Invalid production logic checking method and system based on big data analysis

Abstract

The application provides a big data analysis-based invalid production logic checking method and system. Production session data to be analyzed is obtained from business big data. Key feature optimization is performed on the production session data to be analyzed according to a set data optimization operation to determine at least one group of first defective production theme distributions. The first defective production theme distributions are analyzed to determine whether the business big data has a reference data logic abnormality. In this way, the key feature optimization is used to improve the inaccuracy of big data analysis. The defective production theme distributions are analyzed by a further analysis method, which can accurately determine whether there is an abnormality in the production logic data, thereby ensuring the normal operation of the production equipment and improving the big data production efficiency.

Description

Technical Field

[0001] This application relates to the field of big data inspection technology, and more specifically, to a method and system for inspecting invalid production logic based on big data analysis. Background Technology

[0002] In various industries, the work of collecting industry data, organizing the collected data, conducting in-depth analysis of the organized data, and making industry research, assessments, and predictions based on the data analysis results is called data analysis. If the person is familiar with industry knowledge, company business and processes, and has a certain understanding of the job content, such as being familiar with industry knowledge and the company's business background, the analysis results will be of great value.

[0003] Currently, big data analytics technology is widely integrated into various fields (such as smart office, smart healthcare, and artificial intelligence). Furthermore, big data analytics is also being integrated into production lines. This allows for effective control of production lines, thereby improving their efficiency. However, production data may still contain certain defects. If the existence of defects cannot be accurately determined, it is difficult to ensure the normal operation of production equipment, thus reducing production efficiency. Summary of the Invention

[0004] In view of this, this application provides a method and system for checking invalid production logic based on big data analysis.

[0005] Firstly, a method for checking invalid production logic based on big data analysis is provided. The method includes: obtaining production session data to be analyzed from business big data; optimizing key features of the production session data to be analyzed according to set data optimization operations to determine at least one set of first defective production topic distributions; and analyzing at least one set of first defective production topic distributions to determine whether there are reference data logic anomalies in the business big data.

[0006] It is understood that this embodiment of the disclosure obtains production session data of business big data to be analyzed; performs key feature optimization on the production session data to be analyzed according to the set data optimization operation to determine at least one set of first defective production topic distributions; and analyzes at least one set of first defective production topic distributions to determine whether there are any logical anomalies in the business big data. This approach, firstly through key feature optimization, helps to improve the inaccuracy of big data analysis. Finally, by further analyzing the defective production topic distributions, it is possible to accurately determine whether there are any anomalies in the production logic data, thereby ensuring the normal operation of production equipment and improving the efficiency of big data production.

[0007] In one independently implemented embodiment, analyzing at least one set of first defective production topic distributions to determine whether there are reference data logic anomalies in the business big data includes: performing reference analysis on at least one set of first defective production topic distributions to determine an example standard comparison dataset bound to each set of first defective production topic distributions in at least one set of first defective production topic distributions; integrating the example standard comparison datasets to determine a first example standard comparison dataset; and determining whether there are reference data logic anomalies in the business big data based on the first example standard comparison dataset.

[0008] Understandably, since the first example standard comparison dataset is a standard comparison dataset obtained by integrating the example standard comparison dataset, it can indicate that the constraints specified in the first example standard comparison dataset are most likely to have inaccurate constraints. Compensation analysis using these constraints can help improve the credibility and accuracy of the compensation analysis.

[0009] In one independently implemented embodiment, each group of first defective production topic distributions includes key feature optimization constraints obtained through key feature optimization. Reference analysis is performed on at least one group of first defective production topic distributions to determine an exemplary standard comparison dataset bound to each group of first defective production topic distributions. This includes: performing reference analysis on each group of first defective production topic distributions to determine a first standard comparison dataset bound to each group of first defective production topic distributions; and using the first standard comparison dataset belonging to the key feature optimization constraints in each group of first defective production topic distributions to obtain an exemplary standard comparison dataset.

[0010] It is understandable that using the first standard comparison dataset that globally belongs to the key feature optimization constraint in the first defective production topic distribution of each group as the example standard comparison dataset is beneficial to improve the production information that differs when using non-key feature optimization constraints in subsequent predictions, thereby enabling accurate identification of the production information that differs.

[0011] In one standalone embodiment, determining whether there are any logical anomalies in the reference data of the business big data based on a first example standard comparison dataset includes: determining the description content of the first example standard comparison dataset in the production session data to be analyzed; selecting the constraint production session data to be partitioned from the production session data to be analyzed based on the description content; and analyzing the constraint production session data to be partitioned to determine whether there are any logical anomalies in the reference data of the business big data.

[0012] Understandably, the reference analysis first obtains a set of raw analysis results, such as assuming that the constraints specified in the first paradigm standard comparison dataset should have reference localities. Then, based on the first paradigm standard comparison dataset, the production session data of the constraints to be divided is selected from the production session data to be analyzed. The saliency data in the production session data of the constraints to be divided is used to determine whether there are reference localities in the production session data of the constraints to be divided, so as to further determine whether there are reference data logic anomalies in the business big data. These two analysis methods can make the final output of the remedial analysis results more accurate.

[0013] In one standalone embodiment, obtaining production session data to be analyzed from business big data includes: performing reference analysis on the raw production session data of the business big data to determine a first reference analysis result; if the first reference analysis result includes at least one set of second standard comparison datasets, then determining a second example standard comparison dataset from at least one set of second standard comparison datasets, and determining the production session data to be analyzed based on the second example standard comparison dataset and a set of templates; if the first reference analysis result does not include a second standard comparison dataset, then determining the production session data to be analyzed based on a set of standards and a set of templates.

