A data identification and processing method, system and storage medium based on large model

Abstract

The present application relates to the technical field of data processing, and discloses a method, system and storage medium for data identification and processing based on a large model. The method includes obtaining a standard information set and storing it in a large model, identifying a real-time information set, filtering a filtered information set, evaluating an evaluation information set and organizing to obtain a data identification and processing result. The system and the storage medium both correspond to the method. The present application uses standard information and a large model to improve the ability to identify and process massive amounts of data to improve applicability, combines identification and processing through a closed loop of identification, filtering, evaluation and organization to optimize singularity, mines the intrinsic relationship of data through a data chain and corresponding evaluation and organization to optimize isolation, and outputs data and the corresponding filtering and evaluation process to improve interpretability. Finally, data identification and processing based on a large model is achieved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and specifically to a data identification and processing method, system and storage medium based on a large model. Background Art

[0002] Massive amounts of data are generated with the rapid development of the Industrial Internet of Things. In order to improve the application level of the Industrial Internet of Things, it is of research significance to optimize data recognition and processing. However, looking at the existing data recognition and processing technologies, the inventors found the following technical problems:

[0003] 1. Lack of ability to identify and process massive amounts of data restricts its applicability;

[0004] 2. There is a phenomenon of only identifying or only processing, which leads to its singularity;

[0005] 3. Lack of mining the intrinsic relationship of data leads to its isolation;

[0006] 4. The recognition processing results are mostly output in the form of indicators, which restricts their interpretability.

[0007] Chinese patent number CN202311175388.4 discloses a data processing method for industrial Internet of Things based on deep learning, including the following steps: data collection, data preprocessing, building a deep learning model, model training, model application, and result analysis; the built convolutional neural network includes an input layer, a convolution layer, an activation layer, a pooling layer, a fully connected layer, and an output layer, and has powerful image recognition and classification capabilities. After operations such as convolution, pooling, and full connection, tasks such as classification and prediction can be performed, and rapid and large-scale calculations can be performed; the model is repeatedly trained to increase the amount of data processed by the model, and the limit value of the data that can be processed is obtained. When the data overload model cannot be fully processed, the data can be segmented and sorted, and the data can be processed according to the priority order. However, the invention only realizes the sequential processing based on data priority, and the data recognition and processing capabilities are general.

[0008] In summary, the existing technology urgently needs a technical solution for data recognition and processing based on large models. Summary of the invention

[0009] The purpose of this application is to provide a data recognition and processing method, system and storage medium based on a large model to solve the technical problems raised in the above background technology.

[0010] To achieve the above objectives, this application discloses the following technical solutions:

[0011] In a first aspect, the present application discloses a data recognition and processing method based on a large model, the method comprising:

[0012] S1: Obtain the standard information set corresponding to each data and store it in the preset large model;

[0013] S2: Collect and identify real-time information sets;

[0014] S3: filtering the real-time information set to obtain a filtered information set;

[0015] S4: Evaluate the filtering information set to obtain an evaluation information set;

[0016] S5: Organizing the data corresponding to the evaluation information set to obtain a data identification processing result;

[0017] The standard information set includes data name, data type, data rating, data threshold and data chain;

[0018] The macro model is used for performing the identification, the filtering, the evaluation and the organization;

[0019] The identification is used to identify the real-time information set of each real-time data collected;

[0020] The real-time information set includes the data name, the data type, the data real-time value and the data link;

[0021] The filtering is used to perform data processing on the real-time information set based on the standard information set;

[0022] The evaluation is used to perform data processing on the filter information set based on the standard information set;

[0023] The organization is used to perform data processing on the data corresponding to the evaluation information set.

[0024] Preferably, the data rated value is specifically the data value under rated conditions of the content that the data refers to; and the data chain is specifically obtained by associating related data in a chain form.

