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

47results about How to "Effective memory" patented technology

Method for enhancing memory and cognition in aging adults

InactiveUS20050175972A1Improve “ noisy ” sensory representationShorten time constantMental therapiesElectrical appliancesRandom orderFormant
A method on a computing device is provided for enhancing the memory and cognitive ability of an older adult by requiring the adult to differentiate between rapidly presented stimuli. The method trains the time order judgment of the adult by presenting upward and downward frequency sweeps, in random order, separated by an inter-stimulus interval. The upward and downward frequency sweeps are at frequencies common in formants which form the frequency components common in speech. Icons are associated with the upward and downward frequency sweeps to allow the adult to indicate an order in which the frequency sweeps are presented (i.e., UP-UP, UP-DOWN, DOWN-UP, and DOWN-DOWN). Correct selection of an order causes the inter-stimulus interval to be reduced, and / or the duration of the frequency sweeps to be adaptively shortened.
Owner:POSIT SCI CORP

Method for enhancing memory and cognition in aging adults

InactiveUS20060073452A1Improve “ noisy ” sensory representationShorten time constantElectrical appliancesTeaching apparatusCognition.knowledgeComputer science
A method on a computing device is provided for enhancing the memory and cognitive ability of an older adult by requiring the adult to differentiate between rapidly presented stimuli. The method utilizes a sequence of phonemes from a confusable pair which are systematically manipulated to make discrimination between the phonemes less difficult or more difficult based on the success of the adult. The manipulation includes processing of the consonant and vowel portions of the phonemes by emphasizing the portions, and / or by stretching the portions. Further processing includes separating the consonant and vowel portions by time intervals. As the adult improves in their auditory processing, the discriminations are made progressively more difficult by reducing the amount of processing to that of normal speech.
Owner:NEUROSCI SOLUTIONS CORP +1

Speech synthesis method, device and equipment and storage medium

The invention provides a speech synthesis method, device and equipment and a storage medium. The method comprises the steps that obtained text information is preprocessed through a speech synthesis device, and a text vector of the text information is obtained; the text vector is input into a preset acoustic model, and a first acoustic parameter vector corresponding to the text vector is obtained,wherein the acoustic model is used for processing the text vector according to a memory matrix to obtain the first acoustic parameter vector; speech information corresponding to the text message is synthesized according to the first acoustic parameter vector. Due to the fact that the memory matrix is updated continuously in the acoustic model, historical text information is memorized more effectively, the overall prediction effect of the acoustic model is improved, and then the output quality of the speech information is improved.
Owner:BEIJING XIAOMI MOBILE SOFTWARE CO LTD

Word split memorizing and learning system

The invention provides a word split memorizing and learning system comprising the following modules: an intelligent word split module based on big data which comprises the following submodules: a word big data intelligent calculation and active split submodule and a user big data intelligent analysis and inverse optimization submodule; a word split memorizing and learning module; a word memorizing test module; and a word learning statistical module. According to the word split memorizing and learning system, the learner is enabled to rapidly memorize a group of uncommon and complicated words through the mode of word split memorizing; the learner is enabled to form the connection between knowledge through word splitting so as to form a word network; the memory can be strengthened through relevance testing; and the learner can be assisted to develop the effective word memory.
Owner:杨燕

Aircraft flight path prediction method based on LSTM network

The invention discloses an aircraft flight path prediction method based on an LSTM network, and the method comprises the following steps: (1), reading aircraft flight path data, and carrying out the normalization of the data; (2) establishing an LSTM deep neural network model, and setting the input and output of a neural network, the step number, the LSTM layer number and the number of neurons ofeach layer; (3) setting evaluation indexes to be RMSE and MAE; (4) training a network model, and debugging related parameters to minimize the values of RMSE and MAE, i.e., the network effect is optimal; and (5) outputting the predicted flight path of the aircraft through the trained optimal network. According to the method, the flight path of the aircraft in a period of time in the future can be quickly and effectively predicted, the LSTM network is applied to the flight path prediction problem, the LSTM flight path prediction model is trained through a large amount of data, and the robustnessand accuracy of flight path prediction are effectively improved.
Owner:BEIHANG UNIV

