language analysis on the query. A form of response to the query is identified based on the type of the query. A visualization associated with the form of response is identified. The visualization is presented via a user interface. The presented visualization includes the requested data.

A method and computer system for analyzing a text corpus in a natural language is provided. An initial morphological description having word inflection rules for various groups of words in the natural language is created by a linguist. A plurality of text corpuses are analyzed to obtain information on the occurrence of a plurality of word forms for each word token in each text corpus. A morphological dictionary which contains information about each base form and word inflection rules for each word token with verified hypothesis is generated.

The invention discloses a method and a system for searching relational complex management information system data in a natural language. The system comprises a natural language analysis module which carries out semantic analysis on search conditions input by a user according to a semantic analysis table, recognizes table names, attribute names and attribute values in the input conditions respectively, matches the attribute names and the attribute values according to rules, and completes logic recognition and combination of multiple conditions according to a matching result and set rules; a data query module which is used for processing the data analysis result according to the single-table association search logic and the hierarchical search logic, converting the processed query conditioninto an SQL query statement to execute query, and submitting the query result to the data security control module; a data security control module which realizes two levels of authority control; And asearch result display module which is used for submitting the data information to a user in the form of service information rather than pure form data. According to the system, the data availabilityis improved, and meanwhile, the data utilization rate is also increased.