Artificial intelligence-based process productivity tool construction intelligent management system

Abstract

The invention discloses an artificial intelligence-based intelligent management system for constructing a process productivity tool, and belongs to the technical field of production management. The method is used for solving the technical problems of poor product quality and process production autonomous supervision and analysis effect and poor autonomous optimization and management effect after a process productivity tool is constructed in an existing scheme. According to the invention, monitoring statistics and processing analysis of a local finished product quality effect are carried out on the product quality after the process productivity tool is constructed, and monitoring statistics and processing analysis of a local active processing effect are carried out on the process production after the process productivity tool is constructed. The method comprises the following steps of: performing data integration analysis on different local supervision analysis data obtained by local monitoring analysis in different aspects of product quality and process production after the construction of the processing productivity tool in an integral aspect, and determining the construction implementation integral effect after the construction of the processing productivity tool; and dynamic optimization management is carried out on the process productivity tool according to the construction implementation overall effect.

Description

Technical Field

[0001] The present invention relates to the technical field of production management, and in particular to an intelligent management system based on artificial intelligence-based process productivity tools. Background Art

[0002] Process productivity tool building refers to the creation or customization of software applications that are designed to increase an organization's efficiency and productivity by automating and optimizing business processes; this type of tool is often used to simplify repetitive tasks, reduce errors, speed up the flow of information, and support the decision-making process.

[0003] When implementing the existing intelligent management solutions built with process-based productivity tools, the quality management tools for productivity cannot conduct management effectiveness supervision and analysis from different aspects, and adaptively and dynamically optimize the management based on the supervision and analysis results from different aspects. As a result, the autonomous supervision and analysis of product quality and process production after the construction of process-based productivity tools is not effective, as is the autonomous optimization management. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent management system for building a process productivity tool based on artificial intelligence, which is used to solve the technical problems of poor autonomous supervision and analysis of product quality and process production after the construction of the process productivity tool and poor autonomous optimization management in the existing solutions.

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

[0006] An artificial intelligence-based intelligent management system for constructing process productivity tools, including a tool construction effect monitoring and analysis module, which is used to perform local effect monitoring statistics and processing analysis on different aspects of product quality and process production after the process productivity tool is constructed, and obtain local effect monitoring and processing data corresponding to different aspects;

[0007] The tool construction effect evaluation management module is used to conduct overall data integration analysis on the first local effect monitoring and processing data and the second local effect monitoring and processing data obtained from local monitoring and analysis of different aspects of product quality and process production after the construction of the process productivity tool, determine the overall effect of the construction implementation after the construction of the process productivity tool, and dynamically optimize the management of the process productivity tool based on the overall effect of the construction implementation.

[0008] Preferably, the product quality after the process productivity tool is built is monitored and analyzed for the local finished product quality effect, and the total number of unqualified products N corresponding to the quality inspection of the product production during the monitoring period is obtained, and the formula is used Calculate the quality status value ZZ after the acquisition tool is built; where N′ is the total number of products produced during the monitoring period; ZL is the product failure rate corresponding to the same monitoring period before the process productivity tool is built;

[0009] The quality status value of -2 indicates that the quality of some finished products is unqualified.

[0010] Preferably, a retrospective analysis of the quality effect of the local finished product is performed according to the quality status value of -1, and the formula Calculate and obtain the quality status traceability value ZS after tool construction; where A is the tool construction production quality design value; [*] is the rounding function, which means obtaining the maximum integer that does not exceed the real number *;

[0011] Conduct data analysis on quality status traceability values.

[0012] Preferably, if the quality status traceability value is 0, it indicates that the quality effect of the local finished product is average;

[0013] If the quality status traceability value is greater than 0, it indicates that the quality of the local finished product is excellent;

[0014] The quality status values ​​and quality status traceability values ​​obtained through processing are sorted and combined to obtain the first local effect monitoring processing data of the local finished product quality effect.

[0015] Preferably, the process production after the process productivity tool is constructed is monitored, counted and analyzed for the local active processing effect, and the total number of active processing times and the total number of problem occurrences corresponding to different problem types in product production within the monitoring period are obtained, and the total number of active processing times and the total number of problem occurrences are sorted and combined to obtain the local problem type reaction processing sequence corresponding to the corresponding problem type;

[0016] When different problem types are classified and marked according to the local problem type reaction processing sequence, the local problem type reaction processing sequences corresponding to the different problem types are traversed and analyzed in turn;

[0017] If all elements in the local problem type response processing sequence are 0, the corresponding problem type is marked as a regular problem type;

[0018] If there is an element with a value other than 0 in the local problem type response processing sequence, the corresponding problem type is marked as the target problem type;

[0019] All target question types are sorted and combined to obtain a target question type combination set.

