An AI-based intelligent production data analysis system

Abstract

The present invention discloses an intelligent production data analysis system based on AI intelligence, belonging to the technical field of production data processing; it is used to solve the technical problems that in the existing solutions, the autonomous supervision and analysis effects at different levels in the interaction of different types of production data are not good, and the autonomous analysis and optimization prompt effects are not good; it supervises and statistically analyzes the single interactions of different types of production data during the enterprise production process, digitally processes and analyzes the supervision statistical data of different types of production data in a single interaction state, and performs local interaction state supervision processing and multi-dimensional data analysis between different types according to all the single interaction supervision processing data obtained from the interaction supervision processing of different types of production data. According to the analysis results, it dynamically classifies and marks the interactions between different pairwise types and performs interaction optimization analysis, and adaptively generates internal optimization prompts or internal and external collaborative optimization prompts for the interaction resources according to the analysis results.

Description

Technical Field

[0001] The present invention relates to the technical field of production data processing, and particularly relates to an intelligent production data analysis system based on AI intelligence. Background Art

[0002] Digital workstation production data refers to various production-related information collected from digital workstations (i.e., workstations equipped with computers, sensors, and other automation technologies) in the manufacturing industry or similar industries.

[0003] When implementing existing production data analysis solutions, most of them still stay at the monitoring statistics and alarm prompts of digital workstation production data, and cannot conduct multi-level supervision and evaluation on the interaction status of different types of production data, and adaptively conduct dynamic interaction optimization analysis and prompt on the interaction of different types of production data according to the supervision and evaluation results, resulting in poor autonomous supervision and analysis effects at different levels and poor autonomous analysis optimization prompt effects in the interaction of different types of production data. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent production data analysis system based on AI intelligence, which is used to solve the technical problems of poor autonomous supervision and analysis effects at different levels and poor autonomous analysis optimization prompt effects in the interaction of different types of production data in the existing solutions.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] An intelligent production data analysis system based on AI intelligence includes a single interaction supervision module for production data, a local interaction supervision module for production data, and an interaction optimization analysis module for production data;

[0007] The single interaction supervision module for production data is used to supervise and statistically analyze the single interactions of different types of production data in the enterprise production process, and conduct digital processing and analysis on the supervision and statistical data of different types of production data for single interaction status, so as to obtain single interaction supervision processing data corresponding to different types of production data;

[0008] The local interaction supervision module for production data is used to conduct local interaction status supervision processing and multi-dimensional data analysis between different types based on all single interaction supervision processing data obtained from the interaction supervision processing of different types of production data, and dynamically classify and mark the interactions between different pairs of types according to the analysis results; the interaction classification marks between different pairs of types include normal type marks, first abnormal type marks, second abnormal type marks, and third abnormal type marks;

[0009] A production data interaction optimization analysis module is used to perform interaction optimization analysis on production data of corresponding types according to the classification marking results of interactions between different pairwise types, and adaptively generate internal optimization prompts for interaction resources or internal and external collaborative optimization prompts according to the analysis results;

[0010] Among them, obtain the total remaining amount of local interaction resources corresponding to all the first abnormal types according to the classification markings, and obtain the total lack amount of the first local interaction resources and the total lack amount of the second local interaction resources corresponding to all the second abnormal types and all the third abnormal types respectively according to the classification markings;

[0011] Perform matching analysis on the total remaining amount of local interaction resources with the total lack amount of the first local interaction resources and the total lack amount of the second local interaction resources respectively, and adaptively generate internal optimization prompts for interaction resources or internal and external collaborative optimization prompts according to the analysis results.

[0012] Preferably, when performing supervision processing on the interaction of different types of production data, obtain the corresponding type supervision period according to the types of different production data, and obtain the local interaction period from the start of interaction to the end of interaction between the production data of the target type and the production data of other types within the type supervision period, and obtain the maximum unit interaction data volume during the interaction process of the production data of the target type with the same type;

[0013] Divide the obtained maximum unit interaction data volume by the formula Calculate to obtain the single - time data interaction value DJ corresponding to the interaction process of the production data of the target type with the same type within the local interaction period; in the formula, JL is the obtained maximum unit interaction data volume; JB is the unit standard interaction data volume corresponding to the production data of the target type and the type of interaction; JX is the unit standard interaction redundancy rate corresponding to the production data of the target type; a is the total number of historical active interactions for actively performing production data interactions; b is the total number of historical active interactions for passively performing production data interactions.

