65results about How to "With learning function" patented technology

The invention discloses a system and a method for cloud service real-time falling-down detection. The system comprises an acquisition device, a mobile terminal connected with the acquisition device, a transfer device connected with the acquisition device and the mobile terminal separately, a cloud service platform connected with the transfer device, and a monitoring terminal connected with the cloud service platform, wherein the acquisition device comprises a controller, and a three-axis acceleration sensor, a three-axis gyroscope, a pressure sensor, a body temperature sensor, a heart rate sensor, a pulse sensor, a blood pressure sensor, a positioning module, a communication module and a storage module which are connected with the controller separately. According to the system and the method disclosed by the invention, the acquisition device, the mobile terminal and the transfer device form a stable data communication mode to ensure that the falling-down information of a monitored object is uploaded to the cloud service platform by virtue of the transfer device, and the real-time monitoring of quick falling-down and slow conditions of the monitored object is realized; and the data communication mode can realize functions of hierarchical processing, storage and the like of data, thereby greatly improving completeness and reliability of the data.

The invention discloses a method and a system for intelligent centralized monitoring and management of a photovoltaic power station. The method includes the steps: acquiring and analyzing meteorological data of the photovoltaic power station; acquiring signals of an inverter, a circuit breaker and a transformer of the photovoltaic power station and receiving remote control signals to control related modules; acquiring voltage, current and component temperature data of each sub-module of the photovoltaic power station; converting the data into proper protocols, transmitting the protocols to a network switch through a network and finally transmitting the protocols to a monitoring computer and a server; displaying the data. Operation, maintenance and management of the distributed power station are realized by the centralized monitoring and management method, the data of the photovoltaic power station are deeply analyzed, the problem of shortage of data statistics of the photovoltaic power station is solved, and the operation and maintenance management mode of the photovoltaic power station is optimized.

A distribution transformer fault diagnosis device based on multi-index comprehensive evaluation includes a sound acquisition unit, an oil temperature acquisition unit, a unit for analyzing gas dissolved in oil of a transformer, a fault diagnosis unit and a battery power supply module; the fault diagnosis unit includes an FM receiver module (7) whose output end is connected with an AD converter (8) and an ARM single-chip microcomputer (9) in sequence; and the sound acquisition unit includes a fixed support (2) on which a strong magnet (1) and a pickup head (3) are fixed, the pickup head is connected with a pickup (4), an output end of the pickup is connected with a signal conditioning circuit (5) and an FM transmitter module (6) in sequence, and the FM transmitter module is connected with the FM receiver module through FM electromagnetic waves. The distribution transformer fault diagnosis device based on multi-index comprehensive evaluation can satisfy requirements for performing fault detection on a distribution transformer in operation on site and judging the fault type, does not need a power supply to be provided on site, and is convenient to carry, low in signal acquisition and transmission cost, fast in diagnosis speed and convenient to use.

The invention relates to an intelligent board feeding and discharging transfer robot. The intelligent board feeding and discharging transfer robot is characterized in that the transfer robot comprisesa rack, an X-axis movement module, a Y-axis movement module, a Z-axis movement module and a target storage tank; the X-axis movement module, the Y-axis movement module and the Z-axis movement moduleare mounted on the rack, and the target storage table is connected with the rack; the X-axis movement module and the Y-axis movement module are driven by a stepping motor provided with an encoder to slide in the horizontal direction, and the Z-axis movement module is driven by a drive motor to slide in the vertical direction; the positions, measured by the X-axis movement module, the Y-axis movement module and the Z-axis movement module through a PLC or NC system at fixed time intervals, of a machined are used as target coordinates, and then position control in the axial direction is conductedaccording to the target coordinates. The intelligent board feeding and discharging transfer robot has the advantages that firstly, the torque of the stepping motor is large so that the speed can be adjusted conveniently, and the speed is high; secondly, a cylinder is high in driving speed and bearing capacity and durable; thirdly, full automation is achieved, and labor consumption is reduced; andfourthly, the PLC or NC system is used for establishing a space coordinate system of the spatial positions of the X-axis movement module, the Y-axis movement module and the Z-axis movement module andthe material storage position, a position control program is written, and thus full automation is achieved.

