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

36 results about "Cognitive technology" patented technology

Cognitive technologies are products of the field of artificial intelligence. They are able to perform tasks that only humans used to be able to do. Examples of cognitive technologies include computer vision, machine learning, natural language processing, speech recognition, and robotics.

Distributed cognitive technology for intelligent emotional robot

The invention provides distributed cognitive technology for an intelligent emotional robot, which can be applied in the field of multi-channel human-computer interaction in service robots, household robots, and the like. In a human-computer interaction process, the multi-channel cognition for the environment and people is distributed so that the interaction is more harmonious and natural. The distributed cognitive technology comprises four parts, namely 1) a language comprehension module which endows a robot with an ability of understanding human language after the steps of word division, word gender labeling, key word acquisition, and the like; 2) a vision comprehension module which comprises related vision functions such as face detection, feature extraction, feature identification, human behavior comprehension, and the like; 3) an emotion cognition module which extracts related information in language, expression and touch, analyzes user emotion contained in the information, synthesizes a comparatively accurate emotion state, and makes the intelligent emotional robot cognize the current emotion of a user; and 4) a physical quantity cognition module which makes the robot understand the environment and self state as the basis of self adjustment.
Owner:UNIV OF SCI & TECH BEIJING

Band dynamic selecting and time scheduling method in heterogeneous network

The invention provides a band dynamic selecting and time scheduling method in a heterogeneous network, relating to a method and equipment for dynamically selecting usable frequency resources in a plurality of main system bands in a heterogeneous network system based on the cognitive technology, in particular to a method and equipment used for opportunity spectrum access, frequency resource efficient utilization, and combination of heterogeneous network resource amalgamation and user business service quality (QoS) assurance. The invention has the band dynamic selecting method as follows: firstly, aiming to different main system characteristics, an average main system user detection threshold of each main system of a base station CBS accessory is defined and cognized, and the threshold is an average value of the prior detection threshold in a wireless network transmission environment; secondly, according to the average main system user detection threshold and the throughput needs of a secondary system user, scanning efficient time of CBS to each main system is defined; thirdly, the CBS selects the optimal main system band from a usable band list according to a request of a user, the wireless transmission characteristics and a channel state of a band channel are the basis for selecting the optimal band, and interruption of the equipment CPE transmission throughput is preset according to the user.
Owner:NANJING UNIV OF POSTS & TELECOMM

Method for reducing long term evolution (LTE) radio communication system cell interference by using cognitive technology

The invention provides a method for reducing long term evolution (LTE) radio communication system cell interference by using a cognitive technology. The method comprises the following steps of: 1, setting a threshold value for dividing users in the cell into centre users and edge users; 2, configuring frequency resources for the users in the cell of the base station according to the preset initial frequency resource allocation rule by each base station; 3, judging the type of user equipment (UE) of the service which the newly added cell prepares for initiating according to a threshold value; 4, according to a judged result in 3, allocating frequency resources for the newly added UE according to a second preset frequency resource allocation rule by each base station; or allowing the newly added UE to independently select a usable spectrum for communication by using the cognitive technology; and 5, allocating power resources for the cell according to the UE type configured to each frequency resource. The technical scheme provided by the invention enables the frequency resources used in each cell to realize distribution according to needs and to dynamically change along with the change of the cell load. The cell resource is fully utilized, the interference coordination is effectively realized, and the spectrum utilization rate is improved.
Owner:BEIJING STARPOINT TECH COMPANY

Power line communication method based on channel cognitive technology

The invention provides a power line communication method based on a channel cognitive technology, and the method comprises the following steps of: cognizing a power line channel and obtaining a channel module; determining the configuration parameters of a communication device according to the obtained channel model; configuring a communication transceiver in the communication device according to the determined configuration parameters; and executing data transmission via the communication device which is configured with the configuration parameters. Compared with the prior art, the method provided by the invention can be used for configuring the configuration parameters of the communication transceiver in the power line communication device, thus the whole power line communication system can work in the most appropriate state, thereby improving the reliability, stability and communication rate of power line communication and simultaneously improving the frequency spectrum utilization ratio and the power utilization ratio.
Owner:ASEIT