[0014] Preferably, if the single - time data interaction value is less than or equal to 1, generate that the single - time data interaction is normal, and increment the total number of normal single - time interactions between the two types performing production data interactions by one;

[0015] Conversely, generate that the single - time data interaction is abnormal, and increment the total number of abnormal single - time interactions between the two types performing production data interactions by one;

[0016] Sort and combine the single - time data interaction value, the total number of normal single - time interactions, and the total number of abnormal single - time interactions obtained from the supervision processing of the production data of the type with the production data of the same type within the local interaction period to obtain the single - time interaction supervision processing data corresponding to the interaction between pairwise types.

[0017] Preferably, when supervising and processing the local interaction status between different types of production data interactions, the total number of normal single interactions and the total number of abnormal single interactions for interactions between two types are obtained in sequence, and through the formula calculate to obtain the first local interaction status value JJ1 for interactions between two types; in the formula, NZ and NY are the total number of normal single interactions and the total number of abnormal single interactions for interactions between two types respectively; BJ is the local interaction status standard value for interactions between two types; β is the error influence coefficient for interactions between two types;

[0018] And, through the formula calculate to obtain the second local interaction status value JJ2 for interactions between two types; in the formula, LZ is the total traffic of all interactions for interactions between two types; LB is the standard total traffic of interactions for interactions between two types.

[0019] Preferably, the steps for obtaining the error influence coefficient for interactions between two types include:

[0020] Obtain the preset standard total number of interactions for interactions between two types, and use the formula to calculate the total number of normal single interactions and the total number of abnormal single interactions actually carried out between two types and the preset standard total number of interactions calculate to obtain the corresponding error influence coefficient β; in the formula, NB is the standard total number of single interactions for interactions between two types; k1 and k2 are different proportionality coefficients, and 0 < k1 < k2 < 1.

[0021] Preferably, when determining the local interaction status for interactions between two types according to the first local interaction status value and the second local interaction status value, perform data analysis on the first local interaction status value and the second local interaction status value through the local interaction recognition model, and output the corresponding local interaction status evaluation value JP for interactions between two types; the expression of the local interaction recognition model is .

[0022] Preferably, generate a normal prompt for the local interaction status between the two types to which it belongs according to the local interaction status evaluation value with a value of 0;

[0023] Generate a mild abnormality prompt for the local interaction status between two types according to the local interaction status evaluation value with a value of 1, and at the same time mark both of the two types to which it belongs as the second abnormal type;

[0024] Generate a severe abnormality prompt for the local interaction status between two types according to the local interaction status evaluation value with a value of 2, and at the same time mark both of the two types to which it belongs as the third abnormal type.

[0025] Preferably, when retrospectively classifying the remaining local interaction resources corresponding to the normal local interaction states between pairwise types, all interaction data between pairwise types with normal local interaction states are calculated through the formula to obtain the corresponding normal type value ZL; in the formula, is the maximum value among all the maximum unit interaction data volumes for interactions between pairwise types; is the unit minimum interaction redundancy rate corresponding to the production data of the target type;

[0026] If the normal type value is 0, an abnormality of the remaining local interaction resources between the pairwise types to which it belongs is generated, and both pairwise types to which it belongs are marked as the first abnormal type;

[0027] If the normal type value is -1, a normality of the remaining local interaction resources between the pairwise types to which it belongs is generated, and both pairwise types to which it belongs are marked as the normal type.

[0028] Preferably, the remaining amounts of local interaction resources corresponding to different first abnormal types are statistically counted, and the remaining amounts of local interaction resources corresponding to all first abnormal types are summed up to obtain the total remaining amount of local interaction resources;

[0029] And, the lack amounts of the first local interaction resources corresponding to different second abnormal types and the lack amounts of the second local interaction resources corresponding to different third abnormal types are statistically counted;

[0030] The lack amounts of all first local interaction resources and all local interaction resources are respectively summed up to obtain the total lack amount of the first local interaction resources and the total lack amount of the second local interaction resources.

