Automatic error correction method and system for chip processing exception

Abstract

The invention provides an automatic error correction method and system for chip processing abnormity. The method comprises the following steps: acquiring current processing data and current operation information of a chip; obtaining an abnormal operation reason and abnormal operation information based on the current operation information; obtaining abnormal trend information based on the operation abnormal information; acquiring current abnormal data based on the current processing data; acquiring a data exception reason and a data exception type based on the operation exception reason, the exception trend information and the current exception data; and performing data error correction processing on the current abnormal data based on the data exception reason and the data exception type to realize automatic error correction. According to the automatic error correction method and system for chip processing abnormity provided by the invention, the technical problem of repeated error correction in overall error correction is effectively avoided, the accuracy of error correction is improved while automatic error correction is realized, and the automatic error correction efficiency of the chip is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic error correction of chip processing anomalies, and in particular to an automatic error correction method and system for chip processing anomalies. Background Art

[0002] With the continuous upgrading of chip hardware, the chip's anti-interference ability, computing efficiency, service life, and application scope are constantly improving. However, due to the diversity of external environments and the richness of operating conditions, the application frequency of chips is increasing, and long-term operation under high voltage and high current is accompanied by frequent opening and closing actions, which leads to an increase in the probability of chip abnormalities and more complex chip abnormality types. Therefore, how to timely correct chip processing abnormalities is the current research focus.

[0003] The traditional method of correcting chip processing anomalies is to detect the chip to analyze the cause of the chip anomaly, then correct the cause of the chip anomaly to obtain a normal chip, and use the normal chip to correct the abnormal data. However, this method is slow and repeatedly processing the same data can easily cause a waste of data resources, resulting in low error correction efficiency for chip processing anomalies. Summary of the invention

[0004] The main purpose of the present invention is to provide an automatic error correction method and system for chip processing exceptions, aiming to solve the above-mentioned technical problems, realize accurate error correction of abnormal data, and improve error correction efficiency.

[0005] In order to solve the above technical problems, the present invention provides an automatic error correction method for chip processing abnormality, comprising the following steps:

[0006] Get the current processing data and current operation information of the chip;

[0007] Obtaining the cause of the abnormal operation and the abnormal operation information based on the current operation information;

[0008] Obtain abnormal trend information based on operational abnormality information;

[0009] Obtain current abnormal data based on current processing data;

[0010] Based on the cause of the abnormal operation, abnormal trend information and current abnormal data, obtain the cause of the data abnormality and the type of data abnormality;

[0011] Based on the cause and type of data anomaly, data error correction is performed on the current abnormal data to achieve automatic error correction.

[0012] The above scheme can identify the abnormal cause and abnormal type of the current abnormal data based on the abnormal trend information of the chip, and then perform data error correction, thereby refining the granularity to each abnormal data, and can realize simultaneous error correction of each abnormal data of different abnormal types and abnormal causes. This method makes it unnecessary to return and process all data as a whole when there is an abnormality in the chip, but to perform targeted and accurate error correction on each abnormal data, which not only improves the error correction timeliness and reduces the error correction cost, but also comprehensively improves the error correction efficiency of the chip in handling abnormalities.

[0013] Furthermore, the method of obtaining the cause of the abnormal operation and the abnormal operation information based on the current operation information includes: obtaining the current operation status and current operation distribution information of the chip based on the current operation information; obtaining the cause of the abnormal operation based on the current operation status; obtaining the normal operation range of the chip, and obtaining the abnormal operation information based on the current operation distribution information and the normal operation range.

[0014] Furthermore, the obtaining of abnormal trend information based on abnormal operation information includes: obtaining the abnormal operation degree and the abnormal operation trend based on the abnormal operation information and a preset abnormal analysis network; and predicting the abnormal trend information through a preset data fitting algorithm based on the abnormal operation degree and the abnormal operation trend.

[0015] Furthermore, the obtaining of current abnormal data based on current processed data includes: obtaining a current data processing task, and based on the current data processing task, screening a data detection strategy for the current processed data; generating comparative mapping data based on the data detection strategy and the current processed data; based on the current processed data and the comparative mapping data, identifying the difference data content between the current processed data and the comparative mapping data through a data detection program; and using the difference data content as the current abnormal data.

[0016] Furthermore, the method of obtaining the cause of data anomaly and the type of data anomaly based on the cause of operation anomaly, abnormal trend information and current abnormal data includes: based on the cause of operation anomaly, obtaining the type of data anomaly caused by the cause of operation anomaly through a preset abnormal database; based on the abnormal trend information and current abnormal data, screening and identifying the corresponding predicted abnormal processing result, and using the predicted abnormal processing result as the cause of data anomaly.

