Intelligent ticket forming method, system and device based on AIGC technology and medium

Abstract

The invention discloses an intelligent ticket forming method, system and device based on an AIGC technology, and a medium, and relates to the technical field of power systems and artificial intelligence. The method comprises the following steps: obtaining operation ticket text data of the power system, wherein the operation ticket text data comprises a scheduling instruction and a corresponding operation ticket text; preprocessing the obtained operation ticket text data to obtain operation ticket text training data; training an AIGC model by using the operation ticket text training data; and inputting the scheduling instruction to the AIGC model, and intelligently generating a corresponding operation ticket. According to the invention, the AIGC technology is utilized to realize the intelligent generation of the operation ticket, the dependence on artificial experience is reduced, and the ticket simulation efficiency and the intelligent level are improved.

Description

Technical Field

[0001] The present invention relates to the fields of power systems and artificial intelligence technology, and in particular to an intelligent ticketing method, system, device and medium based on AIGC technology. Background Art

[0002] At present, most of them adopt the standardized work ticket template and generate the operation ticket by manually filling in the relevant information. In dealing with huge operation data and complex business processes, the traditional manual invoicing method has problems such as low efficiency, large workload, and easy errors, which cannot meet the needs of fast, accurate and reliable ticketing. Manually writing operation tickets is very dependent on the professional and technical level and experience of the writers, and the handwriting method is prone to cause the operation tickets to be irregular and inaccurate. At the same time, there are problems such as slow filling speed and easy errors. In actual work, it often causes wrong tickets and invalid tickets, affecting work efficiency. In addition, the content of the operation ticket lacks relevance to the content of the transfer order, and it is easy to issue the ticket without following the transfer order. Manual invoicing can no longer meet the requirements of safe operation of smart grids. The power system urgently needs to use advanced information technologies such as artificial intelligence to realize the intelligent invoicing of operation tickets, reduce the burden on operation and maintenance personnel, standardize the operation process, prevent operation accidents caused by errors in operation tickets, and ensure the safety and stability of power system operation. Summary of the invention

[0003] In view of the problems existing in the prior art, the purpose of the present invention is to provide an intelligent ticketing method, system, equipment and medium based on AIGC technology, which utilizes AIGC technology to realize intelligent ticketing, improve work efficiency, reduce reliance on manual experience, prevent operational accidents caused by operation ticket errors, and ensure the safety and stability of power system operation.

[0004] In order to achieve the above technical objectives, the present invention adopts the following technical solutions to achieve them.

[0005] In a first aspect, a smart ticketing method based on AIGC technology is provided, comprising the following steps: Step S1, obtaining operation ticket text data of the power system, where the operation ticket text data includes a dispatch instruction and a corresponding operation ticket text; Step S2: pre-process the acquired operation ticket text data to obtain operation ticket text training data; Step S3: train the AIGC model using the operation ticket text training data; Step S4: Input the dispatch instruction into the AIGC model to intelligently generate the corresponding operation ticket.

[0006] Furthermore, in step S2, the preprocessing process includes removing duplicate and erroneous data and standardizing the text data format of the operation ticket to ensure data quality.

[0007] Furthermore, in step S3, the AIGC model is based on the pre-trained large language model, and the parameters of the pre-trained large language model are fine-tuned by integrating the operation ticket text training data using an efficient parameter fine-tuning method to complete the training and learning of the AIGC model.

[0008] Furthermore, the pre-trained large language model is an encoder-decoder structure, and the encoder is represented as:

[0009] In the formula, is the input training data; is the encoder weight, is the encoder bias term; is the activation function, is the generated hidden layer representation; The decoder is represented as:

[0010] In the formula, is the decoder weight, is the bias term; is the activation function, is the output of the decoder; The goal of pre-training large language models is to minimize the input and output By minimizing the loss function , complete the update of model parameters such as encoder and decoder weights and bias terms Furthermore, in step S4, after the AIGC model training is completed, the user uses the front-end interface to input scheduling instructions to interactively and intelligently generate operation tickets.

[0011] Furthermore, after step S3, the following steps are further included: The AIGC model is verified using the operation ticket text verification data set, and the operation ticket generated by the AIGC model is evaluated. According to the evaluation results, the AIGC model is saved or retrained to improve the accuracy and rationality of the generated operation ticket; the evaluation function is defined as:

[0012] Where: is an evaluation function, which is used to evaluate each operation in the generated operation ticket; The first operation ticket generated by the AIGC model according to the dispatch instruction i The characteristic value of the strip operation; Indicates the first operation ticket that is manually prepared and verified to be correct and corresponds to the dispatch instruction. i The characteristic value of the strip operation; The analysis factor representing the standard value data, Represents the analysis factor of the data to be evaluated.