[0031] Preferably, if the total remaining amount of local interaction resources simultaneously meets the requirements of the total lack amount of the first local interaction resources and the total lack amount of the second local interaction resources, an internal optimization prompt for interaction resources is generated;

[0032] If the total remaining amount of local interaction resources cannot simultaneously meet the requirements of the total lack amount of the first local interaction resources and the total lack amount of the second local interaction resources, an internal and external collaborative optimization prompt for interaction resources is generated.

[0033] Compared with the existing solutions, the beneficial effects achieved by the present invention are as follows:

[0034] By supervising and statistically counting the single interactions of different types of production data in the enterprise production process, and digitally processing and analyzing the single interaction states of the supervision and statistical data of different types of production data, the present invention can not only process the single interaction data of different types of production data and digitally represent the single data interaction state, but also provide reliable single interaction supervision and processing data support for the subsequent supervision and analysis of the local interaction states corresponding to different types of production data.

[0035] Based on all the single interaction supervision and processing data obtained from the interaction supervision and processing of different types of production data, the present invention conducts local interaction status supervision and multi-dimensional data analysis among different types, and dynamically classifies and marks the interactions between different pairwise types according to the analysis results, realizing the extended utilization of the previous single interaction supervision and processing data between different pairwise types. At the same time, it also conducts multi-level processing and digital representation of the local interaction status between different pairwise types, improving the autonomous supervision and analysis effect of different types of production data at different levels in terms of interaction.

[0036] Based on the classification and marking results of the interactions between different pairwise types, the present invention conducts interactive optimization analysis of the corresponding type of production data, and adaptively generates internal optimization prompts or internal and external collaborative optimization prompts for interactive resources according to the analysis results, realizing the evaluation of the usage of interactive resources between different pairwise types from different dimensions, and dynamically prompting for optimization management of data resources from the internal and external according to the evaluation results, improving the autonomous analysis and optimization prompt effect of different types of production data in terms of interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The present invention will be further described below with reference to the accompanying drawings.

[0038] Figure 1 It is a block diagram of the modules of an intelligent production data intelligent analysis system based on AI intelligence according to the present invention.

[0039] Figure 2 It is a block diagram of the steps of the operation of an intelligent production data intelligent analysis system based on AI intelligence according to the present invention.

[0040] Figure 3 It is a flow chart of data analysis and dynamic classification and marking of different pairwise types according to the present invention.

[0041] Figure 4 It is a flow chart of data analysis of the remaining total amount of local interactive resources according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0042] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0043] Such as Figures 1 to 2As shown in the figure, the present invention is an intelligent production data analysis system based on AI intelligence, including a single interaction supervision module for production data, a partial interaction supervision module for production data, and an interaction optimization analysis module for production data;

[0044] The single interaction supervision module for production data is used to supervise and statistically analyze the single interactions of different types of production data during the enterprise production process, and digitally process and analyze the supervision statistical data of different types of production data for the single interaction status to obtain the single interaction supervision processing data corresponding to different types of production data; including:

[0045] It should be noted that different types of production data can be divided according to the departments of production data, or according to the equipment of production data, or determined according to the actual application rules of the actual application scenario;

[0046] When carrying out supervision and processing on the interaction of different types of production data, obtain the corresponding type supervision period according to the type of different production data. Different types of production data all correspond to a different type supervision period. The unit of the type supervision period is seconds, and the specific value can be determined according to the previous test data of the enterprise production data, so as to implement differential supervision and processing on different types of production data. The interaction of different types of production data refers to the exchange, sharing, and integration between different types of production data, and for the local interaction period from the start of interaction to the end of interaction between the production data of the target type and other types of production data within the type supervision period. The target type refers to the type that actively initiates an interaction application, and obtain the maximum unit interaction data volume of the production data of the target type and the same type of interaction process within the local interaction period;

[0047] Pass the obtained maximum unit interaction data volume through the formula Calculate to obtain the single data interaction value DJ corresponding to the interaction process of the production data of the target type and the same type within the local interaction period; in the formula, JL is the obtained maximum unit interaction data volume; JB is the unit standard interaction data volume corresponding to the production data of the target type and the interaction type, which can be determined according to the previous test data or operation design data before the target type and the interaction type; JX is the unit standard interaction redundancy rate corresponding to the production data of the target type, which can also be determined according to the previous test data or operation design data before the target type and the interaction type; a is the total number of historical active interactions for actively carrying out production data interaction; b is the total number of historical active interactions for passively carrying out production data interaction;

