84results about How to "Save review time" patented technology

The invention discloses an O2O online interactive platform for K12 education, comprising a lesson preparation module, a class module, a question answering and test module, an operation record module, and an online course management module. The platform has a clear structure, and is convenient to operate. The platform meets the need for teaching interaction between students and teachers. Individualized student reminding brings great convenience to students. Students can learn better without going out. The teaching video can be played back for students to review teaching content whenever and wherever possible. Students do not have to worry about forgetting. Students are enabled to get tested and consolidate learning content more efficiently and quickly, and digest knowledge quickly. Teachers and students communicate face to face, and write and perform calculation on the blackboard at the same time. Students are taught step by step, and can understand even a very complex mathematical problem quickly.

An embodiment of the application discloses a method and a device for information output. According to the embodiment, the method includes acquiring a set of to-be-recognized images uploaded by a user,wherein industry identifiers associated with the user refer to a class identifier group; analyzing each to-be-recognized image of the set of to-be-recognized images to determine whether the to-be-recognized image is a credential image of a class of credentials in a preset credential class set or not, if so, then determining whether a set of the credential classes which the to-be-recognized imagesbelong to is the same with the credential class group or not, if they are the same, then subjecting a designated area of each to-be-recognized image of a to-be-recognized image set to character recognition, comparing the recognized character information with text message associated with the user and corresponding to the credential class which the to-be-recognized images belongs to so as to obtaina comparison result, and finally outputting the comparison result to an audit side of auditors. According to the embodiment, auditing time can be saved for the auditors and auditing efficiency can beimproved.

The invention provides an audio-video file detection management method and device. The audio-video file detection management method includes: acquiring audio-video metadata corresponding to an audio-video file from a website where the audio-video file is stored; preliminarily screening the audio-video metadata according to preset rules to classify the audio-video file; deeply analyzing at least one part of the audio-video file according to a classification result to acquire a judgment result aiming at the analyzed audio-video file; detecting whether the analyzed audio-video file is an audio-video file of a specific type or not according to the judgment result. By the audio-video file detection management method and device, safety of the Internet can be improved.

The invention provides an assistant reviewing method. The method includes the steps of collecting biological data, recording audio, and classifying learning states according to the biological data, wherein the learning states include a low-efficiency learning stage and a doze stage; conducting voice identification on the audio recorded during the low-efficiency learning stage or the doze stage; searching corresponding knowledge points according to the text generated by the voice identification; displaying the corresponding knowledge points. The invention also provides an assistant reviewing device and equipment. The device and equipment can solve the technical problems that since knowledge points all need to be reviewed, time consumption is large, the learning content acquired during a low-efficiency learning stage is unimpressive in the massive knowledge points so that the reviewing efficiency is low in the existing techniques, and therefore the reviewing time can be saved, and the reviewing key points can be highlighted.

The invention provides an information pushing method and a mobile terminal, and relates to the technical field of communication, for solving the problem that an existing method for looking up target information on the mobile terminal is tedious and time-consuming. The method comprises the steps of acquiring a target character string which is the character string on a suspending shear plate; extracting a keyword of the target character string; searching at a preset position by using the keyword; and displaying a search result which comprises pushing information matched with the keyword and the source of the pushing information. According to the method provided by the embodiment of the invention, the target pushing information and the source thereof matched with the target character string are acquired by searching according to the target character string, and displayed on the suspending shear plate, so that a user can have more choices, and can acquire the most suitable answer without searching and comparing one by one, and thus lookup time is saved.

The invention provides a method for generating a cross-border tourist map, which comprises: write plan route addresses, plant route time and remark information into a tourist plan template, and load a link of a sub-corpus; import the information into a map data information base; retrieve and match the plant route addresses in the map data information base, display the plant route addresses in a digital map, and display links of the plant route time, the remark information and the sub-corpus based on the mapping relationship; associate the plant route addresses according to the time sequence to form a plant tourist track, and display the plant tourist track on the digital map; form a plant transportation means for two route address on the plant tourist track along the progress direction through retrieve and match, recommendation and selection; and display the plant transportation means on the track between the two route addresses. The method provided herein has the effects of conveniently and directly viewing the tourist plan and referring the corpus efficiently.

The invention provides an auxiliary learning method. The method includes: collecting brain waves; recording audio frequency and/or a video; partitioning levels for learning states according to the brain waves, wherein the learning states include a low-efficient learning period and a sleepy period; carrying out speech recognition on speeches in the audio frequency and/or the video voices recorded in the low-efficient learning period or the sleepy period; setting a text label according to a speech recognition result; and acquiring a selection result of the text label, and playing the audio frequency and/or the video in a corresponding time period. The invention also provides an auxiliary learning device and terminal. According to the method, the device and the terminal, technical problems that in the prior art, consumed time is long and key points are not highlighted when reviewing is carried out through an audiovisual recorded in a classroom, and thus knowledge blind-spots brought when lecture attending efficiency is low are difficult to be eliminated are solved, the reviewing time can be saved, and the key reviewing points can be highlighted.

The embodiment of the invention discloses a method and a device for monitoring data modification. The method comprises the steps of: acquiring a flow task and a corresponding task identifier; judging whether a history audit record of the flow task is stored or not according to the task identifier; if yes, determining the flow task as a flow task which is submitted to be audited for the Nth time, acquiring data content of an audited data block, an audit result and a user identifier corresponding relationship in an auditing process of the flow task which is submitted to be audited for a (N-1)th time according to the history audit record, determining same blocks in the flow task submitted to be audited for the Nth time and the flow task submitted to be audited for the (N-1)th time, and comparing whether data content in the same data blocks is the same or not; and if yes, endowing the same data blocks with corresponding audit results in the name of corresponding user identifiers in the Nth audit of the flow task. Through the adoption of the method, when the flow task is re-submitted to be audited, a condition that an unmodified data block is sent to a user again for auditing is avoided, so that the audit efficiency of re-audit is improved.