GRU based recurrent neural network multi-label learning method

The invention provides a GRU based recurrent neural network multi-label learning method, which comprises the steps of S1, initializing a system parameter [theta]=(W, U, B); S2, inputting a sample {xi,yi}<i=1><N>, calculating a hidden state hT of the output of an RNN (Recurrent Neural Network) at each moment, wherein the sample xi belongs to R<M*1>, yi is a multi-label vector of the sample xi, andyi belongs to R<C*1>; S3, calculating a context vector hT and output zi of an output layer; S4, calculating the predicted output yi^, calculating the loss Li, and determining an objective function J;S5, solving the gradient of the system parameter [theta]=(W, U, B) according to a gradient descent method and a BPTT (Back-propagation Through Time) algorithm; S6, determining a learning rate [eta],and updating each weight gradient W=W-[eta]*[delta]W; S7, judging whether the neural network reaches stable or not, if so, executing a step S8, if not, returning the step S2, and iteratively updatingmodel parameters; and S8, outputting an optimization model. According to the invention, effective feature representation of the sample can be obtained by fully utilizing the RNN so as to improve the accuracy of multi-label classification. In addition, a problem of gradient disappearance is not easy to occur in back propagation.
Owner:HRG INT INST FOR RES & INNOVATION

Rapid mass data cluster processing method for computer

The invention relates to a rapid mass data cluster processing method for a computer. The method comprises the following steps: firstly preprocessing data objects to be analyzed to complete grouping of the data objects; then calculating similarity matrixes of the data objects in a group, and merging to generate new data objects according to the similarity; recording the merging and generation process and meanwhile deleting the original data objects; operating repeatedly until the amount of the data objects is equal to the number of clustering classification expected by user; finally obtaining the results of clustering processing by inquiring the merging records. According to the method, specific composition of each subclass data object with any number of clusters, the number of subclass data objects and centroid thereof can be obtained during once implementation process, and the distribution general situation of each subclass interior data object and characteristics thereof can be inquired, so that rapid effective processing of mass data is greatly facilitated.
Owner:NORTH CHINA ELECTRIC POWER UNIV (BAODING)

Method for modulating listener attention toward synthetic formant transition cues in speech stimuli for training

A method on a computing device for enhancing the memory and cognitive ability of an older adult by requiring the adult to differentiate between rapidly presented stimuli. The method utilizes a sequence of phonemes from a confusable pair which are systematically manipulated to make discrimination between the phonemes less difficult or more difficult based on the success of the adult, such as processing the consonant and vowel portions of the phonemes by emphasizing the portions, stretching the portions, and / or separating the consonant and vowel portions by time intervals. As the adult improves in auditory processing, the discriminations are made progressively more difficult by reducing the amount of processing to that of normal speech. Introductory phonemes may each include a blend of a formant-synthesized phoneme and an acoustically naturalistic phoneme that substantially replicates the spectro-temporal aspects of a naturally produced phoneme, with the blends progressing from substantially natural-sounding to substantially formant-synthesized.
Owner:POSIT SCI CORP

Water body water quality prediction method, system and device

The invention provides a water body water quality prediction method, system and device. The method comprises the following steps that: independently carrying out missing data processing and normalization processing on multiple groups of water quality parameters of a target water body and a corresponding meteorological parameter to obtain a standard meteorological parameter and a standard water quality parameter; and on the basis of the standard meteorological parameter and the standard water quality parameter, utilizing a trained autoencoder and a long short term memory network fusion prediction model to obtain the prediction water quality index of the target water body, wherein the long short term memory network fusion prediction model is obtained in a way that the standard meteorologicalparameter and the corersponding standard water quality parameter of the target water body are utilized in advance to train the constructed autoencoder and long short term memory network fusion prediction model in sequence. By use of the method, a mutual function relationship among water body multiple parameters can be effectively mined so as to effectively predict the water body water quality anddisclose the key rule of a water quality factor change.
Owner:CHINA AGRI UNIV

Method for modulating listener attention toward synthetic formant transition cues in speech stimuli for training

ActiveUS20070054249A1Improve “ noisy ” sensory representationShorten time constantReadingElectrical appliancesNormal speechConsonant
A method on a computing device for enhancing the memory and cognitive ability of an older adult by requiring the adult to differentiate between rapidly presented stimuli. The method utilizes a sequence of phonemes from a confusable pair which are systematically manipulated to make discrimination between the phonemes less difficult or more difficult based on the success of the adult, such as processing the consonant and vowel portions of the phonemes by emphasizing the portions, stretching the portions, and / or separating the consonant and vowel portions by time intervals. As the adult improves in auditory processing, the discriminations are made progressively more difficult by reducing the amount of processing to that of normal speech. Introductory phonemes may each include a blend of a formant-synthesized phoneme and an acoustically naturalistic phoneme that substantially replicates the spectro-temporal aspects of a naturally produced phoneme, with the blends progressing from substantially natural-sounding to substantially formant-synthesized.
Owner:POSIT SCI CORP

