An early warning method and system based on digital auditing and AI in power engineering

Abstract

The present application discloses a warning method and system based on digital auditing of power engineering and AI. The method includes: obtaining current engineering data and historical engineering data of a target power grid; determining a current data digest corresponding to the current engineering data; analyzing the current data digest by using a digital auditing system for power engineering to obtain auditing opinion information; determining a second target object from multiple first target objects of the target power grid based on the auditing opinion information; generating a warning prompt information and a candidate adjustment plan by using an artificial intelligence model based on the current engineering data, historical engineering data, auditing opinion information and object information of the second target object; and performing engineering risk warning based on the warning prompt information and the candidate adjustment plan, so as to be able to automatically complete relevant auditing and give corresponding engineering risk warning results, accurately warn of the risks existing in power engineering, and improve the reliability of engineering construction plans.

Description

Technical Field

[0001] This application relates to the field of power technology, and in particular, to an early warning method and system based on digital auditing of power engineering and AI. Background Art

[0002] At present, after the relevant project plan of the power project is determined, manual auditing is often relied on to review whether the plan meets the requirements (such as safety, design, construction, supervision, etc.). Manual auditing requires manual comparison with various requirements and standards (such as safety, design, construction, supervision, etc.), and checks each parameter and operation process in the plan one by one. This method is extremely inefficient. Facing the increasingly large and complex power engineering data, the manual processing speed far lags behind the actual needs. At the same time, the accuracy of manual auditing is greatly affected by factors such as the professional level and working status of auditors, and it is easy to have omissions, making it difficult to comprehensively guarantee the reliability of power engineering auditing.

[0003] With the development of AI (Artificial Intelligence) technology, although there are some applications in the field of engineering auditing, there are obvious deficiencies in the combination with digital auditing of power engineering. For example, existing AI algorithms are difficult to accurately adapt to the special rules of power engineering auditing, resulting in the inability to effectively utilize the advantages of AI in the process of engineering risk early warning and plan generation, and unable to provide reliable and accurate support for the adjustment of relevant project plans of power engineering. Summary of the Invention

[0004] In order to solve the above technical problems, the embodiments of this application propose an early warning method and system based on digital auditing of power engineering and AI, which can accurately early warn of the risks existing in power engineering and improve the reliability of the engineering construction plan.

[0005] In a first aspect, the embodiments of this application provide an early warning method based on digital auditing of power engineering and AI, including:

[0006] Obtain the current engineering data and historical engineering data of the target power grid, where the current engineering data is obtained by performing text recognition and semantic understanding on the materials of the current project of the target power grid;

[0007] Determine the current data summary corresponding to the current engineering data;

[0008] Use the digital auditing system of power engineering to analyze the current data summary to obtain audit opinion information;

[0009] Based on the audit opinion information, determine a second target object from multiple first target objects of the target power grid;

[0010] Generate a warning prompt message and at least one candidate adjustment plan by using an artificial intelligence model based on the current project data, the historical project data, the audit opinion information, and the object information of the second target object obtained;

[0011] Based on the warning prompt message and the at least one candidate adjustment plan, conduct project risk warning, wherein the warning result is used to adjust the construction plan of the current project.

[0012] Optionally, the conducting project risk warning based on the warning prompt message and the at least one candidate adjustment plan includes:

[0013] According to the warning prompt message, respectively conduct simulation for the at least one candidate adjustment plan to obtain the simulation results of the at least one candidate adjustment plan;

[0014] Based on the simulation results, the warning prompt message, and the at least one candidate adjustment plan, determine an adjustment plan;

[0015] Conduct project risk warning according to the adjustment plan.

[0016] Optionally, the historical project data includes multiple historical sub - data, and the conducting simulation for the at least one candidate adjustment plan according to the warning prompt message to obtain the simulation results of the at least one candidate adjustment plan includes:

[0017] For each candidate adjustment plan,

[0018] Determine at least one historical sub - data that matches the candidate adjustment plan from the multiple historical sub - data;

[0019] Based on the at least one historical sub - data, determine at least one simulation model corresponding to the candidate adjustment plan;

[0020] According to the warning prompt message, call the at least one simulation model to respectively conduct simulation for the candidate adjustment plan to obtain the simulation data corresponding to the at least one simulation model;

[0021] Determine the simulation result of the candidate adjustment plan according to the simulation data.

[0022] Optionally, the determining an adjustment plan based on the simulation results, the warning prompt message, and the at least one candidate adjustment plan includes:

[0023] For each candidate adjustment plan, conduct a difference analysis between its simulation result and the warning prompt message to obtain a difference analysis result, and verify the candidate adjustment plan according to the difference analysis result;

[0024] Determine an adjustment plan based on the at least one candidate adjustment plan and their respective verification results.

[0025] Optionally, the generating of the early warning prompt information and at least one candidate adjustment plan by using an artificial intelligence model based on the current engineering data, the historical engineering data, the audit opinion information, and the obtained object information of the second target object includes:

[0026] Generate key information based on the audit opinion information and the object information;

[0027] Determine a target key scenario from a plurality of preset key scenarios based on the key information and the historical engineering data;

[0028] Generate the early warning prompt information and the at least one candidate adjustment plan by using the artificial intelligence model based on the target key scenario, the current engineering data, and the historical engineering data.

[0029] Optionally, the determining of the target key scenario from a plurality of preset key scenarios based on the key information and the historical engineering data includes:

[0030] Determine at least one candidate key scenario that matches the key information from the plurality of key scenarios;

[0031] Determine the respective evaluation values of the at least one candidate key scenario;

[0032] Determine the target key scenario from the at least one candidate key scenario based on the historical engineering data and the respective evaluation values of the at least one candidate key scenario.