The invention relates to an intelligent control device with orientation identification function, and the infrared way is widely applied in household devices as the main communication control way. In order to carry out the remote control on the device, a user needs to point a remote controller at the controlled device and presses a button for controlling the device. However, as the number of the household devices is increased, the number of the remote controllers is greatly increased, and the conversion among a plurality of remote controllers is very troublesome. The realization of the control, the studying and the operation of a plurality of devices is also very complicated. The intelligent control device with the orientation identification function comprises a sensor unit, wherein the sensor unit is connected with a core control unit, the core control unit is connected with a user feedback unit, the core control unit is connected with a communication unit, the core control unit is connected with a data auxiliary unit, and the intelligent control device is used in the field of electrical appliances.

The invention provides a cross-platform artificial intelligence assistant system application scheme. The whole cross-platform artificial assistant system is constructed by means of artificial intelligence, real-time information collection, a neural network model, cloud computing, cloud data storage and exchange, block chain storage and other technologies and by means of a high-speed data communication network, various networked user terminal devices and electronic sensors. Through intelligent assistant interaction programs running on different intelligent devices and system platforms at the front end, a unified virtual electronic assistant interaction image of a user is created, data interactive aggregation and seamless link switching are adopted by relying on various personal digital terminal electronic device interaction interfaces, omnibearing communication with the user is achieved, and interaction information is provided. The intelligent assistant has the functions of executing user instructions, answering questions, reading information, assisting suggestions, assisting control, planning supervision, advanced learning, continuous accompanying and the like, and meanwhile, according to user authorization, personal information data of a user is accurately collected, archived, sorted and recorded.

The invention discloses an electric appliance box and an automatic control method thereof. The automatic control method of the electric appliance box comprises the steps of collecting electric appliance use operational data of a user; conducting statistic on habitual data of the user according to the operational data; and conducting automatic control on an electric appliance according to the habitual data. By means of the electric appliance box and the automatic control method thereof, the electric appliance box can have the data learning function, and thus, automatic control which meets the habit of the user to a greater extent is achieved.

The invention provides a nerve cell element and a neural network, wherein the nerve cell element comprises a lower heating electrode, a phase change material, an upper electrode and a surrounding medium material, and the nerve cell element is changed into a normal state when a recovery pulse is applied and is changed into an exciting state when a stimulating pulse is applied. The nerve cell element only needs tens of nano time to be changed into the exciting state from the normal state, and requires very small energy consumption when being changed into the normal state from the exciting state. Meanwhile, the nerve cell element has the functions of comprehensively responding to the amplitude, the width and the number of stimulating pulses and providing a weight part and an operation part. The nerve cell element is simple in structure, is compatible with a CMOS (Complementary Metal-Oxide-Semiconductor Transistor) process, and is convenient in massive integration. The neural network comprises a hierarchical nerve cell array comprising a plurality of nerve cell elements, so that multi-channel transmission and storage of information are implemented, a learning function is achieved, and the neural network is expected to be applied in the field of cognitive computers and the like.

The invention relates to an automatic debugging method for a cavity filter. The method comprises the following steps of the first step: fixing a plurality of adjusting screws on an upper cover of the cavity filter at the same height, and then mounting the upper cover of the cavity filter on a cavity filter casing; the second step: performing prepositioning before automatic debugging, recording X / Y coordinate position information of each adjusting screw, numbering each adjusting screw, and a system controlling an automatic screw driving machine for performing a prepositioning motion of a first adjusting screw within a frequency band before adjustment; the third step: debugging the adjusting screw in the second step; the fourth step: repeating the second step and the third step to complete automatic adjustment of all adjusting screws in the frequency band; and the fifth step: repeating the second step, the third step and the fourth step to complete automatic adjustment of all adjusting screws of all frequency bands of the cavity filter.

