A production task online monitoring method and system
By loading the basic production line status monitoring records and dynamic production line monitoring records to the AI algorithm network, using AI algorithms to identify the distribution of key task links of the production line, the problem of inaccurate monitoring in online monitoring of production tasks is solved, and the accuracy of monitoring is improved Sex and credibility.
Patent Information
- Application Number
- CN202210196880.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2022-01-27
- Filing Date
- 2022-03-02
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2042-03-02
AI Technical Summary
During the online monitoring of production tasks, it is difficult for the existing technology to accurately process production information, resulting in inaccurate monitoring and the inability to quickly identify and process critical task links.
By loading the basic production line status monitoring records and dynamic production line monitoring records into the AI algorithm network, using AI algorithms to mine the production task topic description and task update description from it, perform global processing, and determine the node status monitoring records to identify the target Distribution of key tasks bound to the production line.
It realizes the rapid and accurate identification of key task link distribution, improves the accuracy and credibility of monitoring, and ensures that relevant staff can handle key task links in a timely manner.
Smart Images

Figure CN114663753B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data monitoring technology, and in particular to a method and system for online monitoring of production tasks. Background Art
[0002] The monitoring system is one of the most widely used systems in the security system. The most suitable construction site monitoring system on the market is the handheld video communication device. Video monitoring is now the mainstream. From the earliest analog monitoring to the popular digital monitoring in the past few years to the emerging network video monitoring, earth-shaking changes have taken place. With the continuous development of monitoring technology, when monitoring technology is specifically applied to production tasks, there may be a problem of disorder in the processing of the monitored production information, so that the production tasks cannot be accurately monitored online. Therefore, a technical solution is urgently needed to improve the above technical problems. Summary of the invention
[0003] In view of this, the present application provides a method and system for online monitoring of production tasks.
[0004] In a first aspect, a method for online monitoring of production tasks is provided, which is applied to a production task monitoring system, and the method at least comprises:
[0005] Obtain the basic production line status monitoring record bound to the target production line with the help of the production task monitoring thread; determine the state change between the basic production line status monitoring record and the previous set of production line status monitoring records of the basic production line status monitoring record, and obtain the dynamic production line monitoring record corresponding to the state change;
[0006] The basic production line status monitoring record and the dynamic production line monitoring record are loaded into the debugged AI algorithm network, so as to mine the production task subject description from the basic production line status monitoring record and the task update description from the dynamic production line monitoring record with the help of the AI algorithm network, and the production task subject description and the task update description are globally processed to obtain a globalized task monitoring description; wherein the production task subject description represents the production line association label of the key task link in the basic production line status monitoring record, and the task update description represents the change of the key task link in the dynamic production line monitoring record;
[0007] The global task monitoring description and the production task subject description are loaded into the AI algorithm network to determine the node-based status monitoring record with the help of the AI algorithm network; wherein the node-based status monitoring record includes a key link operation log and a non-key link operation log, the project heat of each production project in the key link operation log is the first quantitative data, and the project heat of each production project in the non-key link operation log is the second quantitative data; the distribution of key task links bound to the target production line is determined based on the key link operation log in the node-based status monitoring record.
[0008] In an independently implemented embodiment, the obtaining of the dynamic production line monitoring record corresponding to the state change includes:
[0009] If the state change condition includes a state change type and a state change scene, the state change type is migrated and transformed into a type unit of a preset mapping list, and the state change scene is migrated and transformed into a scene unit of a preset mapping list;
[0010] The dynamic production line monitoring record is obtained according to the type unit and the scene unit.
[0011] In an independently implemented embodiment, the AI algorithm network includes a first local model structure, a second local model structure and a third local model structure; the AI algorithm network is used to mine the production task subject description from the basic production line status monitoring record, and to mine the task update description from the dynamic production line monitoring record, and the production task subject description and the task update description are globally processed to obtain a globalized task monitoring description, including:
[0012] mining the production task subject description from the basic production line status monitoring record by means of the first local model structure of the AI algorithm network, and loading the production task subject description into the third local model structure;
[0013] mining task update descriptions from the dynamic production line monitoring records using the second local model structure of the AI algorithm network, and loading the task update descriptions into the third local model structure;
[0014] The production task subject description and the task update description are globally processed with the help of the third local model structure to obtain a globalized task monitoring description, and the globalized task monitoring description is loaded into the first local model structure.
[0015] In an independently implemented embodiment, the production task subject description and the task update description are globally processed by means of the third local model structure to obtain a globalized task monitoring description, including:
[0016] Performing sliding average processing on the task update description to obtain a task update description after the sliding average processing, and performing migration transformation on the task update description after the sliding average processing by using a trigger mechanism to obtain a task update description after the migration transformation;
[0017] The production task subject description and the task update description after migration transformation are weighted to obtain a global task monitoring description.
[0018] In an independently implemented embodiment, after determining the distribution of key task links bound to the target production line according to the key link operation log in the node status monitoring record, the method further includes:
[0019] Determine log content constraints associated with the distribution of key task links;
[0020] Determine the key task link evaluation bound to the target production line according to the log content constraint conditions;
[0021] Summarize the key task link evaluations that are higher than the set evaluation indicators and pay attention to the time series duration values of the links;
[0022] The key task link distribution, the key task link evaluation and the link attention timing duration value are output in the target process.
