Intelligent generation method and device of two tickets, and computer readable storage medium

Abstract

The invention discloses an intelligent generation method and device of two tickets and a computer readable storage medium. The method comprises the following steps: responding to a two-ticket generation operation acting on a front-end page to generate a screen recording instruction and an information acquisition instruction; controlling a screen recording component to execute a screen recording operation according to the screen recording instruction to obtain screen video data; performing text extraction on the screen video data to obtain screen text information in the screen video data; acquiring the current operation state and work task information of the power system based on the information acquisition instruction; and processing the screen text information, the work task information and the current running state by using a two-ticket generation model to generate a work ticket and an operation ticket. According to the invention, the technical problems of tedious filling and approval processes of the two tickets and low handling efficiency caused by the fact that the operation ticket and the work ticket are generally generated by adopting manual handwriting or a single intelligent algorithm with relatively poor flexibility in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of two-ticket generation in an electric power system, and in particular to an intelligent two-ticket generation method and device, and a computer-readable storage medium. Background Art

[0002] The "two tickets" system of power grid enterprises includes the operation ticket and work ticket system, which is an important guarantee for power safety production. The accuracy and completeness of the content filled in are particularly important, and the time of issuing the ticket directly determines the work efficiency.

[0003] However, at present, there are two major problems in the processing of "two invoices" by power grid enterprises: (1) The processing of "two invoices" is in the form of handwritten or electronic documents, which takes a long time to fill out manually, the approval process is cumbersome, and the processing efficiency is low. This "two invoice" processing mode directly restricts the smooth development of various tasks of power grid enterprises; (2) The level of grassroots employees of power grids is uneven, and there are many subjective factors in the processing of "two invoices". There are problems such as errors in the information filling of "two invoices", irregular filling of safety measures in work tickets, and reversed steps, skipped items, and missing items in operation tickets.

[0004] At present, although some existing ticket-issuing methods based on intelligent algorithms have improved the efficiency of ticket-issuing to a certain extent, there are still some limitations: 1) Insufficient intelligence: At present, the two-ticket generation technology uses natural language processing to complete the text generation task. Regardless of whether it is template-based, statistical-based or deep learning-based text generation technology, it still has the disadvantages of difficulty in training models, easy semantic ambiguity, and difficulty in processing texts in different languages. It cannot simulate the learning and decision-making process of the human brain, cannot identify and encode patterns and relationships in large amounts of data, and then use this information to understand the user's natural language requests or questions and respond with relevant new content; 2) The function is relatively single and cannot realize the full process of "two tickets" automated processing: At this stage, most systems are tailored for specific power grids, and there are problems such as difficulty in establishing a knowledge base, rigid operating rules, insufficient flexibility, and poor versatility. In addition, the operating rule base is huge, and the probability of errors is very high, which affects the accuracy of the two-ticket writing. At present, the system can only realize the billing process of work tickets or operation tickets, but the whole process of "two tickets" is not only about handling work tickets or operation tickets, but also includes grounding line drawing, safety technology disclosure, survey sheets and work measures cards; 3) Poor user experience: At present, the system may not be perfect in user interface and human-computer interaction design, which makes users feel inconvenient when using the system. For example, it is still necessary to manually enter text information such as work content, time, and on-site conditions in the power work ticket to automatically generate the safety measures in the work ticket; the operation and maintenance personnel still need to receive the dispatch pre-order and determine whether the automatic billing mode can be enabled according to whether the on-duty computer is restricted; 4) Insufficient scalability and flexibility: With the continuous changes in business needs, the "two tickets" handling system needs to have good scalability and flexibility. However, at present, the system does not provide enough data interfaces and functional modules, and it is difficult to adapt to changes in business needs, resulting in high difficulty in system upgrades and modifications, and high time and cost.

[0005] Currently, no effective solution has been proposed to the problem that the above-mentioned related technologies usually use manual writing or a single, less flexible intelligent algorithm to generate operation tickets and work tickets, resulting in cumbersome filling and approval processes for the two tickets and low processing efficiency. Summary of the invention

[0006] The embodiments of the present invention provide a method and device for intelligently generating two tickets, and a computer-readable storage medium, so as to at least solve the technical problem that in the related technology, operation tickets and work tickets are usually generated by manual handwriting or a single and less flexible intelligent algorithm, resulting in cumbersome filling and approval processes for the two tickets and low processing efficiency.

[0007] According to one aspect of an embodiment of the present invention, there is provided a method for intelligently generating two tickets, comprising: responding to a two-ticket generation operation acting on a front-end page to generate a screen recording instruction and an information acquisition instruction, wherein the two tickets include: a work ticket and an operation ticket, wherein the work ticket is used to record maintenance tasks for maintaining power equipment, and the operation ticket is used to record operation tasks for operating the power equipment; controlling a screen recording component to perform a screen recording operation according to the screen recording instruction to obtain screen video data, wherein the screen recording operation refers to controlling the screen recording component to record the operation sensed by the front-end page; performing text extraction on the screen video data to obtain screen text information in the screen video data; based on The information acquisition instruction acquires the current operating status and work task information of the power system, wherein the work task information refers to the information of the work task that needs to be recorded in the work ticket and the operation ticket; the screen text information, the work task information and the current operating status are processed using a two-ticket generation model to generate the work ticket and the operation ticket, wherein the two-ticket generation model is trained using multiple sets of training data through deep learning, and each of the multiple sets of training data includes: sample input data, a sample work ticket and a sample operation ticket corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and sample current operating status.

[0008] Optionally, after responding to the two-ticket generation operation acting on the front-end page to generate a screen recording instruction and an information acquisition instruction, the intelligent generation method of the two tickets also includes: acquiring the sensing habit of the front-end page based on the sensing identifier of the two-ticket generation operation sensed by the front-end page, wherein the sensing habit refers to the habit when the two-ticket generation operation acts on the front-end page; optimizing the screen recording instruction according to the sensing habit to obtain the optimized screen recording instruction; acquiring the sensing time when the front-end page senses the two-ticket generation operation; determining the operating habit of the power system according to the time period of the sensing time, wherein the operating habit refers to the operating state of the power system in different time periods; optimizing the information acquisition instruction according to the operating habit to obtain the optimized information acquisition instruction.

[0009] Optionally, text extraction is performed on the screen video data to obtain screen text information in the screen video data, including: decomposing the screen video data to obtain multiple frames of video frame images; identifying the text direction of the text in each of the video frame images to obtain a recognition result, wherein the text direction refers to the direction of the centerline of the text; when the recognition result pair indicates that there is no offset between the text direction and a specific direction, determining that the video frame image is a target video frame image; when the recognition result pair indicates that there is an offset between the text direction and a specific direction, correcting the video frame image until the text direction of the text in the video frame image is the same as the specific direction, determining that the video frame image is the target video frame image, wherein the specific direction refers to a vertical direction; text extraction is performed on each of the target video frame images to obtain the screen text information.

[0010] Optionally, before using the two-ticket generation model to process the screen text information, the work task information and the current running status to generate the work ticket and the operation ticket, the two-ticket intelligent generation method also includes: obtaining multiple groups of sample data, wherein each of the multiple groups of sample data includes: sample input data, a sample work ticket and a sample operation ticket corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and sample current running status; dividing the multiple groups of sample data to obtain sample training data and sample test data, wherein the sample training data is used to train the two-ticket generation model, and the sample test data is used to test the two-ticket generation model; using the multiple groups of sample training data The artificial intelligence generated content model is iteratively trained until the iteration termination condition is reached, and the artificial intelligence generated content model obtained by the current training is determined to be the initial two-vote generation model, wherein the artificial intelligence generated content model is a deep learning model that automatically generates multiple types of content based on input information, and the multiple types of content include at least one of the following: text, image, and the iteration termination condition includes at least one of the following: the number of iterations reaches a preset number of iterations, and the model output error is lower than the error threshold; the initial two-vote generation model is performance verified using the sample test data to obtain a verification result; when the verification result indicates that the performance of the initial two-vote generation model reaches the preset performance standard, the initial two-vote generation model is determined to be the two-vote generation model.

