61results about How to "Realize intelligent classification" patented technology

The invention provides a card sorting device and an automatic electric writing device with the same. The card sorting device comprises a card sorting plate and a rotating shaft, wherein the rotating shaft is horizontally positioned at the lower part of the card sorting plate; the card sorting plate is divided into two layers, namely, a first layer for installing an identification card temporary storage slot, and a second layer for installing a card storage slot, and the first layer can be rotated relative to the second layer; bulges, which are arranged along the circumference, are arranged at the lower bottom part of the first layer of the card sorting plate; a card pushing device for pushing an identification card out of the temporary storage slot is arranged on the card sorting plate; cam mechanisms in match with the bulges at the lower bottom part of the first layer of the card sorting plate are arranged at the end part of the rotating shaft; the automatic electric writing device comprises a base, a card feeding device, a card writing device, an information verifying device, an information processing device and the card sorting device, and the information processing device is positioned in the base; the card feeding device is positioned on the base; the card writing device and the information verifying device are positioned at the upper part of the card feeding device; and the card sorting device is positioned at the tail end of the card feeding device. The card sorting plate has the advantages of being stable, high in sorting capacity, high in efficiency, and small in size.

A substation sag sensitivity grading method based on subordinate user industrial features comprises the first step of determining industry types involved in subordinate users of all substations in a region to be analyzed and setting sensitivity coefficients of all industries, the second step of inputting basic data, namely load ratios of the industries of the subordinate users, of the substations in a power grid in the region to be analyzed, the third step of applying the fuzzy C-means (FCM) algorithm to cluster the substations and outputting a clustering result according to analysis requirements after the number of categories is determined, the fourth step of taking the clustering center of each category of substations as a reference and calculating sag sensitivity of various categories of the substations in the combination of the sensitivity coefficients of the industries, and the fifth step of dividing the substations in the power grid in the region into corresponding grades by the sequence obtained according to the magnitude of the sensitivity. According to the substation sag sensitivity grading method based on the subordinate user industrial features, the sag sensitivity can be analyzed on the level of the substations, the workload is few and is geared to practical situations, and the sag sensitivity of the substations is comprehensively reflected through load diversities.

The invention discloses a power transmission line monitoring system and method and a recognition system and method oriented to cloud edge collaboration. The monitoring system comprises a sensing layer which comprises a state sensing and execution control main body in the power Internet of Things and is used for monitoring, collecting and sensing power system equipment data to obtain sensing data; the edge layer comprises an edge internet-of-things proxy terminal and is used for preprocessing the sensing data at an edge computing node; the network layer comprises a remote communication channel and a local access channel and is used for gathering and transmitting the preprocessed sensing data; and the cloud is used for carrying out data storage, data classification, data exchange and data distribution on the sensing data which are gathered and transmitted, and sending execution instructions to the network layer, the edge layer and the sensing layer in sequence. According to the invention, many problems of insufficient timeliness of field sensor information processing, high information transmission difficulty, difficult implementation of field fault diagnosis and the like in a cloud computing architecture mode are solved.

The invention provides an electric customer service work order classifying method and device and electronic equipment, and relates to the technical field of data processing. The electric service customer work order classifying method includes the steps that a training set is obtained according to historical electric customer service work order classification data; data training is conducted through text segmentation, text parsing and content classification according to the training set to generate a work order classifier; target work orders are classified through the work order classifier according to incoming call content of the target work orders to obtain an electric customer service work order classification result. The technical problem of low efficiency of a classification process inthe prior art is solved.

The invention relates to an innovation projection PDCA process management platform based on mobile internet+, and belongs to the field of the mobile internet. The platform comprises an APP system anda server; the APP system inputs problem discovery, suggestion, occupation innovation, quality control QC, science and technology project and soft topic information through a topic character incorporation module, and records the pictures, the videos and the character information of the PDCA through a recording module, and then the PDCA module transmits the PDCA content to the server through a wireless transmission module; the server performs PDCA aggregation on the PDCA content by using the PDCA aggregation module, the intelligent time sequence integration is performed through a time sequence integration module; a topic display module is used for displaying the achievement file of each topic, and then the achievement file is played and displayed on the PC side and the mobile phone side. Through the encrypted transmission based on the private data channel and the breakpoint technology, the whole process of the science and technology innovation topic is recorded by adopting a data streamcompression algorithm.