[0025] Preferably, the step of identifying specifically includes:

[0026] A1: Get the collected real-time data and corresponding data names;

[0027] A2: Retrieve the corresponding standard information set based on the data name;

[0028] A3: using the standard information set obtained in step A2 to normalize the data type and the data link corresponding to each real-time data obtained in step A1, and normalizing the real-time data value to the real-time value of the data based on the data form of the data rated value and the data threshold;

[0029] A4: Pack the data name obtained in step A1 and the data type, the data real-time value and the data link obtained in step A3 into a real-time information set and output it.

[0030] Preferably, the filtering step is specifically as follows:

[0031] B1: Acquire the real-time information set and the standard information set, and establish a corresponding relationship based on the data name;

[0032] B2: Determine whether the real-time value of the data meets the corresponding data threshold, if yes, execute step B3, otherwise execute step B4;

[0033] B3: Calculate the data real-time value minus the data rated value to obtain the data difference;

[0034] B4: Outputs a preset data anomaly value representing data anomaly;

[0035] B5: Use the data difference value or the data abnormal value to replace the corresponding data real-time value to obtain the filtering information set.

[0036] Preferably, the step of evaluating specifically includes:

[0037] C1: Acquire the filter information set and the standard information set, and establish a corresponding relationship based on the data name;

[0038] C2: Determine whether there is an abnormal value in the data, if yes, execute step C3, otherwise execute step C4;

[0039] C3: using the data outlier value to obtain the corresponding data chain, and based on the data chain, capturing all the data outliers in the data chain, and obtaining a first evaluation result based on the number of data in the data chain and the number of all data outliers in the data chain;

[0040] C4: using the data difference to obtain the corresponding data link, and based on the data link, capturing all the data differences in the data link, and obtaining a second evaluation result based on the number of data in the data link and the data difference;

[0041] C5: Writing the first evaluation result or the second evaluation result into the corresponding filtering information set to obtain the evaluation information set.

[0042] Preferably, when the first evaluation result exists in the evaluation information set, the organizing step specifically includes:

[0043] D1: Obtain each evaluation information set corresponding to the data link;

[0044] D2: using the data difference or the data outlier and combining it with the first evaluation result, obtaining a first organization result; the first organization result is used to characterize the influence degree of the corresponding data on the data chain;

[0045] D3: sorting the corresponding data based on the first organization result and outputting the data and the corresponding identification, filtering and evaluation processes in sequence according to the sorting results.

[0046] Preferably, when the second evaluation result exists in the evaluation information set, the organizing step specifically includes:

[0047] E1: Obtain each evaluation information set corresponding to the data link;

[0048] E2: using the data difference or the data outlier and combining it with the second evaluation result, obtaining a second organization result; the second organization result is used to characterize the influence degree of the corresponding data on the data chain;

[0049] E3: sorting the corresponding data based on the second organization result, and outputting the data and the corresponding identification, filtering and evaluation processes in sequence according to the sorting results.

[0050] Preferably, the output of step D3 precedes the output of step E3.

[0051] In a second aspect, the present application discloses a data recognition and processing system based on a large model, the system is applicable to the data recognition and processing method based on a large model described above, and the system comprises:

[0052] An acquisition module, wherein the acquisition module is configured to acquire a standard information set corresponding to each data and store it into a preset macro model;

[0053] An identification module, wherein the identification module is configured to collect and identify a real-time information set;

[0054] A filtering module, wherein the filtering module is configured to filter the real-time information set to obtain a filtered information set;

[0055] An evaluation module, wherein the evaluation module is configured to evaluate the filtering information set to obtain an evaluation information set;

[0056] An organization module, wherein the organization module is configured to organize the data corresponding to the evaluation information set to obtain a data identification processing result;

[0057] The standard information set includes data name, data type, data rating, data threshold and data chain;

[0058] The macro model is used for performing the identification, the filtering, the evaluation and the organization;

[0059] The identification is used to identify the real-time information set of each real-time data collected;

[0060] The real-time information set includes the data name, the data type, the data real-time value and the data link;

[0061] The filtering is used to perform data processing on the real-time information set based on the standard information set;

[0062] The evaluation is used to perform data processing on the filter information set based on the standard information set;

[0063] The organization is used to perform data processing on the data corresponding to the evaluation information set.

