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

50 results about "DATA STORAGE FAILURE" patented technology

Ferroelectric register, and method for manufacturing capacitor of the same

The present invention discloses a ferroelectric register and a method for manufacturing a capacitor of the same. The ferroelectric register is configured to reduce probability of data storage failure due to a weak state capacitor, by connecting a plurality of capacitors in parallel in a ferroelectric capacitor unit for storing data, instead of using a single capacitor, thereby improving storage reliability and stability. In addition, the ferroelectric register obtains a data sensing margin by pumping a cell plate signal into not a power voltage level but a pumping voltage level.
Owner:SK HYNIX INC

Data storage method and server

Embodiments of the invention disclose a data storage method and server. The method includes the steps of receiving data to be stored that are sent by a client; verifying whether the data to be storedare complete; and if it is verified that the data to be stored are complete, sending the data to be stored to a cache server so that the cache server caches the data to be stored, and storing the datato be stored into a database after the data to be stored is cached. The client caches the data to be stored in the cache server, the cache server then writes into the database in batch, since the performance by the insertion into the cache is higher than the performance of the insertion into the database, the pressure on the database is reduced during the processing of concurrent requests at thepeak time of the database, the processing capability of the database is improved, the connection duration is effectively reduced, and the data storage failure is avoided.
Owner:深圳市诚壹科技有限公司

Ferroelectric register, and method for manufacturing capacitor of the same

The present invention discloses a ferroelectric register and a method for manufacturing a capacitor of the same. The ferroelectric register is configured to reduce probability of data storage failure due to a weak state capacitor, by connecting a plurality of capacitors in parallel in a ferroelectric capacitor unit for storing data, instead of using a single capacitor, thereby improving storage reliability and stability. In addition, the ferroelectric register obtains a data sensing margin by pumping a cell plate signal into not a power voltage level but a pumping voltage level.
Owner:SK HYNIX INC

Data storage method and device of distributed storage system

The invention discloses a data storage method and a device of a distributed storage system. The distributed storage system comprises a distributed document system, a local storage device in a local distributed document system and an external storage device externally connected with the distributed document system. The data storage method of the distributed storage system comprises the steps of monitoring whether a data storage fault of the external storage device occurs in the distributed document system or not and whether the fault is recovered or not; in case of the fault, storing the data needed to store during fault in the local storage device; and if the fault is recovered, storing the data stored in the local storage device during fault to the external storage device. With adoption of the technical scheme provided by the invention, problem of data loss caused by data storage fault of the external storage device in the distributed document system is avoided.
Owner:NANJING ZHONGXING XIN SOFTWARE CO LTD

Power lithium battery SOC storage method

The invention relates to the field of power battery management systems and particularly relates to a power lithium battery SOC storage method. The method comprises a step of storing operation data, wherein the step of storing the running data comprises the following sub-steps of:firstly, whether a battery management system BMS is in a power-off state or not is judged; when the state is not a power-off state; and calculating the variation of the SOC of the battery, when the variation of the SOC of the battery reaches a set value, storing residual capacity in a first storage unit in an electrically erasable programmable read-only memory (EEPROM), increasing a data storage fault mark for the residual capacity in the first storage unit, and reading back and storing data after each time of storage. And when power is off, the residual capacity is stored in the third storage unit. The method has the advantages that when the battery management system BMS stores data in normal operation, a read-back mechanism is added, and the correctness of the stored data is ensured.
Owner:力高(山东)新能源技术股份有限公司

Data storage method, device, equipment and system

The invention discloses a data storage method. The method comprises the following steps: storing data needing to be stored in the fault period in local storage equipment after monitoring that a distributed file system is in data storage fault of the external storage equipment; storing the data stored in the local storage equipment in the storage period to the external storage equipment after the fault of the external storage equipment is recovered. The problem that the data, which is stored in and to be stored in the external storage equipment, of an application program is lost since the distributed file system in the prior art is in data storage fault of the external storage equipment is solved, and the fault tolerance of the distributed storage system is effectively improved. The invention further discloses a data storage device, equipment and system, and a computer readable storage medium capable of realizing the above-mentioned technical effects.
Owner:ZHENGZHOU YUNHAI INFORMATION TECH CO LTD