[0023] In an independently implemented embodiment, the debugging process of the AI algorithm network includes:
[0024] Obtain the basic debugging monitoring records bound to the target production line with the help of the production task monitoring thread;
[0025] Determine the state change debugging information between the basic debugging monitoring record and a previous set of debugging monitoring records of the basic debugging monitoring record, and obtain the state change debugging monitoring record corresponding to the state change debugging information;
[0026] The basic debugging monitoring record and the state change debugging monitoring record are loaded into the basic AI network, so as to mine task update debugging examples from the basic debugging monitoring record and state update debugging examples from the state change debugging monitoring record with the help of the basic AI network, and perform global processing on the task update debugging examples and the state update debugging examples to obtain global processing debugging examples; wherein the task update debugging examples represent the production line association tags of the key task links in the basic debugging monitoring record, and the state update debugging examples represent the changes of the key task links in the state change debugging monitoring record;
[0027] The global processing debugging example and the task update debugging example are loaded into the basic AI network, so as to determine the node state debugging monitoring record with the help of the basic AI network; wherein the node state debugging monitoring record includes a key link operation log and a non-key link operation log, and the project heat of each production project in the key link operation log is the first quantitative data, and the project heat of each production project in the non-key link operation log is the second quantitative data;
[0028] The network performance index is calculated based on the node state debugging monitoring record and the pre-set node state; wherein the node state calculation monitoring record is a calculation monitoring record of the basic debugging monitoring record, and the node state calculation monitoring record includes a key link operation log and a non-key link operation log, and the project heat of each production project in the key link operation log is the first quantitative data, and the project heat of each production project in the non-key link operation log is the second quantitative data;
[0029] The basic AI network is debugged according to the network performance index to obtain an AI algorithm network.
[0030] In an independently implemented embodiment, the debugging of the basic AI network according to the network performance indicator to obtain the AI algorithm network includes:
[0031] Improving the performance variables of the basic AI network according to the network performance indicators to obtain an improved AI network, and determining whether the improved AI network meets the stability determination condition;
[0032] If not, the improved AI network is determined as the basic AI network, and the process returns to the step of loading the basic debugging monitoring record and the state change debugging monitoring record into the basic AI network;
[0033] If yes, the improved AI network is determined as the AI algorithm network.
[0034] In a second aspect, a production task online monitoring system is provided, comprising a processor and a memory communicating with each other, wherein the processor is used to read a computer program from the memory and execute it to implement the above method.
[0035] An online production task monitoring method and system provided in an embodiment of the present application loads basic production line status monitoring records and dynamic production line monitoring records into an AI algorithm network, determines noded status monitoring records with the aid of the AI algorithm network, and determines the distribution of key task links bound to the target production line based on the key link operation logs in the noded status monitoring records. In this way, the distribution of key task links bound to the target production line is determined based on the basic production line status monitoring records and the dynamic production line monitoring records, so that the distribution of key task links can be determined quickly and accurately, prompting relevant staff to quickly query the key task links and process the key task links. By loading the dynamic production line monitoring records into the AI algorithm network, the state change information (i.e., changes in the key task links) can be loaded into the AI algorithm network, so that the AI algorithm network can perform calculations more accurately, improving the accuracy and credibility of the key task link distribution monitoring. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0037] Figure 1 A flowchart of a method for online monitoring of production tasks provided in an embodiment of the present application.
[0038] Figure 2 A block diagram of an online monitoring device for production tasks provided in an embodiment of the present application.
[0039] Figure 3 An architectural diagram of an online production task monitoring system provided in an embodiment of the present application. DETAILED DESCRIPTION
[0040] In order to better understand the above technical scheme, the technical scheme of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.
[0041] See also Figure 1 , shows a method for online monitoring of production tasks, which may include the technical solutions described in the following steps 201-206.
[0042] Step 201, obtain the basic debugging monitoring record bound to the target production line with the help of the production task monitoring thread.
[0043] For example, the production task monitoring thread can obtain the basic monitoring records bound to the target production line and load the basic monitoring records into the production task monitoring system. The basic monitoring records during the debugging process can be recorded as basic debugging monitoring records. Further, the production task monitoring system can obtain the basic debugging monitoring records bound to the target production line.
[0044] Step 202: determine the state change debugging information between the basic debugging monitoring record and a previous set of debugging monitoring records of the basic debugging monitoring record, and obtain the state change debugging monitoring record corresponding to the state change debugging information.
[0045] For example, the production task monitoring thread can obtain multiple groups of basic debugging monitoring records bound to the target production line, and load some basic debugging monitoring records into the production task monitoring system. Based on this, the production task monitoring system can obtain multiple groups of basic debugging monitoring records. When the production task monitoring system obtains each group of basic debugging monitoring records, it can first search for the previous group of debugging monitoring records of the basic debugging monitoring record (that is, the first group of basic debugging monitoring records before the basic debugging monitoring record), and then determine the state change information between the basic debugging monitoring record and the previous group of debugging monitoring records of the basic debugging monitoring record. The state change information in the debugging process can be understood as state change debugging information.
[0046] For example, the state change debugging information between the basic debugging monitoring record and a previous set of debugging monitoring records of the basic debugging monitoring record may be determined in a state change manner.
[0047] For example, the state change debugging information may include the state change type (i.e., the state change type of the state update object) and the state change scenario. For each group of production items in the basic debugging monitoring record, find the standard template associated with the production item from the previous group of debugging monitoring records, and determine the state change type and state change scenario corresponding to the production item based on the distribution of the production item and the standard template. Obviously, the state change debugging information includes the state change type and state change scenario corresponding to each group of production items in the basic debugging monitoring record.
