85results about How to "Realize artificial intelligence" patented technology

The invention relates to a conductive-rubber-based flexible array clip pressure sensor and a manufacturing method. In the conductive-rubber-based flexible array clip pressure sensor, upper and lower electrode wires and electrode rings are printed on an upper electrode layer and an electrode layer; the electrode ring is provided with a rubber voltage-sensitive unit; a silicon rubber liner is arranged at the position where sensitive elements do not exist; the rubber voltage-sensitive unit is nested into the silicon rubber liner; the upper and lower electrode wires are led and connected to an electrode lead-out head; the upper and lower electrode layers are sealed by high viscose; and when force acts on the rubber voltage-sensitive unit, the rubber voltage-sensitive unit is compressed and deformed due to stress, so a resistance value of the rubber voltage-sensitive unit is changed, and pressure or concentrated loads at the point contact position can be reflected according to the variablequantity of the resistance value on the rubber voltage-sensitive unit relative to an initial resistance value. By a manufacturing method based on a silk-screen printing process, the flexible array clip sensor has the characteristics of light weight, low cost, simple manufacturing and mass production, and is long in service life and convenient to operate.

The invention relates to a finger clicking character recognition method and a translation method based on artificial intelligence. The recognition method comprises the following steps of (1) respectively constructing and training each neural network; (2) using the acquisition device to acquire the current image of the pre-detection area in real time, and continuously inputting the image into the pre-trained finger positioning neural network to obtain the finger position information under the finger click state; 3) taking that position of the user's fin as the center, intercepting the image ofthe box area, inputting the angle recognition neural network, and outputting the rotation angle of the text in the image area; 4) rotating the rotation angle to intercept the frame area image with theposition of the user's fin as the center, and outputting the position information and the size information of the detected character area; (5) intercepting a corresponding image, inputting the OCR recognition neural network, and outputting the recognized text content. The invention not only improves the identification efficiency but also enables the identification artificial intelligence to be realized.

The invention relates to an automatic wall plastering machine, which mainly consists of a frame body, an automatic material supply mechanism, an automatic positioning mechanism, a winch mechanism, a slideway mechanism, a plastering plate mechanism and an electric control mechanism, wherein the winch mechanism is connected with a pulley of the slideway mechanism through a steel wire rope; and a feeding pipe of the automatic material supply mechanism is communicated with a feeding opening formed in the back end of a plastering plate of the plastering plate mechanism. A slideway of the automatic wall plastering machine can realize the vertical free extension and retraction, and the plastering plate is driven by a rack pinion to realize the angle adjustment. The winch mechanism comprises a main shaft and a sub shaft; the sub shaft sheaths the main shaft; the power is output through an electromagnetic clutch; the main shaft rigidly outputs the power; the sub shaft flexibly outputs the power; and a slide block realizes the leftward and rightward operation through a lead screw motor. The automatic wall plastering machine has the advantages that the automation and the artificial intelligence are realized to the maximum degree; the automatic feeding, the automatic positioning and the automatic wall plastering can be achieved; the operation is convenient; and the work efficiency is high.

The present invention discloses a natural language machine recognition method, comprising the following steps of (1) establishing a database corresponding to similar predicate calculus form meanings; (2) inputting natural language information; (3) segmenting sentences of the natural language information one by one, and converting the sentences into one or more than one similar predicate calculus form sentence according to a segmentation rule; (4) converting the plurality of similar predicate calculus form sentences into electric signals for machine recognition, inputting the electric signals to a central processing unit to perform logic reasoning or metaphor or association creative thinking function treatment by at least one mode of search or recognition or recursion or substitution, and generating a new numeric code combination; and (5) retroactively converting the numeric code combination into a new natural sentence corresponding to the input natural language information as an output or as a learning result for storage.

