333results about How to "Realize intelligent identification" patented technology

The invention discloses a method for quickly identifying and distinguishing the variety of corn, which belongs to the technical field of the detection of agricultural products. The method identifies the variety of the corn by an image processing technology quickly. Seed image information is obtained by a scanner, corn seeds are identified by a corn variety identification system on a computer, original image information is read, the image information of each pixel in each corn is stored as a 24-bit bmp format file, and the variety of the corn is distinguished by a trained neural network classifier after image processing and feature extraction are completed. The variety distinguishing rate of the model to an unknown sample is greater than 90%, which shows that a condition that the variety of the corn seeds is distinguished by image feature information is feasible. The invention has the characteristics of high automatization degree and quick, simple and convenient operation.

The invention discloses a coal mine underground integrated monitoring and controlling system which mainly comprises a sensing and detection device, a security information network and communication device, a security information management device, a security early warning and decision support device and a rescue information assurance device. The system can perfectly solve the problems of existing coal monitoring and controlling systems, prevent the occurrence of coal mine underground signal loss effectively and improve the level of coal mine security monitoring greatly.

The invention relates to a washing machine with an identification function and a washing method. The washing machine comprises a washing machine body and a clothes identification module, an RFID reader, and an RFID antenna. The clothes identification module comprises a plurality of RFID tags representing clothes classifications and/or materials. The RFID tags are placed on the washing machine body and can be separated from the washing machine body. In washing, the RFID tags are connected with to-be-washed clothes. After washing is finished, a user separates the RFID tags from the clothes and collects the RFID tags to the washing machine body. The RFID reader is used to read information of the RFID tags and transmit the information to a washing machine processor. The RFID antenna transmits radio-frequency signals among the tags and the reader. The washing machine solves problems that the RFID tags are not popularized on clothes and clothes intelligent identification cannot be realized. The method pushes intelligent identification of clothes which just remains in a theoretical research stage to a specific washing machine structure, so that intelligent identification of clothes without the RFID tags is realized. The washing machine realizes optimal washing ratio by minimum water consumption, minimum power consumption, and minimum detergent.

The invention relates to a smart water heater temperature adjustment method and device and a water heater. The smart water heater temperature adjustment method includes: obtaining operations of a user; obtaining the identity information of the user when judging that the user is about to use the water heater according to the operations of the user; matching the obtained identity information of the user and data stored in a household cloud; obtaining historical water temperature adjustment data of the user from the household cloud when matching succeeds; automatically adjusting the current water temperature according to the historical water temperature adjustment data of the user when the user uses the water heater. The smart water heater temperature adjustment method and device can smartly identify the user identity and match the user identity stored in the household cloud with water temperature and other data, and accordingly automatically and smartly adjust the water temperature of the water heater according to the accustomed comfortable temperature of different people; in addition, can automatically adjust the water temperature along with different bath stages of the uses, thereby greatly improving the intelligence of the water heater and improving the use comfort of the water heater.

The invention discloses an assistant analysis system and method for intelligent robot patrol of substations. The assistant analysis system comprises an image shooting servo module, a deep-learning identification module and abnormal state inference module; the image shooting servo module is used for assisting an intelligent robot in shooting sample images and inputting the sample images to the deep-learning identification module; the deep-learning identification module is used for establishing three-level pattern identification systems for identifying equipment, parts and statuses respectively,and each pattern identification system is used for object identification of the sample images and inputting identification results to the image shooting servo module and the abnormal state inferencemodule; the abnormal state inference module is used for performing inference engine on equipment status information identified by the deep-learning identification module and displaying inference results to users. Compared with a traditional characteristic-based image identification method, the assistant analysis method has the advantages of high accuracy and generalization capability.

The invention discloses a voice fraud identification method and an apparatus, terminal equipment and a storage medium. The voice fraud identification method comprises the following steps of acquiringvoice information to be measured; carrying out characteristic extraction on the voice information to be measured and acquiring a voice characteristic; using an identity confirmation model to carry outidentity verification on the voice characteristic and acquiring identity verification information; using a lie monitoring model to carry out lie verification on the voice characteristic and acquiringlie verification information; and based on the identity verification information and the lie verification information, acquiring a fraud risk assessment result. When the voice fraud identification method is used to carry out voice fraud identification, advantages of high efficiency, high accuracy and low labor cost are possessed.