Internet of things (IOT) method based on cognitive technology

The invention discloses an Internet of things (IOT) method based on a cognitive technology. In the method, a monitoring layer, a decision layer and a control layer are utilized, wherein the monitoring layer collects and processes the network layer information of the IOT; the decision layer makes a decision according to the information provided by the monitoring layer, a corresponding decision is directly used if a matched decision exists in the decision layer, and otherwise, a machine learning method is used for obtaining a new strategy; the control layer takes the corresponding action according to the decision made by the decision layer, and controls in a mode of terminal path synergy; and only a terminal in the network is adjusted. In the IOT method, a cognitive plane is added in the network layer of the traditional IOT so as to optimize the structure of the network layer, thus alleviatiing the problem of network congestion and the like in the traditional network. The cognitive plane is divided into the monitoring layer, the intelligent decision layer and the control layer. In the framework, the real-time state information of the network is circulated in the cognitive plane and the network layer of the IOT so as to guarantee the QoS (quality of service) of the network.
Owner:NANJING UNIV OF POSTS & TELECOMM

Hybrid changeable computing system based on server

The invention relates to a hybrid changeable computing system based on a server. Multiple mimic computation board cards are inserted into the server, so modes with high performance-efficiency ratios are configured in an auto or semi-auto manner from levels of hardware and software according to different characteristics of concurrent services; each mimic computation board card comprises one deviceor multiple devices among a FPGA, a GPU and a DSP; and the concurrent services comprise graphic services, computation services and communication services. The system provided by the invention is basedon bionics technologies, cognition technologies, reconfiguration technologies and high-performance computation technologies; through mimic conversion based on a cognitive meta-structure, a physical solution structure set needed by an application target is generated; and through combination of dynamically changeable structures, software and hardware, function-oriented transformation of a computation structure is achieved.
Owner:江苏十月中宸科技有限公司

Soft frequency reusing method and device based on cognitive technology and base station

ActiveCN102448069AGuaranteed co-channel interferenceImprove frequency utilizationNetwork planningFrequency reuseComputer science
The invention provides a soft frequency reusing method and device based on a cognitive technology and a base station. The method comprises the following steps of: configuring frequency points to be distributed in a cell as a preferable frequency point set and configuring distributed frequency points of a neighboring cell of the cell as an optional frequency point set; judging whether resources which can be distributed exists in the preferable frequency point set or not; if so, distributing the frequency points in the preferable frequency point set to a mobile terminal; otherwise, distributing the frequency points in the optional frequency point set to the mobile terminal. through adoption of the soft frequency reusing method and device based on the cognitive technology and the base station, provided by the invention, a concept of a center and edges of the cell is broken through, the current frequency points of a user are sequenced through judging neighboring cell measurement information reported by the user and the frequency points with low same frequency interference are selected for access, therefore the same frequency interference is assured, and higher frequency utilization rate is realized.
Owner:COMBA TELECOM SYST CHINA LTD

Cognitive technology-based indoor wireless communication coverage interference elimination scheme and cognitive technology-based indoor wireless communication coverage interference elimination device

The invention discloses a cognitive technology-based indoor wireless communication coverage interference elimination scheme and a cognitive technology-based indoor wireless communication coverage interference elimination device. In order to enhance the indoor coverage effect of a mobile communication network, femtocells gain great attention because of low power consumption, short transmission distance and other characteristics. Aimed at the situation of poor indoor coverage effect, the invention discloses the method which applies the cognitive radio technology into femtocell interference elimination. By periodical spectrum sensing, femtocells learn and know spectrum utilization information in the surrounding radio magnetic environment, and dynamically access idle subchannels to carry out communication, consequently, interference applied on macrocell base stations / users is prevented, and the high throughput and high reliability of a system are guaranteed.
Owner:BEIJING UNIV OF POSTS & TELECOMM

