Production process knowledge graph annotation method, device, equipment and storage medium

Abstract

The present application provides a method, device, equipment and storage medium for labeling a production process knowledge graph, including: obtaining process parameters corresponding to each of multiple devices from a production process system, and obtaining text information corresponding to each of multiple devices from multiple production process files; inputting the process parameters corresponding to each of the multiple devices and the text information corresponding to each of the multiple devices into a trained neural network model to generate labeling information corresponding to each of the multiple devices, wherein the labeling information includes current process parameters and reference range information of process parameters; labeling multiple devices in the production process knowledge graph based on the labeling information corresponding to each of the multiple devices. The present application can improve the accuracy of data labeling.

Description

Technical Field

[0001] The present application relates to the field of production process technology, and in particular to a method, device, equipment and storage medium for annotating a production process knowledge graph. Background Art

[0002] With the increasing complexity and automation of industrial and mining production processes, accurate labeling of process parameters has become crucial.

[0003] In the prior art, process data is annotated manually, that is, professionals manually input data labels or annotation information. This method has the problems of low annotation efficiency, difficulty in ensuring annotation quality, and is easily affected by human factors.

[0004] It can be seen that a more efficient and accurate annotation method and system is needed to support the construction and application of industrial and mining production process knowledge graphs. Summary of the invention

[0005] Based on this, the present application provides a method, device, equipment and storage medium for labeling a production process knowledge graph, which can improve the accuracy of data labeling.

[0006] In a first aspect, the present application provides a method for annotating a production process knowledge graph, comprising:

[0007] Acquire process parameters corresponding to each of the plurality of devices from a production process system, and acquire text information corresponding to each of the plurality of devices from a plurality of production process files;

[0008] Inputting the process parameters corresponding to each of the plurality of devices and the text information corresponding to each of the plurality of devices into the trained neural network model to generate annotation information corresponding to each of the plurality of devices, wherein the annotation information includes current process parameters and reference range information of the process parameters;

[0009] Based on the labeling information corresponding to each of the multiple devices, multiple devices in the production process knowledge graph are labeled.

[0010] In a possible implementation, the obtaining of process parameters corresponding to each of the multiple devices from the production process system includes: obtaining initial process parameters corresponding to each of the multiple devices from the production process system; preprocessing the initial process parameters, deleting missing data in the initial process parameters, and deleting abnormal data in the initial process parameters; wherein the abnormal data refers to data that deviates from a normal range.

[0011] In one possible implementation, obtaining text information corresponding to each of the multiple devices from multiple production process files includes: selecting at least one target file associated with the production process system from the multiple production process files; and performing text recognition on the at least one target file to obtain text information corresponding to each of the multiple devices.

[0012] In a possible implementation, it also includes: obtaining a training sample set and a verification sample set, wherein the training sample set includes process parameters, text information, and actual annotation information corresponding to each of the multiple first devices, and the verification sample set includes process parameters, text information, and actual annotation information corresponding to each of the multiple second devices; training an initial neural network model according to the process parameters, text information, and actual annotation information corresponding to each of the multiple first devices; determining the accuracy of the initial neural network model through the process parameters, text information, and actual annotation information corresponding to each of the multiple second devices, and if the accuracy is less than a preset threshold, adjusting the initial neural network model until the accuracy is greater than or equal to the preset threshold, thereby obtaining a trained neural network model.

[0013] In one possible implementation, the obtaining of the training sample set and the verification sample set includes: for each first device, obtaining the process parameters corresponding to the first device from the production process system, obtaining the text information corresponding to the first device from multiple production process files, and obtaining the actual annotation information corresponding to the first device through manual annotation, so as to obtain the training sample set; for each second device, obtaining the process parameters corresponding to the second device from the production process system, obtaining the text information corresponding to the second device from multiple production process files, and obtaining the actual annotation information corresponding to the second device through manual annotation, so as to obtain the verification sample set.

[0014] In a possible implementation, the initial neural network model is trained according to the process parameters, text information, and actual annotation information corresponding to each of the multiple first devices, including: inputting the process parameters and text information corresponding to each of the first devices into the initial neural network model, and outputting the test annotation information of each of the first devices; and training the initial neural network model according to the test annotation information of each of the first devices and the actual annotation information of each of the first devices.