Embodiments of the present invention disclose an apparatus and method for lighting a display screen. The apparatus provided by embodiments of the present invention is arranged in a terminal device, and the terminal device is at least provided with a sensor, a first display screen and a second display screen, wherein each of the first display screen and the second display screen is provided with a touch sensing apparatus. The apparatus includes: a detection module used for detecting whether the terminal device meets a trigger condition in real time; a calculation module used for calculating status information about the terminal device if the detection module detects that the terminal device meets the trigger condition through the sensor and/or the touch sensing apparatus; and a lighting module used for lighting one or more of the first display screen and the second display screen of the terminal device according to the status information obtained by the calculation module. The device and method in embodiments of the present invention realize intelligent recognition of the display screens of the terminal device by reasonably designing a mode of lighting the display screen, and a display screen required to be used by a user is automatically lighted by the terminal device, thereby improving the user experience effect.

An acoustic emission signal analytical method for automatically identifying the damage mode of a thermal barrier coating belongs to the technical field of the lossless real-time failure detection of thermal barrier coatings. The acoustic emission signal analytical method comprises the following steps: acquiring acoustic emission signals of the thermal barrier coating damage; performing wavelet packet transform of the acoustic emission signals, and extracting a wavelet energy spectrum coefficient serving as the characteristic parameters of mode identification; establishing a BP nerve network classification system, training the BP network, and obtaining the trained BP network; extracting the wavelet energy spectrum coefficient of an acoustic emission signal to be identified, inputting the wavelet energy spectrum coefficient into the trained BP network, and identifying the damage mode of the acoustic emission signal; accounting the number of each damage acoustic emission event, and obtaining a curve of the relation between numbers of various damage acoustic emission signals and an external load. The acoustic emission signal analytical method performs real-time or in-situ lossless detection of failure process, and provides a direct basis and guide for correctly understanding the failure action of the thermal barrier coating. Moreover, the acoustic emission signal analytical method can accurately identify the acoustic emission signals of different damage modes of the thermal barrier coating, and has great significance for real-time detection of the failure process of the thermal barrier coating.

The invention is applicable to the technical field of optical cable detection, and provides an optical cable circuit fault positioning and detection method and terminal equipment. The method includesthe following steps: establishing an optical cable circuit fault reflected light information sample library according to the reflected light information; establishing an optical cable circuit fault positioning and detection model according to a neural network; determining the theoretical result of the fault position of the optical cable circuit corresponding to the reflected light information in the sample library; judging whether a first difference value of the fault position theoretical result and the optical cable circuit fault position true result corresponding to the reflected light information exceeds a preset first threshold value or not; determining the fault theoretical result if the judgment does not exceed the preset first threshold value; judging whether the second difference value of the fault theoretical result and the fault true result of the optical cable circuit exceeds a preset second threshold value or not; detecting the fault condition of the optical cable circuit to be tested if the judgment does not exceed the preset second threshold value. By adopting the scheme, the accuracy of the fault identification of the optical cable circuit is improved, and the intelligent identification of the fault of the optical cable circuit is realized.

The invention creatively provides an unmanned aerial vehicle (UAV)-based transmission line inspection device comprising a UAV body and a ground control center. The UAV body is equipped with a pod, and the pod is arranged under the UAV body. The UAV body is internally equipped with a flight control subsystem and an image processing subsystem. The pod is internally equipped with an inspection image acquisition module, a servo motor driver module and a servo motor. The servo motor can adjust and correct the real-time posture of the image acquisition module to make a target component in the field-of-view center area of the image acquisition module. The servo motor is electrically connected with the servo motor driver module. With the UAV-based inspection device of the invention, automatic inspection of transmission line equipment and intelligent identification of defective equipment are realized, the posture of an information acquisition device can be adjusted in real time, the accuracy of information acquisition is ensured, the burden of artificial screening is reduced, and the quality and efficiency of transmission line inspection are improved.

The invention discloses a pre-warning system and a pre-warning method for operation safety of railway maintenance. An image collecting unit is used for collecting image information in the construction site; a calculation control unit is used for treating the image information collected by the image collecting unit, performing matching calculation with a railway line equipment template stored in the calculation control unit and confirming the classification of the railway line equipment; the calculation control unit is also used for resolving a practical physical distance between the railway line equipment and the image collecting unit and sending warning and safety operation triggering information according to the practical physical distance between the railway line equipment and the image collecting unit and a corresponding warning and safety operation triggering distance of the railway line equipment; and a user interface unit is used for displaying information in the calculation control unit and setting parameters for the calculation control unit. According to the pre-warning system and the pre-warning method provided by the invention, the intelligent identification for the railway line equipment is realized and avoided; a user can set a construction safety limiting parameter according to the classification of large-size maintenance machinery; and the pre-warning system and the pre-warning method are excellent in adaptability.