Building energy consumption prediction method and system based on improved LSTM

The invention discloses a building energy consumption prediction method and system based on an improved LSTM. The method comprises the following steps: obtaining an optimal parameter corresponding to an LSTM neural network; introducing the optimal parameters into the LSTM variant neural network, optimizing hyper-parameters in the LSTM variant neural network by using a stochastic gradient optimization algorithm based on weight attenuation to obtain optimal hyper-parameters of the LSTM variant neural network, and taking the LSTM variant neural network corresponding to the optimal hyper-parameters as an optimal LSTM prediction model; and processing the acquired data influencing the building load by using the optimal LSTM prediction model, and predicting the load data of the building at specified time to realize building energy consumption prediction. The method is higher in prediction precision, better in stability and more suitable for commercial building short-term energy consumption prediction.
Owner:XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY

Short-term power consumption prediction method based on I-LSTM

The invention relates to a short-term power consumption prediction method based on I-LSTM, and belongs to the field of power system prediction. The method comprises the following steps: S1, collecting historical data of a power system, and processing incomplete data and abnormal values; S2, dividing the data into a training set, a verification set and a test set according to time; S3, constructing an (Improved Long Short Term Memory) I-LSTM network model, and inputting the training set into the I-LSTM network model for training; S4, setting a network loss function, an optimization algorithm, a learning rate and a batchsize of the I-LSTM network model; and S5, predicting the test set, and obtaining a prediction result of the test set according to a model obtained according to the accurate change condition of the verification set. According to the method, the key information in the user historical data sequence and the characteristic relationship between the user power consumption data can be better mined, and the user power consumption prediction precision and stability are effectively improved.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Social short text sentiment classification method and device and storage medium

ActiveCN112214601AImproving the performance of sentiment polarity analysisComprehensive and varied descriptionData processing applicationsSemantic analysisClassification methodsEmotion classification
The invention discloses a social short text sentiment classification method and device and a storage medium, and the method comprises the steps: obtaining a text published by a user when the sentimenttendency of a social short text is automatically analyzed and mined; then extracting and calculating a text context sentiment feature value and a priori polarity sentiment feature value; using pre-training word vector models such as word2Vec and the like for training text word vector representation; using multi-window convolution operation for obtaining text semantic relations of different granularities; using a multi-head self-attention network for effectively capturing and memorizing text long-distance context semantic information, and avoiding the problem that a recurrent neural network cannot conduct parallel computing; using multi-layer convolution and pooling combination for abstracting text sentiment semantic representation from different levels; and finally combining sentiment feature vector representation of different levels, so that explicit and implicit sentiment semantic features contained in the text can be described more comprehensively and diverse, and the performance of short text sentiment polarity analysis is improved.
Owner:XIAMEN MEIYA PICO INFORMATION

Attention LSTM-based reinforcement learning Agent knowledge reasoning method

InactiveCN112116069AEffective memorySolve the problem of not being able to memorize the reasoning path effectivelyMathematical modelsArtificial lifeData setReasoning algorithm
An Attention LSTM-based reinforcement learning Agent knowledge reasoning method can effectively memorize a knowledge graph reasoning path through a bidirectional long-short-term memory network, and meanwhile, an attention mechanism weights the state of the memory path to obtain a state needing to be concerned, inhibits an invalid state, realizes memory path screening, and the problem that knowledge reasoning of a reinforcement learning Agent cannot effectively memorize a reasoning path is effectively solved. The LSTMAttention network model is used in the reinforcement learning Agent for relation path feature extraction, meanwhile, a return mechanism is optimized, and the reasoning precision of a knowledge graph reasoning algorithm based on reinforcement learning under multiple reference data sets is effectively improved.
Owner:SHANDONG ARTIFICIAL INTELLIGENCE INST

Case-related microblog comment irony sentence detection method for dynamically memorizing case description

The invention relates to a case-related microblog comment irony sentence detection method for dynamically memorizing case description, and belongs to the technical field of natural language processing. The method comprises the following steps: constructing a case-related microblog irony data set; carrying out feature coding on the case-related microblog text and the case-related microblog commentsby utilizing word embedding and position embedding, and introducing an attention mechanism into the case-related microblog comments subjected to feature coding; obtaining text representation relatedto the case-related microblog comments through a dynamic memory mechanism; and splicing the obtained text representation and comment representation to obtain a new representation, training a model bytaking the representation as input, and performing case-related microblog comment irony sentence detection through the model. The case description information is used as background information to realize irony detection of the case-related comment sentences, irony sentences are detected from the obtained public opinion data, and support is provided for subsequent sentiment analysis.
Owner:KUNMING UNIV OF SCI & TECH

Storage cabinet door opening and closing control circuit and intelligent cabinet door opening and closing storage cabinet