[0033] Optionally, the artificial intelligence model includes a large model, and the generating of the early warning prompt information and the at least one candidate adjustment plan by using the artificial intelligence model based on the target key scenario, the current engineering data, and the historical engineering data includes:

[0034] Input the target key scenario, the current engineering data, and the historical engineering data into the large model, so that the large model analyzes the current engineering data and the historical engineering data under the prompt of the target key scenario to generate the early warning prompt information and the at least one candidate adjustment plan.

[0035] Optionally, the analyzing of the current data summary by using the power engineering digital audit system to obtain audit opinion information includes:

[0036] Input the current data summary into the power engineering digital audit system;

[0037] The power engineering digital auditing system expands at least part of the information of the current data summary;

[0038] The power engineering digital auditing system queries according to the expanded information to obtain the auditing opinion information.

[0039] Optionally, the power engineering digital auditing system is configured to:

[0040] Use a preset auditing key node analysis strategy to extract information from the current data summary to obtain an original information sequence;

[0041] Obtain auditing prompt information;

[0042] Expand the original information sequence based on the auditing prompt information to obtain the expanded information.

[0043] In a second aspect, an embodiment of the present application provides an early warning system based on power engineering digital auditing and AI, including:

[0044] A data acquisition module, configured to acquire current engineering data and historical engineering data of a target power grid, wherein the current engineering data is obtained by performing text recognition and semantic understanding on the materials of the current project of the target power grid;

[0045] A data summary determination module, configured to determine a current data summary corresponding to the current engineering data;

[0046] An auditing module, configured to use a power engineering digital auditing system to analyze the current data summary to obtain auditing opinion information;

[0047] A second target object determination module, configured to determine a second target object from multiple first target objects of the target power grid based on the auditing opinion information;

[0048] An intelligent analysis module, configured to generate an early warning prompt information and at least one candidate adjustment plan by using an artificial intelligence model based on the current engineering data, the historical engineering data, the auditing opinion information, and the object information of the obtained second target object;

[0049] An early warning module, configured to perform engineering risk early warning based on the early warning prompt information and the at least one candidate adjustment plan, wherein the early warning result is used to adjust the construction plan of the current project.

[0050] In summary, the embodiments of the present application have at least the following beneficial effects:

[0051] By adopting the embodiments of the present application, the current engineering data and historical engineering data of the target power grid are obtained; the current data digest corresponding to the current engineering data is determined; the power engineering digital auditing system is used to analyze the current data digest to obtain auditing opinion information; based on the auditing opinion information, a second target object is determined from multiple first target objects of the target power grid; based on the current engineering data, the historical engineering data, the auditing opinion information, and the object information of the obtained second target object, an artificial intelligence model is used to generate early warning prompt information and at least one candidate adjustment plan; based on the early warning prompt information and the at least one candidate adjustment plan, engineering risk early warning is carried out, wherein the early warning result is used to adjust the construction plan of the current project, so that relevant auditing can be automatically completed and corresponding engineering risk early warning results can be given, so as to accurately warn of the risks existing in the power project and improve the reliability of the project construction plan. Description of the Drawings

[0052] Figure 1 is a schematic flowchart of an early warning method based on power engineering digital auditing and AI provided by an embodiment of the present application;

[0053] Figure 2 is a schematic structural diagram of an early warning system based on power engineering digital auditing and AI provided by an embodiment of the present application;

[0054] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present application. Detailed Embodiments

[0055] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0056] In the description of this application, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of this application, unless otherwise specified, "a plurality of" means two or more. In the description of this application, the term "comprising" and its variants are open-ended, that is, "including but not limited to". The term "based on" means "at least partially based on". The term "according to" means "at least partially according to". The term "an embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments".

[0057] In the description of this application, it should be noted that, unless otherwise clearly specified and defined, the terms "installed", "connected", and "coupled" shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0058] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this application have the same meanings as those commonly understood by those skilled in the technical field to which this application belongs. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0059] In a first aspect, referring to Figure 1 , a schematic flowchart of a warning method based on digital auditing of power engineering and AI (Artificial Intelligence) provided by an embodiment of this application is shown. This method includes steps S101 - S106, which are specifically as follows:

[0060] S101, obtain the current engineering data and historical engineering data of the target power grid, where the current engineering data is obtained by performing text recognition and semantic understanding on the materials of the current project of the target power grid.

[0061] In one example, the above-mentioned current project data may include at least one of the following: project establishment data, design data, construction data, supervision data, settlement data, etc. of the current project of the target power grid. Correspondingly, the materials of the above-mentioned current project may include at least one of the following: project establishment materials, design materials, construction materials, supervision materials, settlement materials, etc. of the current project of the target power grid. Among them, these materials can be stored in the form of text and / or images. The above-mentioned text recognition may include text recognition for images and / or text recognition for text (such as text keyword recognition).

[0062] In one example, the above-mentioned historical project data may include at least one of the following: project establishment data, design data, construction data, supervision data, settlement data, etc. of the historical project of the target power grid.

[0063] S102. Determine the current data summary corresponding to the current project data. This current data summary can eliminate non-critical information in the current project data, so as to facilitate more efficient and accurate audit analysis by the subsequent power engineering digital audit system.

[0064] In one example, the above-mentioned current data summary may be a kind of information used to describe the key features of the current project data. At this time, the current data summary can be obtained by adopting a general feature extraction method for the current project data for feature extraction.