The invention discloses a power grid operation state monitoring and analyzing system for a power system. The power grid operation state monitoring and analyzing system comprises an acquisition client, a terminal server, a data storage device and data acquisition nodes. Each data acquisition node comprises a signal transceiver, a geographic information processor and a signal controller, wherein the signal transceiver acquires a plurality of signals in a set area, the position information of the signals is determined through the maximum signal intensity in the geographic information processor, and the signals are processed through the signal controller and are transmitted to the acquisition client through the signal transceiver. The system has the advantages that the system is complementary with a conventional system, and functions required by scheduling are integrated; the abnormal operating mode, abnormality, early warning and other conditions of a power grid main rack can be intuitively reflected in real time through one interface; intelligent identification of a main transformer N-1, auxiliary processing functions, reactive comprehensive voltage analysis, short message alarm functions are realized; and later development and maintenance are easy. The invention also discloses a monitoring and analyzing method.

The invention relates to a device and a method for counting overlapped round particulate matter, which aims to obtain higher counting precision and improve counting efficiency. The device for counting overlapped round particulate matter comprises a CCD camera, a DSP data processing system and an LCD, wherein the CCD camera is used for acquiring particle images and sending image signals into the DSP data processing system; the DSP data processing system comprises a DSP data signal processor, converts analog images acquired by the CCD camera into digital image signals, realizes image processing algorithm of a text, finishes counting particles, and displays counting results; and the LCD is connected with the output of the DSP data processing system, and is used for displaying acquiring original images of the particles and results after segmentation and outputting counted quantity of the particles.

The invention discloses a visitor management method using face recognition, the visitor management method comprises: collecting a facial image of a visiting user; comparing the collected facial imageof the visiting user with facial images previously passing identity verification, or comparing the collected facial image of the visiting user with facial images obtained from the Ministry of Public Security by internet connection; if the comparison result shows that a facial image meeting a preset similarity threshold with the collected facial image of the visiting user exists in the facial images previously passing identity verification or the facial images obtained from the Ministry of Public Security by internet connection, determining that the visiting user can make a visit. The visitor management method utilizes the face recognition technology to realize the intelligent identity identification of the visiting user, can solve the problem of low processing efficiency and low security of the visitor management scheme in the prior art, can improve the processing efficiency of the visitor management process, and can better ensure the identity security of the visitor.

The invention discloses a power grid tripping event intelligent identification method based on a knowledge graph. The method is based on a knowledge graph technology and a natural language processingtechnology in the field of artificial intelligence. Based on power system knowledge characteristics, the monitoring service work flow and the power grid tripping event judgment logic are deeply studied; based on learning of historical sample data of a power grid tripping event and through knowledge extraction and fusion, the method constructs a power grid tripping event knowledge triple model, forms an association relationship among the entities and completes disambiguation of information with uncertainty, thereby reducing understanding difference caused by improper personnel maintenance or professional barriers and realizing intelligent identification of power grid tripping events; knowledge reasoning is performed based on the knowledge graph, cross confirmation and more information collection are completed in combination with related power grid state perception, and the response efficiency of power grid tripping events is improved while the service pressure of power grid monitoring personnel is effectively reduced.

The invention provides an intelligent identification method for urban violation, which comprises the following steps: step S1, obtaining a plurality of urban violation photos, and labeling the violation categories of the photos manually; step S2, creating an intelligent recognition model, and uploading the artificially labeled photos to the intelligent recognition model for in-depth learning training; step S3, obtaining a city monitoring video, intelligently identify the city monitoring video by using the optimized intelligent identification model, capturing a video frame which is judged to have illegal behavior, and creating a label; step S4, auditing the label of the screenshot manually, and if the label is incorrect, modifying the label, and entering the step S2; if the label is correct, sending the screenshot to the city management system for real-time alarm. The invention has the advantages of realizing the real-time monitoring and intelligent identification of the urban violationbehavior and reducing the cost of supervising the urban violation behavior.