[0014] Understandably, the first reference analysis result is used to characterize the analysis results after reference analysis of the original production session data without subsequent processing. The first reference analysis result includes at least one set of second standard comparison datasets. This can be understood as indicating that inaccurate constraints were found in the original production session data. In this case, the set of second standard comparison datasets with the best first or second evaluation state is determined as the second paradigm standard comparison dataset. Based on this second paradigm standard comparison dataset and template, the original production session data is corrected to determine the production session data to be analyzed. Conversely, if the first reference analysis result does not include a second standard comparison dataset, it can be interpreted as indicating that inaccurate constraints were not found in the original production session data. In this case, the original production session data is corrected based on the set of standards and template to determine the production session data to be analyzed. This ensures that the original production session data is corrected regardless of whether inaccurate constraints are found, guaranteeing the completeness and reliability of the analysis of the production session data to be analyzed by each unit of the AI ​​thread.

[0015] In one standalone embodiment, determining the production session data to be analyzed based on a second paradigm standard comparison dataset and a set template includes: obtaining a first quantification result based on the evaluation result of the template and a first evaluation state or a second evaluation state of the second paradigm standard comparison dataset; and quantifying the original production session data based on the first quantification result to determine the production session data to be analyzed.

[0016] Understandably, based on the analysis of inaccurate constraints in the original production session data, the first quantification result is obtained by comparing the first or second evaluation state of the dataset with the evaluation results of the template and the second example standard. Then, the original production session data is quantified based on the first quantification result, which helps to ensure the integrity and reliability of the analysis of the production session data to be analyzed by each unit of the AI ​​thread.

[0017] In one standalone embodiment, determining the production session data to be analyzed based on a set of standards and a template includes: obtaining a second quantification result based on the evaluation results of the template and a first or second evaluation state of the standard set; and quantifying the original production session data according to the second quantification result to determine the production session data to be analyzed.

[0018] Understandably, if the problem of inaccurate constraints is not found in the original production session data, a second quantification result is obtained based on the evaluation results of the template and the first or second evaluation state of the standard set. The original production session data is then quantified based on the second quantification result, which helps to ensure the integrity and reliability of the analysis of the production session data to be analyzed by each unit of the AI ​​thread.

[0019] In one independently implemented embodiment, a reference analysis is performed on the first defective production topic distribution of each group to determine a first standard comparison dataset bound to the first defective production topic distribution of each group. This includes: performing at least one logical semantic extraction, deep logical semantic extraction, and semantic importance weighting operation, and using the resulting integrated logical semantic set as a reference logical semantic set; optimizing the first defective production topic distribution of each group based on the reference logical semantic set to determine the first standard comparison dataset; wherein, at least one logical semantic extraction, deep logical semantic extraction, and semantic importance weighting operation includes: performing logical semantic extraction on the first defective production topic distribution of each group or the logical semantic set obtained in the previous round of operation to determine a first logical semantic set; performing deep logical semantic extraction on the first defective production topic distribution of each group or the logical semantic set obtained in the previous round of operation to determine a second logical semantic set, wherein the evaluation results of the second logical semantic set are consistent with those of the first logical semantic set, and the situation of each location in the second logical semantic set is used to characterize the distribution of the corresponding location in the first logical semantic set; and performing semantic importance weighting on the situation of each location in the first logical semantic set bound to the second logical semantic set to determine an integrated logical semantic set.

[0020] Understandably, by collecting data from multiple AI threads across different stages to conduct reference analysis on the distribution of the first defective production topic for each group, and incorporating deep logical semantic extraction into the first stage of analysis, the AI ​​threads can learn a flexible processing method for each direction and location of the first defective production topic distribution based on the distribution extracted by deep logical semantics. This means paying more attention to the constraints in the first defective production topic distribution that have not undergone key feature optimization. These constraints usually have important related data, meaning that the reference logical semantic set obtained in the first stage is a logical semantic set with more related data. This allows for optimization processing in the second stage using a reference logical semantic set with more related data, thereby improving the accuracy of judging the salience description content.

[0021] In one independently implemented embodiment, the production session data to be analyzed is optimized for key features according to a set data optimization operation to determine at least one set of first defective production topic distributions. This includes: forming at least one set of queues based on the set data optimization operation, wherein the arrangement of each queue in the at least one set of queues is consistent with the evaluation result of the production session data to be analyzed, and each queue includes a feature with attribute 'a'; extending each queue with the key features of the production session data to be analyzed, so as to optimize the key features in the production session data to be analyzed that are bound to the feature with attribute 'a' as first key features to determine at least one set of first defective production topic distributions, wherein the key feature optimization constraint is the constraint condition optimized into the first key feature in each set of first defective production topic distributions.

[0022] Understandably, a queue is formed based on the set data optimization operations. The queue is then extended with the production session data to be analyzed to optimize the key features of the production session data to be analyzed. This ensures that the problem of inaccurate constraints in the production session data to be analyzed can be included by the first key feature, so as to eliminate the significant and accurate description, and thus facilitate optimization based on the associated data in subsequent reference analysis.

[0023] In one standalone embodiment, reference analysis of at least one set of first defective production topic distributions is performed via an AI thread, which is configured through the following steps: obtaining target production session data and labeled data of reference localities within the target production session data; loading the target production session data into the AI ​​thread for reference analysis to determine at least one set of third standard comparison datasets, and determining a third paradigm standard comparison dataset from at least one set of third standard comparison datasets; quantifying the target production session data based on the third paradigm standard comparison dataset and a template to determine quantified target production session data; optimizing key features of the quantified target production session data to determine at least one set of second defective production topic distributions; and collecting at least one set of second defective production topic distributions, labeled data, and a quantization evaluation model to configure the AI ​​thread to determine the AI ​​thread.

[0024] Understandably, for target production session data that includes issues such as inaccurate constraints, the method of collecting key features for optimization includes the aforementioned reference locality, thereby creating configuration data with logical anomalies in the reference data—that is, the second defective production topic distribution—to improve the problem of abnormal production session data in business big data. Furthermore, collecting the configuration AI thread for the second defective production topic distribution included in the reference locality helps the AI ​​thread pay more attention to the correlated data in the production session data, thus improving the accurate judgment of the salience description of inaccurate constraints.