Data processing method and device based on blockchain, and computer readable storage medium

The embodiment of the invention discloses a data processing method and device based on a blockchain, and a computer readable storage medium, and the method comprises the steps: obtaining a block file, and obtaining m to-be-billed data sets with different data types for a block from the block file; according to the m to-be-billed data sets, executing data writing operation on the m data storage components in parallel, and obtaining data storage results corresponding to the m data storage components; if a data storage failure result exists in the m data storage results, obtaining a block check point corresponding to the block file and component check points corresponding to the m data storage components respectively; and according to the block check point and the m component check points, determining the data storage component belonging to the component abnormal state in the m data storage components, and executing data write operation on the data storage component belonging to the component abnormal state according to the block file. According to the method, the network performance of the blockchain can be improved, and the response time of external services can be reduced.
Owner:TENCENT TECH (SHENZHEN) CO LTD

Reconstruction method and device for data storage failure

ActiveCN106502579AInsert implementationReduce throughput pressureInput/output to record carriersReconstruction methodDATA STORAGE FAILURE
The embodiment of the invention discloses a reconstruction method for a data storage failure. The reconstruction method comprises the following steps that data failed in insertion is registered in a cache region; the data registered in the cache region is aggregated according to service identification information carried by the data; the aggregated data is reinserted in batches. According to the method, by registering the data failed in insertion in the cache region and aggregating the data in the cache region, the total amount of the data failed in insertion is decreased, and the information throughput pressure on storage equipment is decreased; by reinserting the aggregated data in batches, reinserting can be sequentially conducted, the pressure on courses is reduced, and data reinsertion is achieved on the condition that normal operation of services is not affected.
Owner:GUANGZHOU HUADUO NETWORK TECH

Floating grid with multiple layer hetero quantum point structure applicable for memory unit

The invention relates to a stacked quantum dot structure floating gate which is applicable in a memory cell. The stacked quantum dot structure floating gate comprises a buffer layer at the lower part, and a first quantum dot growth layer, a first filling medium layer, an intermediate layer, a second quantum dot growth layer, a second filing medium layer and a filling protective layer at the top, which are arranged on the buffer layer. The cross section of the stacked quantum dot structure floating gate applied in a memory cell is a rectangular, oval or regular hexagonal loop. The invention further relates to a radioprotective nonvolatile memory and a micro-magnetic sensor, which are based on stacked quantum dots and take above stacked quantum dot structure floating gates as memory cells. The stacked quantum dot structure floating gate, the radioprotective nonvolatile memory and the micro-magnetic sensor which are based on the stacked quantum dot structure floating gates, have radiation resistances and overcome the problems of electricity leakage and data storage failure caused by the coupling of the quantum dots.
Owner:INST OF PHYSICS - CHINESE ACAD OF SCI +1

Data protection method, device, equipment and system and computer readable storage medium

The invention discloses a data protection method, which comprises the following steps: when a data storage instruction is received, starting a fault monitoring process; monitoring storage process information in real time through the fault monitoring process; judging whether a data storage fault occurs or not according to the storage process information; if the data storage fault occurs, starting afault processing process, and storing the target storage data to a local storage device through the fault processing process; according to the data protection method, the stored data in the mass datastorage process can be effectively protected, data loss is avoided, and the fault tolerance of the distributed system is further improved. The invention further discloses a data protection device, equipment and system and a computer readable storage medium which all have the above beneficial effects.
Owner:INSPUR BEIJING ELECTRONICS INFORMATION IND