The invention discloses an obstacle-detecting obstacle-avoiding system and method suitable for a full automatic weeding machine. The system comprises an MCU module, the MCU module is connected with anultrasonic transducer, used for transmission, of an ultrasonic phased array through a transmitting circuit, and the ultrasonic transducer used for the transmission is located at the top of the weeding machine; the MCU module controls the transmitting circuit to drive the ultrasonic transducer to transmit ultrasonic signals, the ultrasonic signals are reflected back through an obstacle ahead, thetransmitting signals are received by a plurality of ultrasonic transducers used for receiving, and the plurality of ultrasonic transducers used for receiving are used to form an ultrasonic phased array receiving array; the ultrasonic phased array receiving array is connected with the MCU processing module sequentially through a signal amplification conditioning module, a detection low-pass filterand an A/D conversion module; and the MCU processing module is connected with an upper computer. The system and method provided by the invention use the pattern recognition technology and the ultrasonic phased array technology to recognize and judge the obstacle ahead, thereby realizing intelligent full automatic operation of a robot and the full automatic weeding machine.

The embodiment of the invention discloses an information processing method and device. The method comprises the steps that disclosed information is obtained from a default website in a default time threshold value; an announcement website title and a text title inside an announcement document are obtained, and a service type to which an announcement belongs is determined according to preset service extraction rules; keyword search is conducted on announcement data of all listed companies disclosed by the website; content extraction is conducted on announcement content of different service types according to the set rules, and extracted results generate a notice. The system can face all enterprises and institutions, simple service configuration is conducted for overall identification analysis of the company document, and intelligent identification is achieved according to a standardized function. Accordingly, the office efficiency of the enterprises and institutions is significantly improved; the workload of manual form filling and artificial correlation is greatly reduced. Multiple tool systems are integrated, and diversity and normalization of the whole system are perfected.

The invention relates to the field of control engineering and discloses a recognition method and device for a material pile model for material taking with a material taking machine. The recognition method includes the steps of obtaining the material pile model, dividing a material pile into a plurality of material taking layers according to the size of the material pile, and determining the material taking start point and the material taking termination point of each material taking layer. In this way, intelligent recognition of coal pile information can be realized, implementation of full-automatic operation of the material taking machine is facilitated, and operation efficiency is improved.

The invention discloses a product anti-counterfeiting system based on the internet of things technology and an anti-counterfeiting method. The product anti-counterfeiting system is characterized in the key use part of a product is locked by a password lock; a product anti-counterfeiting code is attached on the product or the product package, and has corresponding relationship with password of the password lock; a consumer sends the product anti-counterfeiting code to a background management system of the manufacturer through telephone, short message or network after purchasing the product; the background management system feeds the password to the consumer; and the consumer can open the password lock to use the product according to the password. The product anti-counterfeiting system provided by the invention solves the problems in the prior art, such as recovery counterfeiting and low query rate of digital anti-counterfeiting, and is a novel anti-counterfeiting technique developed on the basis of the internet of things technology and integrated with a plurality of kinds of modern high technology.

The invention discloses a machine vision detection algorithm for extracting logic circuit diagram information, The method comprises the following steps: S1, color threshold value of multi-pin component information extraction: adopting Color Threshold color threshold algorithm to obtain position information of multi-pin component, firstly selecting RGB color model, and according to the color of multi-pin component name, the invention relates to the technical field of electricity. The machine vision detection algorithm of the logic circuit diagram information extraction, the circuit informationin the logic circuit diagram can be extracted by adopting an image recognition algorithm, Convert to Text Description, so that the text format can be adapted to different circuit design softwares, Then, the text can be imported into circuit design software to generate logic diagrams automatically, which greatly simplifies the process of reproducing logic circuit diagrams and eliminates the need for people to spend a lot of time on analyzing, converting and drawing logic diagrams. The intelligent identification of circuit diagrams by intelligent algorithms is realized, and the logic diagrams are automatically extracted and converted into logic diagrams.

The invention discloses an automatic fruit picking method and device based on visual recognition positioning. The method comprises the following steps of S1, collecting colorful images; S2, extractingthree RGB single-channel gray level images; S3, extracting single-channel images with obvious color components; S4, preprocessing the images; S5, judging whether a fruit target exists in the images or not; S6, obtaining coordinates of the fruit target in a computer pixel coordinate system; S7, converting the pixel coordinates into coordinates of a world coordinate system; S8, calculating a planemotion amount of a grabbing mechanical claw; S9, controlling the grabbing mechanical claw to move, and enabling the fruit target to be located in the center of the camera imaging plane; S10, controlling the grabbing mechanical claw to move forwards perpendicular to the imaging plane; S11, grabbing the fruit target, and cutting off fruit stems; S12, loosening the grabbing mechanical claw, and enabling fruits to fall into a collecting box. The fruit target is determined through image processing and feature matching, the target is tracked and positioned to accurately position the fruit so as to guide accurate picking, and fruit surface damage is reduced.