[0015] In a second aspect, the present application provides a device for labeling a production process knowledge graph, comprising:

[0016] An acquisition module is used to acquire process parameters corresponding to each of the multiple devices from a production process system, and to acquire text information corresponding to each of the multiple devices from multiple production process files;

[0017] A generation module, used for inputting the process parameters corresponding to each of the plurality of devices and the text information corresponding to each of the plurality of devices into the trained neural network model, and generating the annotation information corresponding to each of the plurality of devices, wherein the annotation information includes the current process parameters and the reference range information of the process parameters;

[0018] The labeling module is used to label multiple devices in the production process knowledge graph based on the labeling information corresponding to each of the multiple devices.

[0019] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0020] The memory stores computer-executable instructions;

[0021] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method for labeling the production process knowledge graph as described in the first aspect and various possible designs of the first aspect.

[0022] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the method for labeling the production process knowledge graph as described in the first aspect and various possible designs of the first aspect is implemented.

[0023] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the method for labeling the production process knowledge graph as described in the first aspect and various possible designs of the first aspect.

[0024] The present application provides a method, device, equipment and storage medium for labeling a production process knowledge graph, including: obtaining process parameters corresponding to each of multiple devices from a production process system, and obtaining text information corresponding to each of multiple devices from multiple production process files; inputting the process parameters corresponding to each of multiple devices and the text information corresponding to each of multiple devices into a trained neural network model to generate labeling information corresponding to each of multiple devices, wherein the labeling information includes the current process parameters and the reference range information of the process parameters; based on the labeling information corresponding to each of multiple devices, labeling multiple devices in the production process knowledge graph. In an embodiment of the present application, since the labeling information corresponding to each of multiple devices is automatically generated by the neural network model, the automatic labeling of the production process knowledge graph is realized, the labeling quality of industrial and mining production process data is improved, and labeling errors are reduced, thereby improving the credibility and accuracy of data labeling. At the same time, the present application can also speed up the construction of the knowledge graph, reduce labor costs and time costs, and improve the economic benefits of knowledge graph construction, which has obvious cost advantages for enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0026] Figure 1 A schematic diagram of an application scenario of the method for annotating a production process knowledge graph provided in an embodiment of the present disclosure;

[0027] Figure 2 Process of the method for labeling the production process knowledge graph provided in the embodiment of the present disclosure Figure 1 ;

[0028] Figure 3 The process of the training method of the neural network model provided in the embodiment of the present disclosure Figure 1 ;

[0029] Figure 4 A schematic diagram of the structure of a device for labeling a production process knowledge graph provided in an embodiment of the present disclosure;

[0030] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of methods and devices consistent with some aspects of the present application as detailed in the appended claims.

[0032] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the implementation of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] With the increasing complexity and automation of industrial and mining production processes, accurate labeling of process parameters has become crucial.

[0034] In the prior art, process data is annotated manually, that is, professionals manually input data labels or annotation information. This method has the problems of low annotation efficiency, difficulty in ensuring annotation quality, and is easily affected by human factors.

[0035] It can be seen that a more efficient and accurate annotation method and system is needed to support the construction and application of industrial and mining production process knowledge graphs.

[0036] In response to the above-mentioned problems existing in the prior art, the inventor's technical conception is as follows: through the process parameters of the equipment, and obtaining the text information corresponding to multiple devices from multiple production process files, and then inputting the process parameters and text information into a trained neural network model to automatically obtain the labeling information of the equipment.

[0037] The specific steps may include: first, obtaining the process parameters corresponding to each of the multiple devices from the production process system, and obtaining the text information corresponding to each of the multiple devices from multiple production process files. Then, the process parameters corresponding to each of the multiple devices and the text information corresponding to each of the multiple devices are input into the trained neural network model to generate the annotation information corresponding to each of the multiple devices, wherein the annotation information includes the current process parameters and the reference range information of the process parameters. Finally, based on the annotation information corresponding to each of the multiple devices, the multiple devices in the production process knowledge graph are annotated.

[0038] In the above technical solution, since the labeling information corresponding to multiple devices is automatically generated through the neural network model, the automatic labeling of the production process knowledge map is realized, the labeling quality of industrial and mining production process data is improved, and labeling errors are reduced, thereby improving the credibility and accuracy of data labeling. At the same time, this application can also speed up the construction of the knowledge map, reduce labor costs and time costs, and improve the economic benefits of knowledge map construction, which has obvious cost advantages for enterprises.