This invention discloses a method for reducing power loss of adaptive power feedback by a mobile communication terminal relating to chip adopting digital signals, in which, a supply management circuit provides a relative stable supply to all circuits of a mobile terminal device at its output end to measure the change at this position, and signals entering into RF power amplification can measure envelopes of power of RF power amplification and carry out data sample at the input of the RF amplification and set a final sample point at the output end of the RF amplification after controlling power loss of the mobile terminal circuit based on the test result to the two points to realize test and analysis to the related parameters of mobile terminals and simplify control of output by continuously optimized executing forms.

The invention provides a memory impedance associative memory neural network circuit with a delay learning function, and the circuit comprises a voltage control module, a synaptic neuron module and a delay module. The input end of the voltage control module is connected with the input signal, and the voltage output end of the voltage control module is connected with the input end of the synaptic neuron module and the voltage input end of the delay module respectively. The input end of the delay module is connected with the input signal, the output end of the feedback signal of the delay moduleis connected with the input end of the feedback signal of the delay module and the voltage control module respectively, and the output end of the delay module is connected with the input end of the synaptic neuron module. The output end of the feedback signal of the synaptic neuron module is connected with the input end of the feedback signal of the voltage control module, and the input end of thecontrol signal of the synaptic neuron module is connected with the input signal. The invention has a learning function, and the learning rate is variable, has three forgetting processes and delay learning functions, and is more close to the actual situation.

The invention relates to an input method and a device thereof for characters that are used rarely. The method comprises the steps that: 1) a data base for characters that are used rarely is established, including candidate characters, components of the candidate characters, and a data base for characters that are used rarely of the pronunciation and the etymon sets of the components of the candidate characters; 2) the pronunciationor etymon sets inputted by the user of the components of the characters that are used rarely are received; 3) the components corresponding to the pronunciation or the etymon sets are searched from the data base for characters that are used rarely; 4) the searched components corresponding to the pronunciation are displayed; 5) the components corresponding to the characters that are used rarely are selected by the user; 6) the candidate characters corresponding to the components are selected from the data base for characters that are used rarely according to the components selected by customer; 7) the wanted character that are used rarely is selected from the candidate characters by user. The invention provides an inputting method and a device thereof used for quickly and accurately inputting characters that are used rarely.

The invention discloses an automatic garbage classification treatment device which comprises a Raspberry Pi, garbage cans, a support, a rotary disc steering engine, a steering engine, a bucket, a camera, laser correlation switches and display screens. The camera is installed at the top end of the bucket to shoot garbage placed in the bucket so as to recognize and classify the garbage; the bucket temporarily contains unclassified garbage to be recognized; after identification is completed, the steering engine drives to dump garbage into the garbage cans; the rotary disc steering engine drives the bucket to rotate to the corresponding garbage can; the output end of the rotary disc steering engine is fixedly connected with the bottom end of the steering engine; a nerve rod is built in the Raspberry Pi, deep learning is carried out for garbage identification and classification, and the Raspberry Pi is a central control system of the rotary disc steering engine, the steering engine, the camera, the laser correlation switches and the display screens; the garbage cans are used for containing classified garbage and are evenly distributed and installed on the outer side of the support; and the laser correlation switches are installed in the garbage cans to detect the amount of the garbage in the garbage cans and transmit the amount to the Raspberry Pi. The automatic garbage classification treatment device provided by the invention realizes intelligent garbage classification, has a learning function and is environment-friendly and reliable.

The invention discloses a multi-language instant translation system based on big data processing and manual intervention. The system comprises a parallel corpus and a third-party translation engine. A translation method of the system comprises the steps that a user inputs a to-be-translated language into the parallel corpus, wherein the to-be-translated language is a word language; the parallel corpus retrieves the to-be-translated language, and whether the parallel corpus can directly translate the to-be-translated language is judged; if the parallel corpus can directly translate the to-be-translated language, internally recorded information is retrieved, and then a retrieved translation result is output; if the parallel corpus cannot directly translate the to-be-translated language, the to-be-translated language is input into the third-party translation engine to be translated, and a translation result is output; and the translation result is modified manually, the information obtained after modification is fed back to the parallel corpus, and the information in the parallel corpus is updated continuously. According to the system, through combination of the parallel corpus and the third-party translation engine in combination with manual modification, the translation effect is more intelligent, and meanwhile the translation engine has a learning function.