[0011] Optionally, the intelligent generation method of the two tickets further includes: before iteratively training the artificial intelligence generated content model using multiple groups of the sample training data, randomly initializing the model parameters of the artificial intelligence generated content model using an improved chaotic map, wherein the first expression of the improved chaotic map is: x i represents the state value of the i-th generation population, x i+1 represents the state value of the next generation population of the i-th generation population; in the process of iteratively training the artificial intelligence generated content model using multiple groups of the sample training data, optimizing the learning rate of the artificial intelligence generated content model using a first formula, wherein the first formula is: GP represents the learning rate, n represents the current number of iterations, and n max Represents the maximum number of iterations, and the learning rate is used to control the update step size of the model parameters.

[0012] Optionally, the intelligent generation method of the two tickets further includes: in the process of using the two-ticket generation model to generate the work ticket and the operation ticket, dynamically adjusting the regularization parameter of the two-ticket generation model using a second formula to adaptively optimize the two-ticket generation model, wherein the regularization parameter, the second formula is: a represents the regularization parameter, which is used to determine the degree of penalty for the two-vote generation model.

[0013] Optionally, after using the two-ticket generation model to process the screen text information, the work task information and the current running status to generate the work ticket and the operation ticket, the intelligent generation method of the two tickets also includes: sending the work ticket and the operation ticket to the front-end page for visual presentation to review the work ticket and the operation ticket; when receiving two-ticket adjustment requests, parsing the two-ticket adjustment requests to obtain adjustment strategies for adjusting the work ticket and / or the operation ticket, and receiving update information, wherein the two-ticket adjustment request is an adjustment request generated by the adjustment component sensed by the front-end page when the work ticket and the operation ticket fail to pass the review, and the update information is information that needs to be presented on the work ticket and / or the operation ticket; adjusting the work ticket and / or the operation ticket according to the adjustment strategy based on the update information to obtain the target work ticket and / or target operation ticket.

[0014] According to another aspect of an embodiment of the present invention, there is also provided an intelligent two-ticket generation device, comprising: a first generation unit, used to respond to the two-ticket generation operation acting on the front-end page to generate a screen recording instruction and an information acquisition instruction, wherein the two tickets include: a work ticket and an operation ticket, wherein the work ticket is used to record maintenance tasks for maintaining power equipment, and the operation ticket is used to record operation tasks for operating the power equipment; a first acquisition unit, used to control the screen recording component to perform a screen recording operation according to the screen recording instruction to obtain screen video data, wherein the screen recording operation refers to controlling the screen recording component to record the operation sensed by the front-end page; a second acquisition unit, used to perform text extraction on the screen video data to obtain screen text in the screen video data Information; a third acquisition unit, used to acquire the current operating status and work task information of the power system based on the information acquisition instruction, wherein the work task information refers to the information of the work task that needs to be recorded in the work ticket and the operation ticket; a second generation unit, used to use a two-ticket generation model to process the screen text information, the work task information and the current operating status to generate the work ticket and the operation ticket, wherein the two-ticket generation model is trained by deep learning using multiple sets of training data, each of the multiple sets of training data includes: sample input data, a sample work ticket and a sample operation ticket corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and sample current operating status.

[0015] Optionally, the two-ticket intelligent generation device also includes: a fourth acquisition unit, which is used to obtain the sensing habit of the front-end page according to the sensing identifier of the two-ticket generation operation sensed by the front-end page after generating a screen recording instruction and an information acquisition instruction in response to the two-ticket generation operation acting on the front-end page, wherein the sensing habit refers to the habit when the two-ticket generation operation acts on the front-end page; a fifth acquisition unit, which is used to optimize the screen recording instruction according to the sensing habit to obtain the optimized screen recording instruction; a sixth acquisition unit, which is used to obtain the sensing time when the front-end page senses the two-ticket generation operation; a first determination unit, which is used to determine the operating habit of the power system according to the time period of the sensing time, wherein the operating habit refers to the operating state of the power system in different time periods; a seventh acquisition unit, which is used to optimize the information acquisition instruction according to the operating habit to obtain the optimized information acquisition instruction.

[0016] Optionally, the second acquisition unit includes: a first acquisition module, used to decompose the screen video data to obtain multiple frames of video frame images; a second acquisition module, used to identify the text direction of the text in each of the video frame images to obtain a recognition result, wherein the text direction refers to the direction of the centerline of the text; a first determination module, used to determine that the video frame image is a target video frame image when the recognition result indicates that there is no offset between the text direction and a specific direction; a second determination module, used to correct the video frame image when the recognition result indicates that there is an offset between the text direction and a specific direction, until the text direction of the text in the video frame image is the same as the specific direction, and determine that the video frame image is the target video frame image, wherein the specific direction refers to a vertical direction; a third acquisition module, used to extract text from each of the target video frame images to obtain the screen text information.

[0017] Optionally, the intelligent generation device for the two tickets also includes: an eighth acquisition unit, which is used to acquire multiple groups of sample data before using the two-ticket generation model to process the screen text information, the work task information and the current running status to generate the work ticket and the operation ticket, wherein each of the multiple groups of sample data includes: sample input data, a sample work ticket and a sample operation ticket corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and sample current running status; a ninth acquisition unit, which is used to divide the multiple groups of sample data to obtain sample training data and sample test data, wherein the sample training data is used to train the two-ticket generation model, and the sample test data is used to test the two-ticket generation model; a second determination unit, which is used to use the multiple groups of sample data This training data iteratively trains the artificial intelligence generated content model until the iteration termination condition is reached, and determines that the artificial intelligence generated content model obtained by the current training is the initial two-vote generation model, wherein the artificial intelligence generated content model is a deep learning model that automatically generates multiple types of content based on input information, and the multiple types of content include at least one of the following: text, image, and the iteration termination condition includes at least one of the following: the number of iterations reaches a preset number of iterations, and the model output error is lower than the error threshold; the tenth acquisition unit is used to use the sample test data to perform performance verification on the initial two-vote generation model to obtain a verification result; the third determination unit is used to determine that the initial two-vote generation model is the two-vote generation model when the verification result indicates that the performance of the initial two-vote generation model meets the preset performance standard.

[0018] Optionally, the two-ticket intelligent generation device further includes: an initialization unit, which is used to randomly initialize the model parameters of the artificial intelligence generated content model using an improved chaotic map before iteratively training the artificial intelligence generated content model using multiple groups of sample training data, wherein the first expression of the improved chaotic map is: xi represents the state value of the i-th generation population, x i+1 represents the state value of the next generation population of the i-th generation population; a first optimization unit, used to optimize the learning rate of the artificial intelligence generated content model using a first formula during the iterative training of the artificial intelligence generated content model using multiple groups of the sample training data, wherein the first formula is: GP represents the learning rate, n represents the current number of iterations, and n max Represents the maximum number of iterations, and the learning rate is used to control the update step size of the model parameters.

