Production data processing method, device, equipment, storage medium and program product

Abstract

The present application provides a production data processing method, device, equipment, storage medium and program product, the method comprising obtaining scene information of a production scene to be detected, using a pre-trained model, obtaining at least one production indicator corresponding to the production scene to be detected according to the scene information; obtaining production data corresponding to each of the production indicators, and obtaining a production result prediction value of the production scene to be detected according to the production data corresponding to each of the production indicators; determining whether there are problems to be checked in the production scene to be detected according to the production result prediction value, and performing early warning processing when it is determined that there are problems to be checked in the production scene to be detected. The production data can be analyzed accurately and efficiently, effectively improving the decision-making efficiency, and solving the problem of low efficiency and accuracy of production data analysis in the prior art.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a production data processing method, device, equipment, storage medium and program product. Background Art

[0002] The coal processing process often involves many production equipment, generating a large amount of production data. Accurate analysis of this data plays a vital guiding role in monitoring the production process and allocating production resources.

[0003] In the prior art, the analysis of production data often relies on developers to determine the production data related to each production indicator from massive production data and build business logic for data analysis, resulting in low efficiency and accuracy of data analysis. Summary of the invention

[0004] The present application provides a production data processing method, device, equipment, storage medium and program product, which are used to solve the problem of low efficiency and accuracy of production data analysis in the prior art.

[0005] In a first aspect, the present application provides a production data processing method, comprising: obtaining scene information of a production scene to be detected, and using a pre-trained model to obtain at least one production indicator corresponding to the production scene to be detected based on the scene information; obtaining production data corresponding to each of the production indicators, and obtaining a production result prediction value of the production scene to be detected based on the production data corresponding to each of the production indicators; determining whether the production scene to be detected has any problems to be troubleshooted based on the production result prediction value, and performing early warning processing when it is determined that the production scene to be detected has any problems to be troubleshooted.

[0006] In a specific embodiment, a pre-trained model is used to obtain at least one production indicator corresponding to the production scene to be detected based on the scene information, including: performing semantic splitting processing on the scene information to obtain at least one keyword of the scene information; and querying at least one production indicator corresponding to the production scene to be detected in a database based on the at least one keyword.

[0007] In a specific embodiment, obtaining the production data corresponding to each of the production indicators includes: obtaining the production data of at least one production equipment in the production scene to be detected, and classifying and processing the production data according to the at least one production indicator to obtain the production data corresponding to each of the production indicators.

[0008] In a specific implementation, the production data processing method further includes: generating a production report of the production scenario to be detected according to each of the production indicators and the production data corresponding to each of the production indicators, and displaying the production report.

[0009] In a specific embodiment, the pre-trained model is obtained by: obtaining historical scene information corresponding to at least one historical production scene and at least one historical production indicator corresponding to each of the historical production scenes; based on the historical scene information and the historical production indicators, using a low-rank adaptation fine-tuning algorithm and a retrieval enhancement generation algorithm, to obtain the pre-trained model.

[0010] In a specific implementation, the production data includes a combination of one or more of the following: equipment operation data of the production equipment, equipment parameters, and equipment warning information.

[0011] In the second aspect, the present application provides a production data processing device, including: a data acquisition module, used to obtain scene information of a production scene to be detected; a data processing module, used to use a pre-trained model to obtain at least one production indicator corresponding to the production scene to be detected according to the scene information; the data acquisition module is also used to obtain production data corresponding to each of the production indicators; the data processing module is also used to obtain a production result prediction value of the production scene to be detected based on the production data corresponding to each of the production indicators; based on the production result prediction value, determine whether the production scene to be detected has problems to be checked, and perform early warning processing when it is determined that the production scene to be detected has problems to be checked.

[0012] In a third aspect, the present application provides an electronic device comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the production data processing method as described in the first aspect.

[0013] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the production data processing method as described in the first aspect.

[0014] In a fifth aspect, the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the production data processing method as described in the first aspect.