The invention discloses an intelligent time sequence signal classification method based on gate control circulation unit deep network. The intelligent time sequence signal classification method comprises steps of (1) establishing of code modulation combined time sequence signals; (2)generating of a training sample set and a testing sample set; (3) establishing of a gate control circulation unit deep network model; (4)the setting of the parameters of the gate control circulation unit deep network; (5) the training of the gate control circulation unit deep network model; (6) acquisition of classification accuracy. Artificial characteristic extraction and massive priori knowledge are not required, and automatic characteristic extraction of one-dimensional signals and accurate signal classification can be realized, and therefore complexity is low, classification results are accurate and stable, and the intelligent time sequence signal classification method can be used for military and civil communication fields.

The embodiment of the application discloses a classification method and device of an image, a storage medium and electronic equipment. The pushing method includes: when an operation of moving an imageto a classification library is detected, collecting a multi-dimensional feature, which corresponds to the image, to use the same as a sample, and constructing a sample set corresponding to multiple classification libraries; carrying out sample classification on the sample set according to information gain of features on sample classification to construct a decision tree model of the classification libraries, wherein output of the decision tree model is the multiple corresponding classification libraries; collecting a multi-dimensional feature, which corresponds to the to-be-classified image,to use the same as a prediction sample when an image classification instruction is detected; and predicting a corresponding classification library according to the prediction sample and the decision tree model. Therefore, intelligent classification of the image is realized, and a classification accuracy rate of the image is increased.

The invention belongs to the technical field of garbage sorting, and discloses a cloud-based garbage sorting system and method, an information processing terminal and a storage medium. The cloud-basedgarbage sorting system comprises a garbage image acquisition module, a main control module, an image analysis module, a filtering module, a separation module, a rotating module, a garbage processingmodule, a garbage recycling module and a display module; the garbage image acquisition module acquires garbage image data; the main control module controls each module to work normally; the image analysis module analyzes the collected garbage images; and the separation module separates and classifies the garbage. A complex oil-gas separation system in a traditional garbage pyrolysis process is omitted through the garbage treatment module, and the garbage treatment method is simple, low in cost and easy to operate; and through the garbage recycling module, the garbage treatment and recycling efficiency is improved, resource waste is reduced, the garbage harmless treatment difficulty is reduced, and the influence on the environment is weakened.

The invention discloses a rotary wardrobe realizing intelligent clothes hanging, taking and matching functions. The rotary wardrobe comprises a wardrobe main body, a sliding clothes hanging part, a clothes hanging box part, a sliding clothes hanger part and a mechanical arm part, and is characterized in that first, a picture of each garment is typed in a controller through a first camera, then a rotatable door is opened, the garment is placed at an assigned area, the controller controls a first steering engine to drive partition plates to rotate, so that the area with the garment needing to betaken aligns at a garment inlet, a second stepping motor drives a second gear, so that a clothes hanger on which the garment needing to be taken is hung is driven to slide the position of the garmentinlet, through the mechanical arm part, the target garment is clamped and hung on a hanging buckle, so that people can directly take away the garment needing to be worn from the clothes hanging box and hang the garments not needing to be worn on the clothes hanger, the garments are hung to the original hanging area through the reverse operation of the steps, thus the garment taking and hanging time is saved, the storage amount of the wardrobe is increased, and the intelligent classifying, taking, hanging and matching of the wardrobe are realized.

The invention discloses a rotary wardrobe for intelligently hanging and matching clothes. The rotary wardrobe for intelligently hanging and matching the clothes comprises a wardrobe main body, a sliding clothes hanging part, a clothes hanging box part, a sliding clothes hanger part and a mechanical arm part. The rotary wardrobe is characterized in that firstly, a photograph of each piece of clothes is recorded into a controller by a first camera, then a rotating door is opened to place the clothes into a designated area, and a first steering engine is controlled by the controller to drive a partition plate to rotate so that an area where the clothes are taken is aligned with a clothes inlet; a second step motor drives a second gear so as to drive a clothes hanger hung with clothes to be taken to slide to the position of the clothes inlet; target clothes are clamped up and hung on a hanging fastener by the mechanical arm portion, thus, people can directly take away desired clothes fromthe clothes hanging box, and hang the clothes not needed to the clothes hanger again, and the clothes can be hung into the initial area by reversely operating the steps, the clothes taking and hangingtime is saved, the storage amount of the wardrobe is increased, and intelligent classification, taking and hanging as well as matching are realized.

