156 results about "Problem set" patented technology

Today, students are underperforming on the standardized testing. In an effort to better performance on these tests, software systems allow a student to practice different topics. These software systems, however, do not perform a longitudinal analysis of a student allowing the creation of an adaptable learning environment for the system. In contrast, the present invention provides a system that enables a student to answer one or more questions of a problem set. Next, the system stores information for each answer of the one or more questions over a period of time, analyzes the information for each student answer in a longitudinal manner, and identifies one or more deficiencies in learning of the student based on the longitudinal analysis. In this way, the system uses longitudinal analysis to identify student deficiencies, which allows a teacher or parent, using the analysis, to increase the quality of learning for the student.

A system and method are provided for using networked computer devices to access remote collaborative learning resources. The method uses a student computing device to establish a network-connection with an education program, accesses a problem set screen, and selects a problem. If an incorrect answer is submitted to the problem, the student application has the option of accessing a remote education program collaborative learning resource associated with the selected problem. Subsequent to accessing the collaborative learning resource, the student application submits a problem answer to the education program. In response to the resource flag and the submission of a correct problem answer, the education program grants partial credit to the student application or a user identity associated with the student application. Optionally, the problem answers may be submitted with a problem work area screen. The problem work area screen is frozen once the student application accesses a collaborative learning resource.

A system and method for generating and administering classroom exercises to a student. One or more root questions is generated, where each root question has a stem, a plurality of right answers, and a plurality of wrong answers. A multiple-choice question instance is created by combining the stem with a set of answer choices that are created from one of the right answers and one or more of the wrong answers. The questions are administered to a student. Preferably, the sets of questions based on the same root questions are administered one or more times to the student—e.g., a student may be required to work three sets of question instances based on the same set of root questions, or may be required to continue working new sets of question instances until all of the questions in one set are answered correctly.

The present invention provides systems and methods for electronically delivering banking services to end clients and, more particularly, using Internet based technologies as a means of exposing those services. The solution to this problem set forth in this invention is the creation of a common electronic delivery infrastructure and application deployment environment, exposing an institution's entire portfolio of corporate banking services to its clients at a number of different locations at any time.

The invention provides a method for building an acoustic model and a speech decoding method based on the acoustic model. The method comprises the following steps: (101) based on training data, calculating three-factor Gaussian mixture model statistics which are required by the acoustic model; (102) adopting a self-clustering method to calculate a decision tree problem set according to the statistics, and adopting a decision tree algorithm to conduct partitioning clustering on the statistics based on the decision tree problem set to obtain isotopic phonemes; (103) combining a basic phoneme set with the isotopic phonemes to obtain a phoneme set containing the isotopic phonemes, and adopting the decision tree algorithm to treat an original speech annotation to obtain a speech annotation containing the isotopic phonemes; (104) based on the phoneme set containing the isotopic phonemes and the speech annotation containing the isotopic phonemes, carrying out acoustic model training according to an acoustic model training method to build the acoustic model containing the isotopic phonemes. The method for building the acoustic model aims to solve the problem that the degree of acoustic model confusion is high in an agglutinative language speech recognition system.

The embodiment of the invention provides a problem matching method. The method comprises the following steps: receiving problems submitted by users; with respect to each preset problem set, calculating similarity between the problem set and the problems submitted by the users; and determining that centralized to-be-matched problems in the problem set are matched with the problems submitted by the users if the similarity is greater than a set similarity threshold, wherein at least two to-be-matched problems aiming at the same answer are saved in the same question set. According to the problem matching method provided by the embodiment of the invention, the problem matching accuracy and reliability can be improved. In addition, the embodiment of the invention provides a problem matching device.