[0019] Optionally, the intelligent generation device for two tickets further includes: a second optimization unit, which is used to dynamically adjust the regularization parameter of the two-ticket generation model using a second formula in the process of using the two-ticket generation model to generate the work ticket and the operation ticket, so as to adaptively optimize the two-ticket generation model, wherein the regularization parameter, the second formula is: a represents the regularization parameter, which is used to determine the degree of penalty for the two-vote generation model.

[0020] Optionally, the intelligent generation device of the two tickets also includes: a sending unit, which is used to process the screen text information, the work task information and the current running status using the two-ticket generation model to generate the work ticket and the operation ticket, and then send the work ticket and the operation ticket to the front-end page for visual presentation to review the work ticket and the operation ticket; a receiving unit, which is used to parse the two-ticket adjustment request when receiving the two-ticket adjustment request, obtain an adjustment strategy for adjusting the work ticket and / or the operation ticket, and receive update information, wherein the two-ticket adjustment request is an adjustment request generated by the adjustment component sensed by the front-end page when the work ticket and the operation ticket are not reviewed and approved, and the update information is information that needs to be presented on the work ticket and / or the operation ticket; an eleventh acquisition unit, which is used to adjust the work ticket and / or the operation ticket according to the adjustment strategy based on the update information to obtain the target work ticket and / or target operation ticket.

[0021] According to another aspect of an embodiment of the present invention, there is also provided a system for intelligently generating two tickets, wherein the system for intelligently generating two tickets uses any one of the above-mentioned methods for intelligently generating two tickets.

[0022] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, wherein the computer-readable storage medium includes a stored program, wherein the program executes any one of the above-mentioned two-ticket intelligent generation methods.

[0023] According to another aspect of an embodiment of the present invention, a processor is further provided, wherein the processor is used to run a program, wherein when the program is run, any one of the above-mentioned two-ticket intelligent generation methods is executed.

[0024] According to another aspect of an embodiment of the present invention, there is also provided a computer program product, comprising computer instructions, which, when executed by a processor, execute any one of the above-mentioned two-ticket intelligent generation methods.

[0025] In an embodiment of the present invention, a two-ticket generation operation acting on a front-end page is responded to to generate a screen recording instruction and an information acquisition instruction, wherein the two tickets include: a work ticket and an operation ticket, the work ticket is used to record maintenance tasks for maintaining power equipment, and the operation ticket is used to record operation tasks for performing operations on power equipment; according to the screen recording instruction, the screen recording component is controlled to perform a screen recording operation to obtain screen video data, wherein the screen recording operation refers to controlling the screen recording component to record the operation sensed by the front-end page; text extraction is performed on the screen video data to obtain screen text information in the screen video data; based on the information acquisition instruction, the current operating status and work task information of the power system are obtained, wherein the work task information refers to the information of the work task that needs to be recorded in the work ticket and the operation ticket; the screen text information, the work task information and the current operating status are processed using a two-ticket generation model to generate a work ticket and an operation ticket, wherein the two-ticket generation model is obtained by training using multiple sets of training data through deep learning, and each of the multiple sets of training data includes: sample input data, a sample work ticket and a sample operation ticket corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and sample current operating status. Through the above technical scheme, the operations performed by the operation and maintenance personnel at the front end are recorded and text extracted, the work task information submitted by the operation and maintenance personnel and the current operating status of the power system are obtained, and then the obtained information is processed using the trained two-ticket generation model to generate the work ticket and the operation ticket. The technical effect of more comprehensively obtaining the content required to generate the two tickets from a multi-dimensional perspective and generating the two tickets using the two-ticket generation model is achieved, which improves the efficiency and accuracy of generating the two tickets and simplifies the handling process of the two tickets. This solves the technical problem that the related technology usually uses manual handwriting or a single, less flexible intelligent algorithm to generate operation tickets and work tickets, resulting in cumbersome filling and approval processes for the two tickets and low handling efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0027] Figure 1 It is a hardware structure block diagram of a mobile terminal of an intelligent method for generating two tickets according to an embodiment of the present invention;

[0028] Figure 2 is a flow chart of a method for intelligently generating two tickets according to an embodiment of the present invention;

[0029] Figure 3 is a schematic diagram of a code for optimizing text direction according to an embodiment of the present invention;

[0030] FIG4( a ) is a scatter diagram of a Circle chaotic map according to an embodiment of the present invention;

[0031] FIG4( b ) is a scatter diagram of an improved Circle chaotic map according to an embodiment of the present invention;

[0032] FIG5( a) is a distribution histogram of a Circle chaotic map according to an embodiment of the present invention;

[0033] FIG5( b ) is a distribution histogram of the improved Circle chaotic mapping according to an embodiment of the present invention;

[0034] Figure 6 is a schematic diagram of changes in learning rate parameters according to an embodiment of the present invention;

[0035] Figure 7 is a schematic diagram of a change in a regularization parameter according to an embodiment of the present invention;

[0036] Figure 8 It is a schematic diagram of an intelligent device for generating two tickets according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0039] As introduced in the background technology, the related art usually uses manual handwriting or a single, less flexible intelligent algorithm to generate operation tickets and work tickets, resulting in cumbersome filling and approval processes for the two tickets and low processing efficiency. In view of the above defects, an intelligent generation method and device for two tickets and a computer-readable storage medium are provided in the embodiments of the present invention.

[0040] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0041] The method embodiments provided in the embodiments of the present invention can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal for an intelligent method for generating two tickets according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0042] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer programs corresponding to the intelligent generation method of two tickets in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0043] According to an embodiment of the present invention, a method embodiment of an intelligent method for generating two tickets is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0044] Figure 2 is a flow chart of the intelligent generation method of two tickets according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0045] Step S202, responds to the two-ticket generation operation acting on the front-end page to generate screen recording instructions and information acquisition instructions, wherein the two tickets include: a work ticket and an operation ticket, the work ticket is used to record maintenance tasks for maintaining power equipment, and the operation ticket is used to record operation tasks for performing operations on power equipment.

[0046] In this embodiment, the system background can generate screen recording instructions and information acquisition instructions when the operation and maintenance personnel trigger the operation of handling two tickets (including work tickets and operation tickets) through the previous page, so as to obtain the relevant data required for the subsequent generation of two tickets based on the instructions.

[0047] Step S204, controlling the screen recording component to perform a screen recording operation according to the screen recording instruction to obtain screen video data, wherein the screen recording operation refers to controlling the screen recording component to record the operation sensed by the front-end page.

[0048] In this embodiment, a real-time screen information acquisition system can be constructed. The system can implement the screen recording function through the ScreenCaptureKit provided by the operating system, record the applications opened by the operation and maintenance personnel during the "two tickets" processing, and record the application window information; the ScreenCaptureKit here refers to a toolkit or framework that can implement the screen recording function. In different operating systems or programming environments, the tools or libraries that implement screen recording may have different names.

[0049] Step S206, extracting text from the screen video data to obtain screen text information in the screen video data.

[0050] In this embodiment, an optical character recognition (OCR) model is used to extract text information from screen video data using a picture recognition algorithm, and the extracted information is stored in the data to achieve real-time sharing and unified management of information.

[0051] Step S208, obtaining the current operating status and work task information of the power system based on the information acquisition instruction, wherein the work task information refers to the information of the work task that needs to be recorded in the work ticket and the operation ticket.

[0052] In this embodiment, the work task information about the two tickets submitted or uploaded by the operation and maintenance personnel can also be obtained based on the information acquisition instruction, and the operating status of the current power system can be obtained in real time to provide a data basis for the subsequent generation of the two tickets.

[0053] Step S210, use the two-ticket generation model to process the screen text information, work task information and current running status to generate a work ticket and an operation ticket, wherein the two-ticket generation model is trained by deep learning using multiple sets of training data, and each of the multiple sets of training data includes: sample input data, sample work tickets and sample operation tickets corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and sample current running status.