[0048] It should be explained that the single data interaction value is used to process and calculate the interaction data of the target type and the same type within the local interaction period to digitally represent the single data interaction status between their two types;

[0049] If the single - time data interaction value is less than or equal to 1, it is generated that the single - time data interaction is normal, and the total number of normal single - time interactions between the two types performing production data interaction is incremented by one;

[0050] Conversely, it is generated that the single - time data interaction is abnormal, and the total number of abnormal single - time interactions between the two types performing production data interaction is incremented by one;

[0051] Sort and combine the single - time data interaction value, the total number of normal single - time interactions, and the total number of abnormal single - time interactions obtained from the supervision and processing of the production data of the same type during the local interaction period of the type production data to obtain the single - time interaction supervision and processing data corresponding to the interaction between two - by - two types;

[0052] It can be understood that when supervising and processing the existing digital enterprise production data, in the early stage, according to factors such as the nature, use, security, and real - time nature of the production data, different preset requirements are implemented for the interaction of different types of data generated by the enterprise production data. However, the preset requirements are basically set according to the operation requirements of the enterprise or historical requirements to determine the business data. Different types of data will have different problems during the actual interaction process, but the existing technical solutions do not implement targeted supervision and processing analysis;

[0053] In the embodiments of the present invention, by supervising and statistically analyzing the single - time interactions of different types of production data during the enterprise production process, and digitally processing and analyzing the supervision and statistical data of different types of production data for the single - time interaction status, it is possible to not only process the single - time interaction data of different types of production data and digitally represent the single - time data interaction status, but also provide reliable single - time interaction supervision and processing data support for the subsequent supervision and analysis of the local interaction status corresponding to different types of production data.

[0054] The production data local interaction supervision module is used to perform local interaction status supervision processing and multi - dimensional data analysis between different types according to all single - time interaction supervision and processing data obtained from the interaction supervision and processing of different types of production data, and dynamically classify and mark the interactions between different two - by - two types according to the analysis results; including:

[0055] When performing supervision and processing on the local interaction status between different types performing production data interaction, sequentially obtain the total number of normal single - time interactions and the total number of abnormal single - time interactions for the interaction between two - by - two types, and through the formula Calculate and obtain the first local interaction status value JJ1 for the interaction between two types; in the formula, NZ and NY are respectively the total number of normal single interactions and the total number of abnormal single interactions for the interaction between two types; BJ is the local interaction status standard value for the interaction between two types, which can be determined according to previous test data or operation design data; β is the error influence coefficient for the interaction between two types, which plays a role in improving the accuracy and reliability of data calculation;

[0056] It should be explained that the first local interaction status value is used to process and calculate all single interaction status data for the interaction between two types in terms of the number of interactions, so as to digitally represent the local interaction status between them;

[0057] Among them, the steps for obtaining the error influence coefficient for the interaction between two types include:

[0058] Obtain the preset standard total number of interactions for the interaction between two types, which can be determined according to previous test data or operation design data, and use the formula to calculate the total number of normal single interactions and the total number of abnormal single interactions actually carried out between the two with the preset standard total number of interactions Calculate and obtain the corresponding error influence coefficient β; in the formula, NB is the standard total number of single interactions for the interaction between two types; k1 and k2 are different proportionality coefficients, and 0 < k1 < k2 < 1, k1 can take the value of 0.427, and k2 can take the value of 0.573;

[0059] It should be noted that by integrating and calculating different numbers of interaction data between two types, the local interaction status standard value for the interaction between two types can be dynamically corrected, thereby improving the accuracy and reliability of the calculation of the local interaction status data between two types;

[0060] And, use the formula Calculate and obtain the second local interaction status value JJ2 for the interaction between two types; in the formula, LZ is the total interaction flow for the interaction between two types; LB is the standard interaction total flow for the interaction between two types, which can be determined according to previous test data or operation design data;

[0061] It should be explained that the second local interaction status value is used to process and calculate all single interaction status data for the interaction between two types in terms of interaction flow, so as to digitally represent the local interaction status between them;

[0062] In the embodiments of the present invention, by performing diversified data calculations on different regulatory processing data for interactions between pairwise types, it is possible to digitally represent the local interaction states between pairwise types from different aspects, which can effectively improve the diversity and reliability of the regulatory processing of local interaction states between different types.