[0048] Obtaining the state change debugging monitoring record corresponding to the state change debugging information may include but is not limited to the following contents: transforming the state change type migration to the type unit of the preset mapping list, and transforming the state change scene migration to the scene unit of the preset mapping list, and obtaining the state change debugging monitoring record based on the type unit and the scene unit.
[0049] Furthermore, for the first group of production items in the basic debugging monitoring record, the state change type corresponding to the production item is migrated and transformed into the type unit of the preset mapping list, and the state change scene corresponding to the production item is migrated and transformed into the scene unit of the preset mapping list, and the type unit and the scene unit constitute the project heat of the first production item in the state change debugging monitoring record, and the project heat of all production items in the state change debugging monitoring record can be obtained, and the project heat of all production items can constitute the state change debugging monitoring record, that is, the state change debugging monitoring record is obtained.
[0050] For example, for each group of production items in the basic debugging monitoring record, the state change type corresponding to the production item can be migrated and transformed into a type unit of a preset mapping list. The type unit corresponds to the polar angle of the polar coordinates, and the migration transformation process is no longer limited one by one. The state change scene corresponding to the production item can be migrated and transformed into a scene unit of a preset mapping list, and the migration transformation process is no longer limited one by one. In this way, after obtaining the type unit and the scene unit, the project heat of the preset mapping list can be obtained, and then all the project heats can be combined into a state change debugging monitoring record, that is, a monitoring record of the preset mapping list.
[0051] For the state change debugging monitoring record of the preset mapping list, the state change debugging monitoring record can be a visual monitoring record, and different labels in the state change debugging monitoring record represent different state change types in the state change debugging information, and different dimensions in the state change debugging monitoring record represent different state change scenarios in the state change debugging information. Combined with the above description, for each group of production items in the state change debugging monitoring record, the label of the production item represents the state change type in the state change debugging information, and the dimension of the production item represents the state change scenario in the state change debugging information.
[0052] Step 203, the basic debugging monitoring record and the state change debugging monitoring record are loaded into the basic AI network, so as to mine the task update debugging paradigm from the basic debugging monitoring record with the help of the basic AI network, and mine the state update debugging paradigm from the state change debugging monitoring record, and perform global processing on the task update debugging paradigm and the state update debugging paradigm to obtain a global processing debugging paradigm. The task update debugging paradigm can characterize the production line association label of the key task link in the basic debugging monitoring record, the state update debugging paradigm can characterize the change of the key task link in the state change debugging monitoring record, and the global processing debugging paradigm can characterize the global processing information of the production line association label and the change.
[0053] Step 204, the global processing debugging example and the task update debugging example are loaded into the basic AI network, so as to determine the node state debugging monitoring record with the help of the basic AI network. For example, the node state debugging monitoring record may include a key link operation log and a non-key link operation log, the project heat of each production project in the key link operation log is the first quantitative data, and the project heat of each production project in the non-key link operation log is the second quantitative data.
[0054] For example, a basic AI network (AI network to be debugged) can be built in advance. The basic AI network can be a deep learning AI network or another type of AI network. The structure of this basic AI network is no longer limited one by one. As long as the input of the basic AI network is the basic debugging monitoring record and the state change debugging monitoring record, the basic AI network is determined to be the node state debugging monitoring record.
[0055] For example, the basic AI network may include a first local model structure, a second local model structure, and a third local model structure. The first local model structure is used to process basic debugging monitoring records and descriptions corresponding to the basic debugging monitoring records, the second local model structure is used to process state change debugging monitoring records and descriptions corresponding to state change debugging monitoring records, and the third local model structure is used to process descriptions corresponding to basic debugging monitoring records and descriptions corresponding to state change debugging monitoring records.
[0056] With respect to step 203 and step 204, the basic debugging monitoring record can be loaded into the first local model structure, and the task update debugging paradigm can be mined from the basic debugging monitoring record with the help of the first local model structure, and the task update debugging paradigm can be loaded into the third local model structure. The state change debugging monitoring record can be loaded into the second local model structure, and the state update debugging paradigm can be mined from the state change debugging monitoring record with the help of the second local model structure, and the state update debugging paradigm can be loaded into the third local model structure. After the task update debugging paradigm and the state update debugging paradigm are loaded into the third local model structure, the task update debugging paradigm and the state update debugging paradigm are globally processed with the help of the third local model structure to obtain a globally processed debugging paradigm. After obtaining the globally processed debugging paradigm, the third local model structure loads the globally processed debugging paradigm into the first local model structure. For example, the third local model structure includes at least one sub-network. For each group of sub-networks, the input of the sub-network is a task update debugging paradigm and a state update debugging paradigm. The sub-network is determined as a global processing debugging paradigm. The sub-network is used to perform global processing on the task update debugging paradigm and the state update debugging paradigm to obtain a global processing debugging paradigm.