[0017] Furthermore, the data error correction processing is performed on the current abnormal data based on the data anomaly cause and the data anomaly type to achieve automatic error correction, including: based on the data anomaly type, querying an adaptive data error correction method in a preset error correction database; based on the data anomaly cause and the current abnormal data, identifying the degree of data anomaly through a similarity recognition strategy; based on the adaptive data error correction method, the data anomaly degree and the current abnormal data, obtaining corrected data through a preset data error correction network; based on the corrected data, performing data error correction processing on the current abnormal data to achieve automatic error correction.

[0018] The method for automatic error correction of chip processing anomalies described in the above scheme analyzes and identifies the current operation anomaly information and the current processing data step by step based on a preset anomaly analysis network, a data fitting algorithm, and a data detection program, thereby screening and identifying the current abnormal data, and then selecting an adaptive data error correction mode based on a preset error correction database to accurately and specifically correct the current abnormal data, effectively avoiding the technical problem of repeated error correction in overall error correction. The method for automatic error correction of chip processing anomalies improves the accuracy of error correction while achieving automatic error correction, and improves the efficiency of chip automatic error correction.

[0019] The present invention also provides an automatic error correction system for chip processing anomalies, characterized in that the system is used to implement the automatic error correction method for chip processing anomalies, comprising:

[0020] An information acquisition module is used to obtain the current processing data and current operation information of the chip;

[0021] An operation analysis module is used to obtain the cause of operation abnormality and operation abnormality information based on the current operation information;

[0022] An operation abnormality analysis module is used to obtain abnormal trend information based on the operation abnormality information;

[0023] A data acquisition module, used to acquire current abnormal data based on current processing data;

[0024] The data anomaly analysis module is used to obtain the cause and type of data anomaly based on the cause of operation anomaly, anomaly trend information and current anomaly data;

[0025] The automatic error correction module is used to perform data error correction processing on the current abnormal data based on the data abnormality cause and data abnormality type to achieve automatic error correction.

[0026] The above scheme works through the functions of each module. First, the acquisition module obtains the current operation information and the current processing data. Then, through the operation analysis module, the operation abnormality analysis module, the data acquisition module and the data abnormality analysis module, based on the preset abnormality analysis network, data fitting algorithm and data detection program of each module, step-by-step analysis and identification are performed, so as to obtain the cause of the current abnormal data and the type of data abnormality, so as to facilitate the chip to perform correction operations on the current abnormal data, and finally perform automatic error correction processing through the automatic error correction module and the module preset error correction database, so as to achieve accurate error correction and improve error correction efficiency.

[0027] The above scheme provides an automatic error correction method and system for chip processing exceptions. First, by analyzing the current operation information of the chip, the cause of the current chip processing exception and the operation exception information are identified, thereby identifying the abnormal trend information of the chip, improving the comprehensiveness and accuracy of the analysis of chip abnormalities; then the current abnormal data summarized by the current processing data of the chip is identified, and each abnormal data is corrected in a targeted manner. When there is an abnormality in the chip, there is no need to return all the data for processing as a whole, but each abnormal data is accurately corrected in a targeted manner, which improves the timeliness of error correction, reduces the cost of error correction, and comprehensively improves the efficiency of error correction in chip processing exceptions.

[0028] The present invention also provides a computer-readable storage medium, which includes a stored computer program; wherein the computer program controls the execution of the device where the computer-readable storage medium is located to implement the automatic error correction method for chip processing exceptions when the computer program is running.

[0029] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the automatic error correction method for chip processing exceptions is implemented.

[0030] The present invention also provides a terminal device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the automatic error correction method for chip processing exceptions when executing the computer program. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the scheme in the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0032] Figure 1 It is a flowchart of an automatic error correction method for chip processing abnormality provided by an embodiment of the present invention;

[0033] Figure 2 It is a structural schematic diagram of an automatic error correction system for chip processing abnormality provided by one embodiment of the present invention;

[0034] Figure 3 An internal structure diagram of a terminal device provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0037] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0038] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0039] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] Embodiment 1:

[0042] See also Figure 1 The embodiment of the present invention provides an automatic error correction method for chip processing abnormality, which specifically includes the following steps:

[0043] Step S101: obtaining the current processing data and current operation information of the chip;

[0044] Step S102: Acquire the operation abnormality cause and operation abnormality information based on the current operation information;

[0045] Step S103: Acquire abnormal trend information based on the abnormal operation information;

[0046] Step S104: obtaining current abnormal data based on current processing data;

[0047] Step S105: based on the operation abnormality reason, abnormal trend information and current abnormal data, obtain the data abnormality reason and data abnormality type;

[0048] Step S106: Perform data error correction processing on the current abnormal data based on the data abnormality cause and data abnormality type to achieve automatic error correction.