[0065] In one example, the method described in this application may be executed by a power engineering plan generation system. Since the power engineering digital audit system is usually independently deployed from the power engineering plan generation system, it is necessary to ensure the data communication security between the two systems. Thus, the determination of the current data summary corresponding to the current project data may include: determining the current data summary according to the current project data by using a message digest algorithm to ensure the data integrity and non-tampering of the data corresponding to the current data summary, so as to facilitate ensuring that the power engineering digital audit system can receive a secure and reliable current data summary.

[0066] S103. Use the power engineering digital audit system to analyze the current data summary to obtain audit opinion information.

[0067] In one example, an automatic auditing software can be pre-configured in the above-mentioned digital auditing system for power engineering, so that the digital auditing system for power engineering can be configured to automatically audit and analyze the current data summary according to the set auditing rules, in order to issue corresponding auditing opinion information and feedback it to the above-mentioned power engineering plan generation system. Among them, the automatic auditing software can be a relevant software program pre-written by engineering personnel according to the auditing rules in the field of power engineering. Among them, the auditing rules can be used to audit at least one of the project establishment data, design data, construction data, supervision data, and settlement data.

[0068] The project establishment data can include project feasibility study reports, project proposals, etc., and the project establishment data can be used to evaluate the necessity and feasibility of the project.

[0069] The design data can include the design scheme, drawings, etc. of the power engineering, and the design data can be used to ensure that the design meets the specification requirements (such as the safety requirements of the project) and technical standards.

[0070] The construction data can include various records and reports during the construction process, such as construction logs, quality inspection records, etc., and the construction data can be used to indicate the construction quality and progress.

[0071] The settlement data can include the financial settlement information related to the project.

[0072] In one example, the above-mentioned automatic auditing software can also be obtained by fine-tuning a general large language model using the knowledge collected in the field of power engineering auditing, and this fine-tuning process is a general way of fine-tuning a large language model in this field.

[0073] S104, based on the auditing opinion information, determine a second target object from multiple first target objects of the target power grid; among them, the above-mentioned first target objects can include various types of power generation equipment to be adjusted.

[0074] In one example, the above audit opinion information can be used to indicate the first target object (i.e., the second target object) that needs to be focused on among the multiple first target objects confirmed by the audit in the relevant adjustment plan for the current project corresponding to the current project data. For example, in the constructed project, if it is found through audit that there are problems in the installation of high-voltage equipment (such as transformers, circuit breakers, etc.), then this high-voltage equipment needs to be used as the second target object for key adjustment and attention, and / or, if it is found through audit that there are cable specifications that do not meet the design requirements and / or potential safety hazards in the cable laying in the cable and wiring system (such as cable selection, laying path, and joint treatment), then this cable and wiring system is used as the second target object, and / or, if it is found through audit that there are problems such as excessive grounding resistance value or improper installation of lightning protection devices in the grounding and lightning protection system, then this grounding and lightning protection system is used as the second target object.

[0075] S105. Based on the current project data, the historical project data, the audit opinion information, and the object information of the obtained second target object, use an artificial intelligence model to generate a warning prompt information and at least one candidate adjustment plan.

[0076] In one example, the above artificial intelligence model can be pre-trained through sample data and labels, so that the trained artificial intelligence model can use the current project data, historical project data, audit opinion information, and object information as inputs, and in response to this input, output a warning prompt information and at least one candidate adjustment plan.

[0077] Among them, the sample data can include sample current project data, sample historical project data, sample audit opinion information, and sample object information, and the labels include sample warning prompt information and sample adjustment plans. The specific training process can include: inputting the sample data into the artificial intelligence model to be trained to obtain the output of the artificial intelligence model; based on the difference between the output of the artificial intelligence model and the above labels, use the minimization of the loss function to optimize the model parameters of the artificial intelligence model to be trained, thereby completing the model training.

[0078] S106. Based on the warning prompt information and the at least one candidate adjustment plan, conduct project risk warning, where the warning result is used to adjust the construction plan of the current project.

[0079] In one example, the warning result here can be used to characterize whether the construction safety of the current project can be ensured when applying each candidate adjustment plan (such as the construction safety related to the above high-voltage equipment, cable and wiring system, and grounding and lightning protection system), so as to facilitate the adjustment of the unsafe parts in the construction plan.

[0080] In one example, performing engineering risk warning based on the warning prompt information and the at least one candidate adjustment plan may include: selecting, from the at least one candidate adjustment plan, a candidate adjustment plan that matches the warning prompt information, and performing engineering risk warning according to the selected candidate adjustment plan, wherein the warning result is used to adjust the construction plan of the current project. Among them, the candidate adjustment plan that matches the warning prompt information may refer to the candidate adjustment plan with the highest similarity to the warning prompt information.

[0081] In an alternative embodiment, the performing engineering risk warning based on the warning prompt information and the at least one candidate adjustment plan includes:

[0082] Performing simulation on each of the at least one candidate adjustment plan according to the warning prompt information to obtain the simulation results of the at least one candidate adjustment plan respectively.

[0083] Determining an adjustment plan based on the simulation results, the warning prompt information, and the at least one candidate adjustment plan.

[0084] Performing engineering risk warning according to the adjustment plan.

[0085] In one example, performing simulation on each of the at least one candidate adjustment plan according to the warning prompt information to obtain the simulation results of the at least one candidate adjustment plan respectively may include: making relevant settings for the simulation model according to the warning prompt information, and using the set simulation model to perform simulation on each candidate adjustment plan respectively to obtain the corresponding simulation results. Exemplarily, the above simulation model may include general engineering construction simulation software.