[0054] In this embodiment, the trained two-ticket generation model can be used to process the acquired screen text information, work task information and the current operating status of the power system to generate a work ticket and an operation ticket.

[0055] From the above, it can be seen that the technical solution provided by the above embodiment of the present invention can respond to the two-ticket generation operation acting on the front-end page to generate screen recording instructions and information acquisition instructions, wherein the two tickets include: a work ticket and an operation ticket, the work ticket is used to record the maintenance tasks for maintaining the power equipment, and the operation ticket is used to record the operation tasks for performing operations on the power equipment; according to the screen recording instruction, the screen recording component is controlled to perform the screen recording operation to obtain screen video data, wherein the screen recording operation refers to controlling the screen recording component to record the operation sensed by the front-end page; text extraction is performed on the screen video data to obtain screen text information in the screen video data; based on the information acquisition instruction, the current operating status and work task information of the power system are obtained, wherein the work task information refers to the information of the work tasks that need to be recorded in the work ticket and the operation ticket; the two-ticket generation model is used to perform screen text information, work task information and current The operation status is processed to generate a work ticket and an operation ticket, wherein the two-ticket generation model is trained by deep learning using multiple sets of training data, and each set of the multiple training data includes: sample input data, a sample work ticket and a sample operation ticket corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and sample current operation status, so as to achieve the purpose of recording the operations performed by the operation and maintenance personnel at the front end and extracting the text, obtaining the work task information submitted by the operation and maintenance personnel and the current operation status of the power system, and then using the trained two-ticket generation model to process the obtained information to generate a work ticket and an operation ticket, thereby achieving a more comprehensive acquisition of the content required to generate the two tickets from a multi-dimensional perspective, and using the two-ticket generation model to generate the two tickets. The technical effect improves the efficiency and accuracy of generating the two tickets and simplifies the handling process of the two tickets.

[0056] Therefore, the technical solution provided by the above-mentioned embodiment of the present invention solves the technical problem that the related technology usually adopts manual handwriting or a single and less flexible intelligent algorithm to generate operation tickets and work tickets, resulting in cumbersome filling and approval procedures for the two tickets and low processing efficiency.

[0057] According to the above embodiment of the present invention, after responding to the two-ticket generation operation acting on the front-end page to generate a screen recording instruction and an information acquisition instruction, the intelligent generation method of the two tickets also includes: acquiring the sensing habit of the front-end page according to the sensing identifier of the two-ticket generation operation sensed by the front-end page, wherein the sensing habit refers to the habit when the two-ticket generation operation acts on the front-end page; optimizing the screen recording instruction according to the sensing habit to obtain the optimized screen recording instruction; acquiring the sensing time when the front-end page senses the two-ticket generation operation; determining the operating habit of the power system according to the time period of the sensing time, wherein the operating habit refers to the operating state of the power system in different time periods; optimizing the information acquisition instruction according to the operating habit to obtain the optimized information acquisition instruction.

[0058] Specifically, after generating the screen recording instructions and information acquisition instructions, the screen recording instructions can be optimized according to the sensing habits of the operation and maintenance personnel recorded by the system. For example, the sensing habits of each operation and maintenance personnel (the sensing habits of the operation and maintenance personnel here are equivalent to the sensing habits of the above-mentioned front-end page when sensing the two-ticket generation operation) may be different. Some people may be more accustomed to using keyboard shortcuts, while others may rely more on mouse clicks. The system identifies these habits and stores them so that when the operation and maintenance personnel operate the screen, they can more accurately generate screen recording instructions based on the recorded sensing habits. For example, recording is triggered only when operating key information to avoid recording a large amount of irrelevant content, thereby saving storage space and processing time. The system can also automatically adjust the priority and strategy for obtaining power system status information according to the time period of the current time. For example, the power system may have different operating conditions and operating requirements at different time points, and the operating procedures at night or during peak hours may be different from those during daily hours. The system identifies the operating procedures at these specific times and can automatically adjust the priority and strategy for information acquisition. For example, all necessary equipment status and safety specification information is obtained before key operations to ensure that the content of the two tickets generated meets the current operating environment. By matching the operating procedures of the power system at specific times, the system can obtain all the information required to generate the two tickets more quickly, avoiding repeated queries and confirmations, thereby significantly improving the efficiency of generating the two tickets.

[0059] According to the above embodiment of the present invention, text extraction is performed on screen video data to obtain screen text information in the screen video data, including: decomposing the screen video data to obtain multiple frames of video frame images; identifying the text direction of the text in each video frame image to obtain a recognition result, wherein the text direction refers to the direction of the centerline of the text; in the case where the recognition result shows that there is no offset between the text direction and the specific direction, determining that the video frame image is a target video frame image; in the case where the recognition result shows that there is an offset between the text direction and the specific direction, correcting the video frame image until the text direction of the text in the video frame image is the same as the specific direction, determining that the video frame image is a target video frame image, wherein the specific direction refers to the vertical direction; text extraction is performed on each target video frame image to obtain screen text information.

[0060] Combine the following Figure 3 The above embodiments of the present invention are described in detail. Figure 3 is a schematic diagram of a code for optimizing text direction according to an embodiment of the present invention.

[0061] Specifically, when using OCR technology to extract text from each image frame in screen video data, since the direction classifier has a relatively high recognition accuracy when the text is at 0 degrees and 180 degrees (i.e., the above-mentioned specific directions), in order to improve the accuracy of text recognition and extraction, Figure 3 The optimization code shown converts the direction of video frames with text directions in other directions (other than a specific direction) to 0 degrees or 180 degrees during the preprocessing stage, and then performs text extraction to improve the accuracy of text recognition.

[0062] It should be noted that the text direction here actually refers to the direction of the text seen under normal vision. In the specific recognition process, the principal component analysis can be used to determine the main axis direction of the text outline, and the pre-trained deep learning model can be used to classify the direction of the text. The model has learned to distinguish between horizontal, vertical and inclined text, so as to identify the text direction. Of course, other methods can also be used to identify the text direction, which will not be elaborated here.

[0063] According to the above embodiment of the present invention, before using the two-ticket generation model to process the screen text information, work task information and current running status to generate a work ticket and an operation ticket, the intelligent generation method of the two tickets also includes: obtaining multiple groups of sample data, wherein each of the multiple groups of sample data includes: sample input data, a sample work ticket and a sample operation ticket corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and the sample current running status; dividing the multiple groups of sample data to obtain sample training data and sample test data, wherein the sample training data is used to train the two-ticket generation model, and the sample test data is used to test the two-ticket generation model; using multiple groups of sample training data The artificial intelligence generated content model is iteratively trained until the iteration termination condition is reached, and the artificial intelligence generated content model obtained by the current training is determined to be the initial two-vote generation model, wherein the artificial intelligence generated content model is a deep learning model that automatically generates multiple types of content based on input information, and the multiple types of content include at least one of the following: text, image, and the iteration termination condition includes at least one of the following: the number of iterations reaches a preset number of iterations, and the model output error is lower than the error threshold; the initial two-vote generation model is performance verified using sample test data to obtain a verification result; when the verification result indicates that the performance of the initial two-vote generation model reaches the preset performance standard, the initial two-vote generation model is determined to be the two-vote generation model.