The invention aims to provide a name information-based object classification method and device. The method comprises the steps of determining name information of target objects; based on the name informant of the target objects, determining one or more node objects matched with the target objects in a preset object editing distance tree as reference objects, wherein the node objects correspond toname information and type information; and based on the type information of one or more reference objects, determining type information of the target objects. Compared with the prior art, the time complexity of search can be effectively lowered and the overall classification efficiency of the target objects is improved. In addition, the intervention of manual classification experience is reduced,and classification standards are objectively unified, so that the target object classification accuracy and stability are effectively improved.

The invention discloses a garbage recovery treatment equipment, which comprises a box body, a shroud, a trash can, a drying and deodorizing device and a sewage discharge pipe. The drying and deodorizing device is placed at the bottom of the inner cavity of the box body, and a Set as a funnel, the bottom of the funnel is provided with a funnel upside down, and the funnel upside down is connected to the sewage pipe; the bottom of the trash can is set as a slope C, and the connection between the slope C and the trash can is provided with a filter hole; the shutter is provided with a control module, the control module includes a motor, a scanner and a single-chip microcomputer, the scanner transmits signals to the single-chip microcomputer, the opening of the baffle is that the motor drives the screw sleeve to move through the screw rod, and the screw sleeve passes through the connecting block Drive the movable link to rotate. The recovery treatment equipment disclosed by the invention can realize the intelligent classification of garbage, automatically filter and discharge the garbage, remove the odor of the garbage box, improve people's living environment, be convenient to use, and benefit people's livelihood.

The invention discloses a garbage recycling implementation method and device based on an intelligent perspective classification garbage can. The method comprises the steps that to-be-thrown garbage isrecognized based on a perspective recognition device corresponding to the intelligent perspective classification garbage can when the fact that a garbage throwing demand exists is detected, and a garbage type set is obtained; whether the to-be-thrown garbage can be stored in the same storage space of the intelligent perspective classification garbage can or not is judged according to the garbagetype set; and if yes, a throwing opening capable of recycling the to-be-thrown garbage is controlled to be opened for a user to throw the to-be-thrown garbage. According to the garbage recycling implementation method and device based on the intelligent perspective classification garbage can, when it is judged that the to-be-thrown garbage can be stored in the same storage space of the intelligentperspective classification garbage can, the throwing opening capable of recycling the to-be-thrown garbage is automatically controlled to be opened, so that the user throws the to-be-thrown garbage, intelligent classification and recycling of the garbage can be achieved, the possibility that the user puts different garbage into the same garbage storage space is reduced, and the garbage classification and recovery accuracy and efficiency are improved.

The invention discloses a data analysis method and apparatus. The method comprises the steps of obtaining original communication data; classifying the data according to attribute features to obtain to-be-analyzed data; performing statistics on information matched with a preset database in the to-be-analyzed data to obtain basic statistical items; according to business indexes, performing conversion processing on the basic statistical items to obtain results corresponding to the business indexes; and outputting the results. According to the technical scheme, the sale communication data is classified, so that the purpose of distinguishing both sale communication parties is effectively achieved and a guarantee is provided for comprehensiveness and accuracy of subsequent data analysis; and through intelligent matching, statistics and business index conversion, an intelligent and efficient data analysis method is provided for merchants, so that the manpower and time costs of the data analysis are greatly reduced and the operation efficiency of the merchants is effectively improved.