[0020] Preferably, when performing processing analysis on the local problem processing impact state of the process production after the process productivity tool is constructed according to the target problem type combination set, the local problem type reaction processing sequence associated with different target problem types in the target problem type combination set is obtained in turn, and ... analyzed in the formula Calculate and obtain the local problem processing impact value JYi corresponding to different target problem types; where i is the different target problem types, i = 1, 2, 3, ..., n; n is a positive integer; NYi and NZi are the total number of active processing times and the total number of problem occurrences associated with different target problem types, respectively; e is a natural constant; C is the standard value of the measure processing;

[0021] If the local problem processing impact value is less than or equal to 1, the target problem type is marked as a valid processing problem type.

[0022] Preferably, if the local problem processing impact value is greater than 1, the target problem type is marked as an invalid processing problem type, and the formula Calculate and obtain the invalid processing influence CWi corresponding to the invalid processing problem type; where WYi is the problem type influence factor corresponding to the invalid processing problem type;

[0023] All local problem processing influence values ​​and all invalid processing influences obtained by processing are sorted and combined to obtain the second local effect monitoring processing data of the local active processing effect.

[0024] Preferably, the first local effect monitoring processing data and the second local effect monitoring processing data are respectively traversed and counted, and the formula Calculate and obtain the corresponding cycle overall reliability ZK after the process productivity tool is built; where a and b are different calculation weight coefficients, 0<a<b; B is the cycle overall reliability standard value;

[0025] Perform data analysis on the overall reliability of the cycle.

[0026] Preferably, if the overall reliability of the cycle is greater than or equal to 1, it is indicated that the overall effect of the construction implementation of the process productivity tool after construction is normal, and the subsequent normal use of the constructed process productivity tool is maintained;

[0027] If the overall reliability of the cycle is less than 1, it indicates that the overall effect of the construction implementation of the process productivity tool after construction is abnormal, and the subsequent use of the process productivity tool is dynamically managed.

[0028] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0029] The present invention obtains first local effect monitoring and processing data on local finished product quality effects by monitoring, counting, and processing and analyzing the local finished product quality effects of the product quality after the process productivity tool is constructed. Second local effect monitoring and processing data on local problem processing impact status is obtained by monitoring, counting, and processing and analyzing the local active processing effects of the process production after the process productivity tool is constructed. Reliable local problem processing impact status analysis data support can be provided for the subsequent construction and implementation of an integrated analysis of the overall effect.

[0030] The present invention conducts overall data integration analysis on different local supervision and analysis data obtained from local monitoring and analysis of different aspects of product quality and process production after the construction of the process productivity tool, determines the overall effect of the construction and implementation of the process productivity tool after construction, and dynamically optimizes and manages the process productivity tool according to the overall effect of construction and implementation, thereby realizing the expanded utilization of different local supervision and analysis data in the early stage, and can perform data analysis and dynamic management of the overall effect from an overall dimension, thereby improving the autonomous supervision and analysis effect and autonomous optimization management effect of product quality and process production after the construction of the process productivity tool. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The present invention will be further described below in conjunction with the accompanying drawings.

[0032] Figure 1 A flowchart of building an intelligent management system for an artificial intelligence-based process productivity tool according to the present invention.

[0033] Figure 2 The present invention is a flowchart of the steps for constructing an intelligent management system for a process productivity tool based on artificial intelligence. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] like Figure 1 to Figure 2 As shown, the present invention is an artificial intelligence-based process productivity tool construction intelligent management system, including a tool construction effect monitoring and analysis module and a tool construction effect evaluation and management module;

[0036] The tool construction effect monitoring and analysis module is used to conduct local effect monitoring statistics and processing analysis on different aspects of product quality and process production after the process productivity tool is built, and obtain local effect monitoring and processing data corresponding to different aspects; including:

[0037] After the process productivity tool is built, the product quality is monitored, counted and analyzed for the local finished product quality effect, and the total number of unqualified products N corresponding to the quality inspection of the product production during the monitoring period is obtained. The monitoring period can be determined according to the preset number of monitoring days or the preset total number of products produced. The quality inspection of the production products is implemented by the existing quality inspection plan. The specific steps are not repeated here and are determined by the formula Calculate the quality status value ZZ after the acquisition tool is built; where N′ is the total number of products produced during the monitoring period; ZL is the product failure rate corresponding to the same monitoring period before the process productivity tool is built;

