Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

879 results about "Copying" patented technology

Copying is the duplication of information or an artifact based on an instance of that information or artifact, and not using the process that originally generated it. With analog forms of information, copying is only possible to a limited degree of accuracy, which depends on the quality of the equipment used and the skill of the operator. There is some inevitable generation loss, deterioration and accumulation of "noise" (random small changes, that have not sound) from original to copy when copies are made. This deterioration accumulates with each generation. With digital forms of information, copying is perfect. Copy and paste is frequently used by a computer user when they select and copy an area of text or content.

Multi-image forgery detection method and system based on cross-modal visual large language model

The invention provides a multi-image forgery detection method and system based on a cross-modal vision large language model, and relates to the technical field of image processing and computer vision, and the method comprises the steps: constructing a data set, and carrying out the preprocessing of the data set; according to the preprocessed data, respectively extracting visual features and language features through a pre-trained visual Transform and a language model so as to obtain cross-modal features; according to the cross-modal features, the visual features and the language features are clustered, cross-modal similarity is calculated, a matching relation is established, fusion is carried out, and fused multi-modal features are obtained; and according to the fused multi-modal features, performing adversarial training through a generator and a discriminator to generate an adversarial network. According to the method, high-precision detection and effective detection of multiple image counterfeiting types such as positioning splicing, copying and pasting, AIGC generation and the like are realized.
Owner:GUANGDONG POLYTECHNIC NORMAL UNIV

Semi-supervised semantic segmentation method based on prototype cross-image consistency

The invention discloses a semi-supervised semantic segmentation method based on prototype cross-image semantic consistency. According to the method, the problem of pseudo tag quality is optimized from the perspective of semantic consistency. Firstly, training data are fused by selecting a proper copying and pasting method according to confidence degrees, then the training data are respectively input into two networks, a prediction result is used as a cross pseudo label to obtain loss, then prototype sampling is performed on a marked data part, the marked data part is stored in a semantic library, and a first-in first-out queue updating mode is adopted to update the data. And finally, carrying out sampling and prototype similarity calculation on two output predicted correct same positions. The method comprises three main modules: 1) training to obtain a confidence score for marked data; 2) channels are added, and a space attention module pays attention to other region features; and 3) extracting the marked data prototype and the unmarked data to carry out similarity calculation.
Owner:NANJING TECH UNIV

Concentrator efficient data acquisition optimization method and system

The invention provides a concentrator efficient data acquisition optimization method and system. The method belongs to the technical field of electric power communication, and comprises the following steps: setting each reading task as an exclusive task or a parallel task, performing priority distribution on the reading tasks, and introducing a state machine for executing a first reading task, namely a to-be-read data task configured by a main station; after a system is started, whether exclusive tasks exist in a task pool or not is judged firstly, and if yes, all the exclusive tasks are executed according to a priority sequence; and after the execution of the exclusive task is completed, obtaining all parallel first copying and reading tasks in the task pool, performing parallel execution through a task scheduling mode of the state machine, and obtaining corresponding to-be-copied data items. By setting the reading task as the exclusive task or the parallel task and performing priority allocation, system resources can be utilized more efficiently, and the data acquisition efficiency is improved.
Owner:CHINA POWER HUARUI TECH CO LTD

Data integrity verification in direct memory access (DMA) transfer

In an example, a method includes copying data between a source device and a destination device to form first copied data. The method also includes, responsive to completion of the copying, performing a verify-read operation. The verify-read operation includes determining a first checksum of the first copied data, copying the data between the source device and the destination device to form second copied data, determining a second checksum of the second copied data, comparing the first checksum to the second checksum to determine a comparison result, and determining a data integrity validation result based on the comparison result.
Owner:TEXAS INSTRUMENTS INC

Electric meter intelligent dynamic complementary reading method and equipment based on big data analysis

According to the electric meter intelligent dynamic complementary reading method and device based on big data analysis, the method comprises the steps that historical data are analyzed, the reading data items and the reading priority of an electric meter are intelligently adjusted, task data sets needing complementary reading are combined into a composite task according to requirements, automatic execution is executed in the non-busy time period, and the intelligent dynamic complementary reading efficiency of the electric meter is improved. And the data acquisition efficiency and accuracy are improved. A master station system is used for issuing a configuration scheme and a task to terminal equipment, data items of different electricity meters are sorted, and deep mining and analysis are carried out based on collected data within a past set time (flexible adjustment can be carried out according to specific field requirements); and a set of personalized complementary reading configuration strategy suitable for various ammeters is deeply combed and constructed, so that intelligent dynamic complementary reading is realized. The measure not only effectively guarantees the basic data support of big data processing, but also assists a decision application level to obtain more accurate and effective results.
Owner:CSG SMART SCI&TECH CO LTD +1