The invention discloses a device for application program calling and a method for the same. The method comprises the steps that a display module displays a preset first menu; a receiving module receives a user's trigger operation to a classified option in the first menu; the display module displays a second menu obtained after triggering of the classified option; the user conducts a trigger operation to an application icon in the second menu; and in the end, an application program corresponding to the triggered application icon is called by a calling module. In this way, the problems in the prior art that manual subjectivity and memory are used for selective calling of application programs and thus user experience is poor can be solved; and meanwhile, a mobile terminal can conduct intelligent classification of the application programs, so that the user's operation efficiency and the user's experience degree are increased.

The invention discloses an intelligent classifying dustbin. The intelligent classifying dustbin comprises a dustbin body and a cover plate; two garbage cans are arranged in the dustbin body, the leftgarbage can is a recoverable garbage can, the right garbage can is an unrecyclable garbage can, a control module is arranged in the cover plate, and comprises a motor, a scanner and a single chip microcomputer, the control module is connected with a baffle through a transmission device, the transmission device comprises a screw rod, a screw sleeve and a connecting block, the scanner is arranged onthe front edge portion, protruding out of the dustbin body, of the cover plate, the scanner determines the kind of garbage by scanning garbage, a signal is transmitted to the single chip microcomputer, the single chip microcomputer controls the corresponding baffle to be opened and closed through the motor, the baffle is opened in a manner that the motor drives the screw sleeve to move through the screw rod, the screw sleeve drives a movable connecting part to rotate through the connecting block, the dustbin can achieve intelligent classifying of garbage, manual classifying and putting are not needed, use is convenient, and the dustbin is beneficial to society.

The invention discloses a judgment and grading standard system for heavy-load traffic of national and provincial trunk lines, and the system comprises a data collection module which collects the traffic data of a road section; a traffic volume data vehicle type equivalent conversion module; an axle load spectrum calculation module which is used for obtaining the daily average equivalent axle number of the designed lane in the initial year and the equivalent design axle load accumulative action number on the designed lane within the designed service life; a typical truck discriminating and judging module which is used for judging according to the grounding pressure intensity of the heaviest axle tire and axle group composition; a typical truck daily traffic volume statistical module which is used for performing statistics according to the judged typical truck type; and a heavy traffic judgment and grading module. According to the system, on the basis of analyzing the correlation between the annual average daily traffic volume index of typical trucks and the cumulative traffic volume index of large buses and trucks on the designed lanes within the designed service life, the heavy traffic is graded, a national and provincial trunk line heavy traffic distribution diagram is formed, and aiming at road sections with different heavy traffic levels, an operation management unit provides corresponding operation and maintenance countermeasures.

The invention relates to the technical field of artificial intelligence, and provides a smart phone answering method and system, a medium and an electronic terminal.The method comprises the steps of answering an unknown incoming call on behalf, and obtaining call voice of a calling party of the unknown incoming call; inputting the call voice into a preset voice semantic recognition model for semantic recognition, and obtaining a semantic recognition result; inputting the semantic recognition result into a preset category database for category matching, and determining an incoming call category; inputting the call voice and the semantic recognition result into a preset emotion recognition model for emotion recognition, and obtaining a target emotion recognition result; obtaining the importance degree of the current unknown incoming call by using the incoming call category and the target emotion recognition result; determining a fraud value of the current unknown incoming call according to the call voice, the target emotion recognition result and a preset fraud value acquisition rule; according to the importance degree, the fraud value and the preset call strategy matching rule, matching and executing the corresponding call strategy, and the new crank call can be effectively isolated.

According to the method and the system for searching for the components through the graphs in the BIM, the method for searching for the components through the graphs in the BIM is carried out according to the following steps that 1, a data set is established; 2, training a neural network model by utilizing the data set; 3, inputting a to-be-searched graph, and performing component type recognitionon the input to-be-searched graph by utilizing the trained neural network model; and step 4, according to the component category identified in the step 4, searching all components of the same category from the BIM model. According to the method, the building components can be automatically retrieved in several retrieval modes of text attributes, two-dimensional projection drawings and three-dimensional models, and the retrieval efficiency is high.