Data redundancy processing method and device and storage medium

The embodiment of the invention provides a data redundancy processing method and device and a storage medium. The method comprises the steps of: obtaining and mapping IO data into a set, wherein the set comprises a main node and erasure code nodes corresponding to the main node, and the IO data are respectively mapped and stored into the main node and the erasure code nodes corresponding to the main node; the set receives an IO data processing request and executes IO data processing in the set, wherein the IO data processing comprises write-in IO processing and read-out IO processing; detecting whether a main node in the set and an erasure code node corresponding to the main node have the IO data storage fault or not; if the IO data storage fault exists, the IO data storage fault is eliminated, and then IO data redundancy processing is completed; according to the IO data redundancy processing method and device, whether the IO data can be read and written or not in redundancy processingcan be detected, and then the IO data is recovered when the IO data is lost and fails, so that the integrity of the whole IO data redundancy processing is better.
Owner:PING AN TECH (SHENZHEN) CO LTD

Data storage fault processing method and device, storage medium and processor

PendingCN113312206ARealize the technical effect of thermal repairTo achieve the purpose of thermal schedulingRedundant operation error correctionData synchronizationVideo memory
The invention discloses a data storage fault processing method and device, a storage medium and a processor. The method comprises the steps of, under the condition that it is determined that a hardware fault occurs in an initial physical address space, applying a target physical address space to be used from a plurality of backup physical address spaces, wherein, the initial physical address space and the target physical address space are data storage spaces distributed by a processor for a virtual processing unit; corresponding the initial physical address space to a logic address space currently used by the virtual processing unit; suspending the scheduling of the virtual processing unit; synchronizing data stored in the initial physical address space to a target physical address space; and based on the mapping relationship between the currently used video memory address space and the target physical address space, recovering the scheduling of the virtual processing unit. The technical problem that the hardware fault of the virtual processing unit cannot be subjected to hot repair is solved.
Owner:ALIBABA GRP HLDG LTD

Apparatus and method for automatically positioning fluorescent magnetic powder defect of wheel

The invention provides an apparatus and method for automatically positioning a fluorescent magnetic powder defect of a wheel. The method comprises the following steps: collecting a wheel image of a fluorescent magnetic powder flaw detection area, extracting a defect area in the wheel image, judging a defect type, and recording a collection time of the wheel image; and synchronously rotating, by acode collector with the wheel to generate coded data corresponding to a rotation distance of the wheel, determining the rotation distance of the wheel according to the coded data, determining the position information of the wheel in combination with a preset rotating speed of the wheel, and matching a coding time corresponding to the coded data with the collection time of the wheel image, and andobtaining the position information of the wheel corresponding to the wheel image. By adoption of the apparatus and method provided by the invention, the problems of excessive artificial participation,severe detection environment and long time defect data storage failure in the traditional fluorescent magnetic powder detection can be solved, image data with uniform external brightness can be obtained by adaptively adjusting a purple light lamp, and artificial recheck can be performed to well judge whether the wheel surface has defects.
Owner:BEIJING JIAOTONG UNIV

Data cache access method and device of multi-core processor

The invention provides a data cache access method and device of a multi-core processor, and relates to the technical field of computer processors. The method comprises the following steps: accessing a data cache according to an access instruction, and responding to the access instruction to hit access data and write back the access data, or responding to the access instruction to not hit the access data, fetching back-filling data from a memory access failure queue and forwarding the back-filling data to the access queue. Accessing the data cache according to the data storage instruction, writing the stored data into the data cache in response to the access hit of the data cache, or calling a stored data retransmission unit in response to the access miss of the data cache; and sending a data storage failure request to the memory access failure queue, and taking back the backfill data and / or authority by the memory access failure queue. According to the method, the flexibility of the processing mode of the data cache access pipeline on the memory access instruction and the external consistency request can be improved, the access parallelism degree is improved, and the hardware resource utilization rate of the processor is increased.
Owner:BEIJING VCORE TECH CO LTD