The invention discloses a cross-language emotional speech synthesis method and system. The method comprises steps of establishing a context-dependent label format and a context-dependent clustering problem set; determining a first language annotation document, a second language annotation document, a target emotional Putonghua annotation document, an annotation document to be synthesized, a first language acoustic parameter, a second language acoustic parameter, a target emotional acoustic parameter; based on the first language annotation document, the second language annotation document, the target emotional Putonghua annotation document, the first language acoustic parameter, the second language acoustic parameter, and the target emotional acoustic parameter, determining the multi-speaker target emotional average acoustic model; and finally, inputting the annotation document to be synthesized into the multi-speaker target emotional average acoustic model to obtain a first language or / and a second language target emotional speech synthesis document to realize the synthesis of the same speaker or a different speaker cross-language emotional voice.

The embodiment discloses a user customization contract generation method based on risks and a system and belongs to the technical field of a computer. The method comprises steps that a contract type is acquired; according association relationships between clauses in a clause database and the contract type, a clause set in matching with the contract type is acquired; according to association relationships between guiding problems in a guiding database and the contract type, a guiding problem set in matching with the contract type is acquired; according to association relationships among the contract type, risk types and the risk information, a risk type and the risk information in matching with the contract type are acquired; according to the risk type and the risk information, the guiding problem set is updated; a selection result for the updated guiding problem set is acquired; the clause set is filtered according to the selection result; and a blank contract is generated. Through the method, the contract capable of protecting rights of a client to a maximum degree can be drafted by a user without professional law knowledge through a quite-low-cost and convenient-operation method.

A global computer network method and apparatus for creating and deploying many types of self-tutoring systems across many different platforms is disclosed. A run time engine supports several types of tutorials, in both a client and server context. A Builder enables development and testing of tutorials, formed of teacher composed problems, or an existing approved problems set, or student-user composed problems. The system simplifies the process of tutorial construction to allow educators and students with little or no ITS experience to develop content of problems and teaching strategies (i.e., format of problems including hints, messages and sequencing of related problems). The system provides a Web based interface as a means to build and store these tutorials. A web based reporting component allows for live database reporting to teachers, showing how students are performing. A testing component is web based and allows a teacher to test the quality of student composed problems. Further, the testing component allows addition of the student content to the existing approved problem set as is pertinent. Automated analysis and reporting of experimental tutorials developed by either teacher or student is included.

The invention relates to an unsupervised text similarity calculation method, which comprises the following steps of: 1, pre-training an embedded layer model, and pre-training all words in a problem set to generate word vectors meeting the requirements of the model; 2, mining semantic information of sentences through a coding layer network; step 3, performing model improvement based on TFIDF fusion; the method comprises the steps that when each question sentence is input into a neural network, TFIDF calculation is conducted on each input question sentence, calculated weights are input into theneural network, final sentence vector representation is controlled, a normalized TFIDF calculation method is adopted, and the final sentence vector representation is fused into a coding layer and a representation layer. According to the method, the deep neural network model (Bi-LSTM) is used for unsupervised training of the corpus to obtain the language model, and the information of the large-scale corpus can be fully utilized in an unsupervised training mode, so that the text matching accuracy is improved, and the information retrieval precision is improved.

A system for teaching basic arithmetic facts to students and for measuring their progress and rating their knowledge using a computer program that provides repetitive practice and immediate positive reinforcement is provided. The system features structured practice using problem sets of progressing levels of difficulty with problems selected randomly from each set. Progress made by individual students is tracked by generating a proficiency rating that reflects the arithmetic function tested, the level of difficulty of the problems presented, and the percentage of correct answers provided within a preset time period. Summary reports are generated and displayed at the end of each session as are the proficiency ratings.

The invention provides a key sentence extraction method and device for a text paragraph, and relates to the technical field of data processing. The key sentence extraction method comprises the following steps: carrying out word segmentation on each line of text of each text paragraph in a corpus to obtain a first word segmentation result; selecting effective vocabularies from the first word segmentation result; selecting a key paragraph from each text paragraph according to the composition structure of the text paragraph; classifying the key paragraphs according to the effective vocabularies to obtain a plurality of classification categories; determining a target keyword of each classification category and the weight of each target keyword; and extracting a key sentence of each key paragraph according to the target keyword and the weight of the target keyword. According to the technical scheme, for the customer service industry, classification of customer service question and answer data and extraction of user demands and purposes are achieved, and the period of customer service knowledge accumulation is greatly shortened, and the cost of customer service knowledge accumulation isreduced, and meanwhile a complete problem set is provided for subsequent intelligent customer service.