[0064] Specifically, in the process of training the two-ticket generation model, a large amount of historical data can be obtained as sample training data for AIGC (i.e., artificial intelligence generated content model). For example, the entire history of computer operation by operation and maintenance personnel, including web browsing information and application dialog box content, can be collected to make the computer operation history into a traceable and searchable database, and the historical work task information corresponding to this time and the historical operation status information of the power system can be obtained as much as possible, and used as training data to train AIGC to obtain the two-ticket generation model, and a part of the sample training data is retained as test data to test the performance of the trained two-ticket generation model to ensure the accuracy of the two-ticket generation model; human-computer interaction can also be achieved through signals of multiple modes (such as voice, text, etc.), ultimately making human-computer interaction as convenient and natural as human-human interaction; in addition, when using the two-ticket generation model to learn new tasks or data, it can adapt and update quickly, and its sustainable learning ability can enable the system to evolve and update continuously according to the needs of operation and maintenance personnel, and obtain more personalized and relevant results.

[0065] According to the above embodiment of the present invention, the intelligent generation method of the two tickets further includes: before iteratively training the artificial intelligence generated content model using multiple groups of sample training data, randomly initializing the model parameters of the artificial intelligence generated content model using the improved chaotic mapping, wherein the first expression of the improved chaotic mapping is: x i represents the state value of the i-th generation population, x i+1 represents the state value of the next generation population of the i-th generation population; in the process of iteratively training the artificial intelligence generated content model using multiple sets of sample training data, the learning rate of the artificial intelligence generated content model is optimized using the first formula, wherein the first formula is: GP represents the learning rate, n represents the current number of iterations, and n max Represents the maximum number of iterations, and the learning rate is used to control the update step size of the model parameters.

[0066] Next, in combination with FIG. 4(a), FIG. 4(b), FIG. 5(a), FIG. 5(b) and Figure 6 The above embodiment of the present invention is described in detail. FIG. 4(a) is a scatter diagram of a Circle chaotic mapping according to an embodiment of the present invention. FIG. 4(b) is a scatter diagram of an improved Circle chaotic mapping according to an embodiment of the present invention. FIG. 5(a) is a distribution histogram of a Circle chaotic mapping according to an embodiment of the present invention. FIG. 5(b) is a distribution histogram of an improved Circle chaotic mapping according to an embodiment of the present invention. Figure 6 Schematic diagram of the change of learning rate parameters according to an embodiment of the present invention.

[0067] Specifically, in the AIGC standard model, the pseudo-random initialization method is used in the initialization stage, which easily leads to the aggregation of initial values, and chaotic initialization can effectively improve this phenomenon; there are many methods of chaotic mapping, among which the chaotic value coverage rate generated by Circle chaotic mapping is high, but the chaotic value still has the phenomenon of local uneven distribution, so it needs to be improved; the standard Circle chaotic mapping formula is: The improved Circle chaos mapping formula is: Wherein, i is the dimension of the solution. The scatter distribution diagrams shown in FIG4(a) and FIG4(b) and the distribution histograms shown in FIG5(a) and FIG5(b) can be used to intuitively reflect the improved effect. i can be taken as 2000 (this is only used as an example and can be adjusted according to the actual situation. There is no specific restriction here). As shown in FIG4(a), FIG4(b), FIG5(a) and FIG5(b), it can be intuitively found through comparison that the improved Circle chaotic mapping value distribution is more uniform. Therefore, using the improved Circle chaotic mapping method to initialize the population can enhance the diversity of the population and thus enhance the optimization ability of the optimization algorithm.

[0068] In addition, the learning rate is an important parameter for controlling the update speed of model parameters. If the learning rate is too large, it may cause model oscillation and instability. If the learning rate is fixed, a fixed learning rate is usually used. This is the simplest learning rate adjustment method, that is, the learning rate is kept unchanged during the entire training process. The advantage of this method is that it is simple and intuitive, but the disadvantage is that it may not be well adapted to the training process at different stages, resulting in an unstable training process or too slow convergence speed. For this reason, an adaptive algorithm is needed for parameter tuning, as shown below: GP represents the learning rate, n represents the current number of iterations, and n max Indicates the maximum number of iterations.

[0069] The test found that GP in the interval [0.095, 0.1] can enable the algorithm to have better global search capabilities while taking into account local exploration capabilities (if other GP intervals are found to achieve better performance in the actual process, they can also be adjusted according to the actual situation, and there is no specific restriction here). Figure 6 As shown in the figure, in the early stage of the iteration process, the generation probability is small. As the generation probability continues to increase, the final value is 0.1. The global search ability of the algorithm in the optimization process is continuously enhanced, preventing the algorithm from falling into the local optimum in the later stage of the optimization process.

[0070] According to the above embodiment of the present invention, the intelligent generation method of the two tickets also includes: in the process of using the two-ticket generation model to generate the work ticket and the operation ticket, dynamically adjusting the regularization parameter of the two-ticket generation model using the second formula to adaptively optimize the two-ticket generation model, wherein the regularization parameter, the second formula is: a represents the regularization parameter, which is used to determine the degree of penalty for the two-vote generation model.

[0071] Combine the following Figure 7 The above embodiments of the present invention are described in detail. Figure 7 is a schematic diagram of the change of regularization parameters according to an embodiment of the present invention.

[0072] Specifically, the regularization parameter is used to control the complexity of the model and avoid overfitting. By adjusting the regularization parameter, the model's fitting ability and generalization ability can be balanced. Generally speaking, a larger regularization parameter will reduce the model complexity and is suitable for dealing with high variance problems; while a smaller regularization parameter is suitable for dealing with high deviation problems. In order to balance the algorithm's fitting ability and generalization ability, the sine and cosine ideas are used to tune the regularization parameters, as shown below: like Figure 7 As shown in the figure, a increases nonlinearly from about 0.35 with the number of iterations and finally reaches 0.5. As a changes, the algorithm gradually enhances its local exploration ability, so that the algorithm can find particles infinitely close to the optimal solution within the range of the global optimal solution, thereby improving the algorithm's optimization ability.

[0073] According to the above embodiment of the present invention, after using the two-ticket generation model to process the screen text information, work task information and current running status to generate a work ticket and an operation ticket, the intelligent generation method of the two tickets also includes: sending the work ticket and the operation ticket to the front-end page for visual presentation to review the work ticket and the operation ticket; when receiving a two-ticket adjustment request, parsing the two-ticket adjustment request to obtain an adjustment strategy for adjusting the work ticket and / or the operation ticket, and receiving update information, wherein the two-ticket adjustment request is an adjustment request generated by the adjustment component when the front-end page senses that the work ticket and the operation ticket have not been reviewed, and the update information is information that needs to be presented on the work ticket and / or the operation ticket; adjusting the work ticket and / or the operation ticket according to the adjustment strategy based on the updated information to obtain a target work ticket and / or target operation ticket.

[0074] Specifically, after the work ticket and operation ticket are preliminarily generated using the two-ticket generation model, the preliminarily generated work ticket and operation ticket can be displayed to the operation and maintenance personnel for review. If the operation and maintenance personnel pass the review, they can directly trigger the corresponding button to download and save, and the system will respond and save the work ticket and operation ticket; if the operation and maintenance personnel fail the review, they can trigger the corresponding adjustment button and synchronously upload the information that needs to be updated. While responding to the two-ticket adjustment request, the system will analyze it to determine which specific part of the work ticket and / or operation ticket needs to be adjusted, and make corresponding adjustments based on the updated information submitted by the operation and maintenance personnel, and regenerate the work ticket and / or operation ticket to display it to the operation and maintenance personnel again.