Data storage method, system, device and medium

The invention discloses a data storage method, a system, a device and a medium. Acquiring message data generated by the business process and storing the message data in the target slave; When receiving the target slave feedback data storage failure message, the message data and the related failure information are stored in the exception list as the exception information. Returns to execute the data storage operation until the storage end condition is reached, and writes all the exception information contained in the exception list to the directory log; The target exception information in the directory log is extracted, the message data in the target exception information is processed, and the processed message data is restored based on the failure information of the message data. The method provided by the embodiment of the invention realizes that the storage result of each message data is monitored when the batch data is stored, and when the message data storage fails, the erroneous message data is stored again, so as to ensure the consistency of the message data stored by each slave when the same message data is stored by different slave computers.
Owner:RUN TECH CO LTD BEIJING

High-frequency data storage system based on multi-thread asynchronous communication

The invention provides a high-frequency data storage system based on multi-thread asynchronous communication. The system comprises a sensor group, a data processing module and a database; the sensor group is arranged on the motion carrier, and the data processing module and the database are arranged on the control box; the sensor group is connected with the data processing module through an optical fiber; data collected by the sensor group is processed by the data processing module and then written into the database. In the present invention, the data receiving module asynchronously receives data sent by the sensor group by adopting a communication technology; data in high-frequency communication is accurately received; the data pool is introduced, so that the problems of process blockage,data storage failure and the like caused by frequent database operation are avoided; after the sensing module triggers the data storage module, all data can be transmitted to the data storage module,the data pool is emptied, unnecessary data volume is reduced, and the working efficiency is improved.
Owner:CHINA NONFERROUS METAL CHANGSHA SURVEY & DESIGN INST CO LTD

Methods for optimizing laptop storage performance

The present invention discloses a method for optimizing laptop computer storage performance, relating to the technical field of storage performance optimization. This method evaluates the status of a target storage area, promptly identifying and alerting users to storage anomalies, thereby preventing data loss or data storage failure. Furthermore, during the storage process, the initial storage speed and the speed of removing data requiring clearing are optimized to ensure efficient data writing and management. Furthermore, dynamic monitoring and adjustment of storage status help users maintain system stability and fluidity, extend device life, and enhance the overall user experience, effectively resolving performance bottlenecks encountered during laptop computer data storage.
Owner:WUHAN PANSHENG DINGCHENG TECH CO LTD

Data storage method and device based on distributed system and storage node

The embodiment of the invention discloses a data storage method and device based on a distributed system and a storage node. The method comprises the following steps: if an available storage node does not exist in a distributed system in an original storage table fragment pointed by to-be-stored data, selecting a corresponding target storage table fragment from survival storage table fragments with the available storage node; and storing the to-be-stored data through available storage nodes existing in the distributed system through the target storage table fragments. According to the method provided by the embodiment of the invention, comprehensive disaster tolerance of data storage in the distributed system can be realized without increasing the number of storage nodes specified by the storage table fragments during multi-copy storage, so that the normal overhead of data storage in the distributed system is ensured; the problem of data storage failure caused by failure of each storage node specified by the original storage table fragment in the distributed system is avoided, and the success rate and reliability of data storage disaster tolerance in the distributed system are improved.
Owner:BIGO TECH PTE LTD

Motor controller fault snapshot data acquisition system and data acquisition analysis method

The invention discloses a motor controller fault snapshot data acquisition system and a data acquisition analysis method, the system comprises a motor controller and an upper computer, the motor controller is internally provided with a main control chip, and the main control chip comprises an RAM area, an EEPROM and a CAN communication module; the data acquisition and analysis method comprises the steps of fault data recording, fault data storage, fault data extraction and fault data analysis. According to the invention, additional high-cost car following equipment is not needed, batch controller application is supported, and time and resource costs are reduced; the EEPROM is powered down to store data, so that on-site power protection is not needed, and the use of customers is not influenced; data sampling enables control to prevent data coverage, upper computer off-line analysis improves fault positioning efficiency, and the method has high practicability and adaptability.
Owner:EWEA-TECH CO LTD