[0015] The present application provides a production data processing method, device, equipment, storage medium and program product, the method comprising: obtaining scene information of a production scene to be detected, using a pre-trained model, according to the scene information, obtaining at least one production indicator corresponding to the production scene to be detected; obtaining production data corresponding to each production indicator, using a large language model, according to the production data corresponding to each production indicator, obtaining the production result prediction value of the production scene to be detected; according to the production result prediction value, determining whether there is a problem to be checked in the production scene to be detected, and when it is determined that there is a problem to be checked in the production scene to be detected, performing early warning processing. Compared with the prior art that relies on developers to determine the production data related to each production indicator from massive production data, construct business logic for data analysis, so as to guide the monitoring of the production process and the allocation of production resources, the production data processing method of the present application uses a pre-trained model to determine the production indicator corresponding to the production scene to be detected, obtains the production data corresponding to each production indicator, and obtains the production result prediction value of the production scene to be detected according to the production data corresponding to each production indicator, thereby checking whether there is a problem in the production scene to be detected. It can accurately and efficiently analyze production data, effectively improve decision-making efficiency, and solve the problems of low efficiency and accuracy of production data analysis in existing technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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.

[0017] Figure 1 A flowchart of a production data processing method embodiment 1 provided in the present application;

[0018] Figure 2 A flowchart of a second embodiment of a production data processing method provided by the present application;

[0019] Figure 3 A flowchart of a third embodiment of a production data processing method provided by the present application;

[0020] Figure 4 A flowchart of a fourth embodiment of a production data processing method provided by the present application;

[0021] Figure 5 A schematic diagram of the structure of an embodiment of a production data processing device provided by the present application;

[0022] Figure 6A schematic diagram of the structure of an electronic device embodiment provided in the present application. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments made by ordinary technicians in this field under the enlightenment of the embodiments belong to the scope of protection of the present application.

[0024] 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 interchanged where appropriate, so that the embodiments 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.

[0025] The coal processing process often involves many production equipment, generating a large amount of production data. Accurate analysis of this data plays a vital guiding role in monitoring the production process and allocating production resources.

[0026] In the prior art, the analysis of production data often relies on developers to determine the production data related to each production indicator from massive production data and build business logic for data analysis, resulting in low efficiency and accuracy of data analysis.

[0027] Based on the above technical problems, the technical conception process of this application is as follows: How to provide a production data processing method to solve the problem of low efficiency and accuracy of production data analysis in the prior art.

[0028] The technical solution of the present application is described in detail below through specific embodiments. It should be noted that 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.

[0029] Figure 1 This is a flow chart of a production data processing method embodiment 1 provided in this application. Figure 1 , the production data processing method specifically includes the following steps:

[0030] Step S101: Obtain scene information of a production scene to be detected, and use a pre-trained model to obtain at least one production indicator corresponding to the production scene to be detected based on the scene information.

[0031] In this embodiment, the scene information of the production scene to be detected can be obtained. The production scene to be detected can be a production scene in the coal processing process, such as a production scene of "raw coal processing produces ash". The scene information of the production scene to be detected can represent the information to be detected of the production scene, for example, the scene information of the production scene "raw coal processing produces ash" can be "raw coal ash situation".

[0032] In this embodiment, the production scenario to be detected may correspond to at least one production indicator. For example, the production scenario "ash produced by raw coal processing" may correspond to multiple production indicators, including raw coal, clean coal, sulfidation, water washing, coal quality, etc. The pre-trained model may be used to obtain at least one production indicator corresponding to the production scenario to be detected.

[0033] Specifically, the scene information can be semantically split to obtain keywords of the scene information. For example, the scene information "ash content of raw coal" is semantically split to obtain keywords such as "raw coal" and "ash content". Then, based on these keywords, the production indicators corresponding to the production scene to be tested are queried in the database. For example, based on the keywords "raw coal" and "ash content", the production indicators corresponding to the production scene to be tested "ash content generated by raw coal processing" can be queried in the database as raw coal, clean coal, sulfidation, water washing, coal quality, etc.

[0034] Step S102: Obtain production data corresponding to each production indicator, and obtain a production result prediction value of the production scenario to be detected based on the production data corresponding to each production indicator.

[0035] In this embodiment, production data corresponding to each production indicator can be obtained. The production data may include equipment operation data, equipment parameters, equipment warning information, etc. of each production equipment. Different production indicators may correspond to different production data. For example, the production data corresponding to the production indicator "raw coal" may include "coal consumption" and the like.

[0036] Specifically, the production data of at least one production equipment in the production scenario to be detected can be obtained, and the production data can be classified and processed according to multiple production indicators to obtain the production data corresponding to each production indicator. For example, the production data of multiple production equipment in the production scenario to be detected "ash produced by raw coal processing" can be obtained, and the production data can be classified and processed according to multiple production indicators such as "raw coal", "clean coal", "sulfurization", "water washing", "coal quality", etc., to obtain the production data corresponding to each production indicator.