[0038] The quality status value of -2 indicates that the quality of the local finished product is unqualified;

[0039] In the embodiment of the present invention, by monitoring and counting the local finished product quality effect of the product quality after the process productivity tool is constructed and processing and calculating, the quality status value corresponding to the product production after the tool is constructed is obtained, thereby realizing the digital representation of the local finished product quality effect;

[0040] And, based on the quality status value of -1, the local finished product quality effect is traced back and analyzed, and the formula Calculate and obtain the quality status traceability value ZS after the tool is built; where A is the production quality design value of the tool, which is determined according to the design requirements of the product production quality corresponding to the constructed process productivity tool; [*] is the rounding function, which means obtaining the maximum integer that does not exceed the real number *;

[0041] In the embodiment of the present invention, based on the results of the previous quality status value processing and analysis, the qualified status of the local finished product quality effect is further traced and analyzed, and the quality status traceability value after the tool is constructed is obtained through data calculation, which can provide reliable data support for the subsequent qualified status analysis of the local finished product quality effect.

[0042] Perform data analysis on the quality status traceability value. If the quality status traceability value is 0, it indicates that the quality of the local finished product is average.

[0043] If the quality status traceability value is greater than 0, it indicates that the quality of the local finished product is excellent;

[0044] The quality status values ​​and quality status traceability values ​​obtained by processing are sorted and combined to obtain the first local effect monitoring processing data of the local finished product quality effect;

[0045] In the embodiment of the present invention, by monitoring, counting and processing the local finished product quality effects of the product quality after the process productivity tool is constructed, the first local effect monitoring and processing data of the local finished product quality effects are obtained, which can not only realize the data processing and analysis and digital representation of the local finished product quality effects, but also provide reliable local finished product quality effect analysis data support for the subsequent construction and implementation of the integrated analysis of the overall effect.

[0046] Also, monitor, count and analyze the local active processing effects of the process production after the process productivity tool is built, obtain the total number of active processing times and the total number of problem occurrences corresponding to different types of product production problems within the monitoring period, sort and combine the total number of active processing times and the total number of problem occurrences, and obtain the local problem type response processing sequence corresponding to the corresponding problem type;

[0047] Among them, active processing includes corrective action processing and preventive action processing;

[0048] Different problem types, including but not limited to material handling and sorting problem types, inventory management problem types, process control problem types, safety monitoring problem types, and energy management problem types;

[0049] The process productivity tools we built have corresponding proactive and preventive measures for different types of problems.

[0050] When different problem types are classified and marked according to the local problem type reaction processing sequence, the local problem type reaction processing sequences corresponding to the different problem types are traversed and analyzed in turn;

[0051] If all elements in the local problem type response processing sequence are 0, the corresponding problem type is marked as a regular problem type;

[0052] If there is an element with a value other than 0 in the local problem type response processing sequence, the corresponding problem type is marked as the target problem type;

[0053] Sort and combine all target question types to obtain a target question type combination set;

[0054] In an embodiment of the present invention, different problem types are classified and marked by utilizing a local problem type reaction processing sequence, and the marked results are sorted and combined to obtain a target problem type combination set, which can provide reliable screening data support for subsequent local problem processing and analysis of the impact status.

[0055] When analyzing the impact of local problem processing on the process production after the process productivity tool is built according to the target problem type combination set, the local problem type reaction processing sequence associated with different target problem types in the target problem type combination set is obtained in turn, and the local problem type reaction processing sequence is obtained through the formula Calculate and obtain the local problem processing impact value JYi corresponding to different target problem types; where i is the different target problem types, i = 1, 2, 3, ..., n; n is a positive integer; NYi and NZi are the total number of active processing times and the total number of problem occurrences associated with different target problem types, respectively; e is a natural constant; C is the standard value of the measure processing, which is determined according to the design requirements of the product production quality corresponding to the constructed process productivity tool;

[0056] In the embodiment of the present invention, by performing data calculation on problem data of different aspects corresponding to different target problem types, the corresponding local problem processing impact value is obtained, which can provide reliable data support for the secondary marking of subsequent target problem types;

[0057] If the local problem processing impact value is less than or equal to 1, the target problem type is marked as a valid processing problem type;

[0058] If the local problem processing impact value is greater than 1, the target problem type is marked as an invalid processing problem type, and the formula Calculate and obtain the invalid processing influence CWi corresponding to the invalid processing problem type; where WYi is the problem type influence factor corresponding to the invalid processing problem type;

