Abstract: The present disclosure provides a question correction method and device for oral calculation questions. The feature vector of the question to be searched is obtained according to the content of token in the stem of each question to be searched, and then the feature vector of each question to be searched is used to search for the target test paper that matches the test paper to be searched in the question bank. For the question to be searched in the form of oral calculation question, a second search is performed in the target test paper based on the feature vector of the question, and the search criterion is the minimum shortest editing distance.

Abstract: The invention provides a method and a device for identifying the number of bills and multiple bill areas in an image. The method comprises the following steps: acquiring the image containing a plurality of bills arranged in sequence; processing the image to obtain a plurality of boundary lines of each bill in the image; wherein the boundary lines comprise a first type of boundary lines which are substantially perpendicular to the bill arrangement direction; generating a long line segment which is substantially parallel to the arrangement direction of the bills and passes through the area where all the bills are located, wherein the long line segment has an intersection point with each first type of boundary line; and determining the number of bills in the image according to the lengths of the sub-line segments between the adjacent intersection points.

Abstract: A serial LED driver with a built-in calibratable parameter transmits a grayscale vector, a calibration parameter matrix or an appropriate current value vector and includes: a nonvolatile memory receiving and storing the calibratable parameter; a calibration matrix processing unit reads elements corresponding to the LED lamp bead and being pre-stored in the calibration parameter matrix of the nonvolatile memory, receives the grayscale vector, and performs matrix computation according to the grayscale vector and the calibration parameter matrix to generate a new grayscale vector; and a pulse width modulation circuit, which outputs a constant current to the LED lamp bead according to the first new grayscale vector to adjust the LED lamp bead; or outputs another corresponding constant current to adjust the LED lamp bead according to the new grayscale vector and the appropriate current value vector corresponding to the LED lamp bead and being pre-stored in the nonvolatile memory.

Abstract: A handwritten content removing method and device and a storage medium. The handwritten content removing method comprises: acquiring an input image of a text page to be processed, the input image comprising a handwritten region, which comprises a handwritten content (S10); identifying the input image so as to determine the handwritten content in the handwritten region (S11); and removing the handwritten content in the input image so as to obtain an output image (S12).

Abstract: A serial LED driver with a built-in calibratable parameter transmits a grayscale vector, a calibration parameter matrix or an appropriate current value vector and includes: a nonvolatile memory receiving and storing the calibratable parameter; a calibration matrix processing unit reads elements corresponding to the LED lamp bead and being pre-stored in the calibration parameter matrix of the nonvolatile memory, receives the grayscale vector, and performs matrix computation according to the grayscale vector and the calibration parameter matrix to generate a new grayscale vector; and a pulse width modulation circuit, which outputs a constant current to the LED lamp bead according to the first new grayscale vector to adjust the LED lamp bead; or outputs another corresponding constant current to adjust the LED lamp bead according to the new grayscale vector and the appropriate current value vector corresponding to the LED lamp bead and being pre-stored in the nonvolatile memory.

Abstract: The disclosure provides a calculation practicing method, a system, an electronic device and a computer readable storage medium, the calculation practicing method includes: providing a calculation question; identifying the type and content of the calculation question; generating an answer area according to the type and content of the calculation question; receiving an answering operation in which the user inputs the answer string for the calculation question in the answer area; identifying the answer string inputted by the user; and determining whether each of the answer characters in the answer string is correct, if there is an incorrect answer character, it will be marked, so that the calculation practice can be realized through the electronic device, which is convenient for students to carry out training.

Abstract: A method and a system for intelligent identification and correction of a question, which implements, through artificial intelligence, automatic identification of stems of various types of questions and contents of answering in test papers and auto-corrects the contents of answering. The technical solution is: to train a neural network model (e.g., CNN model) into a model for question type recognition based on numerous test paper samples in advance, and to use this trained model to detect the position of individual questions, the type corresponding to the question, the different components of the question (stem, answer, picture) in the test paper, and then to identify the printed font character information of the stem and the handwriting font character information of the answer part based on the recognition model, and finally to auto-correct based on the identified character information.

Abstract: An examination paper correction method and apparatus, an electronic device, and a storage medium are provided. The method includes: obtaining a first image of a standard examination paper; identifying an area and characters of each standard answer in the first image, and using a marking box to mark an answering area where each standard answer is located; determining position information of each marking box; obtaining a second image of an examination paper to be corrected; determining, according to the position information of each marking box of the first image, an answering area in the second image matching a position of the marking box, and using a marking box to mark the determined answering area; identifying characters of an answer to be corrected in each marking box of the second image; and comparing the characters of the standard answer with the characters of the answer to be corrected.

Abstract: A method and a device for generating a collection of incorrectly-answered questions are provided. The method includes: acquiring an image of a marked test paper (S101); recognizing regions of respective questions in the marked test paper according to a pre-trained first region recognition model (S102); recognizing a question whose marking result is incorrect in the marked test paper as an incorrectly-answered question according to a pre-trained incorrectly-answered question recognition model (S103); and storing the region of the incorrectly-answered question in an incorrectly-answered question database to generate the collection of incorrectly-answered questions (S104). The above solution may solve the problem of low efficiency in generating the collection of incorrectly-answered questions in the prior art.

