57 results about "Knowledge area" patented technology

The invention provides a system and method for improving speech recognition. A computer software system is provided for implementing the system and method. A user of the computer software system may speak to the system directly and the system may respond, in spoken language, with an appropriate response. Grammar rules may be generated automatically from sample utterances when implementing the system for a particular application. Dynamic grammar rules may also be generated during interaction between the user and the system. In addition to arranging searching order of grammar files based on a predetermined hierarchy, a dynamically generated searching order based on history of contexts of a single conversation may be provided for further improved speech recognition. Dialogue between the system and the user of the system may be recorded and extracted for use by a speech recognition engine to refine or create language models so that accuracy of speech recognition relevant to a particular knowledge area may be improved.

Embodiments are computer program product that provides systems and methods as a complete solution for management profession from initiation to closeout; complies with industry standards and requirements. Automated functionality through cloud server, standardized combination of database management systems with five web-based user's interfaces; for each organizational tier and for quick and emergency responses. On real time communication, simultaneous functionality of the integrated databases provides ultimate optimization while the unified filing system and document control solution facilitates system integrations of the management knowledge areas. Stakeholders utilize their permitted part(s) of the solutions to manipulate data through shared platform while classified data is saved for internal use. Automatically saving project related data, while synchronization while shifting from offline to online work environment. Public outreach enhancement with a project specific website displays permitted information to allow public search and view projects general information including alerts and status.

Techniques disclosed herein relate generally to constructing a customized knowledge graph. In one embodiment, entities and relations among entities are extracted from a user dataset based on certain rules to generate a seed graph. Large-scale knowledge graphs are then traversed using a finite state machine to identify candidate entities and / or relations to add to the seed graph. A priority function is used to select entities and / or relations from the candidate entities and / or relations. The selected entities and / or relations are then added to the seed graph to generate the customized knowledge graph.

The invention relates to an interactive mode learning system. The interactive mode learning system comprises a learning content module, an analysis control module and a network interactive mode learning terminal, wherein the learning content module is used for storing knowledge point sets of a plurality of subjects, each subject comprises a plurality of knowledge domains, each knowledge area comprises at least one knowledge chain, and each knowledge chain comprises a plurality of knowledge points; the analysis control module is used for taking out relative knowledge points from the learning content module according to the learned knowledge point collection P to test users so as to generate a learning knowledge point Y, a study plan is generated according to the learning knowledge point Y, and the study plan is output the network interactive mode learning terminal; and the network interactive mode learning terminal is used for taking out relativity knowledge point from the learning content module according to the study plan output by the analysis control module so as to learn by the users, learning tracks of the users are simultaneously recorded, and the learning tracks are fed back to the analysis control module so as to adjust the study plan. The interactive mode learning system provided by the invention can perform distinguished tuition and test according to individual difference and the master degree of knowledge points of trainees, and the established study plan is more scientific and more beneficial to improvement of the trainees.

The invention provides a system and method for improving speech recognition. A computer software system is provided for implementing the system and method. A user of the computer software system may speak to the system directly and the system may respond, in spoken language, with an appropriate response. Grammar rules may be generated automatically from sample utterances when implementing the system for a particular application. Dynamic grammar rules may also be generated during interaction between the user and the system. In addition to arranging searching order of grammar files based on a predetermined hierarchy, a dynamically generated searching order based on history of contexts of a single conversation may be provided for further improved speech recognition. Dialogue between the system and the user of the system may be recorded and extracted for use by a speech recognition engine to refine or create language models so that accuracy of speech recognition relevant to a particular knowledge area may be improved.

A method for data access includes defining an ontology (26) pertaining to a given sphere of knowledge. A computer (22) receives a search query generated using the ontology and provides to a user of the computer at least one document in response to the query. The computer receives tags that the user has associated with data elements in the at least one document and automatically updates the ontology responsively to the tags.

This invention relates to a method and a system for enabling measurement and control of immaterial / intellectual / intangible resources comprising a processing unit and a database, wherein the database comprises a data structure for a plurality of employees, the data structure comprising a plurality of identification data fields, each identification data field representing and identifying a given employee, at least one knowledge area data field, being associated with knowledge profile data and skill / competence profile data, representing a measure of knowledge and / or experience of an employee, and skill / competence profile data representing a measure of competence of an employee. By introducing measurable units for intangible / immaterial / intellectual assets it is possible to plan and control these resource in a department, company, holding company, company portfolio for venture capitalists, etc. in a very simple, efficient and structure manner which may be automated to a very high extent.