The invention relates to an intelligent monitoring device for a screw pump well, which is a high-performance industrial control device combined with optical, mechanical and electronic integration and electronic information and communication technology, and is mainly used for intelligently monitoring oil extraction of the screw pump well in oil field. The intelligent monitoring device mainly comprises a light current part and a strong current part, and is characterized in that the intelligent monitoring device takes connection of parts such as a sensor capable of measuring dynamic liquid level of the screw pump well on line, a sensor capable of measuring the torque and axial force of the screw pump well on line, a sensor capable of measuring electricity using parameters such as running current constantly and a remote wireless communication device and the like with a CPU as a core to realize the effective measurement and intelligent closed-loop control of the screw pump well. The intelligent monitoring device can avoid pump burning phenomenon of a screw pump caused by evacuation through accurate measurement and effective monitoring and dispatching, scientifically make a hot washing system according to wax deposition cause and the like to avoid phenomena such as rod breakage and the like, find eccentric wear problem in time to prolong pump detection cycle, and optimize design of the screw pump well to reasonably determine working parameters and reduce potential safety hazard and the like.

The invention relates to pumping unit intelligent multiplier controller. It mainly includes light and strong current parts. Its feature is that dynamic liquid level transducer and polished rod load and displacement transducer are connected with the CPU to realize exact closed-loop control for the pumping well. The light current part includes main control CUP and controlled CPU; the strong current part includes energy feedback, stand by power frequency, and power frequency conversion interlocking parts. The invention can increase pumping well system efficiency, realize its energy saving and consumption reducing, increase both production and income, input-output ratio, and economic benefit, can be suited for oil field electric network specificity and pumping well variability.

The embodiment of the invention provides a business processing method comprising the steps that after system login is succeeded, existence of work orders to be processed is judged; if the work orders to be processed exist, the process enters a work order performance page, and whether the current performance page is matched with a corresponding page of the preset business logic is judged; and if the current performance page is matched with the corresponding page of the preset business logic, business processing is performed according to the preset business logic. The embodiment of the invention also provides a corresponding business processing device. With application of the business processing method and device disclosed by the embodiment of the invention, artificially completed work in original business processing is configured in advance, images generated after various operation motions are identified as processing codes which are then configured as business logic via the process requirements, and business processing work is completed by a computer so that artificial intelligence at a certain extent is realized, and the blank of substituting artificial processing by the computer with "fixed mode operation" is filled.

The invention relates to an intelligent kitchen robot which comprises a seasoning conveying mechanism, a main side dish conveying mechanism, a round-bottomed frying pan movement mechanism, and a pot heating and overturning mechanism, a liquid seasoning distributing mechanism and an electrical control system. The seasoning conveying mechanism is used for achieving the function of automatic seasoning putting for replacing the manual seasoning inputting action, the main side dish conveying mechanism is used for inputting main and accessorial food ingredients on time, the round-bottomed frying pan movement mechanism is used for achieving food stir-frying and exhausting cooking fume produced during stir-frying, the pot heating and overturning mechanism is used for controlling the frying temperature and pouring out fried food, the liquid seasoning distributing mechanism is used for controlling the input amount of liquid seasoning by controlling the suction time of a liquid seasoning pump, and the electrical control system is used for controlling the action flow, signal interaction, data exchange and manual operation interface connection of the robot. According to the intelligent kitchen robot, full-automatic kitchen machine intelligence is achieved, and standard cooking is achieved, so that labor force is further liberated, the enterprise cost is reduced, and the efficiency is improved.

The invention provides an intelligent tea maker, and belongs to the field of articles of daily use. The intelligent tea maker comprises a controller, a flushing water tank, a tea making water tank, atea making and cleaning mechanism and a justice cup, wherein the input ends of the flushing water tank and the tea making water tank are connected with a water adding device, the output ends of the flushing water tank and the tea making water tank are connected with the input end of the tea making and cleaning mechanism, the output end of the tea making and cleaning mechanism is connected with theinput end of the justice cup, a lower lid for discharging tea leaves is further arranged at the lower end of the tea making and cleaning mechanism, and a water outlet pipe which is connected with a wastewater tank and a water outlet for draining tea water are arranged below the justice cup. The intelligent tea maker has the advantages that the operation is simple and convenient and the time is saved; a full-automatic technology is adopted, and constant glass refilling and automatic replacing of the tea leaves can be achieved.