Abstract: Disclosed is a wireless induction power supply type light-up electric toothbrush, including a toothbrush handle body, a main body support, a mainboard, a battery, a motor, a motor sleeve, a waterproof ring, a toothbrush handle cover plate, a toothbrush head cover plate, a toothbrush head rod and a toothbrush head, wherein the toothbrush head is further provided with bristles and a toothbrush head LED panel arranged with several toothbrush head LED lamps. The toothbrush is added with a healthcare function through LED lamps, and the toothbrush head LED lamps are powered up in a wireless manner.

Abstract: A power bridge device includes: a power management unit (PMU), which is coupled to an external mobile robot and receives and monitors a battery from a mobile robot, wherein the battery provides a power; a control unit, which is coupled to the PMU and operates according to the power provided by the PMU, wherein when the control unit is waken up by the PMU, the control unit passes a handshake protocol with the mobile robot to obtain a battery control of the mobile robot, the control unit determines whether the battery of the mobile robot is sufficient for device charging according to the PMU; a DC/DC converter, which is coupled to the PMU and the control unit, and converts the power into a required voltage value according to the control unit and outputs a DC power source; and a DC/AC inverter, which is coupled to the PMU and the control unit and converts the power to output an AC power source according to the control unit.

Abstract: An examination paper correction method and apparatus, an electronic device, and a storage medium are provided. The method includes: obtaining a first image of a standard examination paper; identifying an area and characters of each standard answer in the first image, and using a marking box to mark an answering area where each standard answer is located; determining position information of each marking box; obtaining a second image of an examination paper to be corrected; determining, according to the position information of each marking box of the first image, an answering area in the second image matching a position of the marking box , and using a marking box to mark the determined answering area; identifying characters of an answer to be corrected in each marking box of the second image; and comparing the characters of the standard answer with the characters of the answer to be corrected.

Abstract: A job shop scheduling method with buffer constraints based on an improved genetic algorithm (IGA) is provided, which specifically includes the following steps: firstly establishing a job shop scheduling mathematical model with buffer constraints; then performing an optimization solution of the improved genetic algorithm, and adopting a job shop scheduling process and a double-layer coding of machines to design a reasonable process adjustment method for decoding; using adaptive crossover mutation probability combined with improved cross operator to improve the algorithm and optimize a solution model. The solution with a higher precision can be obtained under the same buffer capacity, and the efficiency and convergence ability of the algorithm are improved.

Abstract: A method and a device for generating a collection of incorrectly-answered questions are provided. The method includes: acquiring an image of a marked test paper (S101); recognizing regions of respective questions in the marked test paper according to a pre-trained first region recognition model (S102); recognizing a question whose marking result is incorrect in the marked test paper as an incorrectly-answered question according to a pre-trained incorrectly-answered question recognition model (S103); and storing the region of the incorrectly-answered question in an incorrectly-answered question database to generate the collection of incorrectly-answered questions (S104). The above solution may solve the problem of low efficiency in generating the collection of incorrectly-answered questions in the prior art.

Abstract: The disclosure provides an answer correction method and a device, including: determining the target test paper that matches the test paper to be corrected; marking the area of each answer in the test paper to be corrected as the first answer set, and marking the area of each answer in the target test paper as the second answer set; matching each answer area in the first answer set and the second answer set, and adjusting the position of the answer area in the first answer set on the test paper to be corrected; for each answer area in the second answer set, determining the target answer area in the first answer set according to the position information of the answer area on the target test paper, and correcting the answer in the determined target answer area according to the answer in the answer area. The disclosure can solve the problem in the related art that the accurate position of the answer filled by the student cannot be identified, thereby affecting the correction of the answer.

Abstract: The invention provides a method and a device for identifying the number of bills and multiple bill areas in an image. The method comprises the following steps: acquiring the image containing a plurality of bills arranged in sequence; processing the image to obtain a plurality of boundary lines of each bill in the image; wherein the boundary lines comprise a first type of boundary lines which are substantially perpendicular to the bill arrangement direction; generating a long line segment which is substantially parallel to the arrangement direction of the bills and passes through the area where all the bills are located, wherein the long line segment has an intersection point with each first type of boundary line; and determining the number of bills in the image according to the lengths of the sub-line segments between the adjacent intersection points.

Abstract: Disclosed is a wireless induction power supply type light-up electric toothbrush, including a toothbrush handle body, a main body support, a mainboard, a battery, a motor, a motor sleeve, a waterproof ring, a toothbrush handle cover plate, a toothbrush head cover plate, a toothbrush head rod and a toothbrush head, wherein the toothbrush head is further provided with bristles and a toothbrush head LED panel arranged with several toothbrush head LED lamps. The toothbrush is added with a healthcare function through LED lamps, and the toothbrush head LED lamps are powered up in a wireless manner.

Abstract: The present disclosure provides a question correction method and device for oral calculation questions. The feature vector of the question to be searched is obtained according to the content of token in the stem of each question to be searched, and then the feature vector of each question to be searched is used to search for the target test paper that matches the test paper to be searched in the question bank. For the question to be searched in the form of oral calculation question, a second search is performed in the target test paper based on the feature vector of the question, and the search criterion is the minimum shortest editing distance.

Abstract: A method for identifying information carried on a sheet is disclosed. The method comprises: identifying, using one or more computing devices, each of one or more areas on the sheet based on an image of the sheet and a pre-trained first model, wherein each of the one or more areas is associated with all or part of the information carried on the sheet, and the first model is a neural network based model; and identifying, using one or more computing devices, characters in each of the one or more areas based on the image of the sheet, each of the one or more areas and a pre-trained second model so as to determine the information carried on the sheet, wherein the second model is a neural network based model.