Strain copyright protection system and method based on DNA watermark technology

The invention discloses a strain copyright protection system based on a DNA watermark technology. The system comprises a DNA watermark embedding module, a block chain storage and verification module, a strain authentication and tracking module and a security and privacy protection module. The invention further discloses a strain copyright protection method based on the DNA watermarking technology. The method comprises the steps of strain copyright information generation and coding, DNA watermark site selection and editing, strain screening and verification, copyright information uplink and strain use and tracking. According to the method, the copyright information of the strain is coded into the DNA watermark, the DNA watermark is embedded into the genome non-functional region of the strain, and the copyright information is stored and verified in combination with a block chain technology, so that intellectual property protection with high concealment and high safety of the biological strain is realized; illegal copying and tampering of strains are prevented, reliable copyright authentication and tracking functions are provided, and the method has wide application prospects and remarkable market value.
Owner:JIYIN CHUANGWU (SHANGHAI) TECHNOLOGY CO LTD

Automatic data transformation during copying and past operations

A method is provided. The method is executed by a transformation engine implemented as a computer program within a computing environment. The method includes selecting a transformation option to transform source data of a source field and providing an input field that prompts for an input. The source data is in a first format. The method includes transforming the source data into transformed data based on the transformation option and the input and providing the transformed data to a destination field. The transformed data is in a second format.
Owner:UIPATH INC

Text information extraction method and system based on large language model

The invention discloses a text information extraction method and system based on a large language model, and belongs to the technical field of natural language processing. Inputting the obtained text information data into the trained text information extraction model, and performing text information processing; wherein the training of the text information extraction model comprises the following steps: constructing a generative and discriminant text information extraction model based on a large language model; constructing a dialogue strategy gradient discrete prompt optimization framework to enhance the prompt stability; and constructing a noise channel matrix, and performing data enhancement and stability enhancement. According to the method, the stability of the model and the accuracy of the extraction result are effectively improved by introducing the judgment component, the balance between generation and copying is optimized by designing the dynamic generation probability calculation module and the extension word list mechanism, the stability and accuracy of text information extraction are effectively improved, and the user experience is improved. And efficient and reliable technical support is provided for scenes such as public opinion analysis and knowledge graph construction.
Owner:WUHAN UNIV

CAD three-dimensional model modeling design method and device and storage medium

The invention discloses a CAD three-dimensional model modeling design method and device and a storage medium, topological information and geometric data of three-dimensional model data are separated, so that the geometric data can be loaded / unloaded as required, dynamic optimization processing of the geometric data can be better carried out according to different design stages and design scenes, and the design efficiency is improved. Therefore, the loading resource quantity of the three-dimensional model is reduced, geometric data cache processing is further introduced, repeated loading and creation of complex geometric curve / curved surface objects are reduced, and the utilization and processing efficiency of geometric data is improved. Meanwhile, under the condition that different topological edge / surface primitives share the same bottom-layer geometric curve / curved surface, geometric data are set to be shared, so that copying and redundancy of the geometric data are avoided, the three-dimensional model loading resource quantity is further reduced, the operation efficiency of system resources is improved, and the system performance is improved. And finally, the use experience of the user is greatly improved.
Owner:CHONGQING NUOYUAN IND SOFTWARE TECHNOLOGY CO LTD

Data protection method and system based on CDP

The invention relates to the technical field of data protection, and provides a CDP-based data protection method and system, and the method comprises the steps: incremental snapshot generation: a data source agent monitors the data change on a main data source, and generates an incremental snapshot; real-time copying: the transmission engine transmits the incremental snapshot to a backup server in real time; snapshot management: the backup server manages the incoming incremental snapshot data, including operations of storage, indexing, compression and the like; and recovery operation: the user can select proper recovery options through the management console, such as a specific time point, a specific application program or a specific file level to carry out recovery operation. By adopting the method, a user can realize minimum data loss and fastest-speed recovery of key data.
Owner:HANGZHOU PEER TO PEER INFORMATION TECH CO LTD