The invention relates to a navigation terminal and a route preference predicting method thereof. The route preference predicting method thereof comprises the steps that when the navigation terminal starts navigation planning, historical preference data of a current user are obtained; the historical preference data are subjected to learning train through a neutral network model; the trained neutralnetwork model is utilized for planning prediction to obtain a navigation planning route conforming to route preference of the current user; and the navigation planning route is prompted to the current user. Intelligent planning can be well achieved according to different users, provided route planning can meet the preference demands of the users to a great extent, and the subsequent navigation suggesting scheme can be automatically adjusted according to the actual traveling situation of the user.

The invention provides a hand-held artificial intelligence atomizer comprising a host housing and an atomizing cup; the features are that the host housing is used for loading a chargeable battery and disposable cell integration management unit, a power supply interface unit, a signal generation unit, an atomization amount adjusting unit, an automatic cleaning unit, an atomization time control unit, an artificial intelligence unit, a fault detection unit, a liquid medicine liquid level detection unit, a Bluetooth module and a display unit; the atomizing cup is used for containing the liquid medicine and atomizing the liquid medicine; the atomizer is good in atomization effect, can adjust the atomization amount, an automatically clean, can select atomization particles, can realize artificial intelligence, is portable, can detect faults and liquid medicine liquid level, is small in power consumption, comfortable to use, easy to use, can integrally use the chargeable battery and disposable cell, and is low in cost.

The invention provides an implementation method of a passenger and freight separated traffic parameter monitoring system. The implementation method comprises the steps of passenger and freight separated driving monitoring, lane vehicle speed detection, vehicle flow statistics, vehicle driving state monitoring and road congestion state monitoring. Passenger and freight separated driving monitoring is implemented by different vehicle detection of the fixed lane, and real-time monitoring of the traffic parameters is performed on the relevant vehicles of the fixed lane under the premise of classified monitoring. According to the system, a low-cost and high-practicality monitoring means is provided so as to realize passenger and freight separated monitoring on the highway and artificial intellectualization of corresponding traffic parameter monitoring.

The invention relates to a superheated steam efficient temperature reduction system and an intelligent control method, and belongs to the technical field of heat energy conversion. The superheated steam efficient temperature reduction system comprises a temperature reducing device, a separated water storage device, a water feeding pump and a booster pump. The temperature reducing device comprisesa temperature reducing component and a steam-water separating component. Through a pressurizing system, the atomizing effect of the temperature reducing device is improved, and the factors of steam containing water after temperature reduction are reduced. Through the steam-water separating component, the performance of the temperature reduction device is improved, and the factor of steam containing water after temperature reduction is reduced. Through the water storage system, the separated water is effectively recycled, and the waste of water resources is reduced. According to the intelligentcontrol method, the water content condition of steam after temperature reduction is effectively avoided, and the artificial intelligence is realized.

The invention discloses a user power supply recovery emergency degree classification method in large area power failure emergency processing. The method comprises the following steps of: obtaining user description attributes of power failure users in a historical record, randomly sampling an integral power failure user set, obtaining the sample set of the power failure users, and collecting a power supply recovery emergency degree label marked by a service personnel on the sample set to form a power failure user sample set with a label; creating a classification model according to the user description attributes and the power failure user sample set with the label through a preset algorithm, and optimizing and determining classification model parameters according to the classification model and corresponding parameters of the classification model; and obtaining the user description attributes of power failure users to be classified, and classifying the power failure users to be classified into a plurality of categories according to the power supply recovery emergency degrees through the classification model and corresponding parameters of the classification model in a plurality of categories. The user power supply recovery emergency degree classification method provided by the invention can be used for scientifically quantifying the power supply recovery emergency degree, reasonably guiding the power supply recovery work and redeeming the economic loss.

The invention provides an intelligent settlement system based on machine learning. The intelligent settlement system comprises an intelligent menu planning platform, an intelligent product output machine and an AI visual settlement table, wherein the intelligent menu planning platform is connected with the intelligent product output machine and the AI visual settlement desk; the intelligent product discharging machine is used for recording dishes and a product discharging amount; the intelligent menu planning platform is used for generating a menu plan according to the intelligent product output machine; and the AI visual settlement table is used for food settlement. According to the intelligent settlement system and the settlement method, big data analysis is carried out through data acquired by the product output machine and the AI visual settlement desk from the arrangement of the menu plan, reasonable menu recommendation is intelligently generated for a user, manual menu making isalso omitted, the recipe diversity is more comprehensive, and manpower and material resources are saved.