Ram Detection Method Based on March Algorithm

ActiveCN109887539BGuaranteed uptimeReduce storage failuresStatic storageMarch algorithmFailure rate
The invention discloses a RAM detection method based on the March algorithm, comprising: powering on the MCU, completing system initialization and external device parameter configuration; entering the system and judging whether the ROM detection and the RAM detection pass; if not, powering off the MCU ; If yes, configure the Bq76930 chip information and protection parameters, and configure the external device parameter information; read the two Bq76930 chip information, and judge whether it exceeds the set error value; if yes, turn off the MOS tube or blow the FUSE; if not , then clear the watchdog counter and perform other tests; if the test is abnormal, turn off the MOS tube or blow the FUSE; if the test is normal, turn on the MCU output flag to complete the test. The invention adopts the March algorithm for RAM detection. When performing RAM detection, the detection of RAM can be completed, and the detection efficiency is relatively high. By judging the failure rate of the Bq76930 chip, the data integrity rate of the memory detection logic can be guaranteed, and data storage failures can be reduced. .
Owner:GUANG DONG GREENWAY TECH CO LTD

DTU power-off retention circuit and control method based on supercapacitor

The present invention relates to a supercapacitor-based DTU power-off retention circuit and control method, comprising: a 5V system power supply and a subsequent circuit, wherein the 5V system power supply is connected to the input of a switching circuit; a first output of the switching circuit is connected to the subsequent circuit; a second output of the switching circuit is connected to the input of a supercapacitor circuit; the output of the supercapacitor is connected to the input of a DC-DC boost circuit; and the output of the DC-DC boost circuit is connected to a subsequent circuit. By integrating a supercapacitor with a synchronous boost conversion circuit, the present invention provides an efficient and stable power supply solution. When the main power supply of a DTU device fails, the system can provide the required power through the supercapacitor circuit in the shortest possible time, ensuring the device's continued operation and completing necessary data storage, fault detection, and alarm functions, thereby avoiding the loss of historical data and improving the reliability and data security of distribution network automation terminals.
Owner:BEIJING QINGCHANG POWER TECH CO LTD +1

Write-time copy method and device based on data security

The invention provides a write-time copy method and device based on data security. The method comprises the following steps of intercepting an I / O request packet; checking whether the I / O request packet contains a flag indicating that the operation object is allowed to be edited; in the presence of the flag, subjecting the operation object to a storage process in which the target address is a specified area. The invention firstly migrates the file to the designated storage position when the user opens the file, so that the file can be completely and continuously stored in the designated position in the editing process, thereby avoiding the problems of data storage failure and data unidentifiable use caused by incomplete data, and ensuring the normal use of the dump file.
Owner:ANTAIOS (BEIJING) INFORMATION TECH

Floating grid with multiple layer hetero quantum point structure applicable for memory unit

The invention relates to a stacked quantum dot structure floating gate which is applicable in a memory cell. The stacked quantum dot structure floating gate comprises a buffer layer at the lower part, and a first quantum dot growth layer, a first filling medium layer, an intermediate layer, a second quantum dot growth layer, a second filing medium layer and a filling protective layer at the top, which are arranged on the buffer layer. The cross section of the stacked quantum dot structure floating gate applied in a memory cell is a rectangular, oval or regular hexagonal loop. The invention further relates to a radioprotective nonvolatile memory and a micro-magnetic sensor, which are based on stacked quantum dots and take above stacked quantum dot structure floating gates as memory cells. The stacked quantum dot structure floating gate, the radioprotective nonvolatile memory and the micro-magnetic sensor which are based on the stacked quantum dot structure floating gates, have radiation resistances and overcome the problems of electricity leakage and data storage failure caused by the coupling of the quantum dots.
Owner:INST OF PHYSICS - CHINESE ACAD OF SCI +1

Data encryption writing method, device and equipment based on trusted key and medium

Embodiments of the present disclosure disclose a data encryption writing method and device based on a trusted key, equipment and a medium. A specific implementation of the method comprises: determining transmission private key information corresponding to data writing request information based on the data writing request information; performing writing lock state detection processing to obtain writing lock state detection information; in response to determining that the writing lock state detection information represents that writing has not been performed, performing decryption operation on encrypted writing data based on the transmission private key information to obtain decrypted writing data; generating storage key information; performing storage encryption processing on the decrypted writing data based on the storage key information to obtain encrypted storage writing data; generating storage location information corresponding to the encrypted storage writing data; storing the encrypted storage writing data to a storage location corresponding to the storage location information; and sending a data writing feedback message representing that data writing is successful to a mobile terminal. The implementation reduces the number of data storage failures.
Owner:HARBIN ENG UNIV