[0057] Based on the above content, the global processing debugging paradigm and the task update debugging paradigm have been loaded into the first local model structure, and the first local model structure can obtain the node state debugging monitoring record based on the global processing debugging paradigm and the task update debugging paradigm. Further, after the global processing debugging paradigm and the task update debugging paradigm are loaded into a sub-network of the first local model structure, the sub-network can calculate the global processing debugging paradigm and the task update debugging paradigm to obtain the node state debugging monitoring record. Further, the first local model structure includes sub-networks sub_Neural_Networks_A1 and sub-networks sub_Neural_Networks_A2, the second local model structure includes sub-networks sub_Neural_Networks_B1, and the third local model structure includes sub-networks sub_Neural_Networks_C2. The basic debugging monitoring record can be loaded into the sub-network sub_Neural_Networks_A1. The sub-network sub_Neural_Networks_A1 processes the basic debugging monitoring record to obtain the key description des_D1, which is the task update debugging example. The sub-network sub_Neural_Networks_A1 loads the key description des_D1 into the sub-network sub_Neural_Networks_C2, and loads the key description des_D1 into the sub-network sub_Neural_Networks_A2. The state change debugging monitoring record can be loaded into the sub-network sub_Neural_Networks_B1. The sub-network sub_Neural_Networks_B1 processes the state change debugging monitoring record to obtain the key description des_D2, which is the state update debugging example. The sub-network sub_Neural_Networks_B1 loads the key description des_D2 into the sub-network sub_Neural_Networks_C2. After the sub-network sub_Neural_Networks_C2 obtains the key description des_D1 and the key description des_D2, it performs global processing on the key description des_D1 and the key description des_D2 to obtain the key description des_D3. The key description des_D3 is an example of global processing debugging. The sub-network sub_Neural_Networks_C2 loads the key description des_D3 into the sub-network sub_Neural_Networks_A2.After the sub-network sub_Neural_Networks_A2 obtains the key description des_D1 and the key description des_D3, the key description des_D4 can be obtained based on the key description des_D1 and the key description des_D3, such as the key description des_D4 is the sum of the key description des_D1 and the key description des_D3, and the node state debugging monitoring record associated with the key description des_D4 is obtained. The first local model structure includes the sub-network sub_Neural_Networks_A1, the sub-network sub_Neural_Networks_A2 and the sub-network sub_Neural_Networks_A3, the second local model structure includes the sub-network sub_Neural_Networks_B1 and the sub-network sub_Neural_Networks_B2, and the third local model structure includes the sub-network sub_Neural_Networks_C2 and the sub-network sub_Neural_Networks_C2. Sub-network sub_Neural_Networks_A1 processes the basic debugging monitoring records to obtain the key description des_E1 (task update debugging example), and loads the key description des_E1 into sub-network sub_Neural_Networks_C2 and sub-network sub_Neural_Networks_A2. Sub-network sub_Neural_Networks_B1 processes the state change debugging monitoring records to obtain the key description des_E2 (state update debugging example), and loads the key description des_E2 into sub-network sub_Neural_Networks_C2 and sub-network sub_Neural_Networks_B2. Sub-network sub_Neural_Networks_C2 performs global processing on the key description des_E1 and the key description des_E2 to obtain the key description des_E3 (global processing debugging example), and loads the key description des_E3 into sub-network sub_Neural_Networks_A2. The sub-network sub_Neural_Networks_A2 obtains the key description des_E4 based on the key description des_E1 and the key description des_E3, processes the key description des_E4, obtains the key description des_E5 (task update debugging example), and loads the key description des_E5 into the sub-network sub_Neural_Networks_C2 and the sub-network sub_Neural_Networks_A3.Sub-network sub_Neural_Networks_B2 processes key description des_E2 to obtain key description des_E6 (status update debugging example), and loads key description des_E6 into sub-network sub_Neural_Networks_C2. Sub-network sub_Neural_Networks_C2 processes key description des_E5 and key description des_E6 globally to obtain key description des_E7 (global processing debugging example), and loads key description des_E7 into sub-network sub_Neural_Networks_A3. Sub-network sub_Neural_Networks_A3 obtains key description des_E8 (such as the sum of key description des_E5 and key description des_E7) based on key description des_E5 and key description des_E7, and obtains node-based state debugging monitoring records associated with key description des_E8.
[0058] There is no need to limit the basic AI network one by one. As long as the basic AI network can mine task update debugging examples from basic debugging monitoring records, mine state update debugging examples from state change debugging monitoring records, and globally process task update debugging examples and state update debugging examples to obtain global processing debugging examples, it can determine the node-based state debugging monitoring records based on the global processing debugging examples and task update debugging examples.
[0059] In this embodiment, with respect to the task update debugging example, since the critical task links and non-critical task links bound to the target production line are compared, the task update of the critical task links is different from the task update of the non-critical task links, and the basic debugging monitoring record can display the production line association label of each production project. Therefore, after mining the task update debugging example from the basic debugging monitoring record, the task update debugging example can characterize the production line association label of the critical task link and the production line association label of the non-critical task link in the basic debugging monitoring record. Further, the task update debugging example can represent the difference between the critical task link and the non-critical task link, that is, the difference between the critical task link and the non-critical task link is represented by the production line association label of each production project in the basic debugging monitoring record.
[0060] For the status update debugging paradigm, since the critical task links and non-critical task links bound to the target production line are compared, the critical task links have status updates in the matters, while the non-critical task links do not have status updates in the matters, and the state change debugging monitoring records can display the changes in each production item. Therefore, after mining the state update debugging paradigm from the state change debugging monitoring records, the state update debugging paradigm can characterize the changes in the critical task links and the changes in the non-critical task links in the state change debugging monitoring records. Furthermore, the state update debugging paradigm can represent the differences between the critical task links and the non-critical task links, that is, the differences between the critical task links and the non-critical task links are represented by the changes in each production item in the state change debugging monitoring records.
