38results about How to "Automatic classification" patented technology

The invention relates to a method for establishing a classification rule of short messages of a mobile phone, comprising the following steps: firstly, establishing one personalized file folder by a user through selecting a function of the personalized file folder in an option menu of the mobile phone for checking an information interface; secondly, providing a matching condition of the personalized file folder; thirdly, receiving a new short message; fourthly, judging whether a mobile phone number sending the new short message or an information content included in the short message is matchedwith a matching condition provided in the second step, and automatically saving the new short message conforming to the matching condition to the matched personalized file folder; and fifthly, storingthe new short message no conforming to the any provided matching condition to a mobile phone inbox, wherein the matching condition comprises the matched mobile phone number and the matched information content. The method is convenient for users to classify the short message, and check and manage.

An industry investment information and data processing system based on a strength, weakness, opportunity, and threat (SWOT) model comprises an automatic collecting module of industry information on the internet and an industry information manual additional recording module, an information screening processing module, an SWOT analyzing module, an influence quantizing module, an SWOT index processing module, and an information and data output terminal, wherein an information collecting classifying server comprises the automatic collecting module of industry information on the internet and the industry information manual additional recording module, and an information and data processing server comprises the information screening processing module, the SWOT analyzing module, the influence quantizing module, and the SWOT index processing module. The automatic collecting module of the industry information automatically grasps the industry information on the internet. The information screening processing module automatically conducts screening, eliminates duplication and unifies forms, the SWOT analyzing module divides all sub-industry information into a part of strength (S), a part of weakness (W), a part of opportunity (O) and a part of threat (T). The SWOT index processing module sets an influence probability coefficient for the information and obtains SWOT analysis investment indexes. The industry investment information and data processing system based on the SWOT model can automatically search, grasp, screen and process the industry investment information, generates the information and the investment indexes which are classified according to sub-industries and, achieves classification, storage and output of the information and the indexes according to categories including S,W,O, and T.

The invention relates to a system and a method for controlling and managing authority of a conditional electronic file. The system for controlling and managing the authority of the conditional electronic file comprises a managing end and a client; the electronic files formed at the client are sent to the managing end and are performed with content comparison according to the set key words; and then the electronic files are automatically encrypted and classified the authority according to the comparing result. The whole system can simplify encrypting steps and improve the authority controlling and managing effect based on a transparent mode. Besides, the invention also discloses a method for controlling and managing authority of the conditional electronic file.

The invention relates to the field of slope engineering, in particular to an efficient slope reliability analysis method. The method comprises the following main steps: 1, slope stability determinacyanalysis; 2, spatial variability simulation of rock-soil parameters; 3, identifying a representative sliding surface by utilizing a K-mean clustering analysis method; 4, establishing a response surface function relational expression of the representative sliding surface; and 5, calculating a slope reliability index or a slope failure probability. Compared with an existing side slope reliability calculation method, the method a representative sliding surface identification technical method which is simple and efficient and is relatively stable for different statistical parameters. The calculation efficiency of the representative sliding surface-based slope reliability analysis method can be improved, the application of the reliability analysis method in slope design can be expected to be effectively promoted, and the method has certain theoretical innovation significance and engineering practical value.

The invention discloses a prediction method, system and device for a complaint text category of an OTA platform and a storage medium. The prediction method comprises the steps of obtaining historicalcomplaint text data of the OTA platform; clustering and labeling the historical complaint text data to obtain a complaint category of each piece of historical complaint text data; acquiring historicaldimension data and historical entity data; establishing a prediction model for predicting a complaint category to which the complaint text data belongs; obtaining target complaint text data; inputting the target complaint text data into a prediction model, and obtaining a probability value of the target complaint text data belonging to each complaint category; and determining a target complaint category to which the target complaint text data belongs according to the probability value. According to the method, the text classification precision is improved, the user complaint content is automatically classified, so that related responsible personnel can process complaint types in charge of themselves in time, and a large amount of manpower is saved while the user experience is improved.

The invention provides a transformer welding and assembling integrated production line. The production line comprises a first conveying belt, a second conveying belt, a welding device and an assembling device, wherein the welding device comprises a welding pool arranged on a first machine table and a welding grabbing mechanism installed above the welding pool and used for grabbing and releasing atransformer, and the first conveying belt and the second conveying belt are arranged in front of the welding pool; the welding grabbing mechanism comprises a welding grabbing mechanism frame, the welding grabbing mechanism frame is in sliding connection with the first machine table through a sliding rail assembly, a welding gripper assembly is arranged in the frame of the welding grabbing mechanism frame, and the welding gripper assembly is provided with a rotatable welding gripper and can move up and down relative to the welding grabbing mechanism frame so as to clamp the transformer from thefirst conveying belt, place the transformer into the welding pool for tin soldering and then place the transformer to the second conveying belt; and the assembling device is used for flattening the grounding wire of the welded transformer, conveying the iron core, pasting the iron core and encapsulating. By means of the production line, welding and assembling of the transformer can be automatically completed, labor is saved, and efficiency is improved.