[0059] Among them, each problem type is pre-set with a corresponding problem type impact factor, which is used to digitize and differentiate the problem type impact corresponding to the different problem types. The specific value of the problem type impact factor corresponding to the different problem types can be determined by the total number of historical occurrences of the corresponding problem type and the corresponding total negative impact, or can be determined by professional and technical personnel in this field based on work experience;

[0060] All local problem processing impact values ​​and all invalid processing impacts obtained by processing are sorted and combined to obtain the second local effect monitoring processing data of the local active processing effect;

[0061] In the embodiment of the present invention, by monitoring statistics and processing analysis of the local active processing effects of the process production after the process productivity tool is constructed, the second local effect monitoring and processing data of the local problem processing impact status is obtained, which can not only realize the data processing analysis and digital representation of the local problem processing impact status, but also provide reliable local problem processing impact status analysis data support for the subsequent construction and implementation of the integrated analysis of the overall effect.

[0062] The tool construction effect evaluation management module is used to conduct overall data integration analysis on the first local effect monitoring and processing data and the second local effect monitoring and processing data obtained from the local monitoring and analysis of different aspects of product quality and process production after the process productivity tool is constructed, determine the overall construction implementation effect after the process productivity tool is constructed, and dynamically optimize the process productivity tool according to the overall construction implementation effect; including:

[0063] The first local effect monitoring and processing data and the second local effect monitoring and processing data are traversed and counted respectively, and the formula is used Calculate and obtain the corresponding cycle overall reliability ZK after the process productivity tool is constructed; where a and b are different calculation weight coefficients, 0<a<b, and the specific values ​​of a and b are not limited and can be customized according to the actual application requirements of the actual application scenario; B is the cycle overall reliability standard value, which is determined according to the design requirements of the product production quality corresponding to the constructed process productivity tool;

[0064] In an embodiment of the present invention, by integrating and calculating different local monitoring and analysis data of product production after the process productivity tool is constructed, the corresponding overall reliability of the cycle is obtained, which not only realizes the digital representation of the overall effect of the construction implementation, but also provides reliable overall supervision and analysis data support for the dynamic management of the subsequent use of the subsequent process productivity tool.

[0065] Perform data analysis on the overall reliability of the cycle. If the overall reliability of the cycle is greater than or equal to 1, it indicates that the overall effect of the construction and implementation of the process productivity tool after construction is normal, and the subsequent normal use of the constructed process productivity tool is maintained;

[0066] If the overall reliability of the cycle is less than 1, it indicates that the overall effect of the construction and implementation of the process productivity tool after construction is abnormal, and the subsequent use of the process productivity tool is dynamically managed;

[0067] Among them, dynamic management includes design optimization of different local aspects of the constructed process productivity tools, such as local design optimization of finished product quality effects and local design optimization of problem handling impacts.

[0068] In the embodiment of the present invention, by performing overall data integration analysis on different local supervision and analysis data obtained from local monitoring and analysis of different aspects of product quality and process production after the construction of the process productivity tool, the overall effect of the construction and implementation of the process productivity tool after construction is determined, and the process productivity tool is dynamically optimized and managed based on the overall effect of the construction and implementation, thereby achieving expanded utilization of different local supervision and analysis data in the early stage, and performing data analysis and dynamic management of the overall effect from an overall dimension, thereby improving the autonomous supervision and analysis effect and autonomous optimization management effect of product quality and process production after the construction of the process productivity tool.

[0069] In addition, the formulas involved in the above are all dimensionless and numerical calculations. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and simulating it with simulation software.

[0070] In the 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 only illustrative, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0071] 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, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0072] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0073] It is obvious to a person skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the essential characteristics of the present invention.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. An artificial intelligence-based process productivity tool to build an intelligent management system, characterized in that: It includes a tool construction effect monitoring and analysis module, which is used to perform local effect monitoring statistics and processing analysis on different aspects of product quality and process production after the process productivity tool is constructed, and obtain local effect monitoring processing data corresponding to different aspects; the local effect monitoring processing data corresponding to different aspects include first local effect monitoring processing data and second local effect monitoring processing data; The tool construction effect evaluation management module is used to conduct overall data integration analysis on the first local effect monitoring and processing data and the second local effect monitoring and processing data obtained from local monitoring and analysis of different aspects of product quality and process production after the construction of the process productivity tool, determine the overall effect of the construction implementation after the construction of the process productivity tool, and dynamically optimize the management of the process productivity tool based on the overall effect of the construction implementation.