[0049] In the specific implementation process, in step S101, current processing data and current operation information are obtained.

[0050] Optionally, the currently processed data is data information currently being processed by the chip, and the data information being processed includes but is not limited to data information that is undergoing transmission tasks and data information that is undergoing data storage tasks; the current operating information includes but is not limited to the chip's operating speed, data read and write speed, power supply change information, power consumption change information, and temperature change information, etc.

[0051] In the specific implementation process, in step S102, based on the current operation information, the cause of the abnormal operation of the chip and the abnormal operation information of the chip are identified. Specifically, based on the current operation information, the current operation state of the chip and the current operation distribution information of the chip are identified, and based on the current operation state, the cause of the abnormal operation of the chip is queried in the chip preset database; the preset normal operation range of the chip is obtained, and based on the preset normal operation range of the chip, each abnormal operation information of the chip is filtered in the current operation distribution information.

[0052] Optionally, the abnormal operation reasons include, but are not limited to, excessive temperature, oversaturated data processing, poor chip power supply stability, abnormal chip operation rate, and high chip instantaneous power consumption. The abnormal operation information of each chip is the operation information that exceeds the preset normal operation range in the operation distribution information of the chip operation information; the current operation state includes the operation states corresponding to various operation conditions, such as normal state, operation rate fluctuation state, overheating operation state, oversaturated operation state, and high power consumption operation state; the normal operation range is the distribution fluctuation range in the operation distribution information, etc.

[0053] In this embodiment, the operating status and operating distribution information of the chip are identified through the current operating information of the chip, so as to analyze the cause of the abnormal operation of the chip and the abnormal operation information corresponding to the abnormal fluctuation range, thereby improving the recognition accuracy and efficiency.

[0054] In the specific implementation process, in step S103, abnormal trend information is obtained based on the abnormal operation information, and the abnormal trend information of the chip is identified through a preset abnormal analysis network. Specifically, based on the abnormal operation information and the preset abnormal analysis network, the abnormal operation degree and abnormal operation trend are obtained; based on the abnormal operation degree and the abnormal operation trend, the abnormal trend information is predicted through a preset data fitting algorithm.

[0055] Optionally, the abnormal analysis network is a classifier based on a reinforcement learning neural network, which can identify the abnormal operation degree of the chip in each data processing abnormality type and the abnormal operation trend of the chip based on each operation abnormality information of the chip and the position information of each operation abnormality information in the current operation distribution information. The abnormal operation trend includes but is not limited to the operation trend of each operation information of the chip, such as power consumption change trend, operation speed change trend and temperature change trend.

[0056] In this embodiment, by identifying the abnormal trend distribution information of each data processing abnormality type, the abnormal trend distribution information of the chip is obtained, which can improve the comprehensiveness and accuracy of identifying the abnormal trend distribution information.

[0057] In the specific implementation process, in step S104, based on the current processing data, abnormal data in the current processing data is identified through a preset data detection program. Specifically, the current data processing task is obtained, and based on the current data processing task, the data detection strategy of the current processing data is screened; based on the data detection strategy and the current processing data, the comparison mapping data is generated; based on the current processing data and the comparison mapping data, the difference data content between the current processing data and the comparison mapping data is identified through a data detection program; and the difference data content is used as the current abnormal data.

[0058] Optionally, the current data processing task includes a data transmission task and a data storage task, and different data processing tasks correspond to different data detection strategies. For example, the detection method of the data transmission task includes a check bit detection method, forward error correction (FEC), etc., and the detection method corresponding to the data storage task includes a detection strategy corresponding to a cyclic redundancy check (CRC), etc.

[0059] In this embodiment, by screening and adopting detection strategies corresponding to different data processing tasks, different comparison data corresponding to the current data are generated, and then the difference data between the current processed data is detected to obtain the current abnormal data, thereby improving the accuracy of recognition.

[0060] In the specific implementation process, in step S105, based on the chip's operational abnormality cause, abnormal trend information and current abnormal data, the data abnormality cause and data abnormality type are obtained, specifically: based on the operational abnormality cause, the data abnormality type caused by the operational abnormality cause is obtained through a preset abnormality database; based on the abnormal trend information and current abnormal data, the corresponding predicted abnormality processing result is screened and identified, and the predicted abnormality processing result is used as the data abnormality cause.