[0061] For the global processing debugging paradigm, since it is a global processing of the task update debugging paradigm and the state update debugging paradigm, and the task update debugging paradigm can characterize the production line associated labels of the critical task links and the production line associated labels of the non-critical task links, and the state update debugging paradigm can characterize the changes in the critical task links and the changes in the non-critical task links, the global processing debugging paradigm can characterize the global processing information of the production line associated labels and changes, and the global processing information can represent the difference between the critical task links and the non-critical task links, that is, the difference between the critical task links and the non-critical task links can be represented with the help of the production line associated labels and changes.
[0062] For the node-based state debugging monitoring record, the node-based state debugging monitoring record is a binary monitoring record, which can be understood as a black-and-white monitoring record, that is, the project heat of the production project is only the first quantitative data or the second quantitative data. In the process of obtaining the node-based state debugging monitoring record, the node-based state debugging monitoring record can be divided into key link operation logs and non-key link operation logs according to the production line associated tags and changes. The project heat of each production project in the key link operation log is the first quantitative data, and the project heat of each production project in the non-key link operation log is the second quantitative data.
[0063] In combination with the above description, after the basic debugging monitoring record and the state change debugging monitoring record are loaded into the basic AI network, the basic AI network determines the node-based state debugging monitoring record, and subsequent processing can be performed based on the node-based state debugging monitoring record.
[0064] In an alternative embodiment, the task update debugging paradigm and the state update debugging paradigm are globally processed with the help of a third local model structure to obtain a globally processed debugging paradigm, which may include the following contents: performing sliding average processing on the state update debugging paradigm to obtain a state update debugging paradigm after the sliding average processing, and using a trigger mechanism to perform migration transformation on the state update debugging paradigm after the sliding average processing to obtain a state update debugging paradigm after the migration transformation; then, weighted processing is performed on the task update debugging paradigm and the state update debugging paradigm after the migration transformation to obtain a globally processed debugging paradigm.
[0065] Step 205, calculate the network performance index according to the node state debugging monitoring record and the pre-set node state. For example, the node state calculation monitoring record can be a calculation monitoring record of the basic debugging monitoring record, and the node state calculation monitoring record can include a key link operation log and a non-key link operation log, and the project heat of each production project in the key link operation log is the first quantitative data, and the project heat of each production project in the non-key link operation log is the second quantitative data.
[0066] For example, before step 205, the calculation monitoring record of the basic debugging monitoring record can be trained, and the calculation monitoring record can be recorded as the node state calculation monitoring record. Further, when the user calculates the basic debugging monitoring record, the user can obtain the key link operation log and the non-key link operation log in the basic debugging monitoring record. Therefore, the key link operation log and the non-key link operation log in the basic debugging monitoring record can be calculated, and the node state calculation monitoring record can be obtained based on the calculation information. When obtaining the node state calculation monitoring record, the project heat of each production project corresponding to the key link operation log is the first quantitative data, and the project heat of each production project corresponding to the non-key link operation log is the second quantitative data. After obtaining the node state debugging monitoring record and the node state calculation monitoring record, the network performance index can be determined based on the difference between the node state debugging monitoring record and the node state calculation monitoring record. When the network performance index is lower, it means that the node-based state debugging monitoring records and the node-based state calculation monitoring records are more similar, that is, the node-based state debugging monitoring records determined by the basic AI network are more matched; when the network performance index is higher, it means that the node-based state debugging monitoring records and the node-based state calculation monitoring records are less related, that is, the node-based state debugging monitoring records determined by the basic AI network are less reliable.
[0067] Step 206: debug the basic AI network according to the network performance index to obtain an AI algorithm network.
[0068] For example, it is determined whether the improved AI network has met the stability determination condition. If not, the improved AI network is determined as the basic AI network, and the process returns to the step of loading the basic debugging monitoring record and the state change debugging monitoring record into the basic AI network. If yes, the improved AI network is determined as the debugged AI algorithm network.
[0069] For example, if the network performance indicator does not meet the preset network performance indicator judgment value, it is determined that the improved AI network has met the stability judgment condition; if the network performance indicator does not meet the preset network performance indicator judgment value, it is determined that the improved AI network does not meet the stability judgment condition.
[0070] After obtaining the debugged AI algorithm network, key task link monitoring can be implemented based on the debugged AI algorithm network. This method can be applied to a production task monitoring system. The method may include the following steps.
[0071] Step 501: Obtain the basic production line status monitoring record bound to the target production line with the help of the production task monitoring thread.
[0072] For example, the production task monitoring thread can obtain the basic monitoring records bound to the target production line, load the basic monitoring records into the production task monitoring system, and record the basic monitoring records in the monitoring process as basic production line status monitoring records.
[0073] Step 502, determining the state change between the basic production line state monitoring record and a previous group of production line state monitoring records of the basic production line state monitoring record, and obtaining a dynamic production line monitoring record corresponding to the state change.
[0074] For example, when the production task monitoring system obtains each group of basic production line status monitoring records, it can first search for the previous group of production line status monitoring records of the basic production line status monitoring records (that is, the first group of basic production line status monitoring records before the basic production line status monitoring records), and then determine the status change information between the basic production line status monitoring record and the previous group of production line status monitoring records of the basic production line status monitoring records. The status change information in the monitoring process can be understood as the status change situation.