[0013] In a second aspect, an intelligent ticketing system based on AIGC technology is provided, which is used to implement the intelligent ticketing method based on AIGC technology as described above, including: Data collection module: used to obtain the operation ticket text data of the power system, the operation ticket text data includes the dispatching instruction and the corresponding operation ticket text; Data preprocessing module: used to preprocess the acquired operation ticket text data to obtain operation ticket text training data; AIGC model training module: used to train the AIGC model using operation ticket text training data; User interface module: used to input scheduling instructions; Operation ticket generation module: used to input scheduling instructions into the AIGC model and intelligently generate corresponding operation tickets.

[0014] Furthermore, it also includes: Model performance evaluation and optimization module: used to evaluate the generated operation tickets. Based on the evaluation results, the model is further adjusted or retrained to improve the accuracy and rationality of the generated operation tickets.

[0015] In a third aspect, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the intelligent ticketing method based on the AIGC technology as described above is implemented.

[0016] In a fourth aspect, a computer-readable storage medium is provided, on which computer-executable instructions are stored, and the computer-executable instructions are used to implement the intelligent ticketing method based on AIGC technology as described above.

[0017] The present invention proposes an intelligent ticketing method, system, equipment and medium based on AIGC technology, which has the following beneficial effects: In view of the problems of low efficiency, large workload and easy errors in the existing manual ticketing method, the present invention proposes an intelligent ticketing solution based on AIGC technology, which can cope with the complex and changeable power grid forms and huge operation data, quickly, accurately and reliably generate operation tickets intelligently, reduce reliance on manual experience, improve the efficiency and intelligence level of ticket drafting, prevent operation accidents caused by operation ticket errors, and ensure the safety and stability of power system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 This is a flow chart of an intelligent ticketing method based on AIGC technology provided by an embodiment of the present invention; Figure 2 It is a diagram of the AIGC model training structure provided by an embodiment of the present invention; Figure 3 It is a structural diagram of an intelligent ticketing system based on AIGC technology provided by an embodiment of the present invention; Figure 4 This is a local wiring diagram of a 220 kV substation provided by an embodiment of the present invention; Figure 5 This is an example of a smart ticket issuance provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0021] Manual invoicing can no longer meet the requirements of safe operation of smart grids. The power system urgently needs to use advanced information technologies such as artificial intelligence to realize intelligent invoicing of operation tickets, reduce the burden on operation and maintenance personnel, standardize operation procedures, prevent operation accidents caused by operation ticket errors, and ensure the safety and stability of power system operation. At present, the application and development of artificial intelligence (AI) technology is profoundly changing human production and lifestyle. Among them, artificial intelligence generated content (AIGC) technology has developed rapidly in the past two years and has become a new technology of digitalization, networking and intelligence. The generative model represented by the large language model has powerful knowledge encoding, text understanding, generation and reasoning of complex tasks. AIGC technology trains AI models through a large number of data samples, and finally generates content with the help of the trained AI model, analyzes existing data and learns the patterns and laws therein, and then generates new data, new things or new solutions, which provides a new idea for solving the problems faced by manual invoicing. Based on this, the present invention proposes an intelligent invoicing solution based on AIGC technology. The technical solution of the present invention is described in detail below in conjunction with specific embodiments.

[0022] Example 1 This embodiment provides an intelligent ticketing method based on AIGC technology, such as Figure 1 As shown, the following steps are included: Step S1: Obtain the operation ticket text data of the power system, which includes the dispatching instructions and the corresponding operation ticket text. By collecting a large amount of operation ticket text data, a large amount of training data can be provided for subsequent model training. This step is the basic step for building an effective AI model.

[0023] It should be noted that the collected operation ticket text data includes a large number of various types of dispatch instructions and their corresponding operation ticket texts, especially a large amount of operation ticket text data under the currently applied power grid topology structure, so as to ensure the adaptability of the model obtained by subsequent training.

[0024] Step S2: pre-process the acquired operation ticket text data to obtain operation ticket text training data.

[0025] In this embodiment, the preprocessing process includes removing duplicate and erroneous data and standardizing the text data format of the operation ticket to ensure data quality.

[0026] Step S3: Use the operation ticket text training data to train the AIGC model.

[0027] like Figure 2As shown, in this embodiment, the AIGC model is based on a pre-trained large language model, and uses efficient parameter fine-tuning methods (such as prefix tuning, prompt tuning, etc.) to integrate the operation ticket text training data to fine-tune the parameters of the pre-trained large language model to complete the training and learning of the AIGC model.