Embodiments are computer program product that provides systems and methods as a complete solution for management profession from initiation to closeout; complies with industry standards and requirements. Automated functionality through cloud server, standardized combination of database management systems with five web-based user's interfaces; for each organizational tier and for quick and emergency responses. On real time communication, simultaneous functionality of the integrated databases provides ultimate optimization while the unified filing system and document control solution facilitates system integrations of the management knowledge areas. Stakeholders utilize their permitted part(s) of the solutions to manipulate data through shared platform while classified data is saved for internal use. Automatically saving project related data, while synchronization while shifting from offline to online work environment. Public outreach enhancement with a project specific website displays permitted information to allow public search and view projects general information including alerts and status.

The invention provides a method for automatically obtaining short text of the knowledge domain from a community question-and-answer website.Question-and-answer web pages and author web pages of each subject of the domain corresponding to the knowledge domain can be crawled from the community question-and-answer website, a system with comprehensive data is obtained, and learning and using of a user are convenient.The method comprises the following steps that 1, a Web page of the knowledge domain in the community question-and-answer website is crawled; 2, short text, with concentrated web page data, of the knowledge domain is extracted; 3, a domain subject tree is constructed; 4, storing of the domain subject tree is conducted.By means of the method, the short text of the knowledge domain can be automatically extracted from semi-structured data of the community question-and-answer website, the question-and-answer web pages and the author web pages of each subject of the domain corresponding to the knowledge domain are crawled from the community question-and-answer website, a web page data set of the knowledge domain is constructed, the short text of the knowledge domain is automatically extracted from the web page data set, and parent child relationships are found, so that the domain subject tree is constructed, storing of the domain subject tree is achieved, and learning and using of the user are convenient.

The invention discloses a Unity3D-based knowledge forest virtual reality system realization method. The method comprises the steps of obtaining data, wherein the data comprises multiple knowledge domain topics, a cognitive relation among the knowledge domain topics, facets corresponding to the knowledge domain topics and knowledge fragments corresponding to the facets; establishing a knowledge domain topic facet tree; generating coordinate data of each knowledge domain topic through a hierarchical layout algorithm; on the coordinate data, generating coordinate data of points on each side through a numerical differentiation method; establishing a knowledge forest virtual scene; and customizing interaction of a virtual display controller. According to the method, the limitations of a two-dimensional visualization technology in forest scale, layout and interaction are broken through; a strong real sense is brought for users; and the method can be mastered by the users more easily.

The invention provides an adaptive learning system based on big data and deep learning and a construction method thereof. The system comprises a student module which is used for automatically recording a learning process, a learning behavior and a learning result of a learner; an intelligent analysis module which is used for performing learning behavior analysis according to the recorded learning data of the learner and the micro knowledge particles decomposed in the knowledge domain model, automatically evaluating the initial level, the learning target demand and the learning performance of the learner, and forming an associated knowledge graph; and a resource module which is used for feeding back the formed knowledge graph and learning evaluation to a learning recommendation system, and automatically recommending related learning contents, learning resources and learning paths interested by the learner. According to the adaptive learning system based on big data and deep learning and the construction method thereof provided by the invention, the purposes of personalized autonomous learning of students, precise teaching of teachers and compaction of basic subject knowledge can be realized.

The invention discloses an edge relationship prediction method and device based on a knowledge graph, equipment and a storage medium, and relates to the technical field of deep learning and the technical field of knowledge graphs. The method comprises the steps of obtaining a first knowledge graph, wherein the first knowledge graph is constructed based on structured data and unstructured data of atarget knowledge domain; obtaining a first knowledge representation model, wherein the first knowledge representation model is generated by training a first BERT model through the corpus data set ofthe target knowledge domain; and inputting the marking word vectors and the position word vectors of the plurality of nodes of the first knowledge graph into a second BERT model for information aggregation processing to obtain edge relationship information between the plurality of nodes of the first knowledge graph and respective neighbor nodes. By utilizing the embodiment of the invention, the edge relationship information among the nodes in the knowledge graph can be obtained.

The invention discloses a text completion method, electronic equipment and a storage device, and the method comprises the steps of obtaining a to-be-completed text, and determining a text library fromwhich the missing content of the to-be-completed text comes, wherein the text to be completed comprises at least one missing position, and the text library relates to the field of preset knowledge; performing completion prediction on the to-be-completed text by utilizing a knowledge graph and a text library corresponding to a preset knowledge field to obtain at least one candidate word of a missing position; and obtaining a complete text of the to-be-completed text by utilizing the candidate fragments of each missing position. According to the scheme, the text completion efficiency can be improved, and the text completion cost can be reduced.