[0075] The status change situation may include the status change type and status change scenario. For each group of production items in the basic production line status monitoring record, a standard template associated with the production item is found from the previous group of production line status monitoring records. According to the distribution of the production item and the standard template, the status change type and status change scenario corresponding to the production item are determined. The status change situation includes the status change type and status change scenario corresponding to each group of production items in the basic production line status monitoring record.
[0076] Based on this, obtaining the dynamic production line monitoring record corresponding to the state change situation may include the following contents: migrating the state change type into the type unit of the preset mapping list, and migrating the state change scene into the scene unit of the preset mapping list, and obtaining the dynamic production line monitoring record based on the type unit and the scene unit.
[0077] For the dynamic production line monitoring record of the preset mapping list, the dynamic production line monitoring record can be a visual monitoring record. The different labels in the dynamic production line monitoring record represent different state change types in the state change situation, and the different dimensions in the dynamic production line monitoring record represent different state change scenarios in the state change situation.
[0078] Step 503, the basic production line status monitoring record and the dynamic production line monitoring record are loaded into the debugged AI algorithm network, so as to mine the production task subject description from the basic production line status monitoring record and the task update description from the dynamic production line monitoring record with the help of the AI algorithm network, and the production task subject description and the task update description are globally processed to obtain the globalized task monitoring description. The production task subject description represents the production line association label of the key task link in the basic production line status monitoring record, and the task update description represents the change of the key task link in the dynamic production line monitoring record.
[0079] Step 504, the global task monitoring description and the production task subject description are loaded into the AI algorithm network, so as to determine the node status monitoring record with the help of the AI algorithm network. For example, the node status monitoring record may include a key link operation log and a non-key link operation log, the project heat of each production project in the key link operation log is the first quantitative data, and the project heat of each production project in the non-key link operation log is the second quantitative data.
[0080] For example, the calculation process of the AI algorithm network is similar to the calculation process of the basic AI network. Therefore, the AI algorithm network may include a first local model structure, a second local model structure and a third local model structure. The first local model structure is used to process the basic production line status monitoring records and the descriptions corresponding to the basic production line status monitoring records, the second local model structure is used to process the dynamic production line monitoring records and the descriptions corresponding to the dynamic production line monitoring records, and the third local model structure is used to process the descriptions corresponding to the basic production line status monitoring records and the descriptions corresponding to the dynamic production line monitoring records.
[0081] Furthermore, the basic production line status monitoring record is loaded into the first local model structure, the production task subject description is mined from the basic production line status monitoring record with the help of the first local model structure, and the production task subject description is loaded into the third local model structure.
[0082] The dynamic production line monitoring record can be loaded into the second local model structure, and the task update description can be mined from the dynamic production line monitoring record with the help of the second local model structure, and the task update description can be loaded into the third local model structure. After the production task subject description and the task update description are loaded into the third local model structure, the production task subject description and the task update description can be globalized with the help of the third local model structure to obtain a globalized task monitoring description. After obtaining the globalized task monitoring description, the third local model structure can load the globalized task monitoring description into the first local model structure.
[0083] According to the above description, the global task monitoring description and the production task subject description have been loaded into the first local model structure, and the first local model structure obtains the node status monitoring record based on the global task monitoring description and the production task subject description.
[0084] In this embodiment, the production task subject description can characterize the production line association labels of the critical task links and the production line association labels of the non-critical task links in the basic production line status monitoring record, that is, the production task subject description can represent the difference between the critical task links and the non-critical task links. The task update description can characterize the changes in the critical task links and the changes in the non-critical task links in the dynamic production line monitoring record, that is, the task update description can represent the difference between the critical task links and the non-critical task links. The globalized task monitoring description can characterize the globalized processing information of the production line association labels and changes, and the globalized processing information can represent the difference between the critical task links and the non-critical task links, that is, the difference between the critical task links and the non-critical task links is represented by the production line association labels and changes.
[0085] In combination with the above description, after the basic production line status monitoring records and the dynamic production line monitoring records are loaded into the AI algorithm network, the AI algorithm network determines the node-based status monitoring records and can perform subsequent processing based on the node-based status monitoring records.
[0086] For example, the production task subject description and the task update description are globally processed with the help of the third local model structure to obtain a global task monitoring description, which may include the following contents: sliding average processing is performed on the task update description to obtain the task update description after sliding average processing, and a trigger mechanism is used to perform migration transformation on the task update description after sliding average processing to obtain the task update description after migration transformation; then, weighted processing is performed on the production task subject description and the task update description after migration transformation to obtain a global task monitoring description.
[0087] Step 505 , determining the key task link distribution bound to the target production line according to the key link operation log in the node status monitoring record, that is, determining the key link operation log as the key task link distribution bound to the target production line.
[0088] For example, the node status monitoring record includes the key link operation log and the non-key link operation log. The project heat of each production project in the key link operation log is the first quantitative data, and the project heat of each production project in the non-key link operation log is the second quantitative data. Therefore, the set of production items consisting of all the first quantitative data is determined as the key task link distribution bound to the target production line (also understood as the key task link set), that is, the key task link distribution is the set of production items consisting of all the first quantitative data.