Intelligent vehicle threat estimation system and method based on variable-structure Bayesian network

The invention, which relates to the field of the intelligent vehicle cognitive technology, claims for protection of an intelligent vehicle threat estimation system and method based on a variable-structure Bayesian network thereby evaluating a threat degree of a moving target to a vehicle. The system is composed of a threat modeling module, a data collection module and a threat estimation module. At a threat modeling stage, factors affecting intelligent vehicle threat estimation are determined, wherein the factors include an external environmental factor, a target characteristic factor and a driver factor; a topology of a Bayesian network model is constructed; and then a local condition probability table of the model is determined. During the driving process, the data acquisition module uses sensors to collect real-time data of various influence factors; the threat estimation module reconstructs corresponding variable nodes only for quickly changing factors according to changing rates of all factors to obtain a variable-structure Bayesian network model and then carries out reasoning calculation to obtain a target threat index. Therefore, the performance of intelligent vehicle threatestimation can be improved effectively.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Biological-friendly cognitive underwater acoustic network communication method by efficiently utilizing spectrum resources

The invention relates to a biological-friendly cognitive underwater acoustic network communication method by efficiently utilizing spectrum resources. The biological-friendly cognitive underwater acoustic network communication method comprises the following steps that: a primary user in UCANs is a marine mammal; a sensor node is a secondary user; a frequency band occupied by sound production of the marine mammal is used as an authorized frequency band; the authorized frequency band is divided into two parts; for the frequency band having high use frequency, the marine mammal has the prior use right; after receiving communication agreement information of a cognitive centre, a cognitive user performs spectrum sensing of a channel; the sending power is necessary to be lower than a hearing threshold of the marine mammal; the cognitive user performs communication according to distribution information of the cognitive centre; and spectrum sensing is still necessary to carry out in a communication process. According to the biological-friendly cognitive underwater acoustic network communication method disclosed by the invention, interference of communication of the sensor node to communication between marine mammals can be avoided; simultaneously, underwater spectrum resources are reasonably utilized and distributed; and high-efficiency utilization of the spectrum resources is realized based on a cognitive technology.
Owner:TIANJIN UNIV

Near-infrared spectroscopy detection method of ambient light modulated brain cognitive function

The invention belongs to the technical field of brain science cognition, and particularly relates to a near-infrared spectroscopy detection method of an ambient light modulated brain cognition function. According to the method, functional near-infrared spectroscopy (fNIRS) is utilized, a classical paradigm Stroop of cognitive behavioral psychology is combined, and the influence of ambient light change on the cognitive function of a human brain is explored for a prefrontal cortex (PFC) area with high correlation with the cognitive function of the human brain; The near-infrared spectroscopy detection method comprises the steps of designing an experiment environment; designing psychological Stroop experiment stimulation rules; designing an experiment process; building an experiment system; configuring a detection channel; combining a Stroop psychological test method with the fNIRS for testing; and finally, carrying out fNIRS data processing. Brain activation area images under different illumination conditions are obtained, and brain area channels with significant difference (P is smaller than 0.05) under different illumination conditions are obtained through t test, which proves thatthe channels are activated due to ambient light change.
Owner:FUDAN UNIV

Internet of things (IOT) method based on cognitive technology

The invention discloses an Internet of things (IOT) method based on a cognitive technology. In the method, a monitoring layer, a decision layer and a control layer are utilized, wherein the monitoring layer collects and processes the network layer information of the IOT; the decision layer makes a decision according to the information provided by the monitoring layer, a corresponding decision is directly used if a matched decision exists in the decision layer, and otherwise, a machine learning method is used for obtaining a new strategy; the control layer takes the corresponding action according to the decision made by the decision layer, and controls in a mode of terminal path synergy; and only a terminal in the network is adjusted. In the IOT method, a cognitive plane is added in the network layer of the traditional IOT so as to optimize the structure of the network layer, thus alleviatiing the problem of network congestion and the like in the traditional network. The cognitive plane is divided into the monitoring layer, the intelligent decision layer and the control layer. In the framework, the real-time state information of the network is circulated in the cognitive plane and the network layer of the IOT so as to guarantee the QoS (quality of service) of the network.
Owner:NANJING UNIV OF POSTS & TELECOMM