The invention discloses a projection touch control internet of things rescue system applied to an elevator. A fault detection processing module, a health checking module, an emergency rescue module, an advertisement push module and an elevator internet of things projection system are included. The fault detection processing module, the health checking module, the emergency rescue module and the advertisement push module are integrated in the elevator internet of things projection system, and the elevator internet of things projection system is used for obtaining, displaying and feeding back corresponding information or instructions. The elevator internet of things projection system conducts interior processing on the information or instruction data and then conducts displaying or the information or instruction data are sent to the cloud through a wired network or wireless network, software analysis is conducted, and then a result is sent to the elevator internet of things projection system to be received and displayed. By means of the projection touch control internet of things rescue system, elevator internet of things automatic fault detection processing, health checking, emergency rescue and advertisement push are achieved, and elevator artificial intelligence is achieved in cooperation with APP software.

The invention relates to a thin slab continuous casting and rolling roll gap value dynamic self-adaptive control method. The thin slab continuous casting and rolling roll gap value dynamic self-adaptive control method comprises steps that acquisition and normalization processing of production technology parameters of a continuous casting production line are carried out to acquire a data matrix; the dimension reduction decoupling of the normalized data matrix is carried out to establish a characteristic database; a part of historical data is extracted from the characteristic database to establish a training sample set, and a corresponding prediction model is established; a prediction sample set is substituted into the prediction model, and data processing is carried out to acquire a predicted roll gap value; by using the predicted roll gap value, adjustment is carried out until an actual roll gap value is equal to the predicted roll gap value, and the thin slab continuous casting and rolling roll gap value dynamic self-adaptive control is completed. By taking big data analysis as a core, timeliness and roll gap value adjustment prediction precision are improved, and a production process is improved, and production costs are reduced.

The invention discloses high-end artificial intelligent equipment. The high-end artificial intelligent equipment comprises a body and a voice recognition controller which is fixedly arranged on the top end surface of the body, wherein a first cavity is formed in the body; a slide rack is arranged in the first cavity; a first motor is embedded in the slide rack; the left and right sides of the first cavity are symmetrically communicated with guide slide grooves; the left and right sides of the slide rack are symmetrically provided with a left guide slide block and a right guide slide block; theleft guide slide block and the right guide slide block are respectively in slide fit connection with the guide slide grooves at the left and right sides; a second motor is fixedly arranged at the bottom of the guide slide groove at the right side; and the top of the second motor is in power fit connection with a lifting threaded rod. The equipment is simple in overall structure, electric wires can be stored to prevent influence on body movement and aesthetic appearance because of too long electric wires, the space limitation of the equipment is relieved, the portability of the equipment is increased, and the voice recognition controller can intelligently recognize and control instructions so as to realize artificial intelligence.

The invention relates to an artificial intelligence kitchen waste sorting pulper and a garbage pre-sorting treatment technology. A shell is provided with a kitchen waste inlet and a water injection port. The shell is internally provided with impellers and a screw type stirring wheel which is provided with a spiral blade. The impellers and the screw type stirring wheel are coaxial, the impellers are located at the lower portion in the shell, the screw type stirring wheel is located above the impellers, and the impellers and the screw type stirring wheel are driven by a drive motor to rotate. A heavy garbage outlet is formed in the bottom of the shell. A pick-up device used for picking up light garbage is arranged at the upper portion of the shell. By means of the artificial intelligence kitchen waste sorting pulper and the garbage pre-sorting treatment technology, rapid pre-sorting treatment of kitchen waste can be achieved, efficiency is high, and the sorting effect is good.

The invention relates to the technical field of the application of daily supplies, in particular to an intelligent touch-screen-control electric hair dryer. The intelligent touch-screen-control electric hair dryer comprises a shell and is characterized in that an air nozzle is arranged on the left of the shell in a communicated manner, a fastener groove is embedded into the left-end outer wall ofthe shell, the right of the fastener groove is provided with openings, with filter screens, in a front-rear-symmetry manner, protecting plates are symmetrically connected to the left and right sides of each opening in a clamped manner through slide devices, the right of the shell is provided with a dust cover in a communicated manner, the right of the top of the shell is provided with a protrusion, a touch screen is embedded into the left slope of the protrusion, loudspeakers are symmetrically arranged on the front and rear sides of the touch screen, the right of the bottom of the shell is rotatably connected with a handle through a damping rotary shaft, a temperature sensor is embedded into the lower portion of the front surface of the handle, a power line is connected to the bottom of the handle in a penetrating manner, a first support is transversely arranged at the top of the inner cavity of the shell, and a fan is arranged at the center of the bottom of the first support. By the intelligent touch-screen-control electric hair dryer, the defect that an existing electric hair dryer is single in function in the prior art can be overcome.