[0086] In an alternative embodiment, the historical engineering data includes multiple historical sub - data, and the performing simulation on each of the at least one candidate adjustment plan according to the warning prompt information to obtain the simulation results of the at least one candidate adjustment plan respectively includes:

[0087] For each candidate adjustment plan,

[0088] Determining at least one historical sub - data that matches the candidate adjustment plan from the multiple historical sub - data.

[0089] Determining at least one simulation model corresponding to the candidate adjustment plan based on the at least one historical sub - data.

[0090] According to the warning prompt information, calling the at least one simulation model to perform simulation on the candidate adjustment plan respectively to obtain the simulation data corresponding to the at least one simulation model respectively.

[0091] Determine the simulation result of the candidate adjustment plan according to the simulation data.

[0092] In one example, each of the at least one simulation model corresponds one-to-one to at least one configuration parameter, and each of the at least one configuration parameter corresponds one-to-one to at least one historical sub-data, where each configuration parameter is determined by the corresponding historical sub-data and is used to configure the corresponding simulation model. In addition, relevant settings can be made for the at least one simulation model according to the warning prompt information, and the set simulation model can be used to simulate the candidate adjustment plan to obtain the corresponding simulation data. In this way, the simulation model used for simulation can be configured with parameters corresponding to the warning prompt information and historical sub-data to complete the simulation as accurately as possible.

[0093] In one example, the multiple historical sub-data included in the historical engineering data can be obtained by dividing the historical engineering data according to time and / or engineering projects. In this way, each historical sub-data can represent the engineering data of the target power grid in a certain short period of time in the past and / or a certain engineering project. At this time, the historical sub-data selected to match the candidate adjustment plan represents the situation that can be adapted to the candidate adjustment plan in some characteristics.

[0094] In an alternative embodiment, determining the adjustment plan based on the simulation result, the warning prompt information, and the at least one candidate adjustment plan includes:

[0095] For each candidate adjustment plan, perform a difference analysis on its simulation result and the warning prompt information to obtain a difference analysis result, and verify the candidate adjustment plan according to the difference analysis result.

[0096] Determine the adjustment plan based on the at least one candidate adjustment plan and their respective verification results.

[0097] In one example, the above difference analysis result can be used to represent the similarity between the standardized warning risk points at each stage indicated by the calculated warning prompt information (for example, the risk point can be represented in the form of a portrait) and the simulation result. Among them, the higher the similarity, the lower the value corresponding to the difference analysis result. In this way, the candidate adjustment plan that has passed the verification represents that the standardized warning risk points at each stage meet the requirements.

[0098] In one example, verifying the candidate adjustment plan according to the difference analysis result may include: determining the candidate adjustment plans whose difference analysis results meet the difference conditions as the candidate adjustment plans that pass the verification. Among them, the difference conditions may include that the value corresponding to the difference analysis result is higher than the difference threshold, or, if the difference analysis result is a numerical value representing the deviation degree, a maximum allowable difference score may be specified, and the candidate adjustment plans with a difference score lower than this score are considered to pass the verification.

[0099] In one example, determining the adjustment plan based on the at least one candidate adjustment plan and their respective verification results may include: performing a safety assessment process for construction safety (such as construction safety related to the above-mentioned high-voltage equipment, cable and wiring systems, grounding and lightning protection systems) on each of the candidate adjustment plans that pass the verification among the at least one candidate adjustment plan to obtain the safety assessment values of each of the candidate adjustment plans that pass the verification, and determining the candidate adjustment plan with the highest safety assessment value as the adjustment plan.

[0100] In an alternative implementation manner, the generating of the early warning prompt information and at least one candidate adjustment plan by using the artificial intelligence model based on the current project data, the historical project data, the audit opinion information, and the obtained object information of the second target object includes:

[0101] Generating key information based on the audit opinion information and the object information.

[0102] Determining a target key scenario from a plurality of preset key scenarios based on the key information and the historical project data.

[0103] Generating the early warning prompt information and the at least one candidate adjustment plan by using the artificial intelligence model based on the target key scenario, the current project data, and the historical project data.

[0104] In one example, the key scenario may be a preset typical scenario related to power engineering audit. For example, "high-voltage equipment construction scenario", "cable and wiring system construction scenario", "grounding and lightning protection system construction scenario", etc.

[0105] The high-voltage equipment construction scenario may include at least one of the following: high-voltage equipment compliance inspection scenario (checking whether the high-voltage equipment is correctly installed according to technical specifications and standards), high-voltage equipment safety assessment scenario (checking whether the safety and stability of equipment operation are evaluated through strict test and commissioning records).

[0106] The scenarios for the construction of cable and wiring systems may include at least one of the following: specification inspection scenario (used to check whether the cable selection conforms to the design requirements and ensure that its current-carrying capacity and insulation performance meet the actual usage needs), safety hazard investigation scenario (by reviewing the laying path diagram and checking the joint treatment methods to identify potential electrical fire risks or other safety hazards), and quality assessment scenario (performing insulation resistance test simulation to ensure that the cable maintains good insulation before and after installation and improve the safety and reliability of the entire system).

[0107] The scenarios for the construction of grounding and lightning protection systems may include at least one of the following: grounding effect assessment scenario (simulating according to the grounding resistance value to verify the effect of the grounding system), and lightning protection efficacy inspection scenario (checking the installation location, quantity and protection range of lightning protection devices to ensure that buildings and electrical equipment are protected from lightning strikes).

[0108] In this embodiment, the key scenarios can be used to assist the artificial intelligence model in generating warning prompt information and candidate adjustment plans. By determining the target key scenario, the model can focus on the specific situation corresponding to the current project, combine the current project data and historical project data, and more accurately analyze and generate warning prompt information and candidate adjustment plans that conform to the actual situation.