[0039] The application scenarios of the embodiments of the present disclosure are explained below:

[0040] Figure 1 Schematic diagram of an application scenario of the method for labeling a production process knowledge graph provided in an embodiment of the present disclosure. Figure 1 As shown, it can be applied to the scenario of data annotation for multiple devices in the production process knowledge graph. Data can be transmitted between the display terminal 101 and the server 102 in a wired or wireless manner. Exemplarily, the display terminal 101 can send a labeling request for the production process knowledge graph to the server 102. The server 102 receives the labeling request, and labels the production process knowledge graph through the labeling method of the production process knowledge graph provided by the embodiment of the present disclosure, so as to obtain the labeled production process knowledge graph. The server 102 returns the labeled production process knowledge graph to the display terminal 101, and displays the production process knowledge graph through the display terminal 101, providing intelligent support and decision-making reference for industrial and mining production.

[0041] The technical solution of the present application is described in detail below with reference to the accompanying drawings using specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0042] Figure 2 Process of the method for labeling the production process knowledge graph provided in the embodiment of the present disclosure Figure 1 The execution subject of the method in the embodiment of the present application may be a terminal or a server; the embodiment of the present application is described by taking the execution subject being a server as an example. Figure 2As shown, the annotation method of the production process knowledge graph includes:

[0043] S201. Acquire process parameters corresponding to each of the plurality of devices from a production process system, and acquire text information corresponding to each of the plurality of devices from a plurality of production process files.

[0044] In the disclosed embodiment, the production process system may be an industrial and mining production system, such as a coal mine production system. The production process system includes a plurality of devices, such as transmission equipment, classification equipment, detection equipment, etc. The process parameters of the equipment may be any parameter such as power, voltage, rotation speed, temperature, etc. of the equipment.

[0045] In some embodiments, the multiple production process files may be multiple files related to the production process system in an Internet database. Accordingly, obtaining text information corresponding to each of the multiple devices from the multiple production process files may include: selecting at least one target file associated with the production process system from the multiple production process files; performing text recognition on the at least one target file to obtain text information corresponding to each of the multiple devices.

[0046] It should be noted that after obtaining the raw data corresponding to multiple devices, the raw data can also be pre-processed such as cleaning and denoising to ensure the quality and integrity of the data.

[0047] In some embodiments, process parameters corresponding to each of the multiple devices are obtained from the production process system, including: obtaining initial process parameters corresponding to each of the multiple devices from the production process system; preprocessing the initial process parameters, deleting missing data in the initial process parameters, and deleting abnormal data in the initial process parameters; wherein abnormal data refers to data that deviates from a normal range.

[0048] S202. Input the process parameters corresponding to each of the multiple devices and the text information corresponding to each of the multiple devices into the trained neural network model to generate the annotation information corresponding to each of the multiple devices, wherein the annotation information includes the current process parameters and the reference range information of the process parameters.

[0049] The neural network model may be a machine learning model, a deep learning model, etc. The input feature information of the neural network model includes: process parameters of the equipment, text information of the equipment. The output feature information includes: current process parameters and reference range information of the process parameters.

[0050] For example, for the transmission equipment in the coal mine production system. The output characteristic information includes: the current power of the transmission equipment is 2000 watts, the optimal performance power is 2500 watts, and the power of the transmission equipment needs to be adjusted. The current load capacity of the belt in the transmission equipment is 400 kilograms, and the maximum belt load capacity is 500 watts, which has not exceeded the warning. The current speed of the motor in the transmission equipment is 2000 revolutions per second, and the maximum speed is 3000 revolutions per second, which has not exceeded the warning.

[0051] S203. Label multiple devices in the production process knowledge graph based on the labeling information corresponding to each of the multiple devices.

[0052] In some embodiments, the production process knowledge graph includes icons corresponding to multiple devices. Labeling multiple devices in the production process knowledge graph includes: associating device icons corresponding to each device in the production process knowledge graph with labeling information corresponding to each device. The labeling information can be displayed at any position around the device icon.

[0053] Optionally, when a user clicks on a device icon, the annotation information of the device can be displayed in the production process knowledge graph. For example, when a user clicks on the belt icon in the transmission device, the annotation information is displayed on the upper side of the belt icon: the current load capacity is 400 kg, the maximum belt load capacity is 500 watts, and the warning is not exceeded.