The invention provides a data monitoring method and device for a knowledge graph, and the method comprises the steps of constructing a knowledge rule corresponding to a target knowledge field according to the target knowledge field to which a target knowledge graph belongs; according to the knowledge rule corresponding to the target knowledge field, constructing at least one information detection condition meeting the knowledge rule corresponding to the target knowledge field; and obtaining knowledge fact information from a target knowledge graph, verifying the knowledge fact information according to the at least one information detection condition, and obtaining a verification result. According to the invention, in the process of constructing the knowledge graph of the target knowledge field, the nodes or the relationships in the specific range can be checked, so that the nodes or the relationships which do not conform to the specification in the knowledge graph can be quickly positioned, whether updating change of the knowledge graph is reasonable or not is monitored, and timeliness, accuracy and consistency of the knowledge graph are ensured.

The invention discloses an intelligent heat supply valve control knowledge graph construction method and system, and the system comprises a data collection module, a knowledge graph module, a deep learning module, and a data storage module, and the data collection module comprises a historical data module, a network knowledge module, and a real-time data module. The knowledge graph module comprises a data classification module, a knowledge precipitation module and a knowledge application module, the deep learning module comprises an online learning module, an incremental learning module and anassociation analysis module, and the data storage module comprises a relational data module, a graph data module and a data warehouse module. A heat supply valve control knowledge graph is a typicalapplication scene in the field of heat supply knowledge, the knowledge graph can be called by business systems in various fields to provide expert-level knowledge support, the knowledge graph is builtin a cloud environment or an independent data environment, data analysis and disposal are independent of the business systems, and any resource of the business systems is not consumed.

The invention discloses a teaching system suitable for engineering project management of a simulation sand table. The teaching system comprises a teacher platform, a student platform and the simulation sand table. The teacher platform and the student platform are constructed on the data center; the data center is further connected with the big data center through a network, project data of all projects are collected from the big data center, the collected data are classified into nine knowledge field libraries of project management through a data analysis algorithm, and the simulation sand table comprises a sand table system, an Internet of Things system, a project data center and a real-time display system. The sand table system comprises a simulation sand table, the simulation sand tablefurther comprises an auxiliary mechanical arm, and the simulation sand table comprises a lighting system and a physical sand table. By the adoption of the scheme, teachers and students can learn project management of actual engineering to the maximum degree in the practical teaching process, a solid foundation is laid for seamless connection of graduation with related posts of actual engineeringconstruction project management in the future, and extremely high generalization performance is achieved.

The present invention relates to techniques for translating documents characteristic for a specific field of knowledge from a source language in a target language. Elements causing translation errors in exemplary documents translated by a machine translator (e.g., Internet-based translator, etc.) are used to compile databases of such elements or untranslatable symbols thereof and their equivalent constructs in the source and target languages. Then, using the databases, the elements causing translation errors are substituted in the being translated documents with the corresponding equivalent constructs.

The invention discloses a crowdsourcing worker reliability model establishing method and device in a crowdsourcing knowledge verification environment. The method comprises the following steps of: matching a knowledge domain set for crowdsourcing users according to a pre-stored strategy, and allocating knowledge in the knowledge domain set to the crowdsourcing users, so that the crowdsourcing usersverify the knowledge to obtain knowledge tags; establishing a crowdsourcing worker reliability model based on a reinforcement learning algorithm, and calculating a reward value of the knowledge labelthrough the crowdsourcing worker reliability model so as to update the pre-stored strategy according to the reward value; repeatedly executing the above operation until the updating frequency of thepre-stored strategy reaches the preset frequency, and carrying out qualification screening on the crowdsourcing users according to the latest pre-stored strategy; and adding the knowledge which is verified to be correct into the corresponding knowledge graph after knowledge verification is completed. According to the method, the crowdsourcing worker reliability model can be established in the crowdsourcing verification environment based on reinforcement learning, qualification screening of crowdsourcing workers is achieved, and therefore the crowdsourcing knowledge verification efficiency is improved.

The invention provides a self-adaption input method based on a chapter document. Compared with a conventional input method, the self-adaption input method has the advantage that a current knowledge domain of a user is automatically sensed based on a user local document. The self-adaption input method comprises the following steps: firstly, automatically establishing a fundamental data set by a system, establishing corresponding domain data sets in different knowledge domains, perceiving corresponding domains according to character information input by a user and automatically switching to a current domain data set by the system, increasing a specific gravity of the domain data set through adjusting a weight relationship between the domain data sets and the fundamental data set, realizing automatic perception and parameter adjustment among different knowledge domains; with the increase of input information, continuously updating the corresponding field data sets, and extracting high-frequency word string dynamic populating fundamental data set information in the field data sets. According to the self-adaption input method, the information input by the user is more intelligently known, the selection times is reduced, the accuracy of first-time selection is increased, and the rate of coincident code is remarkably reduced.