Data processing method and device, electronic equipment, and storage medium

The application provides a data processing method and device, an electronic device and a storage medium. The method comprises the following steps: when a user exits an application, storing application data corresponding to the user in a cache of a server corresponding to the application, and simultaneously, sending the application data corresponding to the user to a first database for storage; if the storage in the first database fails, sending the application data corresponding to the user to a second database for storage. In the data storage process, the application embodiment increases the cache storage, so that the reading pressure on the first database can be reduced to a certain extent when the stored data is acquired subsequently. In addition, the second database is added, so that when the storage of the application data in the first database fails, the application data can be sent to the second database for storage, thereby improving the robustness of the system and reducing the probability of data storage failure.
Owner:NETEASE (HANGZHOU) NETWORK CO LTD

A blockchain-based multi-backup searchable encryption system and method for data

This invention discloses a blockchain-based multi-backup searchable encryption system and method, comprising: a system administrator for executing system initialization, approving registration requests from data providers and users, deploying blockchain contracts and corresponding nodes, and distributing keys; a data provider for generating data tags, encrypting data, uploading it to the blockchain, and holding servers accountable for malicious fraud; a user for sending search requests and pre-paying search fees; a cloud server consisting of multiple cloud servers; and a blockchain consisting of smart contracts and corresponding deployment nodes to ensure fair transactions between users and the cloud server. Compared with existing technologies, by employing multiple servers to back up data and using the internal fairness and non-repudiation of blockchain and smart contracts to punish fraudulent behavior by users and servers, this invention ensures the fair flow of funds between the transacting parties, avoids the problem of single-data storage failures, and guarantees the fairness of the user search process and the effectiveness of search results.
Owner:CHENGDU UNIVERSITY OF TECHNOLOGY

Flash memory unit and manufacturing method thereof

PendingCN111933644AImprove the problem of insufficient coverageSolve the problem of saving failureSolid-state devicesSemiconductor devicesDATA STORAGE FAILUREMechanical engineering
The invention provides a flash memory unit and a manufacturing method thereof. The manufacturing method of the flash memory unit comprises the steps of firstly, providing a substrate with an isolationside wall, wherein a recess exists in the bottom of the isolation side wall; then forming a first contact etching stop layer on the substrate, and filling the recess with the first contact etching stop layer; secondly, etching the first contact etching stop layer, and reserving the first contact etching stop layer in the recess; and finally, forming a second contact etching stop layer on the substrate and the first contact etching stop layer in the recess. By forming the contact etching stop layer twice, the problem that the bottom of the isolation side wall is insufficiently covered can be solved, and then the problem of data storage failure of the flash memory unit can be solved.
Owner:NEXCHIP SEMICON CO LTD

Data storage fault diagnosis method and system

The invention provides a data storage fault diagnosis method and system, and relates to the technical field of distributed storage. The method comprises the steps of obtaining an I / O request responsecondition of a storage node; inputting the I / O request response condition of the storage node into a pre-created distributed storage node running state model, and calculating a function relationship of I / O request responses of each storage node in different links based on the I / O request response condition of each storage node and the link where each storage node is located; obtaining the health degree of each storage node according to the function relationship of the I / O request response of each storage node in different links, and diagnosing the cause of the I / O fault of each storage node based on the health degree of the storage node; and sending the cause of the I / O fault of the storage node to a client. According to the method, automatic health degree monitoring is carried out on themultiple storage nodes of the large distributed storage cluster, and the storage faults of the storage nodes are diagnosed based on the health degree, so that the labor force required by manual operation and maintenance is reduced.
Owner:国久大数据股份有限公司