[0064] In a third aspect, the present application discloses a storage medium having a computer program stored thereon, which, when executed by a processor, implements the large model-based data recognition and processing method as described above.

[0065] Beneficial effects: The data recognition and processing method, system and storage medium based on a big model of the present application improve the recognition and processing capabilities of massive data through standard information and big models to improve applicability, realize the combination of recognition and processing through a closed loop of recognition, filtering, evaluation and organization to optimize singularity, realize the mining of the intrinsic relationship of data through data chains and corresponding evaluation and organization to optimize isolation, and improve interpretability through output data and corresponding filtering and evaluation processes, thereby realizing data recognition and processing based on a big model. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0067] Figure 1 A flowchart of a data identification and processing method based on a large model provided in an embodiment of the present application;

[0068] Figure 2 A structural block diagram of a large model-based data recognition and processing system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] The technical solutions in the embodiments of the present application are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0070] In this article, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprising..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0071] In a first aspect, this embodiment discloses Figure 1 A data recognition and processing method based on a large model is shown, the method comprising:

[0072] S1: Obtain the standard information set corresponding to each data and store it in the preset large model;

[0073] S2: Collect and identify real-time information sets;

[0074] S3: filtering the real-time information set to obtain a filtered information set;

[0075] S4: Evaluate the filtered information set to obtain an evaluation information set;

[0076] S5: Organizing the data corresponding to the evaluation information set to obtain a data identification processing result;

[0077] The standard information set includes data name, data type, data rating, data threshold and data chain;

[0078] Large models are used to identify, filter, evaluate and organize;

[0079] Identification is used to identify the real-time information set of each real-time data collected;

[0080] The real-time information set includes data name, data type, data real-time value and data link;

[0081] Filtering is used to process the real-time information set based on the standard information set;

[0082] Evaluation is used to perform data processing on the filtered information set based on the standard information set;

[0083] The organization is used to process the data corresponding to the evaluation information set.

[0084] It should be noted that the standard information set of this embodiment is to use existing data annotation technology to perform corresponding annotations on the data, which is well known to those skilled in the art. For example, assuming that the data name is the production volume per unit time, the corresponding standard information set is production capacity data (data type), 100 pieces / day (data rated value), 80 pieces / day (data threshold) and equipment failure rate~personnel attendance rate~raw material attack rate (data link), thereby realizing the mining of data associations; the construction of the large model of this embodiment adopts existing machine learning technology, aiming to realize the corresponding recognition, filtering, evaluation and organization functions; in this embodiment, the process of data recognition and processing is the process of recognition, filtering, evaluation and organization performed by the large model.

[0085] Based on the above, this embodiment provides accurate data reference for data identification and processing by acquiring standard information sets, provides necessary technical support for data identification and processing by acquiring preset big models, and implements data identification and processing based on big models through identification, filtering, evaluation and organization performed by big models, thereby providing the applicability and interpretability of data identification and processing and optimizing its singularity and isolation.

[0086] Specifically, the data rated value refers to the data value under rated conditions of the content that the data refers to; the data chain refers to the data obtained by linking related data in a chain form.

[0087] It should be noted that the data rating of this embodiment is formulated based on the actual data of the corresponding industrial Internet of Things and corresponds to the data threshold, which is well known to those skilled in the art. For example, if the rated operating temperature of a certain device is 25°C, the corresponding data value 25°C under the rated operating temperature is 40°C; if the duration of a certain production link is 1h, the corresponding data value 1h under the rated duration is [0.8h, 1.2h], etc.; the data link of this embodiment is formulated based on the association of the actual data of the corresponding industrial Internet of Things, which is well known to those skilled in the art. For example, if the operating voltage, operating current and operating temperature of a certain device affect the equipment failure rate, then the operating voltage~operating current~operating temperature~equipment failure rate is a data link.