Embodiments are computer program product that provides systems and methods as a complete solution for management profession from initiation to closeout; complies with industry standards and requirements. Automated functionality through cloud-based server, standardized combination of database management systems with five main user interfaces with an additional (extended) two user interfaces for post project completion during warrantee and operations periods / phases. The web-based user's interfaces were set for each organizational tier and for quick and emergency responses using the GPS locations for the users, roadways and providers. On real time communication, simultaneous functionality of the integrated databases provides ultimate optimization while the unified filing system and document control solution facilitates system integrations of the management knowledge areas. Public outreach enhancement with a project specific website displays permitted information to allow public search and view projects general information including alerts and status.

The invention discloses a cross-domain knowledge assistance system based on a neural network and deep learning. The cross-domain knowledge assistance system comprises a plurality of devices (1) distributed in different knowledge fields, a deep learning coordination module (2) and a global data storage module (9), each device (1) comprises a data cleaning module (3), a data acquisition module (4) and a data reading module (5); the device (1) further comprises a single-machine storage module (7), and the single-machine storage module (7) is in data communication connection with the data cleaning module (3), the data acquisition module (4) and the data reading module (5). According to the federated machine learning-oriented full-process service migration method and system, before data record training is carried out, data cleaning is carried out on the data records, so that abnormal parts of the data records are eliminated, the accuracy of the data records is ensured, and the accuracy of a data model is ensured.

The invention is applicable to the technical field of computers, and provides a knowledge graph creation method and device, a storage medium and a server. The knowledge graph creation method comprisesthe steps of obtaining a material text of a knowledge field to which a to-be-created knowledge graph belongs; analyzing the material text according to a pre-constructed graph knowledge layer schema,and extracting instance element data; performing data fusion on the extracted instance element data and the graph knowledge layer schema to obtain a first knowledge graph in the vertical field; searching for other knowledge graphs having at least one associated graph node with the first knowledge graph from a preset knowledge graph library; and transversely fusing the first knowledge graph and theother knowledge graphs by taking the associated graph nodes as connection points to obtain a created knowledge graph. By adopting the knowledge graph creation method provided by the invention, the knowledge graph creation efficiency can be improved.

Techniques disclosed herein relate generally to constructing a customized knowledge graph. In one embodiment, entities and relations among entities are extracted from a user dataset based on certain rules to generate a seed graph. Large-scale knowledge graphs are then traversed using a finite state machine to identify candidate entities and / or relations to add to the seed graph. A priority function is used to select entities and / or relations from the candidate entities and / or relations. The selected entities and / or relations are then added to the seed graph to generate the customized knowledgegraph.

The invention relates to an event element extraction method and device, computer equipment, a storage medium and a computer program product. The method comprises the steps that target public opinion data and a knowledge vector library corresponding to the target public opinion data are obtained, the knowledge vector library comprises multiple reference word vectors, and the multiple reference word vectors and the target public opinion data have the same knowledge field classification dimension; association weights between the target public opinion data and the reference word vectors are determined, fusion description information corresponding to the target public opinion data is determined based on the association weights, and the fusion description information is used for representing public opinion description information, corresponding to the knowledge field classification dimension, included in the target public opinion data; and inputting the fusion description information into an event element extraction model to obtain a target event element tag corresponding to the target public opinion data. By adopting the method, the accuracy of event element extraction can be improved.

The invention provides a migration knowledge determination method, devcie, equipment, and a readable storage medium. The method comprises the steps of obtaining at least two pieces of text generationdata based on different classification tasks; mapping the text generation data based on the different classification tasks to a high-dimensional vector space of a preset dimension; obtaining correlation data of the text generation data based on the different classification tasks in the high-dimensional vector space; and mining shared data in the correlation data, and determining the shared data asmigration knowledge. The problem that knowledge migration is completed by depending on a learner in the knowledge migration field in the prior art is solved.

The invention discloses an open cultivation type online vocational education course system. The system comprises a teacher terminal which is used for a teacher to log in the system, carry out online teaching, and upload teaching data; a student terminal which is used for enabling a student to log in the system, and carrying out knowledge learning, actual operation, online testing and communication and interpretation; a teaching module which is used for providing knowledge field division and constructing a virtual scene for online teaching of teachers and students; a detection module which is used for testing theoretical knowledge and actual operation of students; an analysis module which is used for analyzing the theoretical knowledge mastering condition and the practical operation ability of the students, finding out error-prone points of each student through big data analysis and AI data mining, and performing targeted education; and a central processing unit which is used for coordinating the above modules to work, calling corresponding data in each database within the authority of the data calling command by using the data calling command, and sending the control commands to the corresponding modules.

The embodiment of the invention provides an expert determination method. The expert determination method comprises the steps of obtaining a communication text of a user; processing the communication text to obtain a corresponding theme; and determining an expert corresponding to the theme. According to the expert determination method provided by the embodiment of the invention, the participation degree of each employee in each theme can be obtained by analyzing the employee work communication and contact records, and effective identification of experts in each knowledge field is realized.