The embodiment of the invention provides a traffic recognition model training method and device and electronic equipment, and relates to the technical field of industrial control. The training methodof the traffic recognition model comprises the following steps: acquiring a sample traffic set; wherein the sample flow set comprises sample feature information of a plurality of detected protocol flows; dynamically determining a first number of clustering centers according to sample feature information in the sample flow set so as to divide the sample flow set into a plurality of sample clustersaccording to the obtained first number; and training a preset machine learning model by using the obtained sample cluster to obtain the flow recognition model. In this way, samples in the sample flowset can be automatically and accurately classified even if priori knowledge does not exist. Therefore, the recognition precision of the obtained flow recognition model is improved.

The invention relates to traditional Chinese medicine smashing equipment, in particular to traditional Chinese medicine smashing equipment capable of fast washing and screening the big-powder traditional Chinese medicine. According to the traditional Chinese medicine smashing equipment, the big-powder traditional Chinese medicine can be screened out, and timely and fast washing can be conducted. The traditional Chinese medicine smashing equipment comprises a bottom plate, a first collecting box, a supporting plate, a fixing plate, a first supporting base, a rotating shaft, a first fixing block, an installing plate, a smashing box, a second supporting base and the like. The first collecting box is placed on the right side of the bottom plate. By means of the traditional Chinese medicine smashing equipment capable of fast washing and screening the big-powder traditional Chinese medicine, the effects that the big-powder traditional Chinese medicine can be screened out, and timely and fast washing can be conducted are achieved.

The invention relates to a comprehensive two-dimensional gas chromatography modulation peak intelligent classification method, and a second-dimensional (2D) modulation peak is derived from a comprehensive two-dimensional gas chromatography (GC * GC)-mass spectrometry (MS) combined instrument, and comprises three levels of restrictions. The method can be used for positioning a co-flow region in a GC * GC-MS three-dimensional (3D) array of a complex system, and is convenient for mathematical separation. According to the scheme, the method comprises the following steps: 1) converting original data into a tiled matrix of two-dimensional (2D) slices; 2) making background deduction and peak top (width) calculation; 3) taking a 2D peak top point, a peak starting point or a peak end point time difference as a first limit; 4) constructing a 2D peak-top submatrix, with the first-dimensional (1D) profile extreme value number as the second limit, (5) calculating the third limit based on a movingwindow and the characteristic value of 2D modulation peak mass spectrum information, and (6) calculating a rank graph and analyzing a co-current peak. The scheme is rapid in operation and reliable inresult under the proper parameter setting condition.

The invention provides a bone marrow cell classification and identification method, device and system based on deep learning, and belongs to the field of medical image processing. The method comprises the following steps: (1) acquiring a low-power lens full-slice image of a bone marrow smear by using a low-power lens; (2) cutting the low-power lens full slice image of the bone marrow smear into a plurality of low-power lens small images with the same size as the high-power lens imaging view; (3) classifying the low-power mirror small images obtained in the step (2) by using a trained image classification model to obtain low-power mirror small images with good visual fields; (4) scanning and imaging the low-power lens small image with a good visual field by using a high-power lens to obtain a corresponding high-power lens image; (5) classifying and counting bone marrow cells in the high-power lens image obtained in the step (4) by using the trained target detection model; (6) predicting blood diseases according to classification and counting results of the bone marrow cells. Therefore, identification and classification of bone marrow cells can be reliably and automatically realized, and the accuracy of blood disease prediction can be improved.

The invention discloses a method of discriminating a web page type. The method includes: acquiring page information of a to-be-judged web page; extracting title information from the page information;judging whether the title information contains a preset keyword, wherein the preset keyword is a keyword containing the web page type; and obtaining the web page type of the to-be-judged web page on the basis of page structure information corresponding to the page information and / or the title information if the title information does not contain the preset keyword. The method can solve the problemthat efficiency of depending on a manual manner to carry out web page type classification in the prior art is low. The invention also discloses a device of discriminating the web page type.

The invention relates to the technical field of animal experiment instruments, in particular to a rabbit fixing table which comprises an operating plate. The upper surface of the operating plate is provided with a plurality of drainage grooves, the bottom surface of each drainage groove is obliquely arranged, and the lower end of the bottom surface of each drainage groove is provided with a drainage hole; the bottom end of the operating plate is detachably connected with a collection barrel, and each drainage hole can be communicated with the collection barrel; a filter screen is obliquely arranged in the collection barrel, the collection barrel internally comprises two accommodating grooves, one accommodating groove is located below the filter screen, and the other accommodating groove islocated below the lower end of the filter screen; the operating plate is provided with fixing units for fixing the limbs of a rabbit. When the rabbit is dissected, the fixing units are used for fixing the limbs of the rabbit, by utilizing the obliquely arranged bottom surface of each drainage groove and the obliquely arranged filter screen, dirt generated by dissection is classified and collected, the problems are solved that dirt cannot be automatically classified and collected in the dissection process of the rabbit and the rabbit cannot be accurately dissected due to the fact that the rabbit cannot be fixed, the dissection efficiency is improved, and the dissection experience of an anatomist is improved.