The invention discloses a model training method and device for answering questions, equipment and a storage medium, is applied to the technical field of deep learning, and is used for solving the problem that the answering rate of user consultation questions is low. The method comprises the following steps: detecting negative evaluation information; If the negative evaluation information is detected, obtaining an evaluation problem corresponding to the negative evaluation information; Clustering each evaluation problem to obtain each problem set; Determining a vector center of each problem set; For each problem set, respectively calculating the distance between the vector center of the problem set and the vector center of each preset problem group; For each question set, if the minimum distance is smaller than a preset distance threshold value, combining the question set to a preset question group corresponding to the minimum distance; For each problem set, if the minimum distance is greater than or equal to a preset distance threshold, determining the problem set as a new preset problem group; And retraining the target deep learning model by adopting each updated preset problem group to obtain a trained target deep learning model.

Embodiments of the present disclosure disclose a question answering method, apparatus, electronic device, and storage medium. The method comprises the following steps: classifying the received questions to be answered by using a classification model to obtain a question category of the questions to be answered; Obtaining a target candidate question matching with the question to be answered from acandidate question set corresponding to the question category; Answers to the target candidate questions are used as the answers to the questions to be answered. A technical solution of an embodimentof that present disclosure solve the maintenance inconvenience of a response system in the prior art, The technical defect that it is difficult to cover a large area of the problems put forward by theuser is realized, and most of the problems put forward by the user are answered accurately simply and quickly, and the set of candidate problems can be expanded simply by adding the operation of thecandidate problems, so that the problems put forward by the user can be covered in a larger area.

A design application generates feasible engineering designs that satisfy criteria associated with a particular engineering problem. The design application receives input that outlines a specific engineering problem to be solved, and then synthesizes a problem specification based on this input. The design application then searches a database to identify different classes of approaches to solving the design problem set forth in the problem specification. The design application then selects one or more such classes of approaches, and generates a spectrum of potential design solutions for each such approach. The generated solutions may then be evaluated to determine the degree to which the problems specification has been met.

This invention supplies a method to make the abstract, step-by-step logic of math problems visible via the use of digitized mathematical reasoning blocks, which can be used to construct an interactive teaching program that allows a student to select problem sets from an index of problems, allows the student to view a brief instructional video pertaining to that skill if desired, allows the student to chose the mode of problem presentation (i.e., various learning or test modes), allows the student to work randomly generated problems from within the chosen mode and set by picking mathematical reasoning blocks that represent the various necessary / possible sub-steps in route to the solution of that problem.

A selection method of network answers based on probabilistic latent semantic analysis comprises the following steps: a problem set C, constructing a probabilistic latent semantic analysis model by using a user set u and a word set w as variables, and using the probabilistic latent semantic analysis model to dig the latent theme information of each user u; obtaining problems q newly raised in a question-answering community and the words w forming the questions, determining the joint probability of the current problems and candidate answers, and calculating the joint probability of the current questions and the users answering the current problems; linearly weighting the joint probability of the current problems and the candidate answers and the joint probability of the current questions and the users answering the current problems to obtain candidate answer scores, arranging the candidate answer scores in the manner of descending order, and sending the answers to the user raising the problem according to an arranged order. The invention has the advantages of capability of adequately using the abundant user information in the question-answering community, high accuracy and wide applicability.