The invention discloses a smart electricity meter case based on dual authorization of remote cloud and short-range bluetooth. The smart electricity meter case includes: a case body; a PLC wideload apparatus, an ESAM module in conformity with the domestic commercial password encryption algorithm and a wideload electricity meter device which are arranged inside the case body, and a short-range bluetooth apparatus, a carrier wave power supply, a metering chip, a detection apparatus and a memory which are connected to the PLC wideload apparatus; related data acquired by the metering chip and the detection apparatus being transmitted to a main device through a power line; the carrier wave power supply transmitting a power supply on / off signal to a cloud terminal or a hand-held terminal via an electricity wideload apparatus; the memory and the ESAM module both provided with authorization codes, temporary authorization codes and an invalid self-destruction module; a RS485 interface, an Internet of Things identification and a switch which are arranged outside the case body; a hall sensor which is connected to the switch. According to the invention, the smart electricity meter case enables automatic learning and identification of the electricity meter which is installed inside the case body, which increases safety of the smart electricity meter, and the bluetooth short-range authorization is applied to on-site maintenance staff, which is much easier to use.

The invention relates to a flexible transmission device and a robot provided with the flexible transmission device. The flexible transmission device comprises a driving component, a first relative movement component, a second relative movement component, a third relative movement component, a fourth relative movement component and a fifth relative movement component; the first relative movement component and the second relative movement component are arranged in a manner of being capable of freely and relatively rotating along a first rotation axis; the third relative movement component and the fourth relative movement component are arranged in a manner of being capable of freely and relatively rotating along a second rotation axis; the first relative movement component and the fifth relative movement component are arranged in a manner of being capable of freely and relatively rotating along a third rotation axis; the second relative movement component and the third relative movement component are in sliding connection; and the fourth relative movement component and the fifth relative movement component are in sliding connection. The flexible transmission device can be freely switched between the flexible rotation state and the rigid transmission state.

The invention provides an intelligent speed planning method based on mass single workpiece repeated processing. The method comprises the following steps: S1) machine tool machining; S2) multi-sensor signal acquisition; S3) feature extraction and signal fusion; S4) cutting state judgment: importing samples from a sample library, comparing the samples and the extracted feature signals, if normal, entering the next step, and if having heavy cutting or light cutting, carrying out velocity correction and entering the next step; S5) after finishing single processing, obtaining planning speed; and S6) repeating the steps S1)-S5) to obtain an optimal planning speed. The beneficial effects are that machining efficiency and machining accuracy are improved.

A method for detect prohibited electrical appliance in dormitory By establishing a database containing the power waveforms of qualified and prohibited electrical appliances, the electric power of eachdormitory is collected in real time, and collecting the electric power waveform diagram of the dormitory when the electric power changes and the change is greater than a set threshold value, the collected waveform is compared with the established database, according to the results of correlation comparison to judge whether there are illegal electrical appliances in the dormitory, not only can theswitching of high-power electric appliances be detected, The use of low-power prohibited appliances can also be detected, It provides a more comprehensive detection for the safe use of electricity indormitory, and through the method of correlation judgment, it can more accurately identify the load correlation of electrical appliances, overcomes the limitation of relying on power judgment only and the probability of misjudgment, the judgment result is more accurate and reliable, and further ensures the safety of the entire power environment.