[0054] It should be noted that, based on the annotation information corresponding to each of the multiple devices, multiple devices in the production process knowledge graph are annotated to obtain an annotated production process knowledge graph. At this point, the production process knowledge graph can be manually reviewed to improve the accuracy of the production process knowledge graph. Furthermore, the neural network model can be optimized based on the manual review results.

[0055] The present application provides a method for annotating a production process knowledge graph, including: obtaining process parameters corresponding to each of multiple devices from a production process system, and obtaining text information corresponding to each of multiple devices from multiple production process files; inputting the process parameters corresponding to each of multiple devices and the text information corresponding to each of multiple devices into a trained neural network model to generate annotation information corresponding to each of multiple devices, wherein the annotation information includes the current process parameters and the reference range information of the process parameters; based on the annotation information corresponding to each of multiple devices, annotating multiple devices in the production process knowledge graph. In an embodiment of the present application, since the annotation information corresponding to each of multiple devices is automatically generated by the neural network model, the automatic annotation of the production process knowledge graph is realized, the annotation quality of industrial and mining production process data is improved, and annotation errors are reduced, thereby improving the credibility and accuracy of data annotation. At the same time, the present application can also speed up the construction of the knowledge graph, reduce labor costs and time costs, and improve the economic benefits of knowledge graph construction, which has obvious cost advantages for enterprises.

[0056] Figure 3 The process of the training method of the neural network model provided in the embodiment of the present disclosure Figure 1 In the embodiment of the present disclosure, the training method of the neural network model in step S202 is specifically described. Figure 3 As shown, the training method of the neural network model includes:

[0057] S301. Obtain a training sample set and a verification sample set, wherein the training sample set includes process parameters, text information, and actual annotation information corresponding to each of the multiple first devices, and the verification sample set includes process parameters, text information, and actual annotation information corresponding to each of the multiple second devices.

[0058] In some embodiments, a training sample set and a verification sample set are obtained, including: for each first device, obtaining the process parameters corresponding to the first device from the production process system, obtaining the text information corresponding to the first device from multiple production process files, and obtaining the actual annotation information corresponding to the first device through manual annotation, to obtain a training sample set; for each second device, obtaining the process parameters corresponding to the second device from the production process system, obtaining the text information corresponding to the second device from multiple production process files, and obtaining the actual annotation information corresponding to the second device through manual annotation, to obtain a verification sample set.

[0059] S302: Train the initial neural network model according to the process parameters, text information, and actual annotation information corresponding to each of the plurality of first devices.

[0060] In some embodiments, the initial neural network model is trained according to the process parameters, text information, and actual annotation information corresponding to each of the multiple first devices, including: inputting the process parameters and text information corresponding to each of the first devices into the initial neural network model, and outputting the test annotation information of each of the first devices; training the initial neural network model according to the test annotation information of each of the first devices and the actual annotation information of each of the first devices.

[0061] It should be noted that when the process parameters and text information corresponding to each first device are input into the initial neural network model, the process parameters and text information corresponding to each first device can be converted into a form suitable for processing by the machine learning algorithm to improve the efficiency of model training.

[0062] S303. Determine the accuracy of the initial neural network model through the process parameters, text information, and actual annotation information corresponding to each of the multiple second devices. If the accuracy is less than a preset threshold, adjust the initial neural network model until the accuracy is greater than or equal to the preset threshold to obtain a trained neural network model.

[0063] In the embodiment of the present disclosure, the value of the preset threshold is not specifically limited and can be set and modified as needed. Optionally, the preset threshold can be 85%, 90%, 95%, etc.

[0064] It should be noted that this method can also be combined with a labeling result fusion mechanism to merge the results of manual labeling and automatic labeling, thereby improving the accuracy and credibility of the overall labeling.

[0065] Figure 4 A schematic diagram of the structure of the device for labeling the production process knowledge graph provided in the embodiment of the present application. Figure 4 As shown, the annotation device of the production process knowledge graph includes: an acquisition module 401, a generation module 402 and a annotation module 403.

[0066] The acquisition module 401 is used to acquire process parameters corresponding to each of the multiple devices from the production process system, and to acquire text information corresponding to each of the multiple devices from multiple production process files;

[0067] A generation module 402 is used to input the process parameters corresponding to the multiple devices and the text information corresponding to the multiple devices into the trained neural network model to generate the annotation information corresponding to the multiple devices, wherein the annotation information includes the current process parameters and the reference range information of the process parameters;

[0068] The labeling module 403 is used to label multiple devices in the production process knowledge graph based on the labeling information corresponding to each of the multiple devices.