The invention provides a user intelligent device and an emotion icon processing method thereof. The user intelligent device acquires the input information of a user, performs emotion recognition on the user according to the input information, obtains the corresponding key information according to an emotion recognition result, and generates and obtains a corresponding emotion icon according to thekey information. According to the present invention, the emotion recognition can be carried out according to the user input information, and the emotion pictures, characters or languages and the likeare generated into the corresponding emotion icons, so that the fast input effect of multiple input ways is achieved, the emotion recognition of the longer input information can be achieved, the personalized requirements are met, and the artificial intelligence is achieved to a certain degree.

The invention discloses novel portable artificial intelligence equipment. The novel portable artificial intelligence equipment comprises a machine body and a voice recognition controller fixedly arranged on the top end face of the machine body. A first cavity is formed in the machine body and internally provided with a sliding frame. A first motor is embedded in the sliding frame. Guiding slidinggrooves are symmetrically formed in the left and the right of the first cavity in a communication manner. A left guiding sliding block and a right guiding sliding block are symmetrically arranged on the sliding frame in a left-right manner. The left guiding sliding block and the right guiding sliding block are connected with the left guiding sliding groove and the right guiding sliding groove in asliding fit manner correspondingly. A second motor is fixedly arranged at the bottom of the right guiding sliding groove, and the top of the second motor is connected with a lifting threaded rod in apower fit manner. The device is simple in integral structure, a wire can be stored, influences on machine body movement and attractiveness due to the too long wire can be prevented, the space limitation of the equipment is released, and portability of the equipment is improved; and the voice recognition controller conducts intelligent instruction recognition and control, and artificial intelligence is achieved.

The invention relates to an AI intelligent identification method for numbers of a water meter. The AI intelligent identification method adopts Darknet-19 as a basic network, and is realized based on YOLOv2: numbers in each box in a data source-data annotation and format conversion-creation.Names file-creation.data file-modification.Cfg configuration file-training model-testing model-model is presented on a use interface in a continuous Arabic number combination form. According to the image identification and detection method, water meter number identification is achieved based on YOLOv2, and Darknet-19 is adopted as a basic network, so that the effect is improved without deepening or widening the network while the network is simplified, and obvious advantages are achieved in the aspects ofthe recall rate and positioning; and the precision is high, and finally the numbers can be presented on the use interface in a continuous Arabic numeral combination mode, and complete artificial intelligence is achieved, and a user does not need to analyze and guess, so that the AI intelligent identification method is visual and convenient.

The invention relates to the computer field, in particular to a computer motherboard detection device, comprising a base. A conveyor belt is arranged above the chassis, two ends of the chassis are provided with brackets, a sliding groove is arranged at the top of the bracket, a sliding bar is arranged on the sliding groove, and a sliding block is nested on the sliding bar. Sensors are used to sense the product, so that that position of the equipment is more accurate. A lateral position block and a longitudinal positioning block are used, the motherboard does not move during detection, so thatthe detection is more accurate. As that fixing blocks can be adjusted according to the production needs, the fixing block can be adapted to various type of motherboards, the applicability of the device is increased, and the detection pen can be positioned by using the sliding block for detecting different types of motherboards and parts in different positions, thereby realizing the artificial intelligence detection, greatly improving the work efficiency and reducing the labor cost. The electromagnetic device is used to start the detecting pen, which makes the control more flexible and convenient. The device has simple structure, easy operation and high working efficiency, and is suitable for batch detection.