System for cognitive technical architecture integration

Embodiments of the invention are directed to systems, methods, and computer program products for integration of multiple technical architecture diagrams into a single diagram. Architectural diagrams are commonly used in program level impact analysis and may depict relationships, constraints, and boundaries between components of an individual software program as well as the relationships between multiple software programs, hardware components, and users. The present invention automatically identifies touchpoints, or connections between multiple architecture diagrams and applies a series of image-processing algorithms, generating a single integrated diagram for organizational use. Embodiments of the invention also provide for multiple rounds of image processing, allowing multiple integrated diagrams to be combined into single diagrams.
Owner:BANK OF AMERICA CORP

Cognition-based memory recognition and recovery method and system

InactiveCN109256184AEnhance memoryRestore memoryMedical devicesAcquiring/recognising eyesRecovery methodMemory recognition
The invention belongs to the field of cognition technology improvement, and provides a cognition-based memory recognition and recovery method. The method includes the following steps that: S1, data information in an activity scene is collected through a cognition device; S2, the significant features of the collected scene data information are extracted, and feature marks are generated; S3, mappingrelations between the generated significant marks and the extracted data information are established, memory information is automatically generated in a database and is stored; S4, associated searchmemory data information is inputted; S5, a corresponding mode is selected to query the generated memory information in the database according to the inputted data information; and S6, whether the associated data information exists in the memory data is judged. With the method adopted, the memory of a user can be enhanced, and the recovery of the memory can be facilitated after the memory loses; and the user can be assisted to recover and enhance the memory, so that it is more convenient and quicker to retrieve the memory quickly after the memory loses.
Owner:邓建晖

Ship navigation auxiliary system and method based on deep learning and visual SLAM

The invention discloses a ship navigation auxiliary system and method based on deep learning and visual SLAM, and the system comprises an intelligent terminal, an IOT platform, a streaming media server, a video analysis processing module, and a target recognition tracking module. The streaming media server, the video analysis processing module and the target recognition tracking module are all ininteractive connection with the IOT platform, the IOT platform is in interactive connection with the intelligent terminal, and a semi-automatic labeling module is installed in the intelligent terminalin an embedded mode. According to the ship navigation auxiliary system and method based on deep learning and visual SLAM, the active sensor (such as radar, visible light camera and thermal imaging camera) detection technology, the passive sensor (such as AIS and GPS) detection technology and the highly-fused real-time situation and cognition technology are combined, so that real-time detection, dynamic tracking, intelligent early warning and historical backtracking are carried out on a target in a specific region, the ship safety is guaranteed, and the ship and surrounding targets of the shipare effectively monitored.
Owner:四川智海联科技有限公司

Multi-layer approach to monitor cell phone usage in restricted areas

A system and method are provided for managing mobile device in a restricted area, which includes determining a length of time the mobile device remains in a predetermined area. The method includes incrementing a threat level by a first amount, wherein the first amount is calculated using a predictive model created with historical information derived from a management system. The method includes comparing usage of the mobile device with one or more existing models that describe a behavior of a regular user and a suspect user. The method includes incrementing the threat level by a second amount when usage matches a particular behavior. The method includes using a set of cognitive techniques to further assess potential behavior of a user. In response to determining the threat level associated with the mobile device exceeds a fourth threshold, the method includes initiating a predefined action.
Owner:KYNDRYL INC

A Cognitive Blind Equalization Method for Radar Channel Amplitude and Phase Correction