[0037] In this embodiment, a large language model (LLM) can be used to obtain the production result prediction value of the production scenario to be detected based on the production data corresponding to each production indicator. Exemplarily, the production data corresponding to each production indicator can be calculated according to the operation rules corresponding to the production scenario to be detected in the large language model to obtain the production result prediction value of the production scenario to be detected. For example, the large language model is used to obtain the production result prediction value of the production scenario to be detected "ash generated by raw coal processing" based on the production data corresponding to each production indicator, that is, the ash prediction value.

[0038] Step S103: Determine whether the production scenario to be detected has any problem to be investigated based on the predicted value of the production result, and perform early warning processing when it is determined that the production scenario to be detected has any problem to be investigated.

[0039] In this embodiment, it can be determined whether there are problems to be investigated in the production scenario to be detected based on the predicted value of the production result. For example, it can be determined whether there are problems to be investigated in the production scenario to be detected "ash generated by raw coal processing" based on whether the predicted value of ash content exceeds a preset threshold. When it is determined that there are problems to be investigated in the production scenario to be detected, early warning processing is performed.

[0040] In this embodiment, the scene information of the production scene to be detected is obtained, and at least one production indicator corresponding to the production scene to be detected is obtained according to the scene information using a pre-trained model; the production data corresponding to each production indicator is obtained, and the large language model is used to obtain the production result prediction value of the production scene to be detected according to the production data corresponding to each production indicator; according to the production result prediction value, it is determined whether there is a problem to be checked in the production scene to be detected, and when it is determined that there is a problem to be checked in the production scene to be detected, early warning processing is performed. Compared with the prior art that relies on developers to determine the production data related to each production indicator from massive production data, and construct business logic for data analysis to guide the monitoring of production processes and the allocation of production resources, the production data processing method of the present application uses a pre-trained model to determine the production indicator corresponding to the production scene to be detected, obtains the production data corresponding to each production indicator, and obtains the production result prediction value of the production scene to be detected according to the production data corresponding to each production indicator, and then checks whether there is a problem in the production scene to be detected. The production data can be analyzed accurately and efficiently, effectively improving the decision-making efficiency, and solving the problem of low efficiency and accuracy of production data analysis in the prior art.

[0041] Figure 2 This is a flow chart of a second embodiment of a production data processing method provided by this application. Figure 1 Based on the embodiment shown, see Figure 2, the above steps S101 to S102 specifically include the following steps:

[0042] Step S201: performing semantic splitting processing on the scene information to obtain at least one keyword of the scene information.

[0043] In this embodiment, the pre-trained model can be used to perform semantic segmentation processing on the scene information to obtain keywords of the scene information. For example, the scene information "ash content of raw coal" can be semantically segmented to obtain keywords such as "raw coal" and "ash content".

[0044] Exemplarily, the pre-trained model can be trained based on historical scenario information corresponding to multiple historical production scenarios and multiple historical production indicators corresponding to each historical production scenario through low-rank adaptation (Lora) fine-tuning technology and Retrieval Augmented Generation (RAG) technology.

[0045] Step S202: According to at least one keyword, query at least one production indicator corresponding to the production scenario to be detected in the database.

[0046] In this embodiment, the pre-trained model can be used to query the production indicators corresponding to the production scenario to be detected in the database according to each keyword. As described in the previous example, according to the keywords "raw coal", "ash content", etc., the production indicators corresponding to the production scenario to be detected "raw coal processing produces ash content" can be queried in the database as raw coal, clean coal, sulfidation, water washing, coal quality, etc.

[0047] Step S203: Obtain production data of at least one production device in the production scene to be detected, and classify the production data according to at least one production indicator to obtain production data corresponding to each production indicator.

[0048] In this embodiment, the production scene to be detected may include multiple production equipment. Each production equipment may have multiple production data. The production data may include equipment operation data, equipment parameters, equipment warning information, etc. of the production equipment. Among them, the equipment warning information may be, for example, warning information of equipment overload operation.

[0049] The production data of at least one production equipment in the production scene to be detected can be obtained, and the production data can be preprocessed, that is, the production data can be classified and processed according to at least one production indicator corresponding to the production scene to be detected. As described in the previous example, the production data of each production equipment in the production scene to be detected can be classified and processed according to the production indicators raw coal, clean coal, sulfidation, water washing, coal quality, etc. corresponding to the production scene to be detected "raw coal processing produces ash content", and the production data corresponding to each production indicator can be obtained.