[0075] Through the technical solutions provided by the above embodiments of the present invention, the following technical effects are also achieved: 1) A more natural and smooth human-computer dialogue experience can be achieved. By learning a large amount of text data, it can generate fluent and coherent language expressions, better understand the user's intentions, and have long-term memory capabilities; in addition, its sustainable learning ability can also enable it to evolve and update continuously with user needs, obtain more personalized and relevant results, and enhance the human-computer interaction experience; 2) More advanced incremental learning algorithms and more plastic model structures can be used to adapt to different tasks and data, or more intelligent integrated learning methods can be used to integrate the prediction results of multiple models to improve the generalization ability and adaptability of the system.

[0076] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0077] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0078] According to an embodiment of the present invention, there is also provided a two-ticket intelligent generation device for implementing the above two-ticket intelligent generation method. Figure 8 is a schematic diagram of an intelligent generation device for two tickets according to an embodiment of the present invention, such as Figure 8 As shown, the device includes: a first generating unit 81, a first acquiring unit 83, a second acquiring unit 85, a third acquiring unit 87 and a second generating unit 89. The intelligent generating device of the two tickets is described in detail below.

[0079] The first generating unit 81 is used to respond to two-ticket generating operations acting on the front-end page to generate screen recording instructions and information acquisition instructions, wherein the two tickets include: a work ticket and an operation ticket, the work ticket is used to record maintenance tasks for maintaining power equipment, and the operation ticket is used to record operation tasks for performing operations on power equipment.

[0080] The first acquisition unit 83 is used to control the screen recording component to perform a screen recording operation according to a screen recording instruction to obtain screen video data, wherein the screen recording operation refers to controlling the screen recording component to record the operation sensed by the front-end page.

[0081] The second acquisition unit 85 is used to extract text from the screen video data to obtain screen text information in the screen video data.

[0082] The third acquisition unit 87 is used to acquire the current operating status and work task information of the power system based on the information acquisition instruction, wherein the work task information refers to the information of the work task that needs to be recorded in the work ticket and the operation ticket.

[0083] The second generation unit 89 is used to use the two-ticket generation model to process the screen text information, work task information and current running status to generate a work ticket and an operation ticket, wherein the two-ticket generation model is trained by deep learning using multiple sets of training data, and each of the multiple sets of training data includes: sample input data, a sample work ticket and a sample operation ticket corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and sample current running status.

[0084] It should be noted here that the above-mentioned first generation unit 81, first acquisition unit 83, second acquisition unit 85, third acquisition unit 87 and second generation unit 89 correspond to steps S202 to S210 in the above-mentioned embodiments, and the three modules are the same as the instances and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the above-mentioned embodiments.

[0085] It can be seen from the above that in the scheme recorded in the above-mentioned embodiment of the present invention, the first generating unit can be used to respond to the two-ticket generating operation acting on the front-end page to generate a screen recording instruction and an information acquisition instruction, wherein the two tickets include: a work ticket and an operation ticket, the work ticket is used to record the maintenance task of maintaining the power equipment, and the operation ticket is used to record the operation task of performing operations on the power equipment; then the first acquisition unit is used to control the screen recording component to perform the screen recording operation according to the screen recording instruction to obtain screen video data, wherein the screen recording operation refers to controlling the screen recording component to record the operation sensed by the front-end page; then the second acquisition unit is used to extract text from the screen video data to obtain the screen text information in the screen video data; then the third acquisition unit is used to obtain the current operating status and work task information of the power system based on the information acquisition instruction, wherein the work task information refers to the information of the work task that needs to be recorded in the work ticket and the operation ticket; finally, the second generating unit is used to use the two The ticket generation model processes the screen text information, work task information and current operating status to generate a work ticket and an operation ticket. The two-ticket generation model is trained by deep learning using multiple sets of training data. Each set of the multiple training data includes: sample input data, sample work tickets and sample operation tickets corresponding to the sample input data. The sample input data includes: sample screen text information, sample work task information and sample current operating status. It achieves the purpose of recording the operations performed by the operation and maintenance personnel at the front end and extracting text, obtaining the work task information submitted by the operation and maintenance personnel and the current operating status of the power system, and then using the trained two-ticket generation model to process the acquired information to generate work tickets and operation tickets. It achieves the technical effect of obtaining the content required to generate two tickets from a multi-dimensional perspective in a more comprehensive manner, and using the two-ticket generation model to generate two tickets, thereby improving the efficiency and accuracy of generating two tickets and simplifying the handling process of two tickets.

[0086] Therefore, the technical solution provided by the above-mentioned embodiment of the present invention solves the technical problem that the related technology usually adopts manual handwriting or a single and less flexible intelligent algorithm to generate operation tickets and work tickets, resulting in cumbersome filling and approval procedures for the two tickets and low processing efficiency.

[0087] Optionally, the two-ticket intelligent generation device also includes: a fourth acquisition unit, which is used to obtain the sensing habit of the front-end page according to the sensing identifier of the two-ticket generation operation sensed by the front-end page after responding to the two-ticket generation operation acting on the front-end page to generate a screen recording instruction and an information acquisition instruction, wherein the sensing habit refers to the habit when the two-ticket generation operation acts on the front-end page; a fifth acquisition unit, which is used to optimize the screen recording instruction according to the sensing habit to obtain the optimized screen recording instruction; a sixth acquisition unit, which is used to obtain the sensing time when the front-end page senses the two-ticket generation operation; a first determination unit, which is used to determine the operating habit of the power system according to the time period of the sensing time, wherein the operating habit refers to the operating state of the power system in different time periods; a seventh acquisition unit, which is used to optimize the information acquisition instruction according to the operating habit to obtain the optimized information acquisition instruction.

[0088] Optionally, the second acquisition unit includes: a first acquisition module, used to decompose the screen video data to obtain multiple frames of video frame images; a second acquisition module, used to identify the text direction of the text in each video frame image to obtain a recognition result, wherein the text direction refers to the direction of the centerline of the text; a first determination module, used to determine that the video frame image is a target video frame image when there is no offset between the recognition result indicating the text direction and a specific direction; a second determination module, used to correct the video frame image when there is an offset between the recognition result indicating the text direction and the specific direction, until the text direction of the text in the video frame image is the same as the specific direction, and determine that the video frame image is a target video frame image, wherein the specific direction refers to a vertical direction; a third acquisition module, used to extract text from each target video frame image to obtain screen text information.

[0089] Optionally, the intelligent generation device for the two tickets also includes: an eighth acquisition unit, which is used to acquire multiple groups of sample data before using the two-ticket generation model to process the screen text information, work task information and current operating status to generate work tickets and operation tickets, wherein each of the multiple groups of sample data includes: sample input data, sample work tickets and sample operation tickets corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and sample current operating status; a ninth acquisition unit, which is used to divide the multiple groups of sample data to obtain sample training data and sample test data, wherein the sample training data is used to train the two-ticket generation model, and the sample test data is used to test the two-ticket generation model; a second determination unit, which is used to use multiple groups of sample training data The artificial intelligence generated content model is iteratively trained until the iteration termination condition is reached, and the artificial intelligence generated content model obtained by the current training is determined to be the initial two-vote generation model, wherein the artificial intelligence generated content model is a deep learning model that automatically generates multiple types of content based on input information, and the multiple types of content include at least one of the following: text, image, and the iteration termination condition includes at least one of the following: the number of iterations reaches a preset number of iterations, and the model output error is lower than the error threshold; the tenth acquisition unit is used to perform performance verification on the initial two-vote generation model using sample test data to obtain a verification result; the third determination unit is used to determine that the initial two-vote generation model is a two-vote generation model when the verification result indicates that the performance of the initial two-vote generation model reaches a preset performance standard.