The invention discloses an intelligent garbage can. The intelligent garbage can includes a garbage can shell and a PLC controller, a plurality of solar panels are arranged on the outer side of the garbage can shell and connected to a power supply, the power supply is fixed on a bracket, garbage throwing openings are formed in both sides of the garbage can shell, garbage guiding detection tanks areformed in the lower ends of the garbage throwing openings, and proximity switches, 2mm photoelectric switches, 4mm photoelectric switches and color sensors are fixedly arranged on the plates of the two sides of each garbage guiding detection tank; and a blocking plate moving electrically through an electric cylinder is arranged on the bracket at the lower end of each garbage guiding detection tank, a garbage can rotating disc is arranged at the bottom of the garbage can shell, five garbage storing cans are arranged on the garbage can rotating disc, a rotating disc shaft mounted on the rotating disc is arranged at the bottom of the garbage can shell, and a turbine is arranged at the lower end of the rotating disc shaft and driven by a worm. The intelligent garbage can is simple in structure and reasonable in design, and can automatically open the garbage throwing openings, facilitates the storage of the garbage, and meanwhile, can automatically classify the garbage.

The invention discloses a GIS-based basin land utilization classification method and device. The method comprises the steps of collecting GIS data, extracting a boundary contour of to-be-classified basin land according to the GIS data, and obtaining a GIS boundary image of the to-be-classified basin land; obtaining spectral characteristic values of the GIS boundary images of the to-be-classified drainage basin land, wherein the spectral characteristic values comprise an average value of each waveband, a maximum change among the wavebands and a waveband normalization difference index; and inputting the average value of each waveband of the GIS boundary image, the maximum change among the wavebands and the waveband normalization difference index into a land utilization classifier, and outputting land utilization classification of the to-be-classified drainage basin land. The GIS boundary image of the basin land is obtained through GIS data processing, then basin land utilization classification is obtained according to the spectral feature value of the GIS boundary image and the pre-trained land utilization classifier, classification of land utilization is automatically achieved, manual operation is reduced, and the error rate is reduced.

The invention discloses a fruit weight automatic distribution device used for the tail end of an assembly line. The device comprises a main cylinder provided with an opening at the upper end, whereina main spring is arranged on the top surface of a bottom plate of the main cylinder, a lifting plate is arranged on the top surface of the main spring, multiple discharge ports which are vertically and uniformly distributed are formed in the wall body of the main cylinder and located at the front end of the lifting plate, multiple pushing through holes are formed in the wall body of the main cylinder and located at the rear end of the lifting plate, and pushing rods are arranged in the pushing through holes. The fruit weight automatic distribution device used for the tail end of the assembly line has advantages as follows: the device is placed at the tail end of the assembly line, fruits on the assembly line can roll into the device sequentially, the lifting plate supported by the spring is arranged in the device, the degrees of compression on the spring by fruits with different weights are different, so that the fruits in a certain weight range can stay at different heights of the device, and classification of the fruits with different weights can be automatically realized through pushing air cylinders at the rear part.

The invention relates to the technical field of waste sorting, and particularly relates to an intelligent construction waste sorting device. The device comprises a box body, a funnel, a conveying belt, a support, an electromagnet, a roller, a supporting base, a sedimentation pond and a pressure switch used for controlling opening and closing of the electromagnet, metal waste in the construction waste can be separated out through the electromagnet inside the box body, fine materials in the construction waste are screened out through the roller, large construction waste is screened into the sedimentation pond, water is contained in the sedimentation pond, and the construction waste is sorted by utilizing the fact that different kinds of waste have different buoyancy in the water. According to the intelligent construction waste sorting device, the construction waste can be automatically sorted, manual waste separation is avoided, the time of operators is saved, and resources are saved.

The invention belongs to the technical field of agriculture, and discloses a device for automatically measuring the soft rot spot area of an in-vitro plant. The device for automatically measuring the soft rot spot area of the in-vitro plant comprises an image acquisition module, an image preprocessing module, an image segmentation module, a central control module, an image feature extraction module, a lesion analysis module, a soft rot spot position determination module, an image standardization processing module, a measurement module and an output module. The device can automatically measure the soft rot spot area of the in-vitro plant, is high in measurement precision, is not affected by the environment, and can carry out accurate measurement in a complex environment. According to the device for automatically measuring the soft rot spot area of the in-vitro plant, the soft rot spot area of the in-vitro plant can be automatically measured, the measurement precision is high, meanwhile, the device is not affected by the environment, and accurate measurement can be conducted in the complex environment. Meanwhile, the scab area can be measured, and scab classification can be automatically carried out at the same time.