[0025] Secondly, an invalid production logic inspection system based on big data analysis is provided, including a processor and a memory that communicate with each other. The processor is used to retrieve a computer program from the memory and implement the above-mentioned method by running the computer program.

[0026] The invalid production logic inspection method and system based on big data analysis provided in this application embodiment obtains production session data of business big data to be analyzed; performs key feature optimization on the production session data to be analyzed according to set data optimization operations to determine at least one set of first defective production topic distributions; analyzes at least one set of first defective production topic distributions to determine whether there are reference data logic anomalies in the business big data. This approach, firstly through key feature optimization, helps to improve the inaccuracy of big data analysis; and finally, through further analysis of the defective production topic distributions, it can accurately determine whether there are anomalies in the production logic data, thereby ensuring the normal operation of production equipment and improving big data production efficiency. Attached Figure Description

[0027] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a flowchart illustrating an invalid production logic check method based on big data analysis, provided as an embodiment of this application.

[0029] Figure 2 This is a block diagram of an invalid production logic checking device based on big data analysis, provided as an embodiment of this application.

[0030] Figure 3 This is an architecture diagram of an invalid production logic inspection system based on big data analysis, provided as an embodiment of this application. Detailed Implementation

[0031] To better understand the above technical solutions, the technical solutions of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this application and the specific features in the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. In the absence of conflict, the embodiments of this application and the technical features in the embodiments can be combined with each other.

[0032] Please see Figure 1 This paper presents a method for checking invalid production logic based on big data analysis, which may include the technical solutions described in steps 201-203.

[0033] 201: Obtain production session data for analysis of business big data.

[0034] For example, production session data that is to be analyzed to obtain business big data can include the following.

[0035] 2011: Perform reference analysis on the raw production session data to determine the results of the first reference analysis.

[0036] 2012: If the results of the first reference analysis include at least one set of second standard comparison datasets, then a second paradigm standard comparison dataset is determined from at least one set of second standard comparison datasets, and production session data to be analyzed is determined based on the second paradigm standard comparison dataset and the template.

[0037] 2013: If the second standard comparison dataset is not included in the results of the first reference analysis, the production session data to be analyzed is determined based on the set of standards and templates.

[0038] In a specific embodiment of this disclosure, the first reference analysis result is used to characterize the analysis result of the original production session data after reference analysis without subsequent processing. It is understood that if there is an inaccurate constraint problem in the original production session data, the first reference analysis result will include no less than one set of sample datasets, i.e., the second standard comparison dataset. If there is no inaccurate constraint problem in the original production session data, the first reference analysis result may not include the second standard comparison dataset, i.e., no sample dataset is generated.

[0039] For cases where the first reference analysis results include at least one set of second standard comparison datasets, a first evaluation state and a second evaluation state are obtained for each of the at least one set of second standard comparison datasets. The second standard comparison dataset with the best first evaluation state or the best second evaluation state is determined as the second paradigm standard comparison dataset. Then, based on the second paradigm standard comparison dataset and this template, the production session data to be analyzed is obtained. It can be understood that "best first evaluation state" is used to characterize that the first evaluation state result surpasses all other first and second evaluation state results, and "best second evaluation state" is used to characterize that the second evaluation state result surpasses all other first and second evaluation state results.

[0040] For example, comparing datasets and templates based on second-paradigm standards to determine production session data to be analyzed may include the following.

[0041] 201a1: Based on the evaluation results of the template and the first or second evaluation state of the comparison dataset with the second paradigm standard, the first quantitative result is obtained statistically.

[0042] 201a2: Quantify the raw production session data based on the first quantization result to determine the production session data to be analyzed.

[0043] Assuming the template's evaluation result is 4x4, the best result in the first or second evaluation state of the second paradigm standard comparison dataset is compressed to one-quarter of the template's evaluation result. For example, if the best result in the first or second evaluation state of the second paradigm standard comparison dataset is 3, then one-sixth of the first quantification result is obtained by statistically analyzing the template's evaluation result and the best result 3. The original production session data is then quantified based on the first quantification result, thus obtaining the production session data to be analyzed.

[0044] In this embodiment, based on the analysis of inaccurate constraints in the original production session data, a first quantification result is obtained by comparing the first or second evaluation state of the dataset with the evaluation result of the template and the second example standard. Then, the original production session data is quantified based on the first quantification result, which helps to ensure the integrity and reliability of the analysis of the production session data to be analyzed by each unit of the AI ​​thread.

[0045] For cases where the second standard comparison dataset is not included in the first reference analysis results, the production session data to be analyzed is obtained based on the set of standards and the template. The evaluation results of this standard set can be set according to the target results. For example, typically, the outer standard set of the reference locality with the best evaluation results from several collected production session data sets is set as this standard set.

[0046] For example, determining the production session data to be analyzed based on a set of criteria and templates may include the following.

[0047] 201b1: Based on the evaluation results of the template and the first or second evaluation state of the standard set, the second quantitative result is obtained statistically.

[0048] 201b2: Quantify the raw production session data based on the second quantization result to determine the production session data to be analyzed.

[0049] If the evaluation result of the template is 4x4, then the best result in the first or second evaluation state of the set standard set is compressed to one-quarter of the template evaluation result. For example, if the best result in the first or second evaluation state of the standard set is 4, then the second quantitative result of one-quarter is obtained by statistically analyzing the evaluation result of the template and the best result 4. The original production session data is then quantified based on the second quantitative result, which gives the production session data to be analyzed.

[0050] In this embodiment, since the problem of inaccurate constraints was not found in the original production session data, a second quantification result is obtained based on the evaluation result of the template and the first or second evaluation state of the standard set. The original production session data is then quantified based on the second quantification result, which helps to ensure the integrity and reliability of the analysis of the production session data to be analyzed by each unit of the AI ​​thread.