[0109] In one example, the above key information can be obtained by fusing audit opinion information and object information.

[0110] In one example, determining the target key scenario from a preset plurality of key scenarios based on the key information and the historical project data may include: calculating the first similarity between the key information and the information corresponding to each of the plurality of key scenarios, and calculating the second similarity between the historical project data and the information corresponding to each of the plurality of key scenarios, calculating the third similarity by weighted calculation of the first similarity and the second similarity, and determining the key scenario with the highest third similarity as the target key scenario. Among them, the information types represented by the key information and the historical project data are different. Therefore, when calculating the similarity between the information corresponding to the key scenario, the information similarity calculation can be performed respectively for different information types.

[0111] In one example, the above artificial intelligence model can be pre-trained via sample data and labels, so that the trained artificial intelligence model can take the target key scenario, the current project data and the historical project data as inputs and output warning prompt information and at least one candidate adjustment plan in response to the input.

[0112] Among them, the sample data in this embodiment may include the current project data of the sample, the historical project data of the sample, and the key scenarios of the sample. The labels include the sample warning prompt information and the sample adjustment plan. The specific training process may include: inputting the sample data into the artificial intelligence model to be trained to obtain the output of the artificial intelligence model. Based on the difference between the output of the artificial intelligence model and the above labels, the model parameters of the artificial intelligence model to be trained are optimized by minimizing the loss function, thereby completing the model training.

[0113] In an alternative embodiment, determining the target key scenario from a plurality of preset key scenarios based on the key information and the historical project data includes:

[0114] Determining at least one candidate key scenario that matches the key information from the plurality of key scenarios.

[0115] Determining the evaluation value of each of the at least one candidate key scenario.

[0116] Based on the historical project data and the evaluation value of each of the at least one candidate key scenario, determining the target key scenario from the at least one candidate key scenario.

[0117] In an example, the evaluation value in this embodiment may include at least one of the following: safety evaluation value, benefit evaluation value, etc. The evaluation value can be obtained by evaluating each of the at least one candidate key scenario using a corresponding evaluation model. Among them, the evaluation value can also be obtained by weighted calculation of the safety evaluation value and the benefit evaluation value.

[0118] In an example, based on the historical project data and the evaluation value of each of the at least one candidate key scenario, determining the target key scenario from the at least one candidate key scenario may include: determining each candidate key scenario with an evaluation value higher than the evaluation value threshold from the at least one candidate key scenario, and inputting each candidate key scenario with an evaluation value higher than the evaluation value threshold and the historical project data into a large language model, so that the large language model analyzes the input candidate key scenarios under the prompt of the historical project data, and selects the target key scenario from the input candidate key scenarios according to the analysis result. Among them, the analysis result can be used to indicate safety and / or benefit, etc.

[0119] In an alternative embodiment, the artificial intelligence model includes a large model. Based on the target key scenario, the current project data, and the historical project data, generating the warning prompt information and the at least one candidate adjustment plan using the artificial intelligence model includes:

[0120] Input the target key scenario, the current project data, and the historical project data into the large model, so that the large model analyzes the current project data and the historical project data under the prompt of the target key scenario to generate the warning prompt information and the at least one candidate adjustment plan.

[0121] In one example, the above large model may include a general large language model, and the target key scenario may be converted into semantic information to be used as a prompt word that can be understood by the large model. This prompt word can be used to prompt the large model to analyze the current project data and the historical project data, and make the analysis results include warning prompt information and at least one candidate adjustment plan.

[0122] In an alternative implementation, using the power engineering digital audit system to analyze the current data summary to obtain audit opinion information includes:

[0123] Input the current data summary into the power engineering digital audit system.

[0124] The power engineering digital audit system expands at least part of the information of the current data summary.

[0125] The power engineering digital audit system queries according to the expanded information to obtain the audit opinion information.

[0126] In an alternative implementation, the power engineering digital audit system is configured to:

[0127] Use a preset audit key node analysis strategy to extract information from the current data summary to obtain an original information sequence.

[0128] Obtain audit prompt information.

[0129] Expand the original information sequence based on the audit prompt information to obtain the expanded information.

[0130] In one example, expanding the original information sequence based on the audit prompt information to obtain the expanded information may include: performing content recognition on the original information sequence to generate content text; performing error analysis on the generated content text according to the standard audit text indicated by the audit prompt information; correcting the original information sequence based on the error analysis result; and expanding the corrected original information sequence to obtain the expanded information.

[0131] In one example, the specific generation process of the audit opinion information may include the following aspects.

[0132] Information extraction: Using a preset auditing key node analysis strategy, information is extracted from the current data summary to obtain an original information sequence. Here, the auditing key node analysis strategy can be preset based on professional knowledge and experience in the field of power engineering. For example, it focuses on the key nodes in the current data summary related to the above-mentioned high-voltage equipment, cable and wiring systems, and grounding and lightning protection systems.

[0133] Information expansion: Obtain auditing prompt information, and expand the original information sequence based on the auditing prompt information. Specifically, it includes content recognition of the original information sequence to generate content text; error analysis of the generated content text according to the standard auditing text indicated by the auditing prompt information; based on the error analysis results, correcting the original information sequence; and expanding the corrected original information sequence to obtain the expanded information. The auditing prompt information can be used to indicate equipment operation safety standards, technical specifications, etc. in the field of power engineering.

[0134] In a second aspect, correspondingly, an embodiment of the present application further provides an early warning system based on power engineering digital auditing and AI, which can implement all processes of the early warning method based on power engineering digital auditing and AI provided in the above embodiment.