[0069] In a possible implementation, the acquisition module 401 acquires process parameters corresponding to each of the multiple devices from the production process system, specifically including: acquiring initial process parameters corresponding to each of the multiple devices from the production process system; preprocessing the initial process parameters, deleting missing data in the initial process parameters, and deleting abnormal data in the initial process parameters; wherein the abnormal data refers to data that deviates from a normal range.

[0070] In a possible implementation, the acquisition module 401 acquires text information corresponding to each of the multiple devices from multiple production process files, specifically including: selecting at least one target file associated with the production process system from the multiple production process files; performing text recognition on the at least one target file to obtain text information corresponding to each of the multiple devices.

[0071] In a possible implementation, the labeling device also includes: a training module; the training module is used to obtain a training sample set and a verification sample set, wherein the training sample set includes process parameters, text information, and actual labeling information corresponding to each of the multiple first devices, and the verification sample set includes process parameters, text information, and actual labeling information corresponding to each of the multiple second devices; the initial neural network model is trained according to the process parameters, text information, and actual labeling information corresponding to each of the multiple first devices; the accuracy of the initial neural network model is determined through the process parameters, text information, and actual labeling information corresponding to each of the multiple second devices, and if the accuracy is less than a preset threshold, the initial neural network model is adjusted until the accuracy is greater than or equal to the preset threshold, thereby obtaining a trained neural network model.

[0072] In a possible implementation, the training module obtains a training sample set and a verification sample set, specifically including: for each first device, obtaining the process parameters corresponding to the first device from the production process system, obtaining the text information corresponding to the first device from multiple production process files, and obtaining the actual annotation information corresponding to the first device through manual annotation to obtain the training sample set; for each second device, obtaining the process parameters corresponding to the second device from the production process system, obtaining the text information corresponding to the second device from multiple production process files, and obtaining the actual annotation information corresponding to the second device through manual annotation to obtain the verification sample set.

[0073] In one possible implementation, the training module trains the initial neural network model according to the process parameters, text information, and actual annotation information corresponding to each of the multiple first devices, specifically including: inputting the process parameters and text information corresponding to each of the first devices into the initial neural network model, and outputting the test annotation information of each of the first devices; training the initial neural network model according to the test annotation information of each of the first devices and the actual annotation information of each of the first devices.

[0074] The device for labeling the production process knowledge graph provided in the embodiment of the present application can be used to execute the technical solution of the method for labeling the production process knowledge graph in the above embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0075] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the acquisition module 401 can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The function of the above acquisition module 401. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0076] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 5 As shown, the electronic device may include: a transceiver 501 , a processor 502 , and a memory 503 .

[0077] The processor 502 executes the computer-executable instructions stored in the memory, so that the processor 502 executes the solution in the above embodiment. The processor 502 can be a general-purpose processor, including a central processing unit CPU, a network processor (network processor, NP), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0078] The memory 503 is connected to the processor 502 via a system bus and implements communication therebetween. The memory 503 is used to store computer program instructions.

[0079] The transceiver 501 may be used to obtain tasks to be executed and configuration information of the tasks to be executed.

[0080] The system bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The transceiver is used to realize the communication between the database access device and other computers (such as clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM) and may also include non-volatile memory.

[0081] The electronic device provided in the embodiments of the present application may be a terminal or a server in the above embodiments.

[0082] An embodiment of the present application also provides a chip for running instructions, which is used to execute the technical solution of the business data verification method in the above embodiment.

[0083] An embodiment of the present application also provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed on a computer, the computer executes the technical solution of the business data verification method of the above embodiment.

[0084] An embodiment of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When at least one processor executes the computer program, it can implement the technical solution of the business data verification method in the above embodiment.