[0061] Optionally, if there are several abnormal data during the specific implementation process, each data abnormality type caused by the operating abnormality cause can be obtained, and based on the abnormal trend distribution information of each current abnormal data, the predicted abnormality processing result corresponding to each data processing abnormality type is identified, and in each abnormal data, the sub-abnormality data corresponding to each data processing abnormality type is screened; the data processing abnormality type corresponding to each sub-abnormality data is used as the abnormality type of each sub-abnormality data, and the predicted abnormality processing result of the data processing abnormality type corresponding to each sub-abnormality data is used as the abnormality cause of each sub-abnormality data.

[0062] Optionally, the predicted exception processing results corresponding to each data processing exception type are data results that can be obtained by continuing to execute the currently running program without human interference based on the data of each data processing exception type identified based on the exception trend distribution information of each data processing exception type; the data processing exception types include but are not limited to data storage exceptions, data transmission exceptions, data packet loss, data disorder, and data tampering.

[0063] In this embodiment, by identifying the data processing exception type corresponding to each sub-abnormal data, it is convenient to identify the abnormal type of each sub-abnormal data, and then the predicted abnormal processing result of each data processing exception type is used as the abnormal cause of each sub-abnormal data, thereby improving the intuitiveness and accuracy of identifying the abnormal cause of each sub-abnormal data.

[0064] In the specific implementation process, in step S106, based on the abnormal cause of the abnormal data and the abnormal type of the abnormal data, the data correction network is used to perform data correction processing on the current abnormal data, and the target processing result of the current processed data is obtained, so as to realize automatic error correction. Specifically, based on the data abnormality type, the adaptive data correction method is queried in the preset error correction database; based on the data abnormality cause and the current abnormal data, the degree of data abnormality is identified through the similarity recognition strategy; based on the adaptive data correction method, the degree of data abnormality and the current abnormal data, the corrected data is obtained through the preset data correction network; based on the corrected data, the abnormal data is subjected to data correction processing to realize automatic error correction.

[0065] Optionally, for each sub-abnormal data, based on the data processing abnormality type corresponding to the sub-abnormal data, an adaptive data error correction method for the sub-abnormal data is queried in a preset error correction database, and based on the predicted abnormality processing result corresponding to each sub-abnormal data and each sub-abnormal data, the abnormality degree of each sub-abnormal data is identified through a preset similarity recognition strategy; based on the adaptive data error correction method for each sub-abnormal data and the abnormality degree of each sub-abnormal data, abnormal error correction processing is performed on each sub-abnormal data through a preset data error correction network to obtain corrected data corresponding to each sub-abnormal data; each sub-abnormal data is replaced with the corrected data corresponding to the sub-abnormal data to obtain the target processing result of the currently processed data, thereby completing the data error correction processing and realizing automatic error correction.

[0066] Optionally, the data error correction network is an error correction adjustment program that converts each abnormal data into normal data; the similarity identification strategy is to identify the abnormal process value of each sub-abnormal data, and use the process percentage value corresponding to the abnormal process as the abnormal degree of the sub-abnormal data. The method of identifying the abnormal process value of each sub-abnormal data is as follows: based on each predicted abnormal processing result, identify the abnormal process of each abnormal data converted into the predicted abnormal processing result, then identify the current abnormal process node of the sub-abnormal data, and calculate the process percentage of the current abnormal process node in the abnormal process to obtain the abnormal process value of the sub-abnormal data.

[0067] Optionally, the exception database includes each data processing exception type corresponding to each operation exception cause. One operation exception cause may correspond to one or more data processing exception types. The correspondence between each operation exception cause and the data processing exception type is a correspondence obtained by staff through analysis and collation based on a large amount of experimental data, expert experience and Internet information.

[0068] Optionally, the database involved in this embodiment may include at least one of a relational database and a non-relational database, and the non-relational database may include a distributed database based on blockchain, etc., but is not limited to this.

[0069] It should be understood that, as the various steps in the flowchart involved in Example 1 are displayed in sequence according to the indication of the arrows, the steps are not necessarily executed in sequence in the order indicated by the arrows. Unless clearly stated herein, there is no strict order restriction on the execution of the steps, and these steps can be executed in other orders. Secondly, at least a portion of the steps in the flowchart involved in Example 1 may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the steps or stages in other steps.