Data replication method and device based on DMA, equipment and storage medium

The invention relates to a data replication method and device based on DMA, equipment and a storage medium. The method comprises the following steps: receiving a data copying instruction, wherein the data copying instruction comprises an initial source address, an initial destination address and a copying data length; determining an alignment difference between the initial source address and the initial destination address; an association ID table is determined according to the data copying instruction and the alignment difference, and in the association ID table, the association ID of one write request corresponds to the association ID of one or two read requests; and for one write request, obtaining a corresponding read request according to the associated ID table and the alignment difference, and writing a target result corresponding to the read request into a target storage medium according to the address of the write request. By adopting the method, the problem that the initial address is not aligned during data copying can be effectively solved.
Owner:沐曦集成电路(南京)有限公司

Disaster recovery method, device and system

A disaster recovery method, device and system can be applied to the technical field of storage. The method comprises the steps that a first data center synchronously copies backup data to a second data center through a first synchronous copying link; under the condition that a third data center is normal, the first data center asynchronously copies the backup data to the third data center through a first asynchronous copying link; under the condition that the third data center breaks down, the first data center asynchronously copies the backup data to a fourth data center through a second asynchronous copying link; wherein the first data center and the second data center are both production centers, the first data center and the second data center are located in a first area, the third data center and the fourth data center are both disaster recovery centers, and the third data center and the fourth data center are located in a second area. The disaster recovery performance of the disaster recovery system can be reduced in a stepped manner, so that user demands can be met to the greatest extent.
Owner:CHENGDU HUAWEI TECH CO LTD

Write and retire pages in QLC NAND blocks

A technique for writing data to pages in a QLC block of a QLC NAND flash memory device, where the device comprises a plurality of SLC pages organized in SLC blocks and a plurality of QLC pages organized in QLC blocks. The technique comprises storing received data in SLC pages, dividing equally a QLC block in a predefined number of sub-blocks according to a corresponding QLC page health status of the pages of the QLC block. Upon determining that SLC pages are to be copied from SLC pages to QLC pages, copying device-internal the respective SLC pages to the sub-blocks of the QLC block using device-internal cache registers, where the copying is based on an error-count aware scheme.
Owner:INTERNATIONAL BUSINESS MACHINE CORPORATION

Lock-free single-memory data sharing method and device for embedded real-time system

The invention discloses a lock-free single-memory data sharing method and device for an embedded real-time system. The method comprises the following steps: statically distributing a unique memory space for each message type; when a publisher task needs to update shared data, new data is written into a memory space of a corresponding message type, it is ensured that data writing is completed and is visible to other tasks, the atomic version number of the memory space is progressively increased, and data publishing is completed; and when the subscriber task needs to read the shared data, firstly reading the atomic version number of the memory space, then copying the content in the memory space to the local buffer area, reading the atomic version number again, and if the two version numbers are consistent, confirming that the read data is complete, otherwise, executing the reading process again. According to the method, the use of a lock can be avoided, dynamic memory allocation is avoided, copying of multiple memories is avoided, and efficient, strong-determinacy, extremely-low-memory-overhead, safe and reliable inter-task data communication is realized.
Owner:CHENGDU UNITED AIRCRAFT TECHNOLOGY CO LTD

Clipboard content pasting method and related device

The invention provides a clipboard content pasting method and a related device. The electronic equipment can identify a pasting scene and a user intention of a user for copying and pasting based on a copied page and a pasted page. According to the pasting scene and the user intention, the electronic equipment can extract the to-be-pasted content which meets the user intention and is matched with the input box in the pasting page from the copied content. The electronic equipment can provide the to-be-pasted content on the pasting page for a user to select so as to input the to-be-pasted content into an input box in the pasting page. The method can effectively improve the copying and pasting efficiency of the user and improve the copying and pasting experience of the user.
Owner:HUAWEI TECH CO LTD

Data fragmentation method applied to Internet of Things system and mid-division fusion system

The invention relates to a data fragmentation method and a middle-division fusion system applied to an Internet of Things system, and the method comprises the following steps: pulling and temporarily storing sensor data in the Internet of Things in real time, carrying out the data classification, and moving the data to a corresponding classification queue; constructing a mapping subunit for each classification queue, wherein the mapping subunits are used for copying data segments with fixed positions and fixed lengths in the classification queues according to a set time interval; carrying out fusion processing on the multiple data segments, deleting repeated data, and carrying out data fragmentation on the fused data according to a set fragmentation rule; aiming at the characteristics of real-time performance and continuity of sensor data in the Internet of Things, a unique classification queue temporary storage mode is designed, and a mapping subunit is adopted to carry out segmented copying of the data and a later fusion fragmentation method, so that real-time data is converted into fixed data, fragmentation processing can be carried out by adopting an existing fragmentation algorithm, and therefore, the real-time data can be converted into fixed data. And the system development period and the development cost are reduced.
Owner:优网云计算有限公司