[0051] 202: Based on the set data optimization operation, perform key feature optimization on the production session data to be analyzed to determine at least one set of the first defective production topic distribution.

[0052] For example, performing key feature optimization on the production session data to be analyzed based on the set data optimization operations to determine at least one set of first defective production topic distributions may include the following.

[0053] Based on the set data optimization operations, at least one set of queues is formed. The arrangement of each queue in at least one set of queues is consistent with the evaluation results of the production session data to be analyzed. Each queue includes a feature with attribute 'a'. Each queue is extended with the key features of the production session data to be analyzed, so that the key features in the production session data to be analyzed that are bound to the feature with attribute 'a' are optimized into first key features to determine at least one set of first defective production topic distributions. The key feature optimization constraint is the constraint condition in each set of first defective production topic distributions that is optimized into the first key feature.

[0054] In this specific embodiment, 16 key feature data optimization operations are defined. These 16 operations are used to optimize the key features of the production session data to be analyzed, determining 16 sets of first-stage defective production topic distributions. Further, for each data optimization operation, a queue is formed based on the operation and the evaluation results of the production session data to be analyzed. Taking the first data optimization operation as an example, assuming the evaluation results of the production session data to be analyzed are 20x20 (key features), a queue can be formed based on the distribution of the first and second key features in the first data optimization operation. In this queue, the feature with attribute 'a' can represent the first key feature, and the feature with attribute 'b' can represent the second key feature. Since the queue arrangement is consistent with the evaluation results of the production session data to be analyzed, the queues are extended with the data to obtain the first-stage defective production topic distributions. Each set of first-stage defective production topic distributions includes key feature optimization constraints contained in the first key feature.

[0055] It is understandable that by performing key feature optimization on the production session data to be analyzed based on the above 16 data optimization operations, it can be ensured that the reference locality in the production session data to be analyzed is included by the first key feature in a certain group of the first defective production topic distribution, thereby achieving the purpose of removing the salience description of the reference locality in the production session data to be analyzed.

[0056] In this embodiment, a queue is formed based on the set data optimization operation. The queue and the production session data to be analyzed are extended to optimize the key features of the production session data to be analyzed. This ensures that the problem of inaccurate constraints in the production session data to be analyzed can be included by the first key feature, so as to eliminate the significant and accurate description, and facilitate the optimization processing based on the associated data in subsequent reference analysis.

[0057] 203: Analyze the distribution of at least one group of the first defective production topics to determine whether there are any logical anomalies in the reference data in the business big data.

[0058] For example, analyzing at least one set of first-deficient production topic distributions to determine whether there are any logical anomalies in the reference data in the business big data may include the following:

[0059] 203a1: Perform a reference analysis on at least one set of first defective production topic distributions to determine the exemplary standard comparison datasets for each set of first defective production topic distributions in at least one set of first defective production topic distributions.

[0060] 203a2: Integrate the exemplary standard comparison datasets to determine the first exemplary standard comparison dataset.

[0061] 203a3: Based on the first paradigm standard comparison dataset, determine whether there are any logical anomalies in the reference data for the business big data.

[0062] In this specific embodiment, the first defective production topic distribution of each group is loaded into the AI ​​thread for reference analysis. The sample dataset generated from the first defective production topic distribution of each group is determined as the first standard comparison dataset bound to the first defective production topic distribution of each group. Then, the first standard comparison dataset is filtered, and the first standard comparison dataset that completely belongs to the key feature optimization constraints is retained and determined as the example standard comparison dataset. In this embodiment, when the first standard comparison dataset does not completely belong to the key feature optimization constraints, the saliency data of the corresponding object of the first standard comparison dataset cannot be effectively masked by the key feature optimization constraints. In subsequent prediction, it may be obtained through the saliency data of the reference business data. By using the first standard comparison dataset that globally belongs to the key feature optimization constraints in the first defective production topic distribution of each group as the example standard comparison dataset, it is beneficial to improve the use of non-key feature optimization constraints in subsequent prediction of production information with discrepancies, thereby enabling accurate identification of production information with discrepancies.

[0063] For the identified first paradigm benchmark dataset, since the evaluation results of the first defective production topic distribution are consistent with those of the production session data to be analyzed, the description content of the first paradigm benchmark dataset in the first defective production topic distribution can be used as the description content of the first paradigm benchmark dataset in the production session data to be analyzed. Based on this description content, constraint-based production session data to be partitioned can be selected from the production session data to be analyzed. This constraint-based production session data is then loaded into a support vector machine for analysis. By using the saliency data in the constraint-based production session data to be partitioned, it can be determined whether the constraints specified in the first paradigm benchmark dataset ultimately have a reference locality, thereby determining whether there are any logical anomalies in the reference data in the business big data. For example, if the inaccuracy of the constraints is not anticipated in the constraint-based production session data to be partitioned, it indicates that there is an anomaly of a reference locality in the business big data.

[0064] In this embodiment, the reference analysis first obtains a set of original analysis results, such as assuming that the constraints specified by the first example standard comparison dataset should have reference localities. Then, based on the first example standard comparison dataset, the production session data of the constraints to be divided is selected from the production session data to be analyzed. The saliency data in the production session data of the constraints to be divided is used to determine whether there are reference localities in the production session data of the constraints to be divided, so as to further determine whether there are reference data logic anomalies in the business big data. These two analysis methods can make the final output compensation analysis results more accurate.

[0065] For example, a reference analysis is performed on the first defective production topic distribution of each group to determine the first standard comparison dataset bound to the first defective production topic distribution of each group. This may include the following: performing at least one logical semantic extraction, deep logical semantic extraction, and semantic importance weighting operation, and using the resulting integrated logical semantic set as the reference logical semantic set; and optimizing the first defective production topic distribution of each group based on the reference logical semantic set to determine the first standard comparison dataset.