InactiveCN106249205BRealize closed-loop equalizationImprove convergence reliabilityWave based measurement systemsPhase correctionBlind equalizer
The invention discloses a cognitive blind equalization method for radar channel amplitude and phase correction. The method comprises: a calibration signal is sent to a blind equalizer; an output signal of the blind equalizer is transmitted to a selection switch; a plurality of related parameters of a convergence characteristic of the blind equalizer are monitored and a signal after equalization processing is outputted when the equalization process of the blind equalizer is normal; and when the equalization process of the blind equalizer is abnormal, equalization processing is not carried out and the signal is delayed and then is outputted. The blind equalizer employs several kinds of cognitive technologies for monitoring and whether the blind equalizer is normal is monitored by multiple parameters, thereby guaranteeing reliability of usage of the blind equalizer. According to the invention, closed-loop equalization of a digital array radar in a digital transmitting-receiving assembly is realized and data downloading and equalization coefficient returning are not required. Meanwhile, a cognitive method for a mean square error and weight coefficient vector monitoring is introduced, so that convergence reliability of the constant-modulus blind equalization method is improved and thus reliability of hundreds of radar channel equalizers of the digital array radar can be guaranteed.
Owner:HOHAI UNIV

Voice matching method in multi-person scene

An embodiment of the present application provides a voice matching method in a multi-person scene, including: dividing the audio to be matched into multiple sound segments; performing voice recognition on the sound segments to obtain the voice segments in the sound segments; and obtaining the video corresponding to the voice segments Segment; Face detection is performed on the video segment to obtain all predicted speakers of the voice segment; according to the pixel difference of adjacent gray-scale frames in the video segment, the hit information of each predicted speaker in the adjacent gray-scale frame is obtained; according to The hit information counts the number of hits of each predicted speaker in the video segment, and the predicted speaker with the largest number of hits is the target speaker of the speech segment. The present application realizes the automatic binding of the voice to the target speaker, which can greatly reduce the workload of subsequent manual matching of the voice and the target speaker, and is conducive to promoting the practical application of audio-visual cognition technology.
Owner:YUNNAN POWER GRID CO LTD ELECTRIC POWER RES INST

Cognitive technology-based electric power service data process system and processing method thereof

A cognitive technology-based electric power service data process system and a processing method thereof are provided; the method comprises the following steps: continuously learning and analyzing artificial service data; automatically replying client service requests according to the learning result; requesting artificial customer service assistance if no reply matched with the service request can be found in the learning result, and learning and analyzing the newly generated artificial service data. The cognitive technology-based electric power service data process system and method can use the cognition technology to fast process businesses round-the-clock, thus improving artificial business accepting efficiency by times, greatly reducing enterprise manpower resource cost, enhancing emergent event emergency processing capability, and improving client service experiences.
Owner:SHANGHAI MUNICIPAL ELECTRIC POWER CO

Method for reducing long term evolution (LTE) radio communication system cell interference by using cognitive technology

The invention provides a method for reducing long term evolution (LTE) radio communication system cell interference by using a cognitive technology. The method comprises the following steps of: 1, setting a threshold value for dividing users in the cell into centre users and edge users; 2, configuring frequency resources for the users in the cell of the base station according to the preset initial frequency resource allocation rule by each base station; 3, judging the type of user equipment (UE) of the service which the newly added cell prepares for initiating according to a threshold value; 4, according to a judged result in 3, allocating frequency resources for the newly added UE according to a second preset frequency resource allocation rule by each base station; or allowing the newly added UE to independently select a usable spectrum for communication by using the cognitive technology; and 5, allocating power resources for the cell according to the UE type configured to each frequency resource. The technical scheme provided by the invention enables the frequency resources used in each cell to realize distribution according to needs and to dynamically change along with the change of the cell load. The cell resource is fully utilized, the interference coordination is effectively realized, and the spectrum utilization rate is improved.
Owner:BEIJING STARPOINT TECH COMPANY

Hybrid clustering method for simulating bifurcation and brain inspiration cognition