[0085] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0086] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for labeling a production process knowledge graph, characterized in that: include: Acquire process parameters corresponding to each of the plurality of devices from a production process system, and acquire text information corresponding to each of the plurality of devices from a plurality of production process files; Inputting the process parameters corresponding to each of the plurality of devices and the text information corresponding to each of the plurality of devices into the trained neural network model to generate annotation information corresponding to each of the plurality of devices, wherein the annotation information includes current process parameters and reference range information of the process parameters; Based on the annotation information corresponding to each of the multiple devices, annotate the multiple devices in the production process knowledge graph; Acquire a training sample set and a verification sample set, wherein the training sample set includes process parameters, text information, and actual annotation information corresponding to each of the plurality of first devices, and the verification sample set includes process parameters, text information, and actual annotation information corresponding to each of the plurality of second devices; Training the initial neural network model according to the process parameters, text information, and actual annotation information corresponding to each of the plurality of first devices; Determine the accuracy of the initial neural network model through the process parameters, text information, and actual annotation information corresponding to each of the plurality of second devices; if the accuracy is less than a preset threshold, adjust the initial neural network model until the accuracy is greater than or equal to the preset threshold, thereby obtaining a trained neural network model; The production process knowledge graph includes icons corresponding to multiple devices, and the labeling of multiple devices in the production process knowledge graph includes: The equipment icons corresponding to each equipment in the production process knowledge graph are associated with the annotation information corresponding to each equipment.

2. The marking method according to claim 1, characterized in that: The step of obtaining process parameters corresponding to each of the plurality of devices from the production process system includes: Obtain the initial process parameters corresponding to each of the multiple devices from the production process system; The initial process parameters are preprocessed to delete missing data in the initial process parameters, and to delete abnormal data in the initial process parameters; wherein the abnormal data refers to data that deviates from a normal range.

3. The marking method according to claim 1, characterized in that: The obtaining text information corresponding to each of the plurality of devices from the plurality of production process files includes: Selecting at least one target file associated with the production process system from the plurality of production process files; Perform text recognition on the at least one target file to obtain text information corresponding to each of the multiple devices.

4. The marking method according to claim 1, characterized in that: The obtaining of the training sample set and the verification sample set includes: For each first device, obtaining a process parameter corresponding to the first device from a production process system, obtaining text information corresponding to the first device from a plurality of production process files, and obtaining actual annotation information corresponding to the first device by manual annotation to obtain the training sample set; For each second device, the process parameters corresponding to the second device are obtained from the production process system, the text information corresponding to the second device is obtained from multiple production process files, and the actual annotation information corresponding to the second device is obtained through manual annotation to obtain the verification sample set.

5. The marking method according to claim 1, characterized in that: The training of the initial neural network model according to the process parameters, text information, and actual annotation information corresponding to each of the plurality of first devices includes: Inputting the process parameters and text information corresponding to each first device into the initial neural network model, and outputting the test annotation information of each first device; The initial neural network model is trained according to the test annotation information of each first device and the actual annotation information of each first device.

6. A device for labeling a production process knowledge graph, characterized in that: include: An acquisition module is used to acquire process parameters corresponding to each of the multiple devices from a production process system, and to acquire text information corresponding to each of the multiple devices from multiple production process files; A generation module, used for inputting the process parameters corresponding to each of the plurality of devices and the text information corresponding to each of the plurality of devices into the trained neural network model, and generating the annotation information corresponding to each of the plurality of devices, wherein the annotation information includes the current process parameters and the reference range information of the process parameters; A labeling module, used for labeling a plurality of devices in the production process knowledge graph based on the labeling information corresponding to each of the plurality of devices; A training module, used to obtain a training sample set and a verification sample set, wherein the training sample set includes process parameters, text information, and actual annotation information corresponding to each of the plurality of first devices, and the verification sample set includes process parameters, text information, and actual annotation information corresponding to each of the plurality of second devices; The initial neural network model is trained according to the process parameters, text information, and actual annotation information corresponding to each of the plurality of first devices; the accuracy of the initial neural network model is determined by the process parameters, text information, and actual annotation information corresponding to each of the plurality of second devices, and if the accuracy is less than a preset threshold, the initial neural network model is adjusted until the accuracy is greater than or equal to the preset threshold, thereby obtaining a trained neural network model; The production process knowledge graph includes icons corresponding to multiple devices, and the labeling module is specifically used to associate the device icons corresponding to each device in the production process knowledge graph with the labeling information corresponding to each device.

7. An electronic device, characterized in that: include: Processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the method for labeling the production process knowledge graph as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the processor executes the computer-executable instructions, the method for labeling the production process knowledge graph as described in any one of claims 1 to 5 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the method for labeling the production process knowledge graph as described in any one of claims 1 to 5.

Images