[0089] In an alternative embodiment, the log content constraint condition associated with the distribution of the key task link can also be determined, and the evaluation of the key task link bound to the target production line can be determined based on the log content constraint condition. The link attention time series duration value of the key task link evaluation higher than the set evaluation index can be summarized. In this embodiment, the basic production line status monitoring record and the dynamic production line monitoring record can be loaded into the AI algorithm network, and the node status monitoring record can be determined with the help of the AI algorithm network. The distribution of the key task link bound to the target production line is determined based on the key link operation log in the node status monitoring record. Further, the distribution of the key task link bound to the target production line is determined based on the basic production line status monitoring record and the dynamic production line monitoring record, so that the distribution of the key task link can be quickly and accurately determined, prompting relevant staff to quickly query the key task link and process the key task link. By loading the dynamic production line monitoring record into the AI algorithm network, the state change information (i.e., the change of the key task link) can be loaded into the AI algorithm network, so that the AI algorithm network can perform calculations more accurately and improve the accuracy and credibility of the key task link distribution monitoring.
[0090] Based on the above, please refer to Figure 2, provides a production task online monitoring device 200, which is applied to a production task online monitoring system, and the device comprises:
[0091] The record acquisition module 210 is used to obtain the basic production line status monitoring record bound to the target production line with the help of the production task monitoring thread; determine the state change between the basic production line status monitoring record and the previous group of production line status monitoring records of the basic production line status monitoring record, and obtain the dynamic production line monitoring record corresponding to the state change;
[0092] The description obtaining module 220 is used to load the basic production line status monitoring record and the dynamic production line monitoring record into the debugged AI algorithm network, so as to mine the production task subject description from the basic production line status monitoring record with the help of the AI algorithm network, mine the task update description from the dynamic production line monitoring record, and perform global processing on the production task subject description and the task update description to obtain a global task monitoring description; wherein, the production task subject description represents the production line association label of the key task link in the basic production line status monitoring record, and the task update description represents the change of the key task link in the dynamic production line monitoring record;
[0093] The distribution binding module 230 is used to load the global task monitoring description and the production task subject description into the AI algorithm network, so as to determine the node status monitoring record with the help of the AI algorithm network; wherein the node status monitoring record includes the key link operation log and the non-key link operation log, and the project heat of each production project in the key link operation log is the first quantitative data, and the project heat of each production project in the non-key link operation log is the second quantitative data; the distribution of key task links bound to the target production line is determined based on the key link operation log in the node status monitoring record.
[0094] Based on the above, please refer to Figure 3 , shows a production task online monitoring system 300, including a processor 310 and a memory 320 that communicate with each other, and the processor 310 is used to read and execute a computer program from the memory 320 to implement the above method.
[0095] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method when running.
[0096] In summary, based on the above scheme, the basic production line status monitoring records and dynamic production line monitoring records are loaded into the AI algorithm network, and the node status monitoring records are determined with the help of the AI algorithm network. The distribution of key task links bound to the target production line is determined based on the key link operation logs in the node status monitoring records. In this way, the distribution of key task links bound to the target production line is determined based on the basic production line status monitoring records and the dynamic production line monitoring records, so that the distribution of key task links can be quickly and accurately determined, prompting relevant staff to quickly query the key task links and process the key task links. By loading the dynamic production line monitoring records into the AI algorithm network, the state change information (i.e., the changes in the key task links) can be loaded into the AI algorithm network, so that the AI algorithm network can perform calculations more accurately and improve the accuracy and credibility of the distribution monitoring of key task links.
[0097] It should be understood that the system and its modules shown above can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above methods and systems can be implemented using computer executable instructions and / or included in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application can not only be implemented by hardware circuits such as ultra-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 can also be implemented by software such as executed by various types of processors, and can also be implemented by a combination of the above hardware circuits and software (e.g., firmware).
[0098] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other beneficial effects that may be obtained.
[0099] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.
[0100] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.
[0101] In addition, it will be appreciated by those skilled in the art that various aspects of the present application may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may all be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present application may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.
[0102] A computer storage medium may include a propagated data signal containing computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.
[0103] The computer program codes required for the operation of each part of the present 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 language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, Ruby and Groovy, or other programming languages, etc. The program code can be run entirely on the user's computer, or run on the user's computer as an independent software package, or run partially on the user's computer and partially on a remote computer, or run 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 form, such as a local area network (LAN) or a 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).
[0104] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.
[0105] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this application, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.
[0106] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used for the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers allow adaptive changes. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which can be changed according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values is as accurate as possible within the feasible range.
[0107] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, instructions, publications, documents, etc., cited in this application are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the content of this application, documents that limit the broadest scope of the claims of this application (currently or later attached to this application) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the attached materials of this application are inconsistent or conflicting with the content described in this application, the descriptions, definitions, and / or use of terms in this application shall prevail.
[0108] Finally, it should be understood that the embodiments described in this application are only used to illustrate the principles of the embodiments of the present application. Other variations may also fall within the scope of the present application. Therefore, as an example and not a limitation, the alternative configurations of the embodiments of the present application may be considered to be consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to the embodiments explicitly introduced and described in the present application.
[0109] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.