The invention discloses an intelligent remote control socket. The intelligent remote control socket comprises an infrared receiving unit, a firing wire connecting unit, a master controller and a battery unit, wherein the signal output end of the infrared receiving unit is connected with the control signal input end of the master controller, the control signal output end of the master controller is connected with the control end of the firing wire connecting unit, and the firing wire output end of electric supply is connected with the firing wire output end of the socket through the firing wire connecting unit; the output end of the battery unit is connected with the power input end of the master controller, and the battery unit supplies power to the master controller when the master controller controls the firing wire connecting unit to cut off the connection between a firing wire of the electric supply and a firing wire of the socket. Power supplies of electric appliances connected and inserted into the socket can be physically disconnected or connected, the connection between the socket system and the electric supply can be physically disconnected or connected, therefore, complete separation between a socket interface and the electric supply is achieved, power consumption is reduced, and more safety is achieved.

The invention is based on a Curie module human body posture detection and correction device and a use method thereof, and relates to the technical field of human body posture monitoring. The present invention consists of a main controller (1), a posture correcting module (2) and a posture error recognition microswitch (3), which are connected in an electrical signal mode and displayed in real time through a human body posture detection App (4); wherein, the posture correcting module (2), the micro switch (3) is connected with the main controller (1); the mobile phone body posture detection App (4) can display the changes of human body posture dynamically in real time through the main controller (1) with Bluetooth. The device of the present invention has a learning function, collects personalized data of users, can freely define clothes and designs, and is suitable for the needs of various groups of people. The device has interconnection awareness, and the user's own data can be compared with the data of multiple people, and the data can be uploaded to the cloud for more accurate correction and analysis. The device provides a technical and material basis for the health industry, especially for the market demand for human body posture correction.

A radio receiving device to be shared by the peripheral equipment of computer includes radio receiving circuit, microprocessing circuit, keyboard circuit and interface circuit, among which the microprocessing circuit can receive several different radio signals emitted by a radio emission devices of computer peripheral equipment through the radio circuit and it has the learning mode to make the microprocessing circuit memorize and lock the specific radio emission device by pressing the keyboard circuit as well as to transmitt the signal processed by the microprocessing circuit to the computer through the interface circuit.

The invention relates to an intelligent garbage classification device. The intelligent garbage classification device comprises a shell assembly, a bin door assembly, a bag breaking assembly, a mechanical arm assembly, a measuring assembly and a control assembly. The top of the shell assembly is open. The bin door assembly comprises two vertical hinged doors. The measuring assembly comprises a scanning recognition component, a weighing component and an in-bag detection component. The bag breaking assembly comprises a bag lifting component, an optical distance measuring component and a laser cutting component. The control assembly comprises a central controller, a bin door control module, a mechanical arm control module, a bag breaking control module, a measuring control module and a learning module. The invention further discloses a classification method using the intelligent garbage classification device. The intelligent garbage classification device can receive garbage from mixed bagsand automatically break the bags to sort the garbage in the bags, the garbage which cannot be recognized is manually treated and learned through the intelligent garbage classification device, and thesubsequent recognition capacity is improved. The intelligent garbage classification device is high in automation degree, has a learning function and is wide in application prospect.

The invention discloses a fingerprint detector. The fingerprint detector comprises a power supply assembly, a capacitance type fingerprint sensor, a microcontroller and a signal processor, wherein the power supply assembly is electrically connected with the capacitance type fingerprint sensor, the microcontroller and the signal processor respectively; the microcontroller is connected with one end of the capacitance type fingerprint sensor, and the signal processor is connected with the other end of the capacitance type fingerprint sensor; the capacitance type fingerprint sensor comprises a plurality of sensing units arranged in an array manner and used for acquiring fingerprint information and transmitting the fingerprint information to the signal processor; the signal processor is used for processing the fingerprint information; the microcontroller is used for controlling the capacitance type fingerprint sensor and the signal processor according to the processing result of the signal processor. According to the fingerprint detector disclosed by the invention, when the capacitance type fingerprint sensor acquires the fingerprint information, a high-precision fingerprint image is acquired by enabling the fingerprint to form a capacitance array and then enabling the capacitance array to be combined with the sensing units to form a plurality of micro-capacitors.