[0063] When determining the local interaction state of the interaction between pairwise types according to the first local interaction state value and the second local interaction state value, the first local interaction state value and the second local interaction state value are analyzed through a local interaction recognition model, and the corresponding local interaction state evaluation value JP between the pairwise types is output; the expression of the local interaction recognition model is ;

[0064] The local interaction state evaluation value includes a numerical value of 0, 1, or 2;

[0065] Generate a normal prompt for the local interaction state between the pairwise types to which the local interaction state evaluation value with a value of 0 belongs;

[0066] It can be understood that when the local interaction state between pairwise types is normal, there are still two situations. One is that the remaining state of the local interaction resources between the pairwise types is normal, that is, the actual interaction resource usage between the pairwise types is within the preset requirements; the other is that the remaining state of the local interaction resources between the pairwise types is abnormal, that is, the actual interaction resource usage between the pairwise types is lower than the preset requirements, resulting in idle waste of the preset interaction resources. Therefore, further trace analysis is required;

[0067] Moreover, when classifying the remaining local interaction resources corresponding to the normal local interaction state between pairwise types, all interaction data between the pairwise types with a normal local interaction state is calculated through the formula to obtain the corresponding normal type value ZL; in the formula, is the maximum value among all the maximum unit interaction data volumes for the interaction between the pairwise types; is the unit minimum interaction redundancy rate corresponding to the production data of the target type, , which can be determined according to the previous test data or operation design data;

[0068] As Figure 3 shown, if the normal type value is 0, generate the remaining abnormality of the local interaction resources between the pairwise types to which it belongs, and mark both of the pairwise types as the first abnormal type. The first abnormal type indicates that the actual interaction resource usage between the pairwise types is lower than the preset requirements;

[0069] If the normal type value is -1, generate the remaining normality of the local interaction resources between the pairwise types to which it belongs, and mark both of the pairwise types as the normal type;

[0070] Generate a mild abnormal prompt for the local interaction status between pairwise types according to the local interaction status evaluation value of 1, and at the same time mark all the pairwise types belonging to it as the second abnormal type;

[0071] Generate a severe abnormal prompt for the local interaction status between pairwise types according to the local interaction status evaluation value of 2, and at the same time mark all the pairwise types belonging to it as the third abnormal type;

[0072] In the embodiment of the present invention, all single interaction supervision and processing data obtained according to the interaction supervision and processing of different types of production data are used for local interaction status supervision and processing and multi-dimensional data analysis between different types. According to the analysis results, the interactions between different pairwise types are dynamically classified and marked, realizing the extended utilization of the previous single interaction supervision and processing data between different pairwise types. At the same time, the local interaction status between different pairwise types is processed and digitally represented at multiple levels, improving the autonomous supervision and analysis effects at different levels of the interaction of different types of production data.

[0073] The production data interaction optimization analysis module is used to perform interaction optimization analysis on the production data of the corresponding type according to the classification and marking results of the interactions between different pairwise types, and adaptively generate internal optimization prompts or internal and external collaborative optimization prompts for the interaction resources according to the analysis results; including:

[0074] Statistically calculate the remaining amount of local interaction resources corresponding to different first abnormal types, and sum up the remaining amounts of local interaction resources corresponding to all first abnormal types to obtain the total remaining amount of local interaction resources;

[0075] And, statistically calculate the lack amount of the first local interaction resources corresponding to different second abnormal types, and the lack amount of the second local interaction resources corresponding to different third abnormal types;

[0076] Sum up all the lack amounts of the first local interaction resources and all the lack amounts of the local interaction resources respectively to obtain the total lack amount of the first local interaction resources and the total lack amount of the second local interaction resources;

[0077] As Figure 4 shown, perform matching analysis on the total remaining amount of local interaction resources with the total lack amount of the first local interaction resources and the total lack amount of the second local interaction resources respectively;

[0078] If the total remaining amount of local interaction resources simultaneously meets the requirements of the total lack amount of the first local interaction resources and the total lack amount of the second local interaction resources, generate an internal optimization prompt for the interaction resources;

[0079] If the total remaining amount of local interaction resources cannot simultaneously meet the requirements of the first total shortage of local interaction resources and the second total shortage of local interaction resources, an internal and external collaborative optimization prompt for interaction resources is generated.