[0088] Based on the above, the data rating and data threshold of this embodiment provide accurate data reference for filtering, and the characterization of data association is realized through the data chain, so as to improve the recognition and processing capabilities of massive data to improve applicability and optimize isolation based on the mining of the intrinsic relationships of the data.

[0089] Specifically, the identification steps include:

[0090] A1: Get the collected real-time data and corresponding data names;

[0091] A2: Retrieve the corresponding standard information set based on the data name;

[0092] A3: using the standard information set obtained in step A2 to normalize the data type and data chain corresponding to each real-time data obtained in step A1, and normalizing the real-time data value to the real-time value of the data based on the data form of the data rated value and the data threshold;

[0093] A4: Pack the data name obtained in step A1 and the data type, data real-time value and data link obtained in step A3 into a real-time information set and output it.

[0094] It should be noted that in this embodiment, the real-time data values ​​are normalized to the real-time values ​​of the data using the existing normalization technology, thereby providing data for direct calculation for filtering, evaluation and organization.

[0095] Based on the above, this embodiment obtains a real-time information set through identification, provides a data basis for filtering, evaluating and organizing, and realizes the processing of massive amounts of data, thereby improving applicability.

[0096] Specifically, the filtering steps are as follows:

[0097] B1: Obtain the real-time information set and the standard information set, and build a corresponding relationship based on the data name;

[0098] B2: Determine whether the real-time data value meets the corresponding data threshold, if yes, execute step B3, otherwise execute step B4;

[0099] B3: Calculate the real-time value of the data minus the rated value of the data to obtain the data difference;

[0100] B4: Outputs a preset data anomaly value representing data anomaly;

[0101] B5: Use data difference or data abnormal value to replace the corresponding data real-time value to obtain the filtered information set.

[0102] It should be noted that the judgment of whether the real-time data value meets the corresponding data threshold in this embodiment is based on the actual data of the corresponding industrial Internet of Things and corresponds to the data threshold, which is well known to those skilled in the art. For example, assuming that the real-time data value refers to the attendance rate of the number of employees is 75%, and its corresponding data threshold is 80%, then the real-time data value is less than the corresponding data threshold, that is, it does not meet the corresponding data threshold. For example, assuming that the real-time data value refers to the humidity of the working environment of the equipment, the working humidity is 45%, and its corresponding data threshold is [40%, 60%]. At this time, the real-time data value belongs to the corresponding data threshold, that is, it meets the corresponding data threshold.

[0103] In this embodiment, the calculation formula for calculating the data difference by subtracting the data rated value from the real-time value of the data is:

[0104]

[0105] in, is the real-time value of the data, is the data rating, is the data difference.

[0106] In this embodiment, the data outlier is formulated based on the actual data of the corresponding industrial Internet of Things, which is well known to those skilled in the art, for example, by setting a null value of the character "null".

[0107] Based on the above, this embodiment achieves data filtering by obtaining data differences or data outliers by comparison with data thresholds or data rated values. The obtained filtered information set reduces the amount of data that needs to be evaluated and organized, provides an accurate data basis for evaluation and organization, and provides necessary data references for improving interpretability.

[0108] Specifically, the evaluation steps include:

[0109] C1: Obtain the filter information set and the standard information set, and build a corresponding relationship based on the data name;

[0110] C2: Determine whether there are data outliers. If yes, execute step C3; otherwise, execute step C4.

[0111] C3: using the data outlier to obtain the corresponding data chain, and based on the data chain, capturing all the data outliers in the data chain, and obtaining a first evaluation result based on the number of data in the data chain and the number of all the data outliers in the data chain;

[0112] C4: using the data difference to obtain the corresponding data chain, and based on the data chain, capturing all the data differences in the data chain, and obtaining a second evaluation result based on the number of data in the data chain and the data difference;

[0113] C5: Write the first evaluation result or the second evaluation result into the corresponding filtering information set to obtain an evaluation information set.