The invention discloses a storage cabinet door opening and closing control circuit and an intelligent cabinet door opening and closing storage cabinet. The circuit comprises a power module used for dividing electric supply into three paths including touch switch power input, control circuit power input and motor power input. The touch switch power input is connected with a touch switch module used for sending cabinet door opening or closing signals. The control circuit power input is connected with a programmable control module used for receiving the cabinet door opening / closing signals and outputting motor forward rotation or reverse rotation signals. The motor power input is connected with a storage cabinet motor and a direction switch module. The direction switch module is used for controlling the motor to forwards rotate or reversely rotate according to the motor forward rotation or reverse rotation signals so that a cabinet door can be driven to be folded, ascend and be opened or to be unfolded, descend and be closed. The cabinet door of the intelligent cabinet door opening and closing storage cabinet can be intelligently folded and opened and unfolded and closed, and automatic position memorizing, intelligent jamming protection and other intelligent control can be achieved.
Owner:CMECH (GUANGZHOU) INDUSTRIAL LTD

Method and device for searching and displaying data

The invention relates to a method and a device for searching and displaying data, which, when searching and displaying data according to the content input by a user, display a part of components of the searched data and then display the other components corresponding to the part of components after a selected time. The device for searching and displaying data comprises a user data input device, a data display device, a storage, a data searching device and a database, wherein the user data input device is in unilateral connection with the storage and is used for receiving the data input by the user; the storage is in unilateral connection with the data display device, is in bidirectional connection with the data searching device and is used for temporarily storing the data input by the user; the data searching device unilaterally receives information from the database; and the database is used for storing the data with different sequence numbers respectively.
Owner:林亨泽

A storage cabinet door switch control circuit, and an intelligent cabinet door switch storage cabinet

The invention discloses a storage cabinet door opening and closing control circuit and an intelligent cabinet door opening and closing storage cabinet. The circuit comprises a power module used for dividing electric supply into three paths including touch switch power input, control circuit power input and motor power input. The touch switch power input is connected with a touch switch module used for sending cabinet door opening or closing signals. The control circuit power input is connected with a programmable control module used for receiving the cabinet door opening / closing signals and outputting motor forward rotation or reverse rotation signals. The motor power input is connected with a storage cabinet motor and a direction switch module. The direction switch module is used for controlling the motor to forwards rotate or reversely rotate according to the motor forward rotation or reverse rotation signals so that a cabinet door can be driven to be folded, ascend and be opened or to be unfolded, descend and be closed. The cabinet door of the intelligent cabinet door opening and closing storage cabinet can be intelligently folded and opened and unfolded and closed, and automatic position memorizing, intelligent jamming protection and other intelligent control can be achieved.
Owner:CMECH (GUANGZHOU) INDUSTRIAL LTD

Chinese character reading method

InactiveCN1487483AKnowledge is effectiveAchieve the purpose of literacyTeaching apparatusChinese charactersUtterance
The present invention discloses Chinese character literacy method. The Chinese character to be learned is hidden in some sentence, which contains the radical and / or part of the Chinese character to be learned or contains Chinese character including Chinese character to be learned. The said method is dramatic and interesting and can cause the interest for children to learn and thus result in high learn efficiency.
Owner:王锦壮

Detection method of sarcastic sentences in microblog comments involved in dynamic memory case descriptions

The invention relates to a method for detecting sarcastic sentences of microblog comments involved in dynamic memory case descriptions, and belongs to the technical field of natural language processing. The invention includes the steps of: constructing a satirical data set of microblog involved in the case; using word embedding and position embedding to respectively carry out feature encoding on the text of the microblog involved and the comments on the microblog involved, and introducing an attention mechanism into the microblog comment involved after the feature encoding; Through the dynamic memory mechanism, the text representation related to the microblog comments involved in the case is obtained; the obtained text representation and the comment representation are spliced ​​to obtain a new representation, and the representation is used as an input to train the model, and the model is used to detect the sarcasm of the microblog comments involved in the case. The present invention realizes the irony detection of the comment sentences involved in the case by taking the case description information as the background information, and detects the irony sentences from the obtained public opinion data, which provides support for the subsequent sentiment analysis.
Owner:KUNMING UNIV OF SCI & TECH

Novel intelligence development toy

The invention discloses a novel developing intellectual toy, which comprises a frame and a plastic plate, a hanging ring is connected to the upper end of the frame, and a partition is installed on the frame, a groove is formed between the partition and the frame, and the plastic The board is placed in the groove, the left end of the frame is connected with a card slot, and a magic wand is placed on the card slot, an integrated chip is installed inside the plastic board, and a button is installed at the rear end of the plastic board. The groove is provided with a bump, and the inner wall connecting the groove and the bump is provided with a partition, the spring is connected between the bump and the partition, the bottom surface of the groove is provided with a through hole, and the plastic The bottom surface of the plate is provided with a bell mouth. This new developed intellectual toy is mainly developed to improve children's knowledge and memory. By increasing the scope of children's knowledge and then memorizing, it can effectively develop children's intelligence. At the same time, the plastic board and the frame are detachable force connection devices, which can change positions at will. Memory, flexible.
Owner:孝感市创捷电子科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products