Claims
1. A method for online monitoring of production tasks, characterized in that: Applied to a production task monitoring system, the method at least comprises: Obtain the basic production line status monitoring record bound to the target production line with the help of the production task monitoring thread; determine the state change between the basic production line status monitoring record and the previous set of production line status monitoring records of the basic production line status monitoring record, and obtain the dynamic production line monitoring record corresponding to the state change; The basic production line status monitoring record and the dynamic production line monitoring record are loaded into the debugged AI algorithm network, so as to mine the production task subject description from the basic production line status monitoring record and the task update description from the dynamic production line monitoring record with the help of the AI algorithm network, and the production task subject description and the task update description are globally processed to obtain a globalized task monitoring description; wherein the production task subject description represents the production line association label of the key task link in the basic production line status monitoring record, and the task update description represents the change of the key task link in the dynamic production line monitoring record; The global task monitoring description and the production task subject description are loaded into the AI algorithm network to determine the node-based status monitoring record with the help of the AI algorithm network; wherein the node-based status monitoring record includes a key link operation log and a non-key link operation log, the project heat of each production project in the key link operation log is the first quantitative data, and the project heat of each production project in the non-key link operation log is the second quantitative data; the distribution of key task links bound to the target production line is determined based on the key link operation log in the node-based status monitoring record.
2. The method according to claim 1, characterized in that The obtaining of the dynamic production line monitoring record corresponding to the state change includes: If the state change condition includes a state change type and a state change scene, the state change type is migrated and transformed into a type unit of a preset mapping list, and the state change scene is migrated and transformed into a scene unit of a preset mapping list; The dynamic production line monitoring record is obtained according to the type unit and the scene unit.
3. The method according to claim 1, characterized in that The AI algorithm network includes a first local model structure, a second local model structure and a third local model structure; the AI algorithm network is used to mine the production task subject description from the basic production line status monitoring record, and to mine the task update description from the dynamic production line monitoring record, and the production task subject description and the task update description are globally processed to obtain a global task monitoring description, including: mining the production task subject description from the basic production line status monitoring record by means of the first local model structure of the AI algorithm network, and loading the production task subject description into the third local model structure; mining task update descriptions from the dynamic production line monitoring records using the second local model structure of the AI algorithm network, and loading the task update descriptions into the third local model structure; The production task subject description and the task update description are globally processed with the help of the third local model structure to obtain a globalized task monitoring description, and the globalized task monitoring description is loaded into the first local model structure.
4. The method according to claim 3, characterized in that The production task subject description and the task update description are globally processed by means of the third local model structure to obtain a globalized task monitoring description, including: Performing sliding average processing on the task update description to obtain a task update description after the sliding average processing, and performing migration transformation on the task update description after the sliding average processing by using a trigger mechanism to obtain a task update description after the migration transformation; The production task subject description and the task update description after migration transformation are weighted to obtain a global task monitoring description.
5. The method according to any one of claims 1 to 4, characterized in that: After determining the distribution of key task links bound to the target production line according to the key link operation log in the node status monitoring record, the method further includes: Determine log content constraints associated with the distribution of key task links; Determine the key task link evaluation bound to the target production line according to the log content constraint conditions; Summarize the key task link evaluations that are higher than the set evaluation indicators and pay attention to the time series duration values of the links; The key task link distribution, the key task link evaluation and the link attention timing duration value are output in the target process.
6. The method according to any one of claims 1 to 4, characterized in that: The debugging process of the AI algorithm network includes: Obtain the basic debugging monitoring records bound to the target production line with the help of the production task monitoring thread; Determine the state change debugging information between the basic debugging monitoring record and a previous set of debugging monitoring records of the basic debugging monitoring record, and obtain the state change debugging monitoring record corresponding to the state change debugging information; The basic debugging monitoring record and the state change debugging monitoring record are loaded into the basic AI network, so as to mine task update debugging examples from the basic debugging monitoring record and state update debugging examples from the state change debugging monitoring record with the help of the basic AI network, and perform global processing on the task update debugging examples and the state update debugging examples to obtain global processing debugging examples; wherein the task update debugging examples represent the production line association tags of the key task links in the basic debugging monitoring record, and the state update debugging examples represent the changes of the key task links in the state change debugging monitoring record; The global processing debugging example and the task update debugging example are loaded into the basic AI network, so as to determine the node state debugging monitoring record with the help of the basic AI network; wherein the node state debugging monitoring record includes a key link operation log and a non-key link operation log, and the project heat of each production project in the key link operation log is the first quantitative data, and the project heat of each production project in the non-key link operation log is the second quantitative data; The network performance index is calculated based on the node state debugging monitoring record and the pre-set node state; wherein the node state calculation monitoring record is a calculation monitoring record of the basic debugging monitoring record, and the node state calculation monitoring record includes a key link operation log and a non-key link operation log, and the project heat of each production project in the key link operation log is the first quantitative data, and the project heat of each production project in the non-key link operation log is the second quantitative data; The basic AI network is debugged according to the network performance index to obtain an AI algorithm network.
7. The method according to claim 6, characterized in that The step of debugging the basic AI network according to the network performance indicator to obtain an AI algorithm network includes: Improving the performance variables of the basic AI network according to the network performance indicators to obtain an improved AI network, and determining whether the improved AI network meets the stability determination condition; If not, the improved AI network is determined as the basic AI network, and the process returns to the step of loading the basic debugging monitoring record and the state change debugging monitoring record into the basic AI network; If yes, the improved AI network is determined as the AI algorithm network.
8. A production task online monitoring system, characterized in that: The invention comprises a processor and a memory communicating with each other, wherein the processor is used to read a computer program from the memory and execute the computer program to implement the method according to any one of claims 1 to 7.