Systems, methods, and apparatus for cache operation in storage devices

A device may include a storage medium, a cache medium, a buffer medium, and at least one control circuit configured to perform one or more operations including receiving a first request to access the storage medium, accessing, based on the first request, the cache medium, copying, from a portion of the storage medium to the buffer medium, data, modifying, based on the copying, an availability of the at least a portion of the storage medium, receiving a second request to access the storage medium, and accessing, based on the second request, the buffer medium. The one or more operations may include determining a location of data associated with the second request, and accessing, based on the determining, the buffer medium. The one or more operations may include receiving information about a location of data associated with the second request, and accessing, based on the information, the buffer medium.
Owner:SAMSUNG ELECTRONICS CO LTD

Data zero-copy processing method and system based on eBPF zero-trust gateway

The invention discloses a data zero-copy processing method and system based on an eBPF zero-trust gateway, and belongs to the technical field of computer network security. According to the method, an XDP program is loaded on a network card driving layer, and an AFXDP technology is combined to construct a kernel mode and user mode shared memory pool UMEM; when an original message arrives, an eBPF unit mounted by an XDP program intercepts the message in real time, a tunnel packaging space is reserved in situ in an original memory, and if the head space is insufficient, a new memory page is logically mapped from a UMEM standby buffer pool to achieve extension. Identity fingerprints are generated by extracting message feature vectors, load in-situ encryption is completed in cooperation with a kernel kTLS module, and data are prevented from being returned to a user mode for processing. According to the method, multiple copying and context switching of a kernel-user mode of a traditional SSL VPN are eliminated, the throughput is improved by 2-3 times, the delay is reduced to the microsecond level, the CPU utilization rate is reduced by 40% or above, application layer DDoS attacks are effectively defended, and the method is suitable for 5G edge computing and cloud native zero-trust gateway scenes.
Owner:JIANGSU ENLINK NETWORK TECH CO LTD

Bionic information processing method and system based on electromagnetic metasurface

The invention relates to the technical field of electromagnetic metasurfaces and bionic computing, and discloses a bionic information processing method and system based on an electromagnetic metasurface. The method comprises the following steps: S1, mapping DNA sequence information into a multi-dimensional coding state of the bionic metasurface information processing unit in an electromagnetic adjustable parameter space; s2, realizing co-evolution of the multi-dimensional coding state in space, frequency, phase and amplitude dimensions by dynamically regulating and controlling electromagnetic response parameters of the bionic metasurface information processing unit; and S3, using propagation and interference of electromagnetic waves in the diffraction neural network and a near-field coupling effect between the bionic metasurface information processing units to complete copying, logical operation and information read-write operation of the DNA sequence information. The functions of DNA coding, copying, logic calculation, information reading and writing and the like are uniformly mapped into the programmable electromagnetic metasurface platform, and cooperative processing of information in the aspects of space, electromagnetism and algorithm is achieved.
Owner:苏州仿生材料科学与工程中心

Electromagnetic signature method capable of protecting handwriting characteristics of user

The invention relates to an electromagnetic signature method capable of protecting handwriting characteristics of a user, which comprises the following steps of: S1, capturing handwriting dimension information when the user signs, generating original track data, and sending the original track data to an encryption chip; s2, the encryption chip encrypts the original track data, generates a track ciphertext, stores the track ciphertext in a paperless system, decrypts the track ciphertext to obtain the original track data when signature comparison needs to be carried out, restores the writing process of a signer, and carries out user identity comparison by identifying track characteristics of the signer; and S3, the encryption chip performs encryption processing on the original track data, processes the output features of the handwriting, peels off biological feature information, forms feature-free signature data, and generates a signature which is consistent with the original signature style but does not contain biological features on a screen according to the feature-free signature data. According to the method, copying, imitation and data tampering of handwriting features are effectively prevented, and the security level and authenticity non-replicability of the electronic signature are remarkably improved.
Owner:YUNNAN NANTIAN ELECTRONICS INFORMATION CORP +1