The invention discloses a control method for the compartment intelligent service robot traveling based on the neural network. The method is divided into a training phase and a learning phase, in the training phase, a positioning base station sensor is arranged in a compartment, a robot body is provided with a camera and an infrared detector, position parameters of the robot body are collected as input variables, an SCFNN model architecture is established in the form of at least two input nodes and one output node, and a four-layer operation in an SCFNN model is conducted to obtain an inferenceoutput value; in the learning phase, the input node is subjected to structural learning to generate new rules and subjected to parameter learning to obtain an inference value, a connection weight, the mean value of a member function and the modifier of a standard deviation are corrected, and when each input node enters the SCFNN model, correction is conducted until the SCFNN model is learned. Themethod has the following advantages that the application of the SCFNN neural network can shorten the calculation period and optimize the robot travel distance and speed to achieve the improvement ofartificial intelligence.

The invention relates to the technical field of intelligent homes, in particular to a learning scenario management system based on light control. The learning scenario management system comprises a control module, a voice recognition module, an adjustment module, a matching module, a change-over switch and a storage module, wherein the voice recognition module is used for receiving external voiceand transmitting the received voice information to the matching module; the adjustment module is used for automatically adjusting lighting parameters of a plurality of lamps and feeding back the lighting parameters of the lamps to the control module; the storage module is used for storing a plurality of control instructions for mode control of the lamps; and the matching module is used for matching the voice information received by the voice recognition module to correspond to the control instructions in the storage module and generating execution instructions to the control module. Compared with the prior art, the scenario management system of the application can store and read the control modes for uniformly controlling the lamps, and thus the convenience degree can be improved, and thescenario management system is more convenient.

The invention discloses a reclosing self-checking report security management platform. The security management platform comprises an intelligent meter box, a reclosing module, a safety management module and an alarm module, wherein the intelligent meter box is correspondingly configured with the reclosing module, a transmission mechanism is driven by the reclosing module through a motor, and closing / opening operation of a switch are further driven. The security management platform is characterized in that electric quantity is provided by the intelligent meter box for the security management module as the basis of user payment, intelligent control of the reclosing circuit module is realized by the security management module through a control signal or a monitoring signal according to the user's payment situation or self-checking demands, the alarm function of the alarm module is triggered when reclosing closing / opening action is a fault, and the invention further relates to a control method of the security management platform. The security management platform is advantaged in that intelligent control of a reclosing switch is carried out through utilizing motor motion planning management, on the condition that the use environment of a client is not influenced, timing self-checking, motion self-checking and fault self-report functions are realized.

The invention provides a method and system for achieving a remote control function, a server and a remote control terminal. The method for achieving the remote control function comprises the steps that when remote control code requesting information including controlled product data and function data is received, the remote control code requesting information is compared with controlled product data and function data in stored remote control instruction information, and remote control instruction information matched with the remote control code requesting information is determined; instruction code data in the matched remote control instruction information is sent. By means of the scheme, the instruction code data corresponding to the corresponding function of a controlled product can be sent according to the demand of a user instead of directly releasing all instruction codes related to the controlled product to the user remote control terminal. On the premise that the demand of the user is met, the storage space of the remote control terminal is occupied as little as possible; besides, the remote control terminal only needs to process instruction code data related to the demand of the user when processing the instruction code, and the processing efficiency can be effectively improved.

The invention relates to a fault diagnosis device for a numerically-controlled machine tool. The device comprises a sensor, a signal pick-up circuit, a processing unit, an alarm, an LED (Light Emitting Diode) indicating lamp, an LCD (Liquid Crystal Display), a driving circuit and a key for setting working parameters, wherein the sensor is mounted on the numerically-controlled machine tool; the signal pick-up circuit processes a signal detected by the sensor to form a standard signal so as to be input into the processing unit; the processing unit compares the input signal with a characteristicvalue, the alarm and the LED indicating lamp can give alarm information if the input signal exceeds the set value, and simultaneously, the driving circuit enables the information to be displayed on the LCD; and the processing unit is an STC single chip microcomputer. The device provided by the invention can quickly judge a fault part or perform early warning on a fault, is small in volume and convenient to use, can relatively quickly position the fault, and is convenient to popularize.