[0114] As a preferred implementation of this embodiment, a first evaluation result is obtained using a first evaluation calculation formula, and the first evaluation calculation formula is specifically:

[0115]

[0116] in, is the number of data in the data link, is the number of all data outliers in the data chain, Herein, this embodiment uses the first evaluation result to evaluate the data that does not meet the corresponding data threshold and the corresponding data link.

[0117] As a preferred implementation of this embodiment, a second evaluation result is obtained using a second evaluation calculation formula, and the second evaluation calculation formula is specifically:

[0118]

[0119] in, is the data difference, is the preset data difference threshold, Indicates that the data difference does not fall within the data difference threshold. is the counting function, Indicates the counting result of counting the data whose data difference does not fall within the data difference threshold, that is, the number of corresponding data. is the number of data in the data link, is the second evaluation result. It should be noted that the data difference threshold of this embodiment is formulated based on the actual data of the corresponding industrial Internet of Things and corresponds to the data difference, which is well known to those skilled in the art. For example, if the rated operating temperature of a certain device is 25°C, the corresponding content refers to the data value of 25°C under the rated operating temperature, and the corresponding operating temperature threshold is 40°C, and the data difference is +13°C. It can be understood that even if it meets the operating temperature threshold of 40°C at this time, under normal operation, the device temperature should not increase by +13°C. In this regard, this embodiment implements the evaluation of the data difference and the corresponding data link through the second evaluation result.

[0120] Based on the above, this embodiment realizes the processing of the filter information set through evaluation, thereby improving the interpretability of data processing.

[0121] Specifically, when the first evaluation result exists in the evaluation information set, the organizing steps specifically include:

[0122] D1: Obtain each evaluation information set corresponding to the data chain;

[0123] D2: using the data difference or data outlier, combined with the first evaluation result, to obtain a first organization result; the first organization result is used to characterize the impact of the corresponding data on the data chain;

[0124] D3: sorting the corresponding data based on the first organization result and outputting the data and the corresponding identification, filtering and evaluation processes in sequence according to the sorting results.

[0125] As a preferred implementation of this embodiment, the first tissue result is obtained by using the first tissue calculation formula, and the first tissue calculation formula is specifically:

[0126]

[0127] in, is the first evaluation result, As the first organization result, is the number of first evaluation results or second evaluation results in the first and last two data on the data chain. And calculate Realize the quantification of the impact of corresponding data outliers on the data chain.

[0128] Based on the above, this embodiment obtains the first organization result through the first organization calculation formula, and uses the first organization result to organize the data, thereby optimizing the data output and mining the internal relationship of the data to optimize isolation.

[0129] Specifically, when the second evaluation result exists in the evaluation information set, the organizing steps specifically include:

[0130] E1: Obtain each evaluation information set corresponding to the data link;

[0131] E2: using the data difference or data outlier, combined with the second evaluation result, to obtain a second organization result; the second organization result is used to characterize the impact of the corresponding data on the data chain;

[0132] E3: sorting the corresponding data based on the second organization result and outputting the data and the corresponding identification, filtering and evaluation processes in sequence according to the sorting result.

[0133] As a preferred implementation of this embodiment, the first tissue result is obtained by using the second tissue calculation formula, and the second tissue calculation formula is specifically:

[0134]

[0135] in, is the second evaluation result, As a result of the second organization, is the number of first evaluation results or second evaluation results in the first and last two data on the data chain. And calculate Realize the quantification of the impact of the corresponding data difference on the data link.

[0136] Based on the above, this embodiment obtains the second organization result through the second organization calculation formula, and uses the second organization result to organize the data, thereby optimizing the data output and mining the internal relationship of the data to optimize isolation.

[0137] Specifically, the output of step D3 precedes the output of step E3.