The invention discloses an HMM-based method of Mongolian speech synthesis and front-end processing. The method comprises the following steps of analyzing speech data in a speech corpus; summarizing a context attribute set and a problem set for clustering decision-making trees; performing HMM training and acquiring HMM training results; acquiring corresponding clustering state models, and forming a clustering state model sequence; generating a target acoustic parameter sequence through the dynamic characteristics of parameters, and acquiring synthesis speech through a STRAIGHT synthesizer. The method of front-end processing comprises the following steps of performing special character processing on input Mongolian; transferring Mongolian to Latin; annotating the part of speech of Mongolian; transferring Latin to phonemes by adopting a G2P model; segmenting syllables by adopting rules; synthesizing data in the format required by rhythm forecasting; performing the rhythm forecasting; processing and acquiring a text format required by the synthesis. By the method, the duration and the pitch period parameter of the synthesis speech can be adjusted freely, the naturality and fluency of the synthesis speech are ensured, and the cost of the synthesis is reduced.

The invention discloses a method and a device for the real name authentication of an identity. The method for the real name authentication of the identity comprises the following steps of forwarding identity identification data which are used for identifying a target object and having uniqueness to an identity identification verifying party, wherein the target object is a to-be-validated object, and the identity identification verifying party is used for verifying whether the identity identification data are valid or not; when the identity identification verifying party verifies the identity identification data to be valid, inquiring the identity verification data of the target object in an identity verification database according to the identity identification data; generating a first problem set corresponding to the identity verification data according to the identity verification data; obtaining answers of problems in the first problem set, and carrying out verification on the answers of the problems in the first problem set, so as to obtain a verification result; when the verification result accords with a preset condition, determining that an identity data submitting party is the target object. Through the method and the device for the real name authentication of the identity, the effect of preventing the identity from being usurped is achieved.

The invention relates to the technical field of artificial intelligence, and discloses a text matching method and device based on slot similarity, equipment and a storage medium, which are used for improving the accuracy of problem matching. The text matching method based on slot similarity comprises the following steps: carrying out a series of processing operations such as coarse granularity division, slot establishment and fineness granularity division on a problem in a target field, so as to establish a dictionary in advance and determine a subdivision rule; performing slot filling processing on a target question statement currently input by a user according to the established dictionary and the subdivision rule, and classifying questions in an existing question-answer library according to the question type the same as that of the input target question statement to obtain a candidate question set; and calculating the similarity between the target question statement input by the user and the slot words corresponding to the questions in the candidate question set, and determining a similar question most matched with the input target question statement according to a slot similarity calculation result and a subdivision rule.

The invention relates to a BERT-based intelligent question and answer implementation method and system. The method specifically comprises the following steps of S1, receiving a question input by a user; s2, normalizing the questions input by the user; s3, inputting the questions processed by the preprocessing module into a BERT-based question intention classification model for classification; s4,retrieving corresponding questions and corresponding answers from the knowledge base to obtain a candidate question set and a corresponding answer set; s5, sorting the candidate question set and the answer set according to a certain rule; s6, establishing a matching pair for the input question and the sorted candidate question set, and inputting the matching pair into a BERT-based question similarity matching model to obtain similarity; and S7, obtaining a final answer according to the similarity of the candidate question set, and feeding back the final answer to the user side. According to the intelligent question and answer implementation method and system, the pre-trained Chinese BERT model is adopted, so that a machine has prior knowledge, and the accuracy of intelligent question and answer is improved.

A method for legal knowledge modeling and automated legal evaluation, such as for online, questionnaire-based legal analysis, is provided. Information, such as facts and characteristics of a legal situation or legal scenario, as it relates to a legal conclusion or a legal result, are modeled in a decision tree. The decision tree may comprise a plurality of nodes and a plurality of edges connecting the nodes, wherein each node is associated with a variable that represents either an answer to a legal inquiry or a legal conclusion, and an edge represents a conditional dependency between variables of nodes. The decision tree is automatically updated on a periodic basis to reflect new legislation or court decisions. Using the decision tree, a legal conclusion based on the user's answers to a questionnaire may be determined. The legal conclusion is modified upon the input of evidence, which is typically in the form of answers to a dynamic set of questions designed to identify a legal conclusion or a legal result.