[0135] See Figure 2 , which shows a schematic structural diagram of the early warning system based on power engineering digital auditing and AI provided by an embodiment of the present application. The early warning system based on power engineering digital auditing and AI includes:

[0136] A data acquisition module 201, configured to acquire current project data and historical project data of a target power grid, where the current project data is obtained by text recognition and semantic understanding of the materials of the current project of the target power grid.

[0137] A data summary determination module 202, configured to determine a current data summary corresponding to the current project data.

[0138] An auditing module 203, configured to use a power engineering digital auditing system to analyze the current data summary to obtain auditing opinion information.

[0139] A second target object determination module 204, configured to determine a second target object from multiple first target objects of the target power grid based on the auditing opinion information.

[0140] An intelligent analysis module 205, configured to generate early warning prompt information and at least one candidate adjustment plan by using an artificial intelligence model based on the current project data, the historical project data, the auditing opinion information, and the object information of the obtained second target object.

[0141] The early warning module 206 is configured to perform engineering risk early warning based on the early warning prompt information and the at least one candidate adjustment plan, wherein the early warning result is used to adjust the construction plan of the current project.

[0142] In an alternative embodiment, the performing engineering risk early warning based on the early warning prompt information and the at least one candidate adjustment plan includes:

[0143] Performing simulation for each of the at least one candidate adjustment plan according to the early warning prompt information to obtain the simulation results of the at least one candidate adjustment plan respectively.

[0144] Determining an adjustment plan based on the simulation results, the early warning prompt information and the at least one candidate adjustment plan.

[0145] Performing engineering risk early warning according to the adjustment plan.

[0146] In an alternative embodiment, the historical engineering data includes a plurality of historical sub-data. The performing simulation for each of the at least one candidate adjustment plan according to the early warning prompt information to obtain the simulation results of the at least one candidate adjustment plan respectively includes:

[0147] For each candidate adjustment plan,

[0148] Determining at least one historical sub-data that matches the candidate adjustment plan from the plurality of historical sub-data.

[0149] Determining at least one simulation model corresponding to the candidate adjustment plan based on the at least one historical sub-data.

[0150] Invoking the at least one simulation model to perform simulation for the candidate adjustment plan respectively according to the early warning prompt information to obtain the simulation data corresponding to the at least one simulation model respectively.

[0151] Determining the simulation result of the candidate adjustment plan according to the simulation data.

[0152] In an alternative embodiment, the determining an adjustment plan based on the simulation results, the early warning prompt information and the at least one candidate adjustment plan includes:

[0153] For each candidate adjustment plan, performing a difference analysis on its simulation result and the early warning prompt information to obtain a difference analysis result, and verifying the candidate adjustment plan according to the difference analysis result.

[0154] Determining an adjustment plan based on the at least one candidate adjustment plan and their respective verification results.

[0155] In an alternative embodiment, generating a warning prompt message and at least one candidate adjustment plan by using an artificial intelligence model based on the current engineering data, the historical engineering data, the audit opinion information, and the obtained object information of the second target object includes:

[0156] Generating key information based on the audit opinion information and the object information.

[0157] Determining a target key scenario from a plurality of preset key scenarios based on the key information and the historical engineering data.

[0158] Generating the warning prompt message and the at least one candidate adjustment plan by using the artificial intelligence model based on the target key scenario, the current engineering data, and the historical engineering data.

[0159] In an alternative embodiment, determining a target key scenario from a plurality of preset key scenarios based on the key information and the historical engineering data includes:

[0160] Determining at least one candidate key scenario that matches the key information from the plurality of key scenarios.

[0161] Determining the evaluation value of each of the at least one candidate key scenario.

[0162] Determining a target key scenario from the at least one candidate key scenario based on the historical engineering data and the evaluation value of each of the at least one candidate key scenario.

[0163] In an alternative embodiment, the artificial intelligence model includes a large model. Generating the warning prompt message and the at least one candidate adjustment plan by using the artificial intelligence model based on the target key scenario, the current engineering data, and the historical engineering data includes:

[0164] Inputting the target key scenario, the current engineering data, and the historical engineering data into the large model, so that the large model analyzes the current engineering data and the historical engineering data under the prompt of the target key scenario to generate the warning prompt message and the at least one candidate adjustment plan.

[0165] In an example, the above artificial intelligence model includes a large model. For example, the large model adopts a common deep neural network structure, such as a multi-layer perceptron. Taking a simple multi-layer perceptron as an example, its specific structure may include an input layer, several hidden layers, and an output layer.

[0166] Input layer: The number of nodes is determined according to the dimension of the input data. The input data includes the target key scenario, current project data, and historical project data. Assuming that the combined feature dimension of these data is n, the number of nodes in the input layer is n.

[0167] Hidden layer: Two to three hidden layers can be set, and the number of nodes in each hidden layer can be adjusted according to experience and experiments. For example, they can be set to 128 and 64 respectively. The role of the hidden layer is to extract features and perform non-linear transformation on the input data.

[0168] Output layer: Output warning prompt information and at least one candidate adjustment plan. Assuming that the warning prompt information is represented by m_1 values, the candidate adjustment plan is represented by m_2 values, and k candidate adjustment plans are generated, then the number of nodes in the output layer is m_1 + k × m_2.

[0169] Correspondingly, the training algorithm of this multi-layer perceptron can be divided into an optimizer part and a loss function part.

[0170] Optimizer: Use the stochastic gradient descent optimizer. Stochastic gradient descent is a commonly used optimization algorithm. It randomly selects a part of the samples to calculate the gradient in each iteration and updates the model parameters according to the gradient, thereby gradually reducing the value of the loss function. Its update formula is , where are the parameters of the model, is the learning rate, is the gradient of the loss function with respect to the parameter .