[0090] Optionally, the two-ticket intelligent generation device further includes: an initialization unit, which is used to randomly initialize the model parameters of the artificial intelligence generated content model using the improved chaotic map before iteratively training the artificial intelligence generated content model using multiple sets of sample training data, wherein the first expression of the improved chaotic map is: x i represents the state value of the i-th generation population, x i+1 represents the state value of the next generation population of the i-th generation population; a first optimization unit, used to optimize the learning rate of the artificial intelligence generated content model using a first formula during the iterative training of the artificial intelligence generated content model using multiple groups of sample training data, wherein the first formula is: GP represents the learning rate, n represents the current number of iterations, and n max Represents the maximum number of iterations, and the learning rate is used to control the update step size of the model parameters.

[0091] Optionally, the intelligent generation device of the two tickets further includes: a second optimization unit, which is used to dynamically adjust the regularization parameter of the two-ticket generation model using a second formula in the process of using the two-ticket generation model to generate the work ticket and the operation ticket, so as to adaptively optimize the two-ticket generation model, wherein the regularization parameter, the second formula is: a represents the regularization parameter, which is used to determine the degree of penalty for the two-vote generation model.

[0092] Optionally, the intelligent generation device of the two tickets also includes: a sending unit, which is used to process the screen text information, work task information and current running status using the two-ticket generation model to generate a work ticket and an operation ticket, and then send the work ticket and the operation ticket to the front-end page for visual presentation to review the work ticket and the operation ticket; a receiving unit, which is used to parse the two-ticket adjustment request when receiving the two-ticket adjustment request, obtain an adjustment strategy for adjusting the work ticket and / or the operation ticket, and receive update information, wherein the two-ticket adjustment request is an adjustment request generated by the adjustment component when the front-end page senses that the work ticket and the operation ticket fail to pass the review, and the update information is information that needs to be presented on the work ticket and / or the operation ticket; an eleventh acquisition unit, which is used to adjust the work ticket and / or the operation ticket according to the adjustment strategy based on the updated information to obtain the target work ticket and / or the target operation ticket.

[0093] According to another aspect of an embodiment of the present invention, there is also provided a system for intelligently generating two tickets, and the system for intelligently generating two tickets uses any one of the above-mentioned methods for intelligently generating two tickets.

[0094] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program executes any one of the above-mentioned two-ticket intelligent generation methods.

[0095] Optionally, in this embodiment, the computer-readable storage medium may be located in any one of the computer terminals in a computer terminal group in a computer network, or in any one of the communication devices in a communication device group.

[0096] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: responding to two ticket generation operations acting on the front-end page to generate screen recording instructions and information acquisition instructions, wherein the two tickets include: a work ticket and an operation ticket, the work ticket is used to record maintenance tasks for maintaining the power equipment, and the operation ticket is used to record operation tasks for operating the power equipment; controlling the screen recording component to perform a screen recording operation according to the screen recording instruction to obtain screen video data, wherein the screen recording operation refers to controlling the screen recording component to record the operation sensed by the front-end page; performing text extraction on the screen video data to obtain screen data in the screen video data. text information; based on the information acquisition instruction, the current operating status and work task information of the power system are obtained, wherein the work task information refers to the information of the work task that needs to be recorded in the work ticket and the operation ticket; the screen text information, work task information and current operating status are processed using the two-ticket generation model to generate the work ticket and the operation ticket, wherein the two-ticket generation model is trained by deep learning using multiple sets of training data, and each set of the multiple sets of training data includes: sample input data, sample work tickets and sample operation tickets corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and sample current operating status.

[0097] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: obtaining the sensing habit of the front-end page based on the sensing identifier of the two-ticket generation operation sensed by the front-end page, wherein the sensing habit refers to the habit when the two-ticket generation operation acts on the front-end page; optimizing the screen recording instruction according to the sensing habit to obtain the optimized screen recording instruction; obtaining the sensing time when the front-end page senses the two-ticket generation operation; determining the operating habit of the power system based on the time period of the sensing time, wherein the operating habit refers to the operating state of the power system in different time periods; optimizing the information acquisition instruction according to the operating habit to obtain the optimized information acquisition instruction.

[0098] Optionally, in this embodiment, a computer-readable storage medium is configured to store program codes for executing the following steps: decomposing screen video data to obtain multiple frames of video frame images; identifying the text direction of the text in each video frame image to obtain a recognition result, wherein the text direction refers to the direction of the centerline of the text; in the case where the recognition result indicates that there is no offset between the text direction and a specific direction, determining that the video frame image is a target video frame image; in the case where the recognition result indicates that there is an offset between the text direction and the specific direction, correcting the video frame image until the text direction of the text in the video frame image is the same as the specific direction, determining that the video frame image is a target video frame image, wherein the specific direction refers to a vertical direction; performing text extraction on each target video frame image to obtain screen text information.

[0099] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: obtaining multiple groups of sample data, wherein each of the multiple groups of sample data includes: sample input data, a sample work ticket and a sample operation ticket corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and the current running status of the sample; dividing the multiple groups of sample data to obtain sample training data and sample test data, wherein the sample training data is used to train the two-ticket generation model, and the sample test data is used to test the two-ticket generation model; iteratively training the artificial intelligence generated content model using the multiple groups of sample training data , until the iteration termination condition is reached, the artificial intelligence generated content model obtained by the current training is determined to be the initial two-vote generation model, wherein the artificial intelligence generated content model is a deep learning model that automatically generates multiple types of content based on input information, and the multiple types of content include at least one of the following: text, image, and the iteration termination condition includes at least one of the following: the number of iterations reaches the preset number of iterations, and the model output error is lower than the error threshold; the performance of the initial two-vote generation model is verified using sample test data to obtain a verification result; when the verification result indicates that the performance of the initial two-vote generation model meets the preset performance standard, the initial two-vote generation model is determined to be the two-vote generation model.

[0100] Optionally, in this embodiment, the computer-readable storage medium is configured to store a program code for executing the following steps: before iteratively training the AI-generated content model using multiple sets of sample training data, randomly initializing the model parameters of the AI-generated content model using an improved chaotic map, wherein a first expression of the improved chaotic map is: x i represents the state value of the i-th generation population, x i+1represents the state value of the next generation population of the i-th generation population; in the process of iteratively training the artificial intelligence generated content model using multiple sets of sample training data, the learning rate of the artificial intelligence generated content model is optimized using the first formula, wherein the first formula is: GP represents the learning rate, n represents the current number of iterations, and n max Represents the maximum number of iterations, and the learning rate is used to control the update step size of the model parameters.

[0101] Optionally, in this embodiment, the computer-readable storage medium is configured to store a program code for executing the following steps: in the process of using the two-ticket generation model to generate a work ticket and an operation ticket, dynamically adjusting the regularization parameter of the two-ticket generation model using the second formula to adaptively optimize the two-ticket generation model, wherein the regularization parameter, the second formula is: a represents the regularization parameter, which is used to determine the degree of penalty for the two-vote generation model.

[0102] Optionally, in this embodiment, a computer-readable storage medium is configured to store program code for executing the following steps: sending a work ticket and an operation ticket to a front-end page for visual presentation so as to review the work ticket and the operation ticket; upon receiving an adjustment request for the two tickets, parsing the adjustment request for the two tickets to obtain an adjustment strategy for adjusting the work ticket and / or the operation ticket, and receiving update information, wherein the adjustment request for the two tickets is an adjustment request generated by an adjustment component sensed by the front-end page when the work ticket and the operation ticket fail to pass the review, and the update information is information that needs to be presented on the work ticket and / or the operation ticket; adjusting the work ticket and / or the operation ticket according to the adjustment strategy based on the updated information to obtain a target work ticket and / or a target operation ticket.