The invention discloses an automatic auditing method for illegal parking based on deep learning, and the method comprises the following steps: carrying out the photographing and evidence collection ofan illegal parking vehicle through employing a photographing and camera shooting device, wherein the evidence collection information comprises three evidence images: a license plate close-up image, acab close-up image, and a bill pasting image, and the evidence collection information further comprises license plate number information of the illegal parking vehicles; carrying out region segmentation on the three evidence images by utilizing a segmentation model; performing license plate recognition on the segmented license plate area; judging whether the identified license plate number is thesame as the license plate number in the evidence collection information or not; judging whether the result area obtained through segmentation conforms to the screening principle or not, and giving out a final auditing result. According to the invention, the police is saved, and the illegal auditing efficiency and accuracy are improved.

The present invention provides an intelligent learning method. The method includes the following steps that: brain waves are acquired; audios or videos are recorded; the levels of learning states are classified according to the brain waves; and the audios or videos are replayed according to the levels. The invention also provides an intelligent learning device and a terminal. With the intelligent learning method, the intelligent learning device and the terminal of the invention adopted, the technical problem of difficulty in eliminating knowledge blind spots caused by low class attending efficiency which is further caused by long consumed time and unobtrusiveness of key points in using videos recorded in class to perform review can be solved, review time can be saved, and the key points of the review can be highlighted.

The invention discloses a method and a device for managing marks in a WORD document. The method comprises the following steps of receiving a request message of searching for the marks in the WORD document from a user, and searching for the marks in the document according to a searching condition in the request message; finding each mark consistent with the searching condition from the document one by one, and acquiring corresponding mark information; writing the acquired mark information into a mark file for storage. According to the method and the device, disclosed by the embodiment, for managing the marks in the WORD document, the user can set the searching condition for the searching of the marks according to needs, so that the marks consistent with the condition can be automatically acquired, the operation of the user is greatly simplified, and the lookup time is saved.

The invention discloses a seal recognition method and system based on deep learning and a storage medium, belongs to the technical field of machine vision, and aims to solve the technical problems of few seal recognition scenes, poor seal fan-shaped character correction effect and low character recognition accuracy.According to the technical scheme, he method includes: acquiring a to-be-recognized image; detecting a seal in the to-be-recognized image by using the target detection model, and obtaining coordinate information and a seal type corresponding to the seal in the to-be-recognized image; according to the coordinate information corresponding to the seal in the to-be-recognized image, cutting out the to-be-recognized seal image; using the image rotation angle classification model to recognize the rotation angle of the to-be-recognized seal image, and correcting the to-be-recognized seal image according to the rotation angle; detecting characters in the corrected to-be-recognized seal image by using a character detection model, acquiring coordinate information of the characters, and cutting a to-be-recognized character image according to the coordinate information of the characters; and according to the obtained seal type, recognizing the to-be-recognized character image by using a character recognition model to obtain a seal recognition result.

The invention discloses a traffic violation reporting excitation method and device based on a block chain, and a medium. The method comprises the steps of obtaining a traffic violation reporting instruction and reporting traffic violation subject identity information; calling public traffic monitoring equipment information based on the reported traffic violation instruction; acquiring a public transport monitoring equipment selection instruction; marking the monitoring information of selected monitoring equipment based on the public traffic monitoring equipment selection instruction to form traffic violation evidence information to be checked; checking the traffic violation evidence information to be checked, judging whether a traffic violation case exists or not, and if yes, forming traffic violation reporting case information from the reported traffic violation subject identity information and the traffic violation evidence information to be checked, and uploading the traffic violation reporting case information to a traffic violation reporting block chain; analyzing the traffic violation reporting case information, and obtaining a violation grade value according to a preset traffic violation grade; and determining an excitation mode to excite a reported traffic violation subject based on a traffic violation reporting smart contract according to the violation level value.

The invention discloses a tagging and checking method and system for recorded audios and videos, and the tagging method for recorded audios and videos can be used for carrying out audio and video recording when a user handles a business, and carrying out business normalization detection and data recording on the user while carrying out audio and video recording; and according to the service normalization detection result and the recorded data, generating a corresponding video tag for storage, and adding the video tag to a time node corresponding to the audio and video in the later period. According to the method, the problems of high auditing difficulty and long consumed time in business handling are solved, auditing personnel can directly position the playing position in the player through the marked video tag during later auditing, rapid and visual auditing is facilitated, the watching time of the video is shortened, the workload of the auditing personnel is reduced, and thus, the auditing efficiency of auditing personnel and the business handling efficiency are improved.

The invention provides an intelligent learning method, which comprises the following steps: sending acquisition information to an intelligent wristband, wherein the acquisition information is used for acquiring a blood oxygen saturation of a user; receiving the blood oxygen saturation sent by the intelligent wristband; judging whether the blood oxygen saturation is smaller than a threshold or not; and when the blood oxygen saturation is smaller than the threshold, recording an audio and/or video. The invention also provides an intelligent learning device, terminal and system. The intelligent learning method, device, terminal and system solve the technical problems that a knowledge blind point generated when the lecture attending efficiency is low is difficulty eliminated caused by long review consumed time and non-prominent emphasis through the audio and/or video recorded in a classroom in the prior art and can save the review time and highlight a review emphasis.