[0066] Among them, at least one logical semantic extraction, deep logical semantic extraction, and semantic importance weighting operation may include the following.

[0067] 203b1: Extract logical semantics from the first defective production topic distribution or the logical semantic set obtained from the previous round of operations for each group to determine the first logical semantic set.

[0068] 203b2: Perform deep logical semantic extraction on the first defective production topic distribution or the logical semantic set obtained from the previous round of operation for each group to determine the second logical semantic set. The evaluation results of the second logical semantic set are consistent with those of the first logical semantic set. The situation of each location in the second logical semantic set is used to characterize the distribution of the corresponding location in the first logical semantic set.

[0069] 203b3: The semantic importance weights of each location in the first logical semantic set and the second logical semantic set are processed to determine the integrated logical semantic set.

[0070] In a specific embodiment of this disclosure, multiple AI threads at various stages are used to perform reference analysis on the distribution of the first defective production topic for each group. In the analysis of the first stage, in addition to the general logical semantic extraction operation, deep logical semantic extraction is added. For the loaded first defective production topic distribution, general logical semantic extraction is performed to obtain a first logical semantic set, and deep logical semantic extraction is performed to obtain a second logical semantic set. Since the situation of each location in the second logical semantic set is used to characterize the distribution of the corresponding location in the first logical semantic set, the two can be weighted to determine the third logical semantic set (i.e., the logical semantic set obtained in the previous round of operation) to focus on the unoptimized constraints with related data. General logical semantic extraction is then performed on the third logical semantic set to obtain a fourth logical semantic set, and deep logical semantic extraction is then performed on the third logical semantic set to obtain a fifth logical semantic set. Since the situation of each location in the fifth logical semantic set is used to characterize the distribution of the corresponding location in the fourth logical semantic set, the two can be weighted to determine the sixth logical semantic set. It is understood that by performing two operations of logical semantic extraction, deep logical semantic extraction, and semantic importance weighting, the sixth logical semantic set is the integrated logical semantic set. The sixth logical semantic set can be used as a reference logical semantic set. The integrated logical semantic set can be obtained by performing at least one operation of logical semantic extraction, deep logical semantic extraction, and semantic importance weighting. For example, based on one operation, the third logical semantic set is the integrated logical semantic set.

[0071] The reference logical semantic set can be used as the output of the first-stage analysis. The AI ​​thread in the second stage can perform optimization processing based on the reference logical semantic set, and the resulting sample dataset is the first standard comparison dataset. For example, general logical semantic extraction can also be performed on the reference logical semantic set to determine the output of the first-stage analysis, the seventh logical semantic set. The AI ​​thread in the second stage can also perform optimization processing based on the seventh logical semantic set, and the resulting sample dataset is the first standard comparison dataset.

[0072] In this embodiment, multiple AI threads at different stages perform reference analysis on the distribution of the first defective production topic for each group. Deep logical semantic extraction is incorporated into the analysis in the first stage. Based on the distribution extracted by deep logical semantic extraction, the AI ​​threads can pay more attention to the constraints in the distribution of the first defective production topic that have not been optimized for key features. These constraints usually have important related data. That is, the reference logical semantic set obtained in the first stage is a logical semantic set with more related data. This allows for optimization processing in the second stage using the reference logical semantic set with more related data, thereby improving the accuracy of judging the salience description content.

[0073] It is understood that this disclosure embodiment obtains production session data of business big data to be analyzed; performs key feature optimization on the production session data to be analyzed according to set data optimization operations to determine at least one set of first defective production topic distributions; and analyzes at least one set of first defective production topic distributions to determine whether there are reference data logic anomalies in the business big data bound to the production session data to be analyzed. This approach, firstly through key feature optimization, helps to improve the inaccuracy of big data analysis; and finally, through further analysis of the defective production topic distributions, it can accurately determine whether there are anomalies in the production logic data, thereby ensuring the normal operation of production equipment and improving big data production efficiency.

[0074] This disclosure provides another method for checking invalid production logic based on big data analysis, which may specifically include the following:

[0075] 701: Production session data that is to be analyzed to obtain big data for business operations.

[0076] 702: Based on the set data optimization operation, perform key feature optimization on the production session data to be analyzed to determine at least one set of the first defective production topic distributions.

[0077] 703: Perform a reference analysis on at least one set of first-defect production topic distributions to determine an exemplary standard comparison dataset for each set of first-defect production topic distributions in at least one set of first-defect production topic distributions.

[0078] 704: Integrate the exemplary standard comparison datasets to determine the first exemplary standard comparison dataset.

[0079] 705: Compare the dataset with the first paradigm standard to determine whether there are any logical anomalies in the reference data for the business big data.

[0080] In step 703, the reference analysis of the distribution of at least one first defective production topic is performed by an AI thread, which is configured through the following steps.

[0081] 703a1: Obtain the target production session data and the tag data of the reference locale in the target production session data.

[0082] 703a2: Load target production session data into an AI thread for reference analysis to determine at least one set of third-standard comparison datasets, and determine a third-paradigm standard comparison dataset from at least one set of third-standard comparison datasets.

[0083] 703a3: Based on the third paradigm standard comparison dataset and template, the target production session data is quantified to determine the target production session data after quantification.

[0084] 703a4: Perform key feature optimization on the target production session data after quantification to determine at least one second set of defective production topic distributions.

[0085] 703a5: Collect at least one set of second-defect production topic distributions, labeled data, and quantitative evaluation models (which can be understood as loss functions) to configure AI threads to determine AI threads.

[0086] In a specific embodiment of this disclosure, due to defects in abnormal production session data in business big data, and because artificial intelligence learning requires a large amount of configuration data to configure AI threads, the collection of target production session data, including issues with inaccurate constraints, results in some reference data with logically abnormal configuration data.