[0103] According to another aspect of an embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein when the program is run, any one of the above-mentioned two-ticket intelligent generation methods is executed.

[0104] According to another aspect of an embodiment of the present invention, a computer program product is also provided, comprising computer instructions, which, when executed by a processor, execute any one of the above-mentioned two-ticket intelligent generation methods.

[0105] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0106] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0107] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0108] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0109] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0110] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0111] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent method for generating two tickets, characterized in that: include: In response to two ticket generation operations acting on the front-end page, a screen recording instruction and an information acquisition instruction are generated, wherein the two tickets include: a work ticket and an operation ticket, the work ticket is used to record the maintenance task of maintaining the power equipment, and the operation ticket is used to record the operation task of operating the power equipment; Controlling the screen recording component to perform a screen recording operation according to the screen recording instruction to obtain screen video data, wherein the screen recording operation refers to controlling the screen recording component to record the operation sensed by the front-end page; Performing text extraction on the screen video data to obtain screen text information in the screen video data; Acquire the current operating status and work task information of the power system based on the information acquisition instruction, wherein the work task information refers to the information of the work task that needs to be recorded in the work ticket and the operation ticket; The screen text information, the work task information and the current running status are processed using a two-ticket generation model to generate the work ticket and the operation ticket, wherein the two-ticket generation model is trained by deep learning using multiple sets of training data, and each of the multiple sets of training data includes: sample input data, a sample work ticket and a sample operation ticket corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and sample current running status.

2. The intelligent method for generating two tickets according to claim 1 is characterized in that: After responding to the two-ticket generation operation acting on the front-end page to generate the screen recording instruction and the information acquisition instruction, it also includes: Acquiring a sensing habit of the front-end page according to a sensing identifier of the two-ticket generating operation sensed by the front-end page, wherein the sensing habit refers to a habit when the two-ticket generating operation acts on the front-end page; Optimizing the screen recording instruction according to the sensing habit to obtain the optimized screen recording instruction; Obtaining the sensing time when the front-end page senses the two-ticket generation operation; Determining an operation habit of the power system according to the time period in which the sensing time is located, wherein the operation habit refers to the operation state of the power system in different time periods; The information acquisition instruction is optimized according to the operation habit to obtain the optimized information acquisition instruction.

3. The intelligent method for generating two tickets according to claim 1 is characterized in that: Performing text extraction on the screen video data to obtain screen text information in the screen video data includes: Decomposing the screen video data to obtain multiple video frame images; Identify the text direction of the text in each of the video frame images to obtain a recognition result, wherein the text direction refers to the direction of the center line of the text; In a case where the recognition result pair indicates that there is no offset between the text direction and the specific direction, determining the video frame image as a target video frame image; In the case where the recognition result pair indicates that there is an offset between the text direction and the specific direction, correcting the video frame image until the text direction where the text is located in the video frame image is the same as the specific direction, determining the video frame image as the target video frame image, wherein the specific direction refers to the vertical direction; Text extraction is performed on each of the target video frame images to obtain the screen text information.

4. The intelligent method for generating two tickets according to claim 1 is characterized in that: Before using the two-ticket generation model to process the screen text information, the work task information and the current running status to generate the work ticket and the operation ticket, the method further includes: Acquire multiple sets of sample data, wherein each of the multiple sets of sample data includes: sample input data, a sample work ticket and a sample operation ticket corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and sample current running status; Dividing the plurality of groups of sample data to obtain sample training data and sample test data, wherein the sample training data is used to train the two-vote generation model, and the sample test data is used to test the two-vote generation model; Iteratively train the artificial intelligence generated content model using multiple groups of sample training data until the iteration termination condition is reached, and determine that the artificial intelligence generated content model obtained by the current training is an initial two-vote generation model, wherein the artificial intelligence generated content model is a deep learning model that automatically generates multiple types of content according to input information, and the multiple types of content include at least one of the following: text, image, and the iteration termination condition includes at least one of the following: the number of iterations reaches a preset number of iterations, and the model output error is lower than the error threshold; Using the sample test data to perform performance verification on the initial two-vote generation model to obtain verification results; When the verification result indicates that the performance of the initial two-vote generation model reaches a preset performance standard, the initial two-vote generation model is determined to be the two-vote generation model.

5. The intelligent method for generating two tickets according to claim 4 is characterized in that: Also includes: Before iteratively training the AI-generated content model using multiple groups of sample training data, the model parameters of the AI-generated content model are randomly initialized using an improved chaotic map, wherein a first expression of the improved chaotic map is: x i represents the state value of the i-th generation population, x i+1 The state value representing the next generation population of the i-th generation population; In the process of iteratively training the artificial intelligence generated content model using multiple groups of sample training data, the learning rate of the artificial intelligence generated content model is optimized using a first formula, wherein the first formula is: GP represents the learning rate, n represents the current iteration number, and n max Represents the maximum number of iterations, and the learning rate is used to control the update step size of the model parameters.

6. The intelligent method for generating two tickets according to claim 1 is characterized in that: Also includes: In the process of using the two-ticket generation model to generate the work ticket and the operation ticket, the regularization parameter of the two-ticket generation model is dynamically adjusted using the second formula to adaptively optimize the two-ticket generation model, wherein the regularization parameter, the second formula is: a represents the regularization parameter, which is used to determine the degree of penalty for the two-vote generation model.

7. The intelligent method for generating two tickets according to claim 1 is characterized in that: After the screen text information, the work task information and the current running status are processed by using the two-ticket generation model to generate the work ticket and the operation ticket, the method further includes: Sending the work ticket and the operation ticket to the front-end page for visual presentation so as to review the work ticket and the operation ticket; In the case of receiving two-ticket adjustment requests, parsing the two-ticket adjustment requests, obtaining an adjustment strategy for adjusting the work ticket and / or the operation ticket, and receiving update information, wherein the two-ticket adjustment request is an adjustment request generated by the adjustment component sensed by the front-end page when the work ticket and the operation ticket are not reviewed and approved, and the update information is information that needs to be presented on the work ticket and / or the operation ticket; The work ticket and / or the operation ticket are adjusted according to the update information and the adjustment strategy to obtain a target work ticket and / or a target operation ticket.

8. An intelligent device for generating two tickets, characterized in that: include: A first generating unit is used to generate a screen recording instruction and an information acquisition instruction in response to two ticket generating operations acting on the front-end page, wherein the two tickets include: a work ticket and an operation ticket, the work ticket is used to record a maintenance task for maintaining the power equipment, and the operation ticket is used to record an operation task for operating the power equipment; A first acquisition unit is used to control the screen recording component to perform a screen recording operation according to the screen recording instruction to obtain screen video data, wherein the screen recording operation refers to controlling the screen recording component to record the operation sensed by the front-end page; A second acquisition unit, configured to extract text from the screen video data to obtain screen text information in the screen video data; A third acquisition unit, configured to acquire the current operating state and work task information of the power system based on the information acquisition instruction, wherein the work task information refers to the information of the work task that needs to be recorded in the work ticket and the operation ticket; The second generation unit is used to use the two-ticket generation model to process the screen text information, the work task information and the current running status to generate the work ticket and the operation ticket, wherein the two-ticket generation model is trained by deep learning using multiple sets of training data, and each of the multiple sets of training data includes: sample input data, a sample work ticket and a sample operation ticket corresponding to the sample input data, and the sample input data includes: sample screen text information, sample work task information and sample current running status.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the intelligent method for generating two tickets as described in any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by the processor, the intelligent method for generating two tickets as described in any one of claims 1 to 7 is performed.

Images