The invention discloses an intelligent household garbage can based on multi-mode fusion machine perception, and belongs to the field of household life products. The garbage can comprises a human bodyinduction module, a control module, a voice interaction module and a voice recognition module which are used for obtaining human body induction signals, a garbage can body used for classifying throwngarbage, a power source module, a cloud database, and a cell phone application. The control module is used for converting voice signals into texts and carrying out similarity comparison on the texts and a garbage name text library, each kind of garbage corresponds to one kind of garbage, and a classification result I is obtained; and a visual identification module is used for acquiring an image ofthe thrown garbage to obtain a thrown garbage image signal, the control module is used for performing reasoning operation based on a lightweight deep learning model to obtain a classification resultII, the classification result I is compared with the classification result II, and the classification result I is selected as a final classification result. According to the intelligent household garbage can based on multi-mode fusion machine perception, the garbage treatment efficiency is improved, and the influence of garbage storage and transportation links on the environment is reduced.

The invention discloses an intelligent garbage classification regulation and control system. The intelligent garbage classification regulation and control system comprises a monitoring center, wherein the monitoring center is connected with a garbage processing controller and a vehicle management controller through a network interface, the garbage processing controller is connected with cameras, a buzzer, a data memory, a switch set and a garbage identifier, the switch set comprises switches respectively connected with a recoverable dustbin, a snack dustbin, a harmful dustbin and an other-thing dustbin, the vehicle management controller is connected with a first infrared sensor, a display red lamp and a display green lamp, and the vehicle management controller is used for carrying out scenic area parking lot management. Through the intelligent garbage classification regulation and control system, problems that garbage in scenic areas can not be timely classified and finding parking stalls is difficult are solved, and the intelligent garbage classification regulation and control system is advantaged in that the cameras are convenient to replace and clean.

The invention discloses an intelligent triggering data classification method for a loosening part monitoring system. The method comprises steps that original triggering data of the loosening part monitoring system is acquired; data corresponding to each channel is acquired based on the original triggering data; waveform characteristic extraction of the data of each channel is carried out to acquire a characteristic vector of each channel; a single-channel classification model is established, the data classification result of each channel is acquired based on the single-channel classification model and the characteristic vector of each channel, distinguishing, statistics and management of actual loosening part knock signal data and error triggering data are carried out in an intelligent mode, and data analysis efficiency of a loosening part is improved.

The invention discloses an alarm situation display method, system and device and a storage medium. The method comprises the steps: receiving sent alarm situation information; carrying out classification processing on the alarm information according to alarm indexes; and displaying the warning condition information and the corresponding associated icons on a 3D live-action GIS map in a classified manner according to a classification processing result, wherein the 3D live-action GIS map comprises a 3D model of the position where the warning condition information is located and a real-time videostream. According to the invention, intelligent classification of the alarm information is achieved, immersive live-action 3D browsing and watching experience is provided for monitoring personnel through the 3D live-action GIS map, the on-site situation of the position where the immersive live-action 3D browsing alarm information is located by the monitoring personnel is facilitated, and the working efficiency and capability of alarm information processing are improved. The alarm situation display method, system and device and the storage medium can be widely applied to the technical field ofalarm situation monitoring.

The embodiment of the invention provides an active garbage classification and recovery method. The method is applied to intelligent garbage recovery equipment, and the intelligent garbage recovery equipment comprises an active classification module, a recyclable garbage module and an intelligent measurement and control system; and the active classification module comprises an active classificationdelivery mechanism, an active classification recognition mechanism, a garbage storage chamber, a recognition baffle and an electric push rod. and the intelligent measurement and control system receives a first instruction after detecting that to-be-delivered target garbage exists in the garbage storage chamber; according to the first instruction, determining a target garbage type of the target garbage and determining a target garbage can corresponding to the garbage type; and receiving a second instruction of a user for the target garbage type in a garbage type selection icon, and controllingthe electric push rod to do linear motion through the second instruction so as to slidably open the recognition baffle to throw the target garbage into the target garbage can. According to the scheme, the efficiency and effectiveness of garbage classification and recycling treatment can be improved, and intelligent classification and clearing are achieved.