Data security protection method and system for large model training

The invention discloses a data security protection method and system for large model training. The core of the method is that a data safe box trusted application (TA application) is deployed in a trusted execution environment (TEE) and cooperatively works with a user-defined virtual file system driver at a host machine side, so that an end-to-end secret state data access control link is constructed. Before encryption protection of sensitive data, a measurement value (including code hash, configuration parameters and a runtime state) of a current TEE instance is submitted to a remote verification service through a data safe box TA application, and the verification service only sends the measurement value (including code hash, configuration parameters and a runtime state) of the current TEE instance to the remote verification service after confirming that the TEE environment meets a preset security policy (such as a kernel version, a software version and configuration parameter compliance). And generating a secret key encrypted by a custom virtual file system on a host machine side through derivation. And malicious copying of a system memory and a storage medium is prevented, so that the traditional attack defense capability is effectively improved.
Owner:PANOVASIC TECHNOLOGY CO LTD

Disk reconstruction method and device, equipment and storage medium

The invention provides a disk reconstruction method and device, equipment and a storage medium, relates to the technical field of disk management, is applied to a controller, and comprises the following steps: when a target member disk in a disk array breaks down, classifying each strip in the target member disk based on a reconstruction bitmap, obtaining a first strip containing the data and a second strip not containing the data; performing reconstruction operation on the data of the stripe in the new disk based on the reconstruction bitmap and the first stripe; after the reconstruction operation is completed, metadata, corresponding to the second stripe, in the reconstruction bitmap is copied to an initialization bitmap corresponding to the new disk, in the copying process, the to-be-initialized stripe in the new disk is determined by checking the reconstruction bitmap and the initialization bitmap, then initialization is conducted, and the reconstructed disk is obtained. Therefore, according to the method and the device, the data are reconstructed firstly, then the metadata are copied, and stripe initialization is performed in combination with the metadata of the reconstructed bitmap or the initialized bitmap, so that the occupation of the reconstructed bitmap can be reduced, and the efficiency is improved.
Owner:INSPUR SUZHOU INTELLIGENT TECH CO LTD

Animation copyboard

The utility model relates to the technical field of copyboards, and discloses an animation copyboard which comprises a shell, ground glass arranged on the shell, a lamp box arranged below the ground glass and located in the shell, a first clamping mechanism and a second clamping mechanism. The second clamping mechanism comprises an extrusion roller and a sliding assembly, the extrusion roller makes contact with the upper surface of the ground glass, and sliding grooves allowing the sliding assembly to slide are formed in the two sides of the shell; the sliding assembly comprises a sliding column, a connecting column and a spring; a movable cavity for the connecting column to slide is formed in the top of the sliding column, a sliding shaft matched with the sliding groove is formed on the side wall of the sliding column, the spring is fixedly installed in the movable cavity, the top end of the spring is fixedly connected to the bottom of the connecting column, and the bottom end of the spring is fixedly connected to the cavity bottom of the movable cavity. The problem that when original manuscript paper and blank paper are clamped by a copyboard in the prior art, a gap exists between the original manuscript paper and the blank paper, and the copying effect is affected is solved.
Owner:CHONGQING TECH & BUSINESS INST

Data processing method and system

The invention discloses a data processing method and system, and the method comprises the steps that a first client broadcasts a write command, the write command comprises a first identifier, the first content of a to-be-written first object and a to-be-written first version number, and the first identifier is the local maximum duration identifier of more than half of servers in a copy group; when a local maximum duration identifier of the server in the copy group is a first identifier and a maximum version number corresponding to a local first object is smaller than the first version number, first content and the first version number are written in by the server, and first information indicating agreement of the write command is sent to the first client; the first client broadcasts a submission command when receiving first information sent by more than half of servers including the first server in the copy group, and the submission command indicates that the state of the first content corresponding to the first version number is updated to be submitted. When data copying is achieved, a certain degree of error-tolerant rate is achieved, write operation delay can be reduced, and data processing efficiency is improved.
Owner:HUAWEI TECH CO LTD

Distributed large model reasoning method and system based on modular cache

The invention provides a distributed large model reasoning method and system based on modular cache, and the method comprises the steps: disassembling a prompt into modules which can be independently reused through modular division driven by Schema, and calculating the attention Key-Value state of each module in advance before reasoning for caching. When a user request arrives, the system firstly performs module analysis and cache assembly on a prompt, loads a cache as required and supplements a missed part, and then injects a complete KV state into a reasoning process. Meanwhile, a layered and distributed scheduling mechanism is designed, a global scheduler selects a target GPU based on a cache hit rate and a node load, and a local scheduler manages cache copying and elimination in a node, so that load balancing and cache multiplexing are both considered. According to the scheme, repeated calculation can be remarkably reduced, the first Token delay is reduced, the system throughput rate is increased, and the method is suitable for high-repetition prompt scenes such as code generation and long text question and answer.
Owner:ZHEJIANG UNIV