[0028] The pre-trained large language model is an encoder-decoder structure, and the encoder is represented as:

[0029] In the formula, is the input training data; is the encoder weight, is the encoder bias term; is the activation function, is the generated hidden layer representation; The decoder is represented as:

[0030] In the formula, is the decoder weight, is the bias term; is the activation function, is the output of the decoder; The goal of pre-training large language models is to minimize the input and output By minimizing the loss function , complete the update of model parameters such as encoder and decoder weights and bias terms.

[0031] In some preferred embodiments, in order to improve the accuracy and rationality of the generated operation ticket, after step S3, it also includes: evaluating the generated operation ticket to improve the accuracy and rationality of the generated operation ticket.

[0032] The model performance evaluation and optimization process aims to optimize the model performance. After the operation ticket content is generated, the generated operation ticket needs to be evaluated to check its quality. During implementation, the operation ticket text data is divided into an operation ticket text training data set and an operation ticket text verification data set. The AIGC model is trained using the operation ticket text training data set, and then the trained AIGC model is verified using the operation ticket text verification data set. The operation ticket generated using the AIGC model is evaluated. Based on the evaluation results, the AIGC model is saved or retrained to improve the accuracy and rationality of the generated operation ticket. The evaluation function is defined as:

[0033] Where: is an evaluation function, which is used to evaluate each operation in the generated operation ticket; The first operation ticket generated by the AIGC model according to the dispatch instruction i The characteristic values ​​of the operations are used as the data to be evaluated; Indicates the first operation ticket that is manually prepared and verified to be correct and corresponds to the dispatch instruction. i The characteristic values ​​of the strip operations are used as standard data; represents the analysis factor of the standard data, It should be noted that the first i The first operation and the first operation ticket manually prepared and verified i The eigenvalues ​​of each operation are obtained by vectorizing the operation and taking the eigenvalue of the vector.

[0034] For example, the dispatching instruction 220 kV xx line 606 from operation to cold standby (II mother) is input into the AIGC model for testing, and the AIGC model generates the following operation tickets: 1. Open the 6063 disconnector; 2. Open the 606 circuit breaker; 3. Open the 6062 disconnector. For the dispatching instruction 220 kV xx line 606 from operation to cold standby (II mother), the corresponding manually drafted and verified operation ticket is as follows: 1. Open the 606 circuit breaker; 2. Open the 6063 disconnector; 3. Open the 6062 disconnector. When evaluating, each operation of the generated operation ticket is evaluated. First, the data to be evaluated "1. Open the 6063 disconnector" is evaluated and compared with the set standard value "1. Open the 606 circuit breaker". If they are consistent, the current step is recorded as correct. If they are inconsistent, the current step is recorded as incorrect, until all the data to be evaluated are evaluated. When the proportion of inaccurate records exceeds a threshold (such as 3% or 5%), the AIGC model is retrained to improve the accuracy and rationality of the generated operation tickets; otherwise, no retraining is required.

[0035] Step S4: The user inputs the dispatch instruction into the AIGC model through the front-end interface, and the corresponding operation ticket is intelligently generated.

[0036] Taking the switching operation as an example, the intelligent generation process of the operation ticket is explained as follows: the 220kV XX line 604 circuit breaker is switched from operation to cold standby (Ⅰ mother).

[0037] Figure 4The figure shows a local wiring diagram of a 220 kV substation in an embodiment of the present invention. The meanings of the numbers of the power equipment in the figure are: 1M (1 mother busbar), 2M (2 mother busbars), 6041 (6041 disconnector), 6042 (6042 disconnector), 6043 (6043 disconnector), 604 (604 circuit breaker), 6041-1 (6041-1 grounding disconnector), 6043-1 (6043-1 grounding disconnector), 6043-2 (6043-2 grounding disconnector).

[0038] The user inputs the dispatching instruction: 220kV XX line 604 circuit breaker switches from operation to cold standby (Ⅰ mother); then the AIGC model intelligently generates an operation ticket, such as Figure 5 shown.

[0039] This embodiment provides an intelligent ticket-making method based on AIGC technology, which can cope with complex and changeable power grid forms and huge operating data, quickly, accurately and reliably generate operation tickets intelligently, reduce reliance on manual experience, improve the efficiency and intelligence level of ticket drafting, prevent operational accidents caused by operation ticket errors, and ensure the safety and stability of power system operation.

[0040] Example 2

[0041] This embodiment provides an intelligent ticketing system based on AIGC technology, which is used to implement the intelligent ticketing method based on AIGC technology described in the above embodiment. Figure 3 As shown, including, Data collection module: used to obtain the operation ticket text data of the power system, the operation ticket text data includes the dispatching instruction and the corresponding operation ticket text; Data preprocessing module: used to preprocess the acquired operation ticket text data to obtain operation ticket text training data; AIGC model training module: used to train the AIGC model using operation ticket text training data; User interface module: used to input scheduling instructions; Operation ticket generation module: used to input scheduling instructions into the AIGC model and intelligently generate corresponding operation tickets.