The invention discloses an improved carrot computer vision elaborate classification, feeding and discharging device. The device comprises a feeding device and a discharging device. The feeding device is a push plate type step feeder, and the discharging device is a flat belt type pneumatic classifying machine. The core of the push plate type step feeder is composed of two sets of fixed push plates. Under the drive of an eccentric wheel, power is provided for the push plates through a connecting rod, and step feeding of a carrot is achieved; and the core of the flat belt type pneumatic classifying machine is composed of a plane conveying belt and an eight-opening air gun, when the long carrot moves to the position of a corresponding classifying opening under the drive of the plane conveying belt, the air gun blows air, and fruits and vegetables are blown into the corresponding classifying opening. The feeding device and the discharging device are used in cooperation with a V-shaped conveying belt, a computer vision system and a control system the feeding and passing efficiency and the classification efficiency are improved, and automatic classification of carrots is achieved.

The invention discloses a control system based on improvement of scenic spot overall performance. The control system comprises a monitoring center, wherein the monitoring center is connected with a garbage disposal controller and a vehicle management controller through network interfaces and connected with a scenic spot patrol controller through a wireless communication module; the garbage disposal controller is connected with a first camera, a buzzer, a data storage unit, a switch set and a garbage recognizer; the vehicle management controller is connected with a first infrared sensor, a display red light, a display green light, a vehicle grate bar, a photographing device and a vehicle license plate storer; the scenic spot patrol controller is connected with an alarm button set, a second camera, a second microphone, a tracking locator and a GPRS module; the scenic spot patrol controller is in communication connection with a mobile phone of a manager. Therefore, the problems that garbage of a conventional scenic spot cannot be classified and treated in time, finding parking spaces is troublesome, and potential garbage safety hazards in the scenic spot cannot be discovered in time are solved.

The invention relates to a making method of Jiuhua hook-shaped / bow-shaped hairy green tea. The making method comprises the following technological processes of picking fresh leaves; performing humidifying and performing tedding; performing steam dehydration and fixation; performing enzyme addition and rolling; performing electrothermal rolling for shaping; performing electric stir-frying for shaping; performing baking for tightening the shape; performing shaking and screening for selecting fine long hairs; performing fanning and tipping; performing electromagnetic baking on tea leaves subjected to tipping; and performing color selection and classification, thereby obtaining the Jiuhua hook-shaped / bow-shaped hairy green tea. The Jiuhua hook-shaped / bow-shaped hairy green tea made by the making method is emerald green in shape color and bent, and has golden fine long hair; and through the making method disclosed by the invention, the intelligent classification of the Jiuhua hook-shaped / bow-shaped hairy green tea is realized, the classification is efficient and accurate, and the production cost is reduced by about 60%.

A gravity casting machine with a detection device is characterized in that it includes a frame mechanism, a movable mold mechanism, a mechanical detection mechanism, and a control mechanism; the rotary cylinder using the mechanical detection mechanism rotates the mechanical arm to the bottom of the product after the lower mold is separated from the product, There is an air nozzle under the detection frame; the lifting cylinder is used to make the product frame close to the product, and the upper and lower cylinders are used to make the detection head of the detection frame with the detector close to the necessary inspection parts that are easy to shrink and loosen for contact inspection and sand removal, replacing online manual labor. Pick-up detection; when the online mechanical detection mechanism receives the unqualified signal from the inspection, the products that have been removed from the mold are pushed by the lifting cylinder to push the product rack, so that the unqualified products are sent to another place to realize intelligent classification; this application can use The transformation of the original gravity casting machine can save investment, reduce waste and reduce product cost.

The invention discloses a three-dimensional CAD model intelligent classification method based on an improved depth residual network, and the method comprises the steps of representing a model througha plurality of views of a three-dimensional CAD model, carrying out the data enhancement on the views to obtain a multi-view data set, and further obtaining a training data set through the gray scaletransformation and the normalization processing; importing the training data set into an improved deep residual network for training, and storing the trained network; when classification is needed, obtaining and preprocessing one or more views of any size of the new model, further calling the trained network to recognize the input views, and finally obtaining the category with the highest score after the average value of all view recognition results as the category to which the model belongs. According to the present invention, by adopting the improved deep residual network, the intelligent classification of the three-dimensional CAD model is achieved, and the method has the advantages of being flexible and convenient in classification input, high in classification accuracy, good in practicability, high in intelligent degree and the like.