Processing method for cleaning, governance and analysis of commercial data

The invention relates to a processing method for cleaning, managing and analyzing commercial data. The processing method comprises the following steps: S1, inputting original commercial data; inputting original business data as source data of a data processing flow; s2, copying and backing up data; and the input original data is comprehensively copied, and a copy is stored in a backup system, so that the security and traceability of the data are ensured. According to the processing method for cleaning, managing and analyzing the commercial data, multiple data processing algorithms are combined, accurate classification marking and flexible screening and filtering are carried out, deep cleaning is carried out according to data types, after error data are corrected, the data are standardized, integrated and output, the data are verified, and feedback information is generated; meanwhile, the data processing flow is continuously optimized according to feedback, the data cleaning quality is improved, the high efficiency, safety, accuracy, integrity and consistency of data cleaning are ensured, and reliable technical support is provided for business data cleaning.
Owner:JINZHONG (WUXI) TECHNOLOGY CO LTD

Data sharing method and related equipment

The invention discloses a data sharing method, which is characterized in that a system-level file encryption control sharing function can be provided for a sender and sender equipment, a certain application is not required to be installed on the sender equipment, and the sender can select a file to be shared from a system through the sender equipment and set an authority control strategy; sending the information to a receiver device through one or more different sending modes; for a receiver, a receiver device can provide a data management and control function, the receiver can receive and open the shared file through the receiver device, and the system can dynamically adjust permissions of different functions of an application access system based on a permission control strategy set in the file, for example, the permissions of different functions of the application access system. A receiving party can be controlled to be incapable of performing operations such as copying, screen capturing and printing on the file, and an attacker cannot perform the operations on the file even if attacking an application for opening the file. In this way, the scene support degree, safety, eco-friendliness and the like are all improved, and the user experience is better.
Owner:HUAWEI TECH CO LTD

Graph drawing method and device and electronic equipment

The embodiment of the invention provides a graph drawing method and device and electronic equipment, in the graph drawing method, the electronic equipment responds to a vertical synchronizing signal, obtains an input callback instruction, then obtains a touch point, draws a graph according to the touch point, and draws a graph drawing result into a default frame buffer object. And then, the electronic equipment copies the graph drawing result from a default FBO to an eglImage bound FBO, obtains a callback instruction of a drawing frame in response to the vertical synchronizing signal, obtains the graph drawing result in the eglImage bound FBO in response to the callback instruction of the drawing frame, and fills the created bitmap with the graph drawing result. And finally, the electronic equipment draws the filled bitmap on the canvas. In this way, rendering can be executed on the time sequence of the original control view in the mode that off-screen rendering is combined with rapid copying, and the handwriting effect and handwriting chirality of handwriting applications can be improved.
Owner:HUAWEI TECH CO LTD

Printer

1. Name of the Design Product: Printer. 2. Use of the Design Product: For scanning, copying or printing. 3. Design Key Points of the Design Product: Lies in the shape. 4. Picture or Photograph that Best Indicates the Design Key Points: Perspective view. 5. The bottom view is an infrequently used view, so the bottom view is omitted.
Owner:ZHUHAI PANTUM ELECTRONICS CO LTD

Design method of intelligent document indication copying and clearing system based on artificial intelligence

The invention relates to a design method of an intelligent document indication copying and clearing system based on artificial intelligence, and belongs to the field of computer software. According to the handwritten endorsement content recognition method, a handwritten recognition algorithm model is established for handwritten endorsement content recognition, firstly, the handwritten endorsement area image is obtained, input is provided for handwritten content recognition, the handwritten endorsement content is recognized and extracted, manual extraction and input work is avoided, and the difficulty and measurement of manual recognition work are reduced. In order to improve the accuracy of content finally obtained by handwritten instructions, a content error correction link is added, a content error correction algorithm model is established, error detection is carried out from the two aspects of word granularity and word granularity through word segmentation, an optimal correction word is obtained through a language model, error correction is completed, and the final accuracy of handwritten content recognition is greatly improved. And through a template engine technology, the document is automatically generated according to the constructed copying and clearing template, so that the work of manually sorting and inputting the document is omitted, and the document circulation speed is greatly improved.
Owner:BEIJING INST OF COMP TECH & APPL