64 results about "Natural language parsing" patented technology

The system retrieves information from the internet using multiple search engines that are simultaneously launched by the search engine commander. The commander is responsive to a speech-enabled system including a speech recognizer and natural language parser. The user speaks to the system in natural language requests, and the parser extracts the semantic content from the user's speech, based on a set of goal oriented grammars. The preferred system includes a fixed grammar and an updatable or downloaded grammar, allowing the system to be used without extensive training and yet capable of being customized for a particular user's purposes. Results obtained from the search engines are filtered based on information extracted from an electronic program guide and from prestored user profile data. The results may be displayed on screen or through synthesized speech.

The present invention provides a method and a parser for syntactically analyzing an input string. The parser applies a plurality of rules which describe syntactic properties of the language of the input strings. The plurality of rules comprise two types of rules. A first type of rules comprises immediate dominance rules and linear precedence rules. A second type of rules being sequence rules. All rules of the plurality of rules are applied according to a predefined order to the input string. This new incremental parsing architecture has advantages with respect to grammar engineering and allows a more efficient parsing.

The present invention is uniquely designed to interact with web retailer's customers with real agent reaction times as they give astute answers directly concerning web retailer's products and goals. The entire process is manageable through a third-party website which includes scripting, settings and other parameters selected by the web retailer. An artificial intelligence engine uses the combination of Bayesian probability keyword selection, natural language parsing and regular expression processing. The technology updates its response database with every client interaction-learning always takes place as it simulates a live agent, in real time. Every client interaction is recorded and analyzed, and as a result of the analysis the changes in the answer database are made.

There is disclosed a method of facilitating interaction between users of an electronic community. In an embodiment, the method comprises: reviewing a user activity log for each user in the electronic community; executing a natural language parser to extract significant noun phrases from the user activity log; updating user profiles from the newly extracted noun phrases, based on their usage frequency and importance value; and storing the updated profiles in a user profile and relationship data base; and executing a similarity based clustering algorithm to cluster user profiles, thereby discovering relationships among users and storing them in a user profile and relationship database. The method may further comprise displaying for each user the one or more relationships to which the user is assigned, together with a list of users assigned to the one or more relationships. The method may also comprise storing for each user the relationship to which the user is assigned in a user profile and relationship database.

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.

Semantic understanding of hypotheses returned by a speech engine could improve the quality of recognition and in cases of misrecognition speed the identification of errors and potential substitutions. Unfortunately, semantic recognition using natural language parsers is hard since semantic and syntactic rules for processing language are complex and computationally expensive. Additionally, semantic recognition should be performed in a knowledge domain—a domain of interest such as radiology, pathology, or tort law. This adds additional complexity to building semantic rules. The method described achieves semantic understanding by coupling a speech recognition engine to a semantic recognizer, which draws from a database of domain sentences derived from a document corpus, and a knowledge base created for these domain sentences. The method is able to identify in near real-time the best sentence hypotheses from the speech recognizer and its associated meanings, i.e. propositions, which belong to the knowledge domain, and if no hypotheses are found mark it as invalid for easy identification. For invalid sentences, closely matched sentences from the domain database can be displayed to speed correction. The semantic propositions can be semantically typed, such as normal and abnormal, further aiding in the identification of recognition errors. The system automatically displays the semantic meaning of related ideas of valid sentences by retrieving proposition (s) from the knowledge base.

The present invention discloses an intelligent interactive question-answering system, which includes a knowledge module used to provide information for the user to query; an interactive module used for information interaction between the system and the user; and a processing module used for searching the answering information in knowledge module according to the question of the user; the knowledge module includes a question classification base used to store the question information and a knowledge base used to store the answering information; the processing module includes a semantic analysis module used to analyze the natural language for the problem of the user to generate query conditions; an information searching module used to search in the knowledge base according to the query condition; and a result generation module used to generate answers according to the searching results. The present invention discloses a question-answering processing method of an intelligent interactive question-answering system simultaneously. The present invention provides a rapid and simple system and method for obtaining the demanded information, so as to improve the processing ability for problems and the processing accuracy.

A computer readable medium for analyzing and predicting the future behavior of organizations is disclosed. An embodiment of this invention is comprised of one or more repositories of data which involve comments or other actions by actors with some kind of relationship to a target organization, a repository of metadata relating to this data, a repository of updatable models of organizations, a natural language parsing engine, an engine for generating and comparing the organizational models, and presentations of avatars.

A computer readable medium for analyzing and predicting the future behavior of organizations is disclosed. An embodiment of this invention is comprised of one or more repositories of data which involve comments or other actions by actors with some kind of relationship to a target organization, a repository of metadata relating to this data, a repository of updatable models of organizations, a natural language parsing engine, and an engine for generating and comparing the organizational models.

A natural language parser creates parsed commands or output for an external system from user commands entered on a user interface. The parser utilizes symbols arranged in an object-oriented hierarchical manner, and a grammar information and state table to constrain language inputs so that they conform to requirements of the external system. The parser provides feedback to the user via the user interface to assist in the formation of valid output to the external system and reduce the complexity for the user. The parser may be applied to the field of control systems in general, as well as a flight control system for an aircraft.