[0138] It should be noted that, under the premise of data congestion, the output of step D3 is an output that does not meet the data threshold, which has a higher priority for the industrial Internet of Things.

[0139] Based on the above, this embodiment further improves the recognition and processing capability of massive data by limiting the order of data output to improve applicability.

[0140] In a second aspect, this embodiment discloses Figure 2 A data recognition and processing system based on a large model is shown, and the system is applicable to the data recognition and processing method based on a large model as described above, and the system includes:

[0141] An acquisition module, the acquisition module is configured to acquire a standard information set corresponding to each data and store it into a preset large model;

[0142] An identification module, the identification module is configured to collect and identify a real-time information set;

[0143] A filtering module, the filtering module is configured to filter the real-time information set to obtain a filtered information set;

[0144] An evaluation module, the evaluation module is configured to evaluate the filtering information set to obtain an evaluation information set;

[0145] An organization module, the organization module is configured to organize the data corresponding to the evaluation information set to obtain a data identification processing result;

[0146] The standard information set includes data name, data type, data rating, data threshold and data chain;

[0147] Large models are used to identify, filter, evaluate and organize;

[0148] Identification is used to identify the real-time information set of each real-time data collected;

[0149] The real-time information set includes data name, data type, data real-time value and data link;

[0150] Filtering is used to process the real-time information set based on the standard information set;

[0151] Evaluation is used to perform data processing on the filtered information set based on the standard information set;

[0152] The organization is used to process the data corresponding to the evaluation information set.

[0153] It should be noted that the big model-based data recognition and processing system of this embodiment corresponds to the big model-based data recognition and processing system in the previous text. Therefore, the contents not specifically described in this embodiment may include but are not limited to the functional definition, working principle and technical effect, which are the same as the big model-based data recognition and processing method in the previous text, and this text will not elaborate on them.

[0154] In a third aspect, this embodiment discloses a storage medium on which a computer program is stored. When the computer program is executed by a processor, the data recognition and processing method based on the large model as described above is implemented.

[0155] In summary, the data identification and processing method, system and storage medium based on the big model of the present embodiment improve the identification and processing capabilities of massive data through standard information and big models to improve applicability, realize the combination of identification and processing through a closed loop of identification, filtering, evaluation and organization to optimize singularity, realize the mining of the intrinsic relationship of data through data links and corresponding evaluation and organization to optimize isolation, and improve interpretability through output data and corresponding filtering and evaluation processes, thereby realizing data identification and processing based on the big model.

[0156] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code, or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to implement the functions described herein, or a combination thereof. For software implementation, part or all of the processes of the embodiment can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein the communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The storage medium can be any available medium that can be accessed by a computer. Computer-readable storage media can include, but are not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer.