[0070] The above embodiment provides an automatic error correction method for chip processing exceptions, which can be applied to the application environment of chip abnormal data error correction. It can be applied to terminals, servers, and systems including terminals and servers, and is implemented through the interaction between terminals and servers. Among them, the terminal can be, but is not limited to, various computers, laptops, smart phones, tablet computers, etc. Specifically, the terminal first analyzes the current operation information of the chip to identify the operation abnormality cause and operation abnormality information of the current chip processing abnormality, thereby identifying the abnormal trend information of the chip, improving the comprehensiveness and accuracy of the analysis of chip abnormalities, and then identifying the abnormal data summarized by the current processing data of the chip, so as to perform error correction processing on each abnormal data in a targeted manner, reduce the error correction cost, improve the error correction accuracy, and avoid the inefficiency of overall error correction. Further, based on the operation abnormality cause, abnormal trend information and current abnormal data of the chip, the abnormal cause and abnormal type of each abnormal data can be identified, and then data error correction can be performed, thereby refining the granularity to each abnormal data, and simultaneously correcting each abnormal data of different abnormal types and abnormal causes. The error correction timeliness and accuracy have been improved, so that when an abnormality occurs in the chip, there is no need to return and process all data as a whole. Instead, targeted and accurate error correction processing can be performed on each abnormal data, which comprehensively improves the error correction efficiency of the chip in handling abnormalities.

[0071] Embodiment 2:

[0072] See also Figure 2 , an embodiment of the present invention provides an automatic error correction system for chip processing exceptions. The implementation scheme for solving the problem provided by the automatic error correction system for chip processing exceptions is similar to the implementation scheme recorded in the automatic error correction method for chip processing exceptions, so the specific limitations in one or more embodiments of the automatic error correction system for chip processing exceptions provided below can refer to the limitations of the automatic error correction method for chip processing exceptions above, and will not be repeated here.

[0073] The automatic error correction system for chip processing abnormality comprises an information acquisition module, an operation analysis module, an operation abnormality analysis module, a data acquisition module, a data abnormality analysis module and an automatic error correction module, wherein:

[0074] An information acquisition module is used to obtain the current processing data and current operation information of the chip;

[0075] An operation analysis module is used to obtain the cause of operation abnormality and operation abnormality information based on the current operation information;

[0076] An operation abnormality analysis module is used to obtain abnormal trend information based on the operation abnormality information;

[0077] A data acquisition module, used to acquire current abnormal data based on current processing data;

[0078] The data anomaly analysis module is used to obtain the cause and type of data anomaly based on the cause of operation anomaly, anomaly trend information and current anomaly data;

[0079] The automatic error correction module is used to perform data error correction processing on the current abnormal data based on the data abnormality cause and data abnormality type to achieve automatic error correction.

[0080] It should be noted that the database involved in this embodiment may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto.

[0081] In the specific implementation process, in the automatic error correction system for chip processing exceptions described in the above solution, each module can be implemented in whole or in part through software, hardware and their combination.

[0082] Optionally, each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in the computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0083] The present embodiment provides an automatic error correction system for chip processing exceptions. The information acquisition module obtains the current processing data and current operation information of the chip, and then uses the operation analysis module to obtain the cause of the operation exception and the operation exception information, thereby obtaining the abnormal trend information through the operation exception analysis module, and then obtains the current abnormal data through the data acquisition module, and uses the data exception analysis module to analyze and obtain the cause of the data exception and the type of data exception, and finally uses the automatic error correction module to perform data error correction based on the processing results of each module described above, so as to realize automatic error correction. Through the progressive analysis of each module layer by layer, accurate error correction processing is realized for each current abnormal data, which improves the error correction efficiency and reduces the error correction cost.

[0084] Embodiment three:

[0085] See also Figure 3 The present invention provides a terminal device, including a memory and a processor, for implementing the automatic error correction method for abnormal chip processing, wherein the memory stores a computer program and the processor executes the computer program. The terminal device can be a computer device, and its internal structure diagram can be as shown in FIG. Figure 3 As shown: the computer device includes a processor, a memory, a communication interface, a display unit and an input device connected through a system bus and an I / O interface.

[0086] Furthermore, the processor of the computer device is used to provide computing and control capabilities. Optionally, the processor can be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc., but is not limited thereto.

[0087] Furthermore, the memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium.

[0088] Furthermore, the communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. Optionally, the wireless manner can be implemented through WIFI, mobile cellular network, NFC (near field communication) or other technologies.