[0080] Different from the existing technical solutions, which only stay at supervising and analyzing the interaction of different production data and directly expanding and optimizing external resources based on the analysis results, resulting in poor comprehensiveness of expansion and optimization and poor resource usage effects.

[0081] In the embodiments of the present invention, according to the classification marking results of the interactions between different pairwise types, the interaction optimization analysis of the corresponding type of production data is carried out, and an internal optimization prompt for interaction resources or an internal and external collaborative optimization prompt is adaptively generated according to the analysis results, realizing the evaluation of the usage of interaction resources between different pairwise types from different dimensions, and dynamically prompting the optimization management of data resources from the internal and external according to the evaluation results, improving the autonomous analysis and optimization prompt effect of different types of production data in terms of interaction.

[0082] In several embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the above-described embodiments of the invention are merely illustrative. For example, the division of modules is only a logical function division, and there can be other division methods in actual implementation.

[0083] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules. They can be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0084] In addition, in each embodiment of the present invention, the functional modules can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of a combination of hardware and software functional modules.

[0085] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and can be implemented in other specific forms without departing from the basic characteristics of the present invention.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An AI-based intelligent production data analysis system, characterized in that: It includes a production data single interaction supervision module, a production data local interaction supervision module and a production data interaction optimization analysis module; The production data single interaction supervision module is used to supervise and collect data statistics on the single interactions of different types of production data in the enterprise's production process, and to digitally process and analyze the single interaction status of the supervision statistical data of different types of production data to obtain the single interaction supervision processing data corresponding to different types of production data; The local interaction supervision module of production data is used to perform local interaction status supervision processing and multi-dimensional data analysis between different types of production data according to all single interaction supervision processing data obtained from the interaction supervision processing of different types of production data, and dynamically classify and mark the interactions between different types according to the analysis results; the interaction classification marks between different types include normal type marks, first abnormal type marks, second abnormal type marks and third abnormal type marks; The production data interaction optimization analysis module is used to perform interaction optimization analysis on the corresponding type of production data according to the classification and labeling results of interactions between different types, and to adaptively generate internal optimization prompts for interactive resources or internal and external collaborative optimization prompts according to the analysis results; Wherein, the corresponding total amount of remaining local interactive resources is obtained according to all first abnormal types of classification marks, and the corresponding total amount of missing first local interactive resources and total amount of missing second local interactive resources are obtained according to all second abnormal types and all third abnormal types of classification marks respectively; The remaining total amount of local interactive resources is matched and analyzed with the total amount of missing first local interactive resources and the total amount of missing second local interactive resources, and an internal optimization prompt or an internal and external collaborative optimization prompt of interactive resources is adaptively generated according to the analysis results.

2. According to claim 1, the AI-based production data intelligent analysis system is characterized in that: When conducting supervision on the interaction of different types of production data, obtain the corresponding type supervision cycle according to the type of different production data, and obtain the local interaction period from the start to the end of the interaction between the target type of production data and other types of production data within the type supervision period, and obtain the maximum unit interaction data volume of the target type of production data and the same type of interaction process within the local interaction period; The maximum unit interaction data volume obtained is calculated by the formula Calculate the single data interaction value DJ corresponding to the interaction process between the target type's production data and the same type in the local interaction period; where JL is the maximum unit interaction data volume obtained; JB is the unit standard interaction data volume corresponding to the target type's production data and the interaction type; JX is the unit standard interaction redundancy rate corresponding to the target type's production data; a is the total number of historical active interactions for active production data interaction; b is the total number of historical active interactions for passive production data interaction.