[0171] Loss function: Use the mean squared error loss function. For a sample , its true label is , and the model prediction value is , then the calculation formula of the mean squared error loss function is , where is the number of samples. By minimizing the mean squared error loss function, the prediction value of the model can be made as close as possible to the true label.

[0172] In an optional implementation manner, using the power engineering digital audit system to analyze the current data summary to obtain audit opinion information includes:

[0173] Input the current data summary into the power engineering digital audit system.

[0174] The power engineering digital audit system expands at least part of the information of the current data summary.

[0175] The power engineering digital audit system queries according to the expanded information to obtain the audit opinion information.

[0176] In an alternative embodiment, the power engineering digital audit system is configured to:

[0177] Use a preset audit key node analysis strategy to extract information from the current data summary to obtain an original information sequence.

[0178] Obtain audit prompt information.

[0179] Expand the original information sequence based on the audit prompt information to obtain the expanded information.

[0180] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the early warning method based on power engineering digital audit and AI described in any one of the above are implemented.

[0181] In a fourth aspect, an embodiment of the present application provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, the steps of the early warning method based on power engineering digital audit and AI described in any one of the above are implemented.

[0182] In a fifth aspect, an embodiment of the present application provides a computer device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the steps of the early warning method based on power engineering digital audit and AI described in any one of the above are implemented.

[0183] See Figure 3 , the computer device of this embodiment includes: a processor 301, a memory 302, and a computer program stored in the memory 302 and executable on the processor 301, such as an early warning program based on power engineering digital audit and AI. When the processor 301 executes the computer program, the steps in the above various embodiments of the early warning method based on power engineering digital audit and AI are implemented, such as Figure 1 the steps S101 - S106 shown.

[0184] Exemplarily, the computer program can be divided into one or more modules / units. The one or more modules / units are stored in the memory 302 and executed by the processor 301 to complete the present application. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and this instruction segment is used to describe the execution process of the computer program in the computer device.

[0185] The computer device may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art can understand that the schematic diagram is only an example of the computer device, and does not constitute a limitation on the computer device. It may include more or fewer components than shown, or combine some components, or different components. For example, the computer device may also include input / output devices, network access devices, buses, etc.

[0186] The processor 301 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor 301 may also be any conventional processor, etc. The processor 301 is the control center of the computer device, and connects various parts of the entire computer device through various interfaces and lines.

[0187] The memory 302 can be used to store the computer program and / or module. The processor 301 realizes various functions of the computer device by running or executing the computer program and / or module stored in the memory 302, and by calling the data stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0188] Among them, if the modules / units integrated in the computer device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above method embodiments of this application, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor 301, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0189] In summary, the embodiments of this application at least have the following beneficial effects:

[0190] By adopting the embodiments of this application, by obtaining the current engineering data and historical engineering data of the target power grid; determining the current data digest corresponding to the current engineering data; using the power engineering digital audit system to analyze the current data digest to obtain audit opinion information; based on the audit opinion information, determining a second target object from multiple first target objects of the target power grid; based on the current engineering data, the historical engineering data, the audit opinion information, and the object information of the obtained second target object, using an artificial intelligence model to generate a warning prompt information and at least one candidate adjustment plan; based on the warning prompt information and the at least one candidate adjustment plan, performing engineering risk warning, where the warning result is used to adjust the construction plan of the current project, so as to be able to automatically complete relevant audits and give corresponding engineering risk warning results, to accurately warn of the risks existing in the power project, and improve the reliability of the engineering construction plan.

[0191] Through the description of the above embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus a necessary hardware platform. Of course, it can also be implemented entirely by hardware. Based on this understanding, all or part of the technical solution of this application that contributes to the background technology can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM (Read-Only Memory), RAM (Random Access Memory), magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0192] The above is the preferred embodiment of this application. It should be noted that for those of ordinary skill in the art, without departing from the principle of this application, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of this application.

Claims

1. An early warning method based on digital auditing and AI in power engineering, characterized in that, Including: Obtain the current engineering data and historical engineering data of the target power grid, where the current engineering data is obtained by performing text recognition and semantic understanding on the materials of the current project of the target power grid; Determine the current data summary corresponding to the current engineering data; Use the digital auditing system for power engineering to analyze the current data summary to obtain audit opinion information, including: inputting the current data summary into the digital auditing system for power engineering; expanding at least part of the information of the current data summary by the digital auditing system for power engineering; querying according to the expanded information by the digital auditing system for power engineering to obtain the audit opinion information; Based on the audit opinion information, determine the second target objects from multiple first target objects of the target power grid, where the second target objects include: high-voltage equipment, cable and wiring systems, grounding and lightning protection systems; Based on the current engineering data, the historical engineering data, the audit opinion information and the object information of the obtained second target objects, use an artificial intelligence model to generate early warning prompt information and at least one candidate adjustment plan; Based on the early warning prompt information and the at least one candidate adjustment plan, conduct engineering risk early warning, where the early warning result is used to adjust the construction plan of the current project; Wherein, the digital auditing system for power engineering is configured to: Use a preset audit key node analysis strategy to extract information from the current data summary to obtain an original information sequence, where the audit key node analysis strategy is suitable for indicating key nodes related to high-voltage equipment, cable and wiring systems, grounding and lightning protection systems in the current data summary; Obtain audit prompt information, where the audit prompt information is used to indicate the equipment operation safety standards and technical specifications in the field of power engineering; Perform content recognition on the original information sequence to generate content text; perform error analysis on the generated content text according to the standard audit text indicated by the audit prompt information; based on the error analysis result, correct the original information sequence; expand the corrected original information sequence to obtain the expanded information.