The present invention relates to the field of automation technology, in particular to a fractional prediction system and a prediction method. The system comprises: a student practice terminal, the student practice terminal is used for dividing the score prediction nodes of the test questions in the test question bank according to the rule of the student 's problem making or the rule of the test paper' s problem setting, then forming the test questions between two score prediction nodes into sub-node sets, and counting the number of the corresponding sub-node sets to generate the number of testquestions, and then calculating the proportion between them according to the sub-node sets and the number of the students' test questions, and generating the coverage rate of answering, then dividingthe weight of the test questions from different sources according to the source of the test questions, and calculating the scores of the node items according to the correct rate of the test exercisesfrom different sources, and calculating the predicted scores of the child node sets of the students according to the answer coverage, the node item scores and the smoothing function as the basis of the prediction scores.

The invention provides a domain question and answer-oriented knowledge graph construction method, which comprises the following steps: S1, collecting common questions and answers of a user to a domainon the basis of the professional domain, classifying the questions to form a question set, and training a Chinese pre-training classification model on the basis of the data; s2, performing word segmentation and part-of-speech tagging classification on each question in the question set by using the question set in the step S1, constructing a knowledge graph of the current classification by using aword dictionary obtained after each question formed by the same category is subjected to word segmentation and part-of-speech tagging, and storing the knowledge graph in a graph database; s3, performing sub-category division on the user problems according to actual requirements, performing retrieval on retrieval rules used in the knowledge graph of the corresponding category in the graph databaseaccording to sub-category results and the keyword set, and obtaining retrieval labels; and S4, retrieving corresponding labels, extracting questions represented by the labels in the database, and returning answers corresponding to the questions to the user.

The invention provides a reading understanding method based on composite questions, which comprises the following steps: acquiring a question set, and acquiring a target text from a data set accordingto the question set; obtaining a plurality of associated paragraphs in the target text according to the question set; obtaining a plurality of answers of the question set from the associated paragraph, and creating a probability model of the plurality of answers; fusing the output of the probability model to obtain the output response of the question set; according to the method, the correctnessand comprehensiveness of reading understanding can be effectively improved.

The invention relates to the technical field of artificial intelligence, and provides a multi-type question intelligent question answering method, a system, a device and a computer readable storage medium. Through natural language processing, the problem type of the target problem is determined by utilizing the deep network model, so that the problem positioning accuracy is improved; entity recognition and multi-level semantic analysis are carried out on the first target problem, so that the model complexity is effectively reduced, and the first target problem with complex semantics can be efficiently and accurately replied; a plurality of rounds of questions and answers are carried out with a client for a second target question; according to the method and the system, the second target question needing to acquire the multiple related information can be accurately replied until the associated reply of the client to the associated question set is acquired, so that the system can accurately reply other questions with more complex semantics and more diversified answers or questions needing to be answered after the multiple related information is acquired, wherein the reply informationof the target question can be stored in the blockchain.

A system for solving a dynamic constraint satisfaction problem comprises a constraint network of variables and constraints. The system creates a first sub-problem model that includes a first model type, one or more first variables and zero or more first constraints. The system propagates the first constraints through the constraint network and determines if a first conflict is detected from propagating the first constraints. If the first conflict is detected, the system restores the constraint network variables to a first previous state before the first constraints were propagated. The system creates a first sub-problem set that includes a second model type and one or more sub-problem models. The system connects the first sub-problem model to the first sub-problem set via a second constraint and propagates the second constraint through the constraint network.

The invention discloses a historical-data-based communication tower to-be-solved problem set generation method and system. The system comprises a tower parameter importance matrix setting module, a sensor data timing acquisition and tower current problem coefficient matrix calculation module, a parameter historical data extraction and current problem coefficient matrix modification module, a problem severity matrix calculation module and a problem severity arrangement and to-be-solved problem set generation module. The method comprises: firstly setting a tower parameter importance matrix and a tower current problem severity coefficient matrix; then according to historical generation frequency of problems, performing severity coefficient modification; and finally, calculating a problem severity matrix, and generating a to-be-solved problem set with a problem sequence. The historical-data-based communication tower to-be-solved problem set generation method and system, which are provided by the invention, solve a technical problem that the historical problem data is not considered when the tower problem severity is calculated.