3. According to claim 2, the AI-based production data intelligent analysis system is characterized in that: If the single data interaction value is less than or equal to 1, a single data interaction is generated to be normal, and the total number of single interactions between the two types of production data interaction is increased by one; Otherwise, a single data interaction exception is generated, and the total number of single interaction exceptions between the two types of production data interaction is increased by one; The single data interaction values, the total number of normal single interactions and the total number of abnormal single interactions obtained through the supervision and processing of type production data and the same type production data within the local interaction period are sorted and combined to obtain the single interaction supervision and processing data corresponding to the interaction between two types.

4. According to claim 3, the AI-based production data intelligent analysis system is characterized in that: When supervising the local interaction status between different types of production data interaction, the total number of normal single interactions and the total number of abnormal single interactions between two types are obtained in turn, and the formula is used to calculate the normal and abnormal single interactions. Calculate and obtain the first local interaction state value JJ1 of the interaction between two types; where NZ and NY are the total number of normal single interactions and the total number of abnormal single interactions between two types, respectively; BJ is the standard value of the local interaction state between two types; β is the error influence coefficient of the interaction between two types; And, through the formula The second local interaction state value JJ2 of the interaction between two types is calculated; where LZ is the total interaction flow of all interaction between two types; LB is the standard interaction total flow of interaction between two types.

5. According to claim 4, the AI-based production data intelligent analysis system is characterized in that: The steps for obtaining the error influence coefficients for interaction between two types include: Get the total number of preset standard interactions between two types, and add the total number of normal single interactions and the total number of abnormal single interactions between two types to the total number of preset standard interactions through the formula Calculate and obtain the corresponding error influence coefficient β; where NB is the total number of single interaction standards between two types of interactions; k1 and k2 are different proportional coefficients, and 0<k1<k2<1.

6. The AI-based production data intelligent analysis system according to claim 4 is characterized in that: When determining the local interaction state of interaction between two types according to the first local interaction state value and the second local interaction state value, the first local interaction state value and the second local interaction state value are subjected to data analysis through the local interaction recognition model, and the local interaction state evaluation value JP corresponding to the two types is output; the expression of the local interaction recognition model is: .

7. The AI-based production data intelligent analysis system according to claim 6 is characterized in that: Generate a normal prompt of the local interaction status between the two types according to the local interaction status evaluation value of 0; According to the local interaction state evaluation value of 1, a local interaction state slight abnormality prompt between two types is generated, and at the same time, the two types are marked as the second abnormal type; According to the local interaction state evaluation value of 2, a severe abnormal prompt of the local interaction state between the two types is generated, and the two types are marked as the third abnormal type.

8. The AI-based production data intelligent analysis system according to claim 7 is characterized in that: When tracing back and classifying the local interaction resource surplus corresponding to the normal local interaction status between two types, all the interaction data between two types with normal local interaction status are classified by formula Calculate and obtain the corresponding normal type value ZL; where, It is the maximum value of all maximum unit interaction data volumes between two types of interactions; The minimum interactive redundancy rate per unit corresponding to the target type production data; If the normal type value is 0, a local interaction resource remaining exception between the two types is generated, and the two types are marked as the first exception type; If the normal type value is -1, the remaining local interaction resources between the two types are generated to be normal, and the two types are marked as normal types.

9. The AI-based production data intelligent analysis system according to claim 8, characterized in that: Counting the remaining local interaction resources corresponding to different first exception types, and summing the remaining local interaction resources corresponding to all first exception types to obtain a total remaining local interaction resource; and, counting the first local interaction resource shortage amounts corresponding to different second abnormality types and the second local interaction resource shortage amounts corresponding to different third abnormality types; All first local interaction resource shortage amounts and all local interaction resource shortage amounts are summed up respectively to obtain the first local interaction resource shortage total amount and the second local interaction resource shortage total amount.

10. The AI-based production data intelligent analysis system according to claim 9, characterized in that: If the remaining total amount of local interactive resources simultaneously meets the requirements of the total amount of missing first local interactive resources and the total amount of missing second local interactive resources, an interactive resource internal optimization prompt is generated; If the remaining total amount of local interactive resources cannot simultaneously meet the needs of the first local interactive resource shortage total amount and the second local interactive resource shortage total amount, an interactive resource internal and external collaborative optimization prompt is generated.

Images