[0087] Furthermore, labeled data can be obtained by drawing bounding boxes to mark reference localities in the target production session data. Then, the target production session data is loaded into the AI ​​thread for reference analysis, generating a sample dataset, which is the third standard comparison dataset. At least one set of third standard comparison datasets is used to obtain the first and second evaluation states for each third standard comparison dataset. The third standard comparison dataset with the best first or second evaluation state is determined as the third paradigm standard comparison dataset. Based on the evaluation results of the set template and the first and second evaluation states of the third paradigm standard comparison dataset, a quantitative result is obtained. This quantitative result is used to quantify the target production session data to determine the quantified target production session data. Based on data optimization operations, key features of the quantified target production session data are optimized to obtain at least one set of second defective production topic distributions. These second defective production topic distributions are loaded into the AI ​​thread for calculation. The quantification results of the AI ​​thread are optimized using labeled data, a quantitative evaluation model, and calculation results. After several updates, a configured AI thread is obtained.

[0088] In this embodiment, for target production session data that includes issues with inaccurate constraints, the method of collecting key feature optimization includes the aforementioned reference portion to create configuration data with logical anomalies in the reference data, i.e., a second defective production topic distribution, thereby improving the problem of abnormal production session data in business big data. Furthermore, collecting the configuration AI thread of the second defective production topic distribution included in the reference portion helps the AI ​​thread pay more attention to the related data in the production session data, thereby improving the accurate judgment of the salience description of inaccurate constraints.

[0089] The above procedure includes the following requirements for performing the following steps: obtaining production session data to be analyzed from business big data; optimizing key features of the production session data to be analyzed based on the set data optimization operations to determine at least one first set of defective production topic distributions; and analyzing at least one set of first defective production topic distributions to determine whether there are any reference data logic anomalies in the business big data.

[0090] Understandably, the process involves obtaining production session data from business big data to be analyzed; optimizing key features of the production session data based on predefined data optimization operations to determine at least one set of first-stage defective production topic distributions; and analyzing these first-stage defective production topic distributions to determine if there are any reference data logic anomalies in the business big data bound to the production session data to be analyzed. This approach, starting with key feature optimization, helps improve the inaccuracy of big data analysis. Finally, further analysis of the defective production topic distributions accurately determines whether there are anomalies in the production logic data, thereby ensuring the normal operation of production equipment and improving big data production efficiency.

[0091] In one possible implementation, the processor performs analysis on at least one set of first defective production topic distributions to determine whether there are reference data logic anomalies in the business big data. This may include: performing reference analysis on at least one set of first defective production topic distributions to determine an example standard comparison dataset bound to each set of first defective production topic distributions in the at least one set of first defective production topic distributions; integrating the example standard comparison datasets to determine a first example standard comparison dataset; and determining whether there are reference data logic anomalies in the business big data based on the first example standard comparison dataset.

[0092] In one possible implementation, each group of first defective production topic distributions includes key feature optimization constraints obtained through key feature optimization. The processor performs a reference analysis on at least one group of first defective production topic distributions to determine an example standard comparison dataset bound to each group of first defective production topic distributions. This may include: performing a reference analysis on each group of first defective production topic distributions to determine a first standard comparison dataset bound to each group of first defective production topic distributions; and using the first standard comparison dataset belonging to the key feature optimization constraints in each group of first defective production topic distributions to obtain an example standard comparison dataset.

[0093] In one possible implementation, the processor performs a process based on a first paradigm standard comparison dataset to determine whether there are any logical anomalies in the reference data of the business big data. This process may include: determining the description content of the first paradigm standard comparison dataset in the production session data to be analyzed; selecting constraint production session data to be partitioned from the production session data to be analyzed based on the description content; and analyzing the constraint production session data to be partitioned to determine whether there are any logical anomalies in the reference data of the business big data.

[0094] In one possible implementation, the processor executes the process of obtaining production session data of business big data to be analyzed, which may include the following: performing reference analysis on the raw production session data of business big data to determine a first reference analysis result; if the first reference analysis result includes at least one set of second standard comparison datasets, then determining a second example standard comparison dataset from at least one set of second standard comparison datasets, and determining the production session data to be analyzed based on the second example standard comparison dataset and a set template; if the first reference analysis result does not include the second standard comparison dataset, then determining the production session data to be analyzed based on the set standard dataset and the template.

[0095] In one possible implementation, the processor executes a process based on a second paradigm standard comparison dataset and a set template to determine the production session data to be analyzed. This process may include the following: obtaining a first quantification result based on the evaluation results of the template and a first or second evaluation state of the second paradigm standard comparison dataset; and quantifying the original production session data according to the first quantification result to determine the production session data to be analyzed.

[0096] In one possible implementation, the processor executes a process based on a set of standards and templates to determine the production session data to be analyzed. This process may include: obtaining a second quantification result based on the evaluation results of the template and a first or second evaluation state of the standards set; and quantifying the original production session data according to the second quantification result to determine the production session data to be analyzed.

[0097] In one possible implementation, the processor performs a reference analysis on the first defective production topic distribution of each group to determine a first standard comparison dataset bound to the first defective production topic distribution of each group, including: performing at least one logical semantic extraction, deep logical semantic extraction, and semantic importance weighting operation, and using the resulting integrated logical semantic set as a reference logical semantic set; optimizing the first defective production topic distribution of each group based on the reference logical semantic set to determine the first standard comparison dataset; wherein the at least one logical semantic extraction, deep logical semantic extraction, and semantic importance weighting operation includes: performing logical semantic extraction on the first defective production topic distribution of each group or the logical semantic set obtained in the previous round of operation to determine a first logical semantic set; performing deep logical semantic extraction on the first defective production topic distribution of each group or the logical semantic set obtained in the previous round of operation to determine a second logical semantic set, the evaluation results of the second logical semantic set being consistent with those of the first logical semantic set, and the situation of each location in the second logical semantic set being used to characterize the distribution of the corresponding location in the first logical semantic set; and performing semantic importance weighting on the situation of each location in the first logical semantic set bound to the second logical semantic set to determine an integrated logical semantic set.