2. According to claim 1, a process productivity tool based on artificial intelligence to build an intelligent management system, characterized in that: After the process productivity tool is built, the quality of the local finished product is monitored, counted and analyzed, and the total number of unqualified products in the corresponding quality inspection of the product production during the monitoring period is obtained, and the formula is used to calculate the total number of unqualified products. Calculate the quality status value ZZ after the acquisition tool is built; where N′ is the total number of products produced during the monitoring period; ZL is the product failure rate corresponding to the same monitoring period before the process productivity tool is built; The quality status value of -2 indicates that the quality of some finished products is unqualified.

3. According to claim 2, a process productivity tool based on artificial intelligence to build an intelligent management system, characterized in that: According to the quality status value of -1, the local finished product quality effect is traced back and analyzed, and the formula Calculate and obtain the quality status traceability value ZS after tool construction; where A is the tool construction production quality design value; [*] is the rounding function, which means obtaining the maximum integer that does not exceed the real number *; Conduct data analysis on quality status traceability values.

4. According to claim 3, an artificial intelligence-based process productivity tool to build an intelligent management system, characterized in that: If the quality status traceability value is 0, it indicates that the quality of the local finished product is average; If the quality status traceability value is greater than 0, it indicates that the quality of the local finished product is excellent; The quality status values ​​and quality status traceability values ​​obtained through processing are sorted and combined to obtain the first local effect monitoring processing data of the local finished product quality effect.

5. According to claim 4, a process productivity tool based on artificial intelligence to build an intelligent management system, characterized in that: Monitor and analyze the local active processing effects of process production after the process productivity tool is built, obtain the total number of active processing times and the total number of problem occurrences corresponding to different types of product production problems during the monitoring period, sort and combine the total number of active processing times and the total number of problem occurrences, and obtain the local problem type response processing sequence corresponding to the corresponding problem type; When different problem types are classified and marked according to the local problem type reaction processing sequence, the local problem type reaction processing sequences corresponding to the different problem types are traversed and analyzed in turn; If all elements in the local problem type response processing sequence are 0, the corresponding problem type is marked as a regular problem type; If there is an element with a value other than 0 in the local problem type response processing sequence, the corresponding problem type is marked as the target problem type; All target question types are sorted and combined to obtain a target question type combination set.

6. According to claim 5, an artificial intelligence-based process productivity tool to build an intelligent management system, characterized in that: When analyzing the impact of local problem processing on the process production after the process productivity tool is built according to the target problem type combination set, the local problem type reaction processing sequence associated with different target problem types in the target problem type combination set is obtained in turn, and the local problem type reaction processing sequence is obtained through the formula Calculate and obtain the local problem processing impact value JYi corresponding to different target problem types; where i is the different target problem types, i = 1, 2, 3, ..., n; n is a positive integer; NYi and NZi are the total number of active processing times and the total number of problem occurrences associated with different target problem types, respectively; e is a natural constant; C is the standard value of the measure processing; If the local problem processing impact value is less than or equal to 1, the target problem type is marked as a valid processing problem type.

7. According to claim 6, a process productivity tool based on artificial intelligence to build an intelligent management system, characterized in that: If the local problem processing impact value is greater than 1, the target problem type is marked as an invalid processing problem type, and the formula Calculate and obtain the invalid processing influence CWi corresponding to the invalid processing problem type; where WYi is the problem type influence factor corresponding to the invalid processing problem type; All local problem processing influence values ​​and all invalid processing influences obtained by processing are sorted and combined to obtain the second local effect monitoring processing data of the local active processing effect.

8. According to claim 7, a process productivity tool based on artificial intelligence to build an intelligent management system, characterized in that: The first local effect monitoring and processing data and the second local effect monitoring and processing data are traversed and counted respectively, and the formula is used Calculate and obtain the corresponding cycle overall reliability ZK after the process productivity tool is built; where a and b are different calculation weight coefficients, 0<a<b; B is the cycle overall reliability standard value; Perform data analysis on the overall reliability of the cycle.

9. The method of claim 8 for constructing an intelligent management system for process productivity tools based on artificial intelligence, characterized in that: If the overall reliability of the cycle is greater than or equal to 1, it indicates that the overall effect of the construction and implementation of the process productivity tool after construction is normal, and the subsequent normal use of the constructed process productivity tool is maintained; If the overall reliability of the cycle is less than 1, it indicates that the overall effect of the construction implementation of the process productivity tool after construction is abnormal, and the subsequent use of the process productivity tool is dynamically managed.

Images