2. The method according to claim 1, wherein The performing engineering risk early warning based on the early warning prompt information and the at least one candidate adjustment plan includes: According to the early warning prompt information, perform simulation on each of the at least one candidate adjustment plan to obtain the simulation results of each of the at least one candidate adjustment plan; Based on the simulation results, the early warning prompt information and the at least one candidate adjustment plan, determine the adjustment plan; Conduct engineering risk early warning according to the adjustment plan.

3. The method according to claim 2, wherein The historical engineering data includes multiple historical sub-data, and the performing simulation on each of the at least one candidate adjustment plan according to the early warning prompt information to obtain the simulation results of each of the at least one candidate adjustment plan includes: For each candidate adjustment plan, Determine at least one historical sub-data that matches the candidate adjustment plan from the multiple historical sub-data; Based on the at least one piece of historical sub-data, determine at least one simulation model corresponding to the candidate adjustment plan; According to the warning prompt information, call the at least one simulation model to respectively perform simulation on the candidate adjustment plan, and obtain the simulation data corresponding to each of the at least one simulation model; Determine the simulation result of the candidate adjustment plan according to the simulation data.

4. The method according to claim 2, wherein The determining the adjustment plan based on the simulation result, the warning prompt information, and the at least one candidate adjustment plan includes: For each of the candidate adjustment plans, perform a difference analysis on its simulation result and the warning prompt information to obtain a difference analysis result, and verify the candidate adjustment plan according to the difference analysis result, where the difference analysis result is used to characterize the similarity between the normative warning risk points at each stage indicated by the warning prompt information and the simulation result; Based on the at least one candidate adjustment plan and their respective verification results, determine the adjustment plan, including: performing a safety assessment process for construction safety on each of the candidate adjustment plans that pass the verification among the at least one candidate adjustment plan to obtain the safety assessment values of the candidate adjustment plans that pass the verification, and determining the candidate adjustment plan with the highest safety assessment value as the adjustment plan, where the construction safety is related to the high-voltage equipment, the cable and wiring system, and the grounding and lightning protection system.

5. The method according to claim 1, wherein The generating the warning prompt information and at least one candidate adjustment plan by using the artificial intelligence model based on the current project data, the historical project data, the audit opinion information, and the obtained object information of the second target object includes: Generate key information based on the audit opinion information and the object information; Based on the key information and the historical project data, determine a target key scenario from a preset plurality of key scenarios, where the plurality of key scenarios include a high-voltage equipment construction scenario, a cable and wiring system construction scenario, and a grounding and lightning protection system construction scenario; Based on the target key scenario, the current project data, and the historical project data, use the artificial intelligence model to generate the warning prompt information and the at least one candidate adjustment plan.

6. The method according to claim 5, wherein The determining the target key scenario from a preset plurality of key scenarios based on the key information and the historical project data includes: Determine at least one candidate key scenario that matches the key information from the plurality of key scenarios; Determine the evaluation value of each of the at least one candidate key scenario; Based on the historical project data and the evaluation values of each of the at least one candidate key scenario, determine the target key scenario from the at least one candidate key scenario.

7. The method according to claim 5, characterized in that, The artificial intelligence model includes a large model, and the generating the warning prompt information and the at least one candidate adjustment plan by using the artificial intelligence model based on the target key scenario, the current project data, and the historical project data includes: Input the target key scenario, the current project data, and the historical project data into the large model, so that the large model analyzes the current project data and the historical project data under the prompt of the target key scenario to generate the warning prompt information and the at least one candidate adjustment plan.

8. An early warning system based on digital auditing and AI in power engineering, characterized in that, Including: A data acquisition module, configured to acquire the current project data and the historical project data of a target power grid, wherein the current project data is obtained by performing text recognition and semantic understanding on the materials of the current project of the target power grid; A data summary determination module, configured to determine the current data summary corresponding to the current project data; An audit module, configured to use a power engineering digital audit system to analyze the current data summary to obtain audit opinion information, including: inputting the current data summary into the power engineering digital audit system; expanding at least part of the information of the current data summary by the power engineering digital audit system; querying according to the expanded information by the power engineering digital audit system to obtain the audit opinion information; A second target object determination module, configured to determine a second target object from multiple first target objects of the target power grid based on the audit opinion information, wherein the second target object includes: high-voltage equipment, cable and wiring systems, grounding and lightning protection systems; An intelligent analysis module, configured to generate warning prompt information and at least one candidate adjustment plan by using an artificial intelligence model based on the current project data, the historical project data, the audit opinion information, and the object information of the obtained second target object; A warning module, configured to perform project risk warning based on the warning prompt information and the at least one candidate adjustment plan, wherein the warning result is used to adjust the construction plan of the current project; Wherein, the power engineering digital audit system is configured to: Extract information from the current data summary by using a preset audit key node analysis strategy to obtain an original information sequence, wherein the audit key node analysis strategy is adapted to indicate attention to key nodes in the current data summary related to the high-voltage equipment, cable and wiring systems, grounding and lightning protection systems; Obtain audit prompt information, wherein the audit prompt information is used to indicate the equipment operation safety standards and technical specifications in the field of power engineering; Perform content recognition on the original information sequence to generate content text; perform error analysis on the generated content text according to the standard audit text indicated by the audit prompt information; correct the original information sequence based on the error analysis result; expand the corrected original information sequence to obtain the expanded information.

Images