[0157] Finally, it should be noted that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A data recognition and processing method based on a large model, characterized in that: The method includes: S1: Obtain the standard information set corresponding to each data and store it in the preset large model; S2: Collect and identify real-time information sets; S3: filtering the real-time information set to obtain a filtered information set; S4: Evaluate the filtering information set to obtain an evaluation information set; S5: Organizing the data corresponding to the evaluation information set to obtain a data identification processing result; The standard information set includes data name, data type, data rating, data threshold and data chain; The macro model is used for performing the identification, the filtering, the evaluation and the organization; The identification is used to identify the real-time information set of each real-time data collected; The real-time information set includes the data name, the data type, the data real-time value and the data link; The filtering is used to perform data processing on the real-time information set based on the standard information set; The evaluation is used to perform data processing on the filter information set based on the standard information set; The organization is used to perform data processing on the data corresponding to the evaluation information set; The filtering steps are specifically as follows: B1: Acquire the real-time information set and the standard information set, and establish a corresponding relationship based on the data name; B2: Determine whether the real-time value of the data meets the corresponding data threshold, if yes, execute step B3, otherwise execute step B4; B3: Calculate the data real-time value minus the data rated value to obtain the data difference; B4: Outputs a preset data anomaly value representing data anomaly; B5: using the data difference value or the data abnormal value to replace the corresponding data real-time value to obtain the filtering information set; The steps of the assessment specifically include: C1: Acquire the filter information set and the standard information set, and establish a corresponding relationship based on the data name; C2: Determine whether there is an abnormal value in the data, if yes, execute step C3, otherwise execute step C4; C3: using the data outlier value to obtain the corresponding data chain, and based on the data chain, capturing all the data outliers in the data chain, and obtaining a first evaluation result based on the number of data in the data chain and the number of all data outliers in the data chain; C4: using the data difference to obtain the corresponding data link, and based on the data link, capturing all the data differences in the data link, and obtaining a second evaluation result based on the number of data in the data link and the data difference; C5: writing the first evaluation result or the second evaluation result into the corresponding filtering information set to obtain the evaluation information set; When the first evaluation result exists in the evaluation information set, the organizing step specifically includes: D1: Obtain each evaluation information set corresponding to the data link; D2: using the data difference or the data outlier and combining it with the first evaluation result, obtaining a first organization result; the first organization result is used to characterize the influence degree of the corresponding data on the data chain; D3: sorting the corresponding data based on the first organization result and outputting the data and the corresponding identification, filtering and evaluation processes in order according to the sorting results; When the second evaluation result exists in the evaluation information set, the organizing step specifically includes: E1: Obtain each evaluation information set corresponding to the data link; E2: using the data difference or the data outlier and combining it with the second evaluation result, obtaining a second organization result; the second organization result is used to characterize the influence degree of the corresponding data on the data chain; E3: sorting the corresponding data based on the second organization result, and outputting the data and the corresponding identification, filtering and evaluation processes in sequence according to the sorting results.

2. The data recognition and processing method based on a large model according to claim 1 is characterized in that: The data rated value is specifically the data value under rated conditions of the content that the data refers to; the data chain is specifically obtained by associating related data in a chain form.

3. The data recognition and processing method based on a large model according to claim 1 is characterized in that: The identification steps specifically include: A1: Get the collected real-time data and corresponding data names; A2: Retrieve the corresponding standard information set based on the data name; A3: using the standard information set obtained in step A2 to normalize the data type and the data link corresponding to each real-time data obtained in step A1, and normalizing the real-time data value to the real-time value of the data based on the data form of the data rated value and the data threshold; A4: Pack the data name obtained in step A1 and the data type, the data real-time value and the data link obtained in step A3 into a real-time information set and output it.

4. The data recognition and processing method based on a large model according to claim 1 is characterized in that: The output of step D3 precedes the output of step E3.

5. A data recognition and processing system based on a large model, the system is applicable to the data recognition and processing method based on a large model as described in any one of claims 1 to 4, characterized in that: The system includes: An acquisition module, wherein the acquisition module is configured to acquire a standard information set corresponding to each data and store it into a preset macro model; An identification module, wherein the identification module is configured to collect and identify a real-time information set; A filtering module, wherein the filtering module is configured to filter the real-time information set to obtain a filtered information set; An evaluation module, wherein the evaluation module is configured to evaluate the filtering information set to obtain an evaluation information set; An organization module, wherein the organization module is configured to organize the data corresponding to the evaluation information set to obtain a data identification processing result; The standard information set includes data name, data type, data rating, data threshold and data chain; The macro model is used for performing the identification, the filtering, the evaluation and the organization; The identification is used to identify the real-time information set of each real-time data collected; The real-time information set includes the data name, the data type, the data real-time value and the data link; The filtering is used to perform data processing on the real-time information set based on the standard information set; The evaluation is used to perform data processing on the filter information set based on the standard information set; The organization is used to perform data processing on the data corresponding to the evaluation information set.

6. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the large model-based data recognition and processing method as described in any one of claims 1 to 4 is implemented.

Images