[0042] In some preferred embodiments, it also includes: Model performance evaluation and optimization module: used to evaluate the generated operation tickets. Based on the evaluation results, the model is further adjusted or retrained to improve the accuracy and rationality of the generated operation tickets.

[0043] It should be understood that the functional unit modules in the embodiments of the present invention may be concentrated in one processing unit, or each unit module may exist physically separately, or two or more unit modules may be integrated in one unit module, and may be implemented in the form of hardware or software.

[0044] Example 3

[0045] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the intelligent ticketing method based on the AIGC technology described in the aforementioned embodiment is implemented.

[0046] Example 4

[0047] This embodiment provides a computer-readable storage medium on which computer-executable instructions are stored. The computer-executable instructions are used to implement the intelligent ticketing method based on AIGC technology described in the above embodiment.

[0048] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0049] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0050] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0051] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0052] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0053] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An intelligent ticketing method based on AIGC technology, characterized in that: The following steps are involved: Step S1, obtaining operation ticket text data of the power system, where the operation ticket text data includes a dispatch instruction and a corresponding operation ticket text; Step S2: pre-process the acquired operation ticket text data to obtain operation ticket text training data; Step S3: train the AIGC model using the operation ticket text training data; Step S4: Input the dispatch instruction into the AIGC model to intelligently generate the corresponding operation ticket.

2. The intelligent ticketing method based on AIGC technology according to claim 1 is characterized in that: In step S2, the preprocessing process includes removing duplicate and erroneous data and standardizing the text data format of the operation ticket.

3. The intelligent ticketing method based on AIGC technology according to claim 1 is characterized in that: In step S3, the AIGC model is based on the pre-trained large language model, and the parameters of the pre-trained large language model are fine-tuned by integrating the operation ticket text training data using an efficient parameter fine-tuning method to complete the training and learning of the AIGC model.

4. The intelligent ticketing method based on AIGC technology according to claim 3 is characterized in that: The pre-trained large language model is an encoder-decoder structure, and the encoder is represented as: ； In the formula, is the input training data; is the encoder weight, is the encoder bias term; is the activation function, is the generated hidden layer representation; The decoder is represented as: ； In the formula, is the decoder weight, is the bias term; is the activation function, is the output of the decoder; The goal of pre-training large language models is to minimize the input and output By minimizing the loss function , complete the parameter update of the encoder and decoder.

5. The intelligent ticketing method based on AIGC technology according to claim 1 is characterized in that: In step S4, after the AIGC model training is completed, the user uses the front-end interface to input the scheduling instructions to interactively and intelligently generate the operation ticket.

6. The intelligent ticketing method based on AIGC technology according to claim 1 is characterized in that: After step S3, the following steps are also included: The AIGC model is verified using the operation ticket text verification data set, and the operation ticket generated by the AIGC model is evaluated. According to the evaluation results, the AIGC model is saved or retrained to improve the accuracy and rationality of the generated operation ticket; the evaluation function is defined as: ； Where: is an evaluation function, which is used to evaluate each operation in the generated operation ticket; The first operation ticket generated by the AIGC model according to the dispatch instruction i The characteristic value of the strip operation; Indicates the first operation ticket that is manually prepared and verified to be correct and corresponds to the dispatch instruction. i The characteristic value of the strip operation; represents the analysis factor of the standard data, Represents the analysis factor of the data to be evaluated.

7. An intelligent ticketing system based on AIGC technology, characterized in that: The intelligent ticketing method based on AIGC technology for implementing any one of claims 1 to 6 comprises: Data collection module: used to obtain the operation ticket text data of the power system, the operation ticket text data includes the dispatching instruction and the corresponding operation ticket text; Data preprocessing module: used to preprocess the acquired operation ticket text data to obtain operation ticket text training data; AIGC model training module: used to train the AIGC model using operation ticket text training data; User interface module: used to input scheduling instructions; Operation ticket generation module: used to input scheduling instructions into the AIGC model and intelligently generate corresponding operation tickets.

8. The intelligent ticketing system based on AIGC technology according to claim 7 is characterized in that: Also includes: Model performance evaluation and optimization module: used to evaluate the generated operation tickets. Based on the evaluation results, the model is further adjusted or retrained to improve the accuracy and rationality of the generated operation tickets.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the intelligent ticketing method based on the AIGC technology as described in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: Computer executable instructions are stored thereon, and the computer executable instructions are used to implement the intelligent ticketing method based on AIGC technology as described in any one of claims 1 to 6.

Images