The embodiment of the invention provides a live video topic classification method and device and an electronic device. The method comprises: through collecting bullet screen information of a live video and splicing bullet screen information of the live video, obtaining bullet screen long text, matching the bullet screen long text with bullet screen information in a corpus, and taking single characters or words matched in the bullet screen long text as keywords; and determining the keywords of which the first occurrence frequency is greater than a first preset threshold and the second occurrence frequency is less than a second preset threshold as topic keywords, and determining a topic classification result of the live video based on the topic keywords. By adopting the method and the device, the topic classification of the live video can be automatically realized based on the bullet screen information generated in the live video, and the topic classification of the live video does not need to be manually performed, so that the cost of the topic classification of the live video is reduced and the classification efficiency is improved.

The invention discloses metal component flaw detection screening equipment. A machine body is included and internally provided with a conveying cavity. The left side of the conveying cavity is provided with a detection cavity. A classification cavity is formed in the left side of the detection cavity. A power cavity is formed in the rear side of the detection cavity. An analysis system is fixedlyarranged on the left side of the machine body. A hydraulic pump is fixedly arranged on the lower side of the analysis system. An inlet is fixedly formed in the right side of the machine body. A wastecavity and a finished product cavity are fixedly formed in the lower side of the classification cavity. A detection device for ultrasonic detection is arranged in the power cavity and comprises a mainmotor fixedly arranged on the rear side wall of the power cavity. The main motor is in power connection with a motor shaft. The equipment can automatically achieve batched component detection and classification, detection is finished during component production, detecting and machining are synchronous, the production efficiency can be improved, and the component rejection rate is reduced.

The invention discloses an urban induction and identification garbage can. The urban induction and identification garbage can comprises a box body, wherein a first cavity and a second cavity are formed in the box body; a snapshot mechanism is arranged on the inner wall of the lower side of the first cavity; the snapshot mechanism comprises a snapshot motor; the snapshot motor is fixedly arranged on the inner wall of the lower side of the first cavity; a first rotating shaft is rotationally arranged on the upper end surface of the snapshot motor; the first rotating shaft is fixedly connected with a rotating disc; third cavities with openings facing the direction of the box body are formed in the left end surface and the right end surface of the rotating disc; and distance sensors are fixedly arranged on the inner walls of the lower sides of the third cavities. According to the urban induction and identification garbage can, when the garbage can senses that someone wants to throw garbage, the garbage can be automatically classified, if the garbage can is full of the garbage, the garbage can be popped up, and a lamp is turned on for warning; and if people do not take back the garbage,the people are supposed to throw the garbage about, the urban induction and identification garbage can take pictures, so that law enforcement personnel can be helped to enforce the law.

The invention discloses a fish baking device capable of separating big fish from small fish. The fish baking device comprises three conveying devices which are sequentially arranged from top to bottom. The right end of the conveying device located below stretches out, wherein the conveying device comprises a first conveyer belt which is provided with long fish falling through grooves allowing the fish to fall into. A stop plate is arranged at the lower portion of the left end of the first conveyer belt and provided with a bearing plate. A baffle is arranged on the bearing plate. One end of the baffle is provided with a narrowing part. A fish falling through groove is formed in the portion, corresponding to the narrowing part, of the bearing plate. A first baking machine is arranged under the fish falling through groove. A conical push block is movably arranged on the bearing plate and can squeeze the fish on the bearing plate into the fish falling through groove to fall into the first baking machine through the fish falling through groove when moving towards the narrowing part. The fish baking device is high in mechanization degree, simple in structure, convenient to move, specially suitable for the places such as piers where the fish baking device needs to be frequently moved, and capable of automatically sorting the fish according to the sizes of the fish.

The invention discloses an error detection device for machining, and belongs to the technical field of detection devices. The error detection device for machining comprises: a lower fixing plate, an upper fixing plate and a cylinder body, and further comprises a first mounting plate and a second mounting plate which are connected with the lower fixing plate; a first positioning shaft which is rotationally connected to the first mounting plate; a servo motor which is connected with the first positioning shaft; a second positioning shaft which is rotationally connected to the second mounting plate; and a driving assembly which is connected to the lower fixing plate and used for driving the second mounting plate to move. According to the invention, the cylinder body is equally photographed for four times, and then is compared with the preset graph meeting the size requirement, so that the detection accuracy is improved, the measurement efficiency can be improved, and meanwhile, the detected cylinder body can be distinguished and placed by using the conveyor belt.