[0098] In one possible implementation, the processor performs key feature optimization on the production session data to be analyzed based on a set data optimization operation to determine at least one set of first defective production topic distributions. This may include the following: forming at least one set of queues based on the set data optimization operation, wherein the arrangement of each queue in the at least one set of queues is consistent with the evaluation result of the production session data to be analyzed, and each queue includes a feature with attribute 'a'; extending each queue with the key features of the production session data to be analyzed to optimize the key features in the production session data to be analyzed that are bound to the feature with attribute 'a' as first key features to determine at least one set of first defective production topic distributions, wherein the key feature optimization constraint is the constraint condition optimized into the first key feature in each set of first defective production topic distributions.

[0099] In one possible implementation, the reference analysis of at least one set of first defective production topic distributions is performed via an AI thread. The processor executes the configuration steps of the AI ​​thread, which may include the following: obtaining target production session data and labeled data of reference localities in the target production session data; loading the target production session data into the AI ​​thread for reference analysis to determine at least one set of third standard comparison datasets, and determining a third paradigm standard comparison dataset from at least one set of third standard comparison datasets; quantizing the target production session data based on the third paradigm standard comparison dataset and a template to determine the quantized target production session data; optimizing the key features of the quantized target production session data to determine at least one set of second defective production topic distributions; and collecting at least one set of second defective production topic distributions, labeled data, and a quantization evaluation model to configure the AI ​​thread to determine the AI ​​thread.

[0100] Based on the above, please refer to the following: Figure 2 A device 200 for checking invalid production logic based on big data analysis is provided, which is applied to an invalid production logic checking system based on big data analysis. The device includes:

[0101] Data acquisition module 210 is used to acquire production session data of business big data to be analyzed;

[0102] Theme optimization module 220 is used to perform key feature optimization on the production session data to be analyzed according to the set data optimization operation to determine at least one first defective production theme distribution;

[0103] The logic analysis module 230 is used to analyze the distribution of the first defective production topics of at least one group to determine whether there are any logical anomalies in the reference data of the business big data.

[0104] Based on the above, please refer to the following: Figure 3 The present invention illustrates an invalid production logic inspection system 300 based on big data analysis, comprising a processor 310 and a memory 320 that communicate with each other. The processor 310 is used to read computer programs from the memory 320 and execute them to implement the above-described method.

[0105] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method during runtime.

[0106] In summary, based on the above scheme, production session data for analysis of business big data is obtained; key feature optimization is performed on the production session data to be analyzed according to the set data optimization operations to determine at least one set of first defective production topic distributions; the distributions of at least one set of first defective production topics are analyzed to determine whether there are any logical anomalies in the reference data of the business big data. This approach, firstly through key feature optimization, helps to improve the inaccuracy of big data analysis; finally, through further analysis of the defective production topic distributions, it is possible to accurately determine whether there are anomalies in the production logic data, thereby ensuring the normal operation of production equipment and improving the efficiency of big data production.

[0107] It should be understood that the systems and modules described above can be implemented in various ways. For example, in some embodiments, the systems and modules can be implemented by hardware, software, or a combination of both. The hardware portion can be implemented using dedicated logic; the software portion can be stored in memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated-design hardware. Those skilled in the art will understand that the methods and systems described above can be implemented using computer-executable instructions and / or included in processor control code, for example, such code provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The systems and modules of this application can be implemented not only by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field-programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, or by a combination of the aforementioned hardware circuits and software (e.g., firmware).

[0108] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects may be any one or a combination of the above, or any other possible beneficial effects.

[0109] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are suggested in this application, and therefore remain within the spirit and scope of the exemplary embodiments of this application.

[0110] Furthermore, this application uses specific terms to describe embodiments of the application. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of the application. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this specification do not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of the application can be appropriately combined.

[0111] Furthermore, those skilled in the art will understand that aspects of this application can be described and illustrated through several patentable types or situations, including any new and useful combination of processes, machines, products, or substances, or any new and useful improvements thereof. Accordingly, aspects of this application can be implemented entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. All of the above hardware or software may be referred to as a “data block,” “module,” “engine,” “unit,” “component,” or “system.” Furthermore, aspects of this application may manifest as a computer product located on one or more computer-readable media, the product including computer-readable program code.

[0112] Computer storage media may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and suitable combinations thereof. Computer storage media can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer storage medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0113] The computer program code required for the operation of each part of this application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby, and Groovy, or other programming languages. This program code can run entirely on the user's computer, or as a standalone software package on the user's computer, or partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network, such as a local area network (LAN) or wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as Software as a Service (SaaS).

[0114] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this application are not intended to limit the order of the processes and methods of this application. Although the foregoing disclosure has discussed some currently considered useful embodiments of the invention through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the substance and scope of the embodiments of this application. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely through software solutions, such as installing the described system on existing servers or mobile devices.

[0115] Similarly, it should be noted that, in order to simplify the description of the present application and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of the embodiments of the present application sometimes combines multiple features into a single embodiment, drawing, or description thereof. However, this disclosure method does not imply that the subject matter of the application requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of the single embodiments disclosed above.

[0116] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are open to adaptive variation. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters are taken into account a specified number of significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of application in some embodiments of this application are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0117] For each patent, patent application, patent application publication, and other material such as articles, books, specifications, publications, and documents referenced in this application, the entire contents of that patent are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this application, as well as documents that limit the broadest scope of the claims in this application (currently or subsequently appended to this application). It should be noted that if there are any inconsistencies or conflicts between the descriptions, definitions, and / or terminology used in the supplementary materials of this application and the content of this application, the descriptions, definitions, and / or terminology used in this application shall prevail.