[0089] Optionally, the display unit of the computer device may be a liquid crystal display or an electronic ink display; the input system of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0090] Optionally, the automatic error correction method and system for chip processing exceptions proposed in the present invention can be completed by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0091] Furthermore, any reference to memory, database and other media used in this embodiment may include at least one of non-volatile and volatile memory. The database involved in each embodiment provided by the present invention may include at least one of a relational database and a non-relational database.

[0092] Furthermore, non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc.; volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0093] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for automatically correcting chip processing anomalies, characterized in that: The following steps are involved: Get the current processing data and current operation information of the chip; Obtaining the cause of the abnormal operation and the abnormal operation information based on the current operation information; Obtain abnormal trend information based on operational abnormality information; Obtain current abnormal data based on current processing data; Based on the cause of the abnormal operation, abnormal trend information and current abnormal data, obtain the cause of the data abnormality and the type of data abnormality; Based on the cause and type of data anomaly, data error correction is performed on the current abnormal data to achieve automatic error correction.

2. The automatic error correction method for chip processing abnormality according to claim 1, characterized in that: The obtaining of the operation abnormality cause and the operation abnormality information based on the current operation information includes: Acquire the current operation state and current operation distribution information of the chip based on the current operation information; Acquire the cause of the abnormal operation based on the current operation status; A normal operation range of the chip is obtained, and based on the current operation distribution information and the normal operation range, operation abnormality information is obtained.

3. The automatic error correction method for chip processing abnormality according to claim 1, characterized in that: The obtaining of abnormal trend information based on abnormal operation information includes: Based on the abnormal operation information and a preset abnormal operation analysis network, obtaining the abnormal operation degree and abnormal operation trend; Based on the abnormal operation degree and the abnormal operation trend, the abnormal trend information is predicted by a preset data fitting algorithm.

4. The automatic error correction method for chip processing abnormality according to claim 1, characterized in that: The obtaining of current abnormal data based on current processing data includes: Acquire a current data processing task, and based on the current data processing task, filter a data detection strategy for the currently processed data; Based on the data detection strategy and the currently processed data, generating comparative mapping data; Based on the current processing data and the comparison mapping data, identifying the difference data content between the current processing data and the comparison mapping data through a data detection program; The difference data content is used as the current abnormal data.

5. The automatic error correction method for chip processing abnormality according to claim 1, characterized in that: The method of obtaining the cause of data anomaly and the type of data anomaly based on the cause of operation anomaly, abnormal trend information and current abnormal data includes: Based on the operation abnormality reason, obtaining the data abnormality type caused by the operation abnormality reason through a preset abnormality database; Based on the abnormal trend information and the current abnormal data, the corresponding predicted abnormal processing result is screened and identified, and the predicted abnormal processing result is used as the cause of the data abnormality.

6. The automatic error correction method for chip processing abnormality according to claim 1, characterized in that: The data error correction processing is performed on the current abnormal data based on the data abnormality cause and the data abnormality type to realize automatic error correction, including: Based on the data anomaly type, querying an adapted data error correction method in a preset error correction database; Based on the cause of the data anomaly and the current abnormal data, identifying the degree of data anomaly through a similarity identification strategy; Based on the adapted data error correction mode, the data abnormality level and the current abnormal data, corrected data is obtained through a preset data error correction network; Based on the correction data, data error correction processing is performed on the abnormal data to achieve automatic error correction.

7. An automatic error correction system for chip processing anomalies, characterized in that: A method for automatically correcting chip processing anomalies according to claims 1 to 6, comprising: An information acquisition module is used to obtain the current processing data and current operation information of the chip; An operation analysis module is used to obtain the cause of operation abnormality and operation abnormality information based on the current operation information; An operation abnormality analysis module is used to obtain abnormal trend information based on the operation abnormality information; A data acquisition module, used to acquire current abnormal data based on current processing data; The data anomaly analysis module is used to obtain the cause and type of data anomaly based on the cause of operation anomaly, anomaly trend information and current anomaly data; The automatic error correction module is used to perform data error correction processing on the current abnormal data based on the data abnormality cause and data abnormality type to achieve automatic error correction.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program; wherein, when the computer program is run, it controls the device where the computer-readable storage medium is located to execute the automatic error correction method for chip processing abnormality as described in any one of claims 1 to 6.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, an automatic error correction method for chip processing abnormality according to any one of claims 1 to 6 is implemented.

10. A terminal device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements an automatic error correction method for chip processing abnormality according to any one of claims 1 to 6 when executing the computer program.

Images