[0050] In this embodiment, the scene information is semantically split to obtain keywords, and the production indicators corresponding to the production scene to be detected are queried in the database based on the keywords, so that the production indicators corresponding to the production scene to be detected can be accurately and efficiently obtained; according to the production indicators of the production scene to be detected, the production data of the production equipment in the production scene to be detected are classified and processed, and the production data corresponding to each production indicator can be accurately obtained, which provides a prerequisite for subsequently obtaining the production result prediction value of the production scene to be detected according to the production data corresponding to each production indicator to make accurate decisions.

[0051] Figure 3 This is a flow chart of a third embodiment of a method for producing data provided by this application. Figure 1 to Figure 2 Based on the embodiment shown, see Figure 3 , the production data processing method specifically includes the following steps:

[0052] Step S301: Obtain scene information of a production scene to be detected, and use a pre-trained model to obtain at least one production indicator corresponding to the production scene to be detected based on the scene information.

[0053] In this embodiment, the scene information of the production scene to be detected can be obtained. The production scene to be detected can be a production scene in the coal processing process, such as a production scene of "raw coal processing produces ash". The scene information of the production scene to be detected can represent the information to be detected of the production scene, for example, the scene information of the production scene "raw coal processing produces ash" can be "raw coal ash situation". Exemplarily, the scene information of the production scene to be detected can be obtained by human-computer interaction.

[0054] In this embodiment, the production scenario to be detected may correspond to at least one production indicator. For example, the production scenario "ash produced by raw coal processing" may correspond to multiple production indicators, including raw coal, clean coal, sulfidation, water washing, coal quality, etc. The pre-trained model may be used to obtain at least one production indicator corresponding to the production scenario to be detected.

[0055] Specifically, the scene information can be semantically split to obtain keywords of the scene information. For example, the scene information "ash content of raw coal" is semantically split to obtain keywords such as "raw coal" and "ash content". Then, based on these keywords, the production indicators corresponding to the production scene to be tested are queried in the database. For example, based on the keywords "raw coal" and "ash content", the production indicators corresponding to the production scene to be tested "ash content generated by raw coal processing" can be queried in the database as raw coal, clean coal, sulfidation, water washing, coal quality, etc.

[0056] Step S302: Obtain production data corresponding to each production indicator, and obtain a production result prediction value of the production scenario to be detected based on the production data corresponding to each production indicator.

[0057] In this embodiment, production data corresponding to each production indicator can be obtained. The production data may include a combination of one or more of the following: equipment operation data of the production equipment, equipment parameters, and equipment warning information. Different production indicators may correspond to different production data. For example, the production data corresponding to the production indicator "raw coal" may include "coal consumption" and the like.

[0058] Specifically, the production data of at least one production equipment in the production scenario to be detected can be obtained, and the production data can be classified and processed according to multiple production indicators to obtain the production data corresponding to each production indicator. For example, the production data of multiple production equipment in the production scenario to be detected "ash produced by raw coal processing" can be obtained, and the production data can be classified and processed according to multiple production indicators such as "raw coal", "clean coal", "sulfurization", "water washing", "coal quality", etc., to obtain the production data corresponding to each production indicator.

[0059] In this embodiment, a large language model (LLM) can be used to obtain the production result prediction value of the production scenario to be detected based on the production data corresponding to each production indicator. Exemplarily, the production data corresponding to each production indicator can be calculated according to the operation rules corresponding to the production scenario to be detected in the large language model to obtain the production result prediction value of the production scenario to be detected. For example, the large language model is used to obtain the production result prediction value of the production scenario to be detected "ash generated by raw coal processing" based on the production data corresponding to each production indicator, that is, the ash prediction value.

[0060] Step S303: Determine whether the production scenario to be detected has any problem to be investigated based on the predicted value of the production result, and perform early warning processing when it is determined that the production scenario to be detected has any problem to be investigated.

[0061] In this embodiment, it can be determined whether there are problems to be investigated in the production scenario to be detected based on the predicted value of the production result. For example, it can be determined whether there are problems to be investigated in the production scenario to be detected "ash generated by raw coal processing" based on whether the predicted value of ash content exceeds a preset threshold. When it is determined that there are problems to be investigated in the production scenario to be detected, early warning processing is performed.

[0062] Step S304: Generate a production report of the production scenario to be detected according to each production indicator and the production data corresponding to each production indicator, and display the production report.

[0063] In this embodiment, a production report of the production scenario to be detected is generated according to each production indicator and the production data corresponding to each production indicator, and the production report is displayed.

[0064] In a possible implementation, a data report may be generated according to each production indicator and the production data corresponding to each production indicator, and a production report of the production scene to be detected may be obtained and displayed.