[0118] Finally, it should be understood that the embodiments described in this application are merely illustrative of the principles of the embodiments of this application. Other modifications may also fall within the scope of this application. Therefore, alternative configurations of the embodiments of this application are considered as examples and not limitations, and are regarded as consistent with the teachings of this application. Accordingly, the embodiments of this application are not limited to the embodiments explicitly described and illustrated in this application.

[0119] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for checking invalid production logic based on big data analysis, characterized in that, Applied to a logic checking system, the method includes at least: Obtain production session data that is ready for analysis from the business big data; Based on the set data optimization operations, the production session data to be analyzed is optimized for key features to determine at least one first distribution of defective production topics; Analyze the distribution of the first defective production topics of at least one group to determine whether there are any logical anomalies in the reference data of the business big data; The production session data to be analyzed, which constitutes the obtained business big data, includes: The original production session data of the aforementioned business big data is subjected to reference analysis to determine the first reference analysis result; If the first reference analysis result includes at least one set of second standard comparison datasets, then a second example standard comparison dataset is determined from the at least one set of second standard comparison datasets, and the production session data to be analyzed is determined based on the second example standard comparison dataset and the set template. If the first reference analysis result does not include the second standard comparison dataset, then the production session data to be analyzed is determined based on the set of standards and the template. The process of determining the production session data to be analyzed based on the second paradigm standard comparison dataset and the set template includes: Based on the evaluation results of the template and the first or second evaluation state of the second example standard comparison dataset, a first quantitative result is obtained statistically. The original production session data is quantified based on the first quantization result to determine the production session data to be analyzed. The process of determining the production session data to be analyzed based on the set of standards and the template includes: Based on the evaluation results of the template and the first or second evaluation state of the standard set, a second quantitative result is obtained statistically. The original production session data is quantified based on the second quantization result to determine the production session data to be analyzed. Specifically, a reference analysis is performed on the first defective production topic distribution of each group to determine the first standard comparison dataset bound to the first defective production topic distribution of each group, including: performing at least one logical semantic extraction, deep logical semantic extraction and semantic importance weighting operation, and using the resulting integrated logical semantic set as the reference logical semantic set; Based on the reference logical semantic set, the first defective production topic distribution of each group is optimized to determine the first standard comparison dataset; wherein, at least one logical semantic extraction, deep logical semantic extraction and semantic importance weighting operation is performed, including: performing logical semantic extraction on the first defective production topic distribution of each group or the logical semantic set obtained in the previous round of operation to determine the first logical semantic set. Deep logical semantic extraction is performed on the first defective production topic distribution or the logical semantic set obtained from the previous round of operation for each group to determine the second logical semantic set. The evaluation results of the second logical semantic set are consistent with those of the first logical semantic set. The situation of each location in the second logical semantic set is used to characterize the distribution of the corresponding location in the first logical semantic set. The semantic importance weights of each location in the first logical semantic set and the second logical semantic set are processed to determine the integrated logical semantic set; The step of optimizing the key features of the production session data to be analyzed to determine at least one first distribution of defective production topics includes: Based on the set data optimization operation, at least one set of queues is formed. The arrangement of each queue in the at least one set of queues is consistent with the evaluation result of the production session data to be analyzed. Each queue includes a feature with attribute a. The feature with attribute a in the queue can characterize the first key feature. Each queue is extended with the key features of the production session data to be analyzed, so as to optimize the key features in the production session data to be analyzed that are bound to the feature with attribute 'a' into the first key feature to determine the distribution of the first defective production topic of at least one group. The key feature optimization constraint is the constraint condition of the first key feature in each group of the first defective production topic distribution. The reference analysis of the distribution of at least one group of first-defect production topics is performed by an AI thread, which is configured through the following steps: Obtain the target production session data and the tag data of the reference locale in the target production session data; The target production session data is loaded into the AI ​​thread for reference analysis to determine at least one set of third standard comparison datasets, and a third paradigm standard comparison dataset is determined from the at least one set of third standard comparison datasets. Based on the third paradigm standard comparison dataset and the template, the target production session data is quantified to determine the quantified target production session data. The target production session data after the quantification results are optimized for key features to determine at least one set of second defective production topic distributions; The AI ​​thread is configured by collecting at least one set of second defective production topic distributions, the labeled data, and the quantitative evaluation model to determine the AI ​​thread.

2. The method according to claim 1, characterized in that, The analysis of the distribution of the first defective production topics in at least one group to determine whether the business big data has any logical anomalies in the reference data includes: A reference analysis is performed on the not less than one set of first defective production topic distributions to determine the exemplary standard comparison dataset bound to each set of first defective production topic distributions in the not less than one set of first defective production topic distributions; The exemplary standard comparison datasets are integrated to determine the first exemplary standard comparison dataset; The first example standard comparison dataset is used to determine whether the business big data has any logical anomalies in the reference data.

3. The method according to claim 2, characterized in that, Each group of first-defect production topic distributions includes key feature optimization constraints obtained through key feature optimization. The reference analysis of the at least one group of first-defect production topic distributions to determine the exemplary standard comparison dataset bound to each group of first-defect production topic distributions includes: A reference analysis is performed on the first defective production topic distribution of each group to determine the first standard comparison dataset bound to the first defective production topic distribution of each group; The first standard comparison dataset belonging to the key feature optimization constraints in the first defective production topic distribution of each group is used to obtain the exemplary standard comparison dataset.

4. The method according to claim 2, characterized in that, The step of determining whether there are any logical anomalies in the reference data based on the first example standard comparison dataset includes: Determine the descriptive content of the first exemplary standard comparison dataset in the production session data to be analyzed; Based on the description, select the constraint-based production session data to be segmented from the production session data to be analyzed. The production session data of the constraints to be divided is analyzed to determine whether there are any logical anomalies in the reference data of the business big data.

5. A system for checking invalid production logic based on big data analysis, characterized in that, The method includes a processor and a memory that communicate with each other, the processor being configured to retrieve a computer program from the memory and to implement the method of any one of claims 1-4 by running the computer program.

Images