The present invention provides a technique for building natural language parsers by implementing a country and / or jurisdiction specific set of training data that is automatically converted during a build phase to a respective predictive model, i.e., an automated country specific natural language parser. The predictive model can be used without the training data to quantify any input address. This model may be included as part of a larger Geographic Information System (GIS) data-set or as a stand alone quantifier. The build phase may also be run on demand and the resultant predictive model kept in temporary storage for immediate use.

A method and system converts statements entered in an ordered natural language into an event-driven model, which may be easily parsed to discover missing or contradictory conditions. A user interface allows a user to enter functional requirements of a design into the system in a well-defined manner. An ordered natural language parser checks each phrase entered by the user for syntax errors and alerts the user of errors or unclear statements. Once any ambiguities are resolved, an engine generates a dynamic event-driven sub model. A parser checks the sub model for logical errors, such as missing or contradictory conditions and alerts the user of the same. A second engine then generates a complete dynamic event-driven model, which can be a combination of several sub models. The complete model can then be simulated and validated.

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.

The present invention is uniquely designed to interact with web retailer's customers with real agent reaction times as they give astute answers directly concerning web retailer's products and goals. The entire process is manageable through a third-party website which includes scripting, settings and other parameters selected by the web retailer. An artificial intelligence engine uses the combination of Bayesian probability keyword selection, natural language parsing and regular expression processing. The technology updates its response database with every client interaction-learning always takes place as it simulates a live agent, in real time. Every client interaction is recorded and analyzed, and as a result of the analysis the changes in the answer database are made.

The invention provides a method and device for a semantic analysis of a natural language. When a received natural language corresponds to at least two lexemes in a preset data base, a lexeme of the natural language is determined according to a history analytic result. In other words, the history analytic result serves as reference, and the lexeme of a current natural language is analyzed. Generally, the use habit of a user has continuity. Therefore, the purpose of current operation of the user can be reflected through the history analytic result. Therefore, when the natural language corresponds to more than one lexeme, instead of only depending on the preset data base to determine the analytic result, the method and device for the semantic analysis of the natural language can deduce the purpose of the user. Therefore, accuracy of the analysis of the natural language can be improved.

The present invention is uniquely designed to interact with web retailer's customers with real agent reaction times as they give astute answers directly concerning web retailer's products and goals. The entire process is manageable through a third-party website which includes scripting, settings and other parameters selected by the web retailer. An artificial intelligence engine uses the combination of Bayesian probability keyword selection, natural language parsing and regular expression processing. The technology updates its response database with every client interaction-learning always takes place as it simulates a live agent, in real time. Every client interaction is recorded and analyzed, and as a result of the analysis the changes in the answer database are made.

The present invention discloses a method and apparatus for improving the performance of a natural language parser. During training, natural language inputs are processed such that statistical information is extracted, concerning the frequency of attachment of certain phrase types of interest to certain other host phrase types. In one embodiment, only unambiguous attachments are examined during training. During runtime this statistical information is used in cases where the attachment of some phrase type of interest is ambiguous. In such cases, the statistical model is used to evaluate the relative likelihood of the alternative attachments resulting in a good interpretation. A syntactic representation can be produced for each alternative attachment that the statistical model deems likely to result in a good interpretation.

In the invention, the information enquiring system comprises: a front-end enquiry subsystem used for transmitting the received natural language type enquiry request to the information enquiring server, and relaying the information enquiry result returned from the information enquiring server; a information enquiring server used for extracting the key words from the information enquiring request, and using the extracted key word to make enquiry in its information data-base. By the invention, users can uses natural language to enquire the database of the information enquiring serve by means of network chat.

The present invention is uniquely designed to interact with web retailer's customers with real agent reaction times as they give astute answers directly concerning web retailer's products and goals. The entire process is manageable through a third-party website which includes scripting, settings and other parameters selected by the web retailer. An artificial intelligence engine uses the combination of Bayesian probability keyword selection, natural language parsing and regular expression processing. The technology updates its response database with every client interaction-learning always takes place as it simulates a live agent, in real time. Every client interaction is recorded and analyzed, and as a result of the analysis the changes in the answer database are made.

The invention discloses a method, a system and a server for product or service reservation through network, wherein, the method is as follow: a reservation sentence is sent to a reservation server via a reservation information sending apparatus in instant message form; the received reservation sentence is analyzed to natural language by the reservation server, and the demand description information and the characteristic information of users is obtained; the product or service meeting the user demand is queried in the information database of product or service by the reservation server depending on the demand description information; the order is generated based on the queried description information of product or service and the characteristic information of users; the system comprises the reservation information sending apparatus and the reservation server; the product or service reservation server comprises a information interface module, a query module and an order generation module. The invention has the advantages of convenient and instant product or service reservation for users through the instant message, and simultaneous human resource saving for product or service providers.

A computer-implemented method for developing a parser is provided. The method includes accessing a corpus of sentences and parsing the sentences to generate a structural description of each sentence. The parser is trained based on the structural description of each sentence.