The invention discloses an intelligent analysis and diagnosis system for software-designed livestock and poultry disease pictures. The intelligent analysis and diagnosis system is composed of a user side (1), a color analysis side (2), an area analysis side (3), a data processing side (4) and a result processing side (5). According to the system, an artificial intelligence picture database is established without the help of massive picture data, intelligent acquisition and intelligent analysis of livestock and poultry disease information and intelligent matching of a livestock and poultry disease database can be realized; the system is advantaged in that complete intelligentization is realized, the method can be applied to a traditional artificial intelligence image database, the number ofmassive case images required for establishing the traditional artificial intelligence image database is reduced, and through adding the operation analysis rules, deep learning and analysis capabilityof the artificial intelligence database can be improved.

The invention belongs to the technical field of electric power equipment, in particular to a material connection and information collection platform for power distribution equipment. An intelligent data acquisition system is unattended in the whole process. It can not only reduce the human cost of enterprises, but also collect a large amount of power data, and through the intelligent conversion mechanism, the original equipment signal can be converted into accurate, high-value big data for power analysis and operation and maintenance. The system comprises a data acquisition chip, a proxy server, a data acquisition server, a data service server, a big data analysis server, a data application server and a client. Through production data collection and analysis of the system , liberation of manual duty and saving resources and expenditure are achieved. Real-time view of the operation of power equipment is performed , a variety of operationsfordata are performed to control the operation.The system has the advantages of efficient data collection without manual duty, all-weather intelligent monitoring data analysis, multi-dimensional comparison of business data and rich and diverse forms of data display.

The invention discloses a full-artificial-intelligence system based on a multi-rotor unmanned aerial vehicle flight type nuclide identification instrument, and relates to the field of nuclear industry. The system comprises the nuclide identification instrument, a multi-rotor unmanned aerial vehicle flight system and a command and control system, wherein the nuclide identification instrument and the multi-rotor unmanned aerial vehicle flight system are connected with the command and control system through a wireless communication module; the input end of the nuclide identification instrument isprovided with an ultrasonic sensor and a laser sensor; the output end of the nuclide identification instrument is provided with an alarm; and the connecting end of the nuclide identification instrument is connected with a camera, a GPS satellite positioning system, a metering distribution diagram drawing module and an artificial intelligence analysis module. The invention provides the multi-rotorunmanned radiographic surveying and mapping and nuclide identification scheme which is unmanned, of a full-artificial-intelligence type and safe in the true sense, the labor cost and the risk of manual misoperation are greatly reduced, the full-artificial-intelligence system is convenient, simple and efficient, and a radiographic surveying and mapping result and a nuclide identification result can be obtained at the first time.

The invention discloses a stairs climbing machine. The stairs climbing machine comprises a cargo cabin vertical plate, wherein a rear part of the cargo cabin vertical plate is connected with a fence for loading cargoes, two sides of a front part of the cargo cabin vertical plate are provided with a guide rail groove, and two sides of an upper end of the cargo cabin vertical plate are connected with a first pawl through a first connecting rod; and a stairs climbing vertical plate, wherein two sides of a rear part of the stairs climbing vertical plate are provided with a guide rail, the guide rail is slidably connected in the guide rail groove, two sides of the stairs climbing vertical plate are connected with a sucker through a hollow rod, a front part of the stairs climbing vertical plateis centrally fixedly provided with a telescopic-type hydraulic cylinder, the top of a piston rod of the telescopic-type hydraulic cylinder is connected with a horizontal cross rod through a connectingbase, and a front part of the horizontal cross rod is connected with a second pawl through a second connecting rod. The stairs climbing machine is capable of enabling intelligence to be combined witha mechanical device, adequately developing advantages of climbing stairs, wherein manual operation is not needed in a process of climbing the stairs from adsorption, automatically controlling througha PLC controller, conveying cargoes to a designated site, and realizing the artificial intelligence.

The invention discloses a data processing method and system. According to the method, by determining a current input scene, words matched with the current input scene are recommended on the basis of the current input scene. According to the scheme, the words matched with the input scene are recommended through the input scene, different words are correspondingly input in different scenes to prevent the situation that the recommended words are not in accordance with the words which a user needs to input during scene change, and therefore the problems of inaccurate recommended words, slow inputand decreased user input experience are solved. The artificial intelligence and scene identification are achieved, and alternative items which are most possibly required by the user are provided, so that the data processing method and system can meet the user demands best.