[0065] In a possible implementation, a production trend graph may be generated based on each production indicator and the production data corresponding to each production indicator, and a production report of the production scenario to be detected may be obtained and displayed.

[0066] In a possible implementation, a production report for the production scenario to be detected may be generated and displayed based on each production indicator and the production data corresponding to each production indicator in combination with the predicted value of the production result.

[0067] In this embodiment, a production report of the production scene to be detected is generated according to each production indicator and the production data corresponding to each production indicator, and the production report is displayed. In this way, the data analysis results can be visualized on the basis of accurately and efficiently analyzing the production data, further improving the decision-making efficiency and solving the problem of low efficiency and accuracy of production data analysis in the prior art.

[0068] Figure 4 This is a flow chart of a fourth embodiment of a production data processing method provided by this application. Figures 1 to 3 Based on the embodiment shown, see Figure 4 , the method of obtaining the pre-training model specifically includes the following steps:

[0069] Step S401: Acquire historical scenario information corresponding to at least one historical production scenario and at least one historical production indicator corresponding to each historical production scenario.

[0070] In this embodiment, historical scene information corresponding to multiple historical production scenes can be obtained. For example, the historical production scenes can be "raw coal processing to produce ash", "clean coal processing", etc. Each historical production scene corresponds to at least one historical production indicator. For example, the historical production indicators can be raw coal, clean coal, sulfidation, water washing, coal quality, etc.

[0071] Step S402: According to historical scene information and historical production indicators, a pre-trained model is obtained using a low-rank adaptation fine-tuning algorithm and a retrieval enhancement generation algorithm.

[0072] In this embodiment, a pre-trained model can be obtained based on historical scene information and historical production indicators using a fine-tuning algorithm and a retrieval enhancement generation algorithm.

[0073] The pre-trained model can be trained based on historical scenario information corresponding to multiple historical production scenarios and multiple historical production indicators corresponding to each historical production scenario through low-rank adaptive Lora fine-tuning technology and retrieval enhancement generation RAG technology.

[0074] Specifically, historical scene information corresponding to multiple historical production scenes can be applied, and the Lora fine-tuning algorithm can be used for semantic segmentation processing to obtain keywords for model training, so that the pre-trained model can perform semantic segmentation of scene information more accurately.

[0075] Multiple historical production indicators corresponding to each historical production scenario and the keywords obtained through splitting can be used for model training, so that the pre-trained model can more accurately match the production indicators corresponding to the keywords.

[0076] In this embodiment, historical scene information corresponding to the historical production scenes and historical production indicators corresponding to each historical production scene are obtained, and a pre-trained model is obtained by utilizing a fine-tuning algorithm and a retrieval enhancement generation algorithm based on the historical scene information and the historical production indicators. This provides a prerequisite for subsequent more accurate semantic splitting of the scene information of the production scenes to be detected, and accurate matching of the production indicators corresponding to the split keywords.

[0077] Figure 5 The schematic diagram of the structure of a production data processing device embodiment provided by the present application includes a data acquisition module 51 and a data processing module 52 .

[0078] Among them, the data acquisition module 51 is used to obtain scene information of the production scene to be detected; the data processing module 52 is used to use the pre-trained model to obtain at least one production indicator corresponding to the production scene to be detected according to the scene information; the data acquisition module 51 is also used to obtain the production data corresponding to each production indicator; the data processing module 52 is also used to obtain the production result prediction value of the production scene to be detected according to the production data corresponding to each production indicator; based on the production result prediction value, determine whether there are problems to be checked in the production scene to be detected, and when it is determined that there are problems to be checked in the production scene to be detected, perform early warning processing.

[0079] The production data processing device provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0080] In a possible implementation, the data processing module 52 is specifically used to perform semantic splitting processing on the scene information to obtain at least one keyword of the scene information; based on the at least one keyword, query at least one production indicator corresponding to the production scene to be detected in the database.

[0081] In a possible implementation, the data acquisition module 51 is specifically used to obtain production data of at least one production equipment in the production scene to be detected, and classify the production data according to the at least one production indicator to obtain production data corresponding to each production indicator.

[0082] The production data processing device provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0083] In a possible implementation, the data processing module 52 is further used to generate a production report of the production scenario to be detected according to each production indicator and the production data corresponding to each production indicator, and to display the production report.

[0084] In a possible implementation, the data processing module 52 is also used to obtain historical scene information corresponding to at least one historical production scene and at least one historical production indicator corresponding to each historical production scene; based on the historical scene information and the historical production indicator, the pre-trained model is obtained using a low-rank adaptation fine-tuning algorithm and a retrieval enhancement generation algorithm.