The embodiment of the invention discloses a natural language analyzing method and device, a server and a storage medium, wherein the method comprises the following steps: cutting the natural languagetext to be analyzed to obtain a plurality of corresponding cutting fragments; obtaining at least one concept label by carry out concept labeling on each word segmentation segment; arranging and combining at least one concept tag to obtain a plurality of concept tag sequence; for each concept tag sequence, obtaining the intent and slot of the natural language text by combining the pre-established entity intent knowledge network, wherein the entity intent knowledge network comprises an entity intent set of a plurality of different service scenarios, and the entity intent sets of different service scenarios are related to each other through entities. The embodiment of the invention abstracts entities, different entities can reuse common intention knowledge, and different service scenarios only need to introduce required entity knowledge, so that the true intention of the related entities can be deduced quickly.

The embodiment of the invention discloses a natural language utilized distributed intelligent interaction achieving method and a system thereof. The natural language utilized distributed intelligent interaction achieving method includes that a human-computer interaction control module enables a request which is expressed in the form of natural language to be sent to a natural language parsing or understanding module and a processing result which is expressed in the form of machine language is obtained and returned to the human-computer interaction control module according to the request which is expressed in the form of the natural language; the processing result which is expressed in the form of the machine language is converted into a machine executable command; task analysis is performed on the machine executable command to obtain a task execution routing table; task processing is achieved through at least one processing node and a return result which is expressed in the form of the machine language is obtained; the return result which is expressed in the form of the machine language is converted into a return result which is expressed in the form of the natural language and sent to the human-computer interaction control module; display is performed through a human-computer interaction device. The embodiment of the natural language utilized distributed intelligent interaction achieving method and the system thereof can solve the complex problems and greatly improve the success rate of task achievement.

Systems, devices, and methods for automating network account transfers based on predicted inactivity are disclosed. In one embodiment, the system comprises a mail server providing access to an email account of a user; a social graph monitor configured to: periodically query, over a network, a social graph associated with the user to retrieve at least one social network feed associated with the user, calculate a sentiment score for the social network feed based on parsing the social network feed using a natural language parser, and determining that a transfer condition has occurred if the sentiment score exceeds a pre-defined sentiment score threshold; and a condition processor configured to: transmit, via the mail server, a password reset request to a network application associated with the transfer condition, intercept an email from the network application, via the mail server, transmitted in response to the password reset request, forward, via the mail server, the email to a recipient associated with the transfer condition, determine that the recipient has reset a password associated with the network application, and forward, to the recipient via the mail server, subsequent emails from the network application.

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.

A computer readable medium for analyzing and predicting the future behavior of Organizations, where an embodiment of this invention is comprised of one or more repositories of data which involve comments or other actions by actors with some kind of relationship to a target organization, a repository of metadata relating to this data, a repository of updatable models of organizations, a natural language parsing engine, an engine for generating and comparing the organizational models, and presentations of avatars.

The invention relates to an automatic structured carding method for a monitoring information table. The automatic structured carding method comprises the following steps: acquiring monitoring table information; establishing a monitoring information structured model; constructing a word bank; performing natural language analysis and machine learning; and performing inspection and identification. According to the automatic structured carding method, the electric power professional noun and the monitoring information knowledge base are expanded, and the monitoring information is automatically classified to the equipment identification basis; a basis is provided for tracing monitoring data to equipment-interval-wiring form-voltage class-transformer substation, manufacturers and equipment models, and a basis is established for subsequent big data analysis; and association between a large amount of monitoring information and equipment can be realized only by a small amount of human intervention. While the manpower is liberated, the working quality is improved, and the effective management of the monitoring information of the operation station is accelerated to a great extent.

Disclosed are embodiments of systems and methods that allow for simplified creation of a calendar event. In embodiments, an entry may be provided via a simplified entry form. In embodiments, the present invention simplifies the creation of an event through natural language parsing. Embodiments may enable creation of an event for a calendaring application and / or within an application that is not primarily a calendaring application, such as, by way of example, an email application, an SMS / text messaging application, an instant messaging (IM) application, and a social networking application.

The invention belongs to the technical field of computers and information services, and relates to a system for achieving Chinese near-natural language query interfaces. The system comprises a database management module for database operation, a natural language analysis module for morphology and semantic syntax analysis, and a natural language paraphrasing module for generating an intermediate language. The interfaces aiming at query operation in correlation fields are reserved in all the modules. By means of the database management module, task requirements in different fields can be correspondingly configured, and corresponding query systems are established. The system can be widely used for information query service systems in different fields and the like.

The present invention provides a technique for building natural language parsers by implementing a country and / or jurisdiction specific set of training data that is automatically converted during a build phase to a respective predictive model, i.e., an automated country specific natural language parser. The predictive model can be used without the training data to quantify any input address. This model may be included as part of a larger Geographic Information System (GIS) data-set or as a stand alone quantifier. The build phase may also be run on demand and the resultant predictive model kept in temporary storage for immediate use.