The invention relates to a hybrid clustering method for simulating bifurcation and brain heuristic cognition. Initializing a cluster core, extracting distribution characteristics of data points through combinatorial optimization clustering, and automatically obtaining the gravity center of the data points from a global perspective, namely the initial cluster core; a cognitive technology of brain excitation is introduced, and a selective attention mechanism is introduced, so that attention is focused in a middle region of a cluster kernel. And solving the established QUBO model through a quantum heuristic algorithm. Iterations are repeated until convergence is achieved and the clustering result is kept unchanged.
Owner:上海图灵智算量子科技有限公司

Attention improving method and system

The embodiment of the invention provides an attention improving method, and relates to the technical field of cognition. The method comprises the steps of performing independent game training on a user by using a visual motion path task and a visual identification target task respectively, and determining visual information of the user and a learning area upper limit of target identification respectively; performing mixed game training on the user by using the mixed visual motion path task and the visual discrimination target task, and respectively determining visual information of the user and a learning area lower limit of target discrimination; and based on the upper and lower limits of the learning area for visual information classification and target discrimination, determining the learning area corresponding to visual information classification and target discrimination in concentration training of the user in real time. The embodiment of the invention further provides an attention improving system. According to the embodiment of the invention, test training is carried out on the user in different dimensions, the learning area of concentration training which can be accepted by each user is determined, concentration training is carried out on the user through the learning area, it is guaranteed that the user can be trained with high attention, and the training effect is improved.
Owner:江苏瑞脑启智医疗科技有限公司

Cognitive-technology-based video data synthesis method

InactiveCN102595099BRealize anti-counterfeitingEffectively monitor whether the work is standardizedTelevision system detailsColor television detailsVideo monitoringDatabase
The invention discloses a cognitive-technology-based video data synthesis method which belongs to the field of fault diagnosis systems of automatic systems. The method comprises the following steps of: (1) checking whether the line of a video monitoring system is normal or not; (2) carrying out data encryption and storing encrypted data into a data server of the video monitoring system; (3) implementing the positioning and the integration of video data and article electronic tag data; and (4) generating a text signal for specific characters requiring overlying in the video monitoring system by utilizing a corresponding relation of the video data and the article electronic tag data which are generated in the step (3) as well as temperature and humidity data, and meanwhile, finding the recorded text signal of the image in the data server of the video monitoring system; and comparing the two text signals. The method has the advantages of implementing the association of the video data and the data requiring overlaying, implementing data fake prevention, judging whether the line has unexpected cases or not and monitoring whether the work of monitoring flow operation staff is formal or not.
Owner:BEIJING JIAOTONG UNIV

A near-infrared spectroscopy detection method for ambient light modulation of brain cognitive function

The invention belongs to the cognitive technical field of brain science, and specifically relates to a near-infrared spectrum detection method for ambient light modulation of brain cognitive function. The method of the present invention uses functional near-infrared spectroscopy technology, combined with the classic paradigm Stroop of cognitive behavioral psychology, to explore the impact of environmental light changes on the cognitive function of the human brain, aiming at the frontal lobe region of the brain that has a strong correlation with the cognitive function of the human brain. Including designing the experimental environment, designing the psychological Stroop experimental stimulus rules, designing the experimental process, building the experimental system, and configuring the detection channel; using the Stroop psychological test method combined with functional near-infrared spectroscopy for testing; finally, fNIRS data processing; Images of brain activation regions under different lighting conditions, and through the t test, the brain region channels with significant differences (P<0.05) under different lighting conditions were obtained, which proved that the channels were activated due to changes in ambient light.
Owner:FUDAN UNIV

Method and system for judging whether network communication behavior is abnormal or not and electronic equipment

The invention relates to a method and system for judging whether a network communication behavior is abnormal or not and electronic equipment, and aims to judge whether the network communication behavior is abnormal or not according to a group of network communication data to be judged with the same communication information and a neural network model based on a neural network and corresponding to the same communication information. The implementation difficulty is low, detection personnel do not need to have deep industry knowledge and cognition, the technical threshold is low, and the learning cost of the detection personnel is reduced.
Owner:四川英得赛克科技有限公司
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