[0085] In a possible implementation manner, the production data includes a combination of one or more of the following: equipment operation data of the production equipment, equipment parameters, and equipment warning information.

[0086] The production data processing device provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0087] Figure 6 This is a schematic diagram of the structure of an electronic device embodiment provided by the present application. Figure 6 As shown, the electronic device 60 includes: a processor 61, a memory 62 communicatively connected to the processor 61, and a communication interface 63; wherein the memory 62 stores computer-executable instructions; the processor 61 executes the computer-executable instructions stored in the memory 62 to implement the technical solution in any of the aforementioned method embodiments.

[0088] Optionally, the memory 62 may be independent or integrated with the processor 61 .

[0089] Optionally, when the memory 62 is a device independent of the processor 61, the electronic device 60 may further include: a bus 64 for connecting the above devices.

[0090] The electronic device is used to execute the technical solution in any of the aforementioned method embodiments, and its implementation principle and technical effect are similar and will not be repeated here.

[0091] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the technical solution in any of the aforementioned method embodiments.

[0092] The present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the technical solution in any of the aforementioned method embodiments is implemented.

[0093] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A production data processing method, characterized in that: include: Acquire scene information of a production scene to be detected, and use a pre-trained model to acquire at least one production indicator corresponding to the production scene to be detected according to the scene information; The scene information of the production scene to be detected represents the information to be detected of the production scene to be detected; Acquire production data of at least one production equipment in the production scene to be detected, and classify and process the production data according to the at least one production indicator to obtain production data corresponding to each production indicator; the production data includes a combination of one or more of the following: equipment operation data, equipment parameters and equipment warning information of the production equipment; According to the production data corresponding to each of the production indicators, the production result prediction value of the production scenario to be detected is obtained; the production result prediction value is the prediction value of the information to be detected; if the production scenario to be detected is that raw coal processing produces ash, then the scenario information is the ash content of the raw coal, and the production result prediction value is the ash content prediction value; According to the predicted value of the production result, it is determined whether the production scene to be detected has any problem to be investigated, and when it is determined that the production scene to be detected has any problem to be investigated, early warning processing is performed.

2. The production data processing method according to claim 1, characterized in that: Using the pre-trained model, according to the scenario information, obtaining at least one production indicator corresponding to the production scenario to be detected, including: Performing semantic splitting processing on the scene information to obtain at least one keyword of the scene information; According to the at least one keyword, at least one production indicator corresponding to the production scenario to be detected is queried in a database.

3. The production data processing method according to claim 1 or 2, characterized in that: Also includes: According to each of the production indicators and the production data corresponding to each of the production indicators, a production report of the production scenario to be detected is generated, and the production report is displayed.

4. The production data processing method according to claim 1 or 2, characterized in that: The pre-training model is obtained as follows: Acquire historical scenario information corresponding to at least one historical production scenario and at least one historical production indicator corresponding to each of the historical production scenarios; According to the historical scene information and the historical production indicators, the pre-trained model is obtained by utilizing a low-rank adaptation fine-tuning algorithm and a retrieval enhancement generation algorithm.

5. A production data processing device, characterized in that: include: A data acquisition module, used to obtain scene information of the production scene to be detected; The scene information of the production scene to be detected represents the information to be detected of the production scene to be detected; A data processing module, used to obtain at least one production indicator corresponding to the production scenario to be detected according to the scenario information by using a pre-trained model; The data acquisition module is further used to obtain production data of at least one production equipment in the production scene to be detected, and classify and process the production data according to the at least one production indicator to obtain production data corresponding to each production indicator; the production data includes a combination of one or more of the following: equipment operation data, equipment parameters and equipment warning information of the production equipment; The data processing module is further used to obtain a production result prediction value of the production scenario to be detected according to the production data corresponding to each of the production indicators; the production result prediction value is a prediction value of the information to be detected; if the production scenario to be detected is that raw coal processing produces ash, then the scenario information is the ash content of the raw coal, and the production result prediction value is an ash content prediction value; The data processing module is also used to determine whether there are any problems to be investigated in the production scene to be detected based on the predicted value of the production result, and perform early warning processing when it is determined that there are problems to be investigated in the production scene to be detected.

6. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the production data processing method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the production data processing method according to any one of claims 1 to 4 when executed by a processor.

8. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the production data processing method according to any one of claims 1 to 4 is implemented.

Images