Resident step tariff intelligent management method and system based on RPA

Abstract

The invention belongs to the technical field of power grid service, and particularly relates to a resident step tariff intelligent management method and system based on RPA. The invention discloses an RPA-based resident step tariff intelligent management method and system, and the method comprises the steps: designing a process automatic login marketing system through employing an RPA platform and a prediction model, querying user information, and predicting the future power utilization trend of a user; step electricity prices of the users are calculated and compared with standard electricity prices, and whether early warning reminding needs to be sent to the users or not is judged; storing the electric quantity data, storing the electric quantity data in the user information table in a database, processing the electric quantity data of the user by using a prediction model, an optimization model and an evaluation model, visualizing the electric charge information of the user, and sending out an early warning prompt; according to the invention, the management efficiency of resident step tariff is improved, and the management cost is reduced. And the energy-saving awareness of residents is improved by evaluating and feeding back the power consumption and the energy-saving effect of the user.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of power grid services, and particularly relates to a resident ladder electricity price intelligent management method and system based on RPA. BACKGROUND

[0002] According to the 2022 public industry satisfaction evaluation report, customers complain more strongly about "ladder electricity price". Customers complain that "ladder electricity price" is unreasonable and expensive. The main reason is that customers lack understanding of the "ladder electricity price" policy and are not clear about the grading and corresponding electricity price. When reaching the next ladder critical value, most customers do not understand the warning prompt issued by the power supply bureau, and do not handle the relevant electricity business in time, resulting in increased electricity cost. At present, only manual monitoring by customer managers is used, and one household is notified when one household is found, which is low in efficiency and has high service risk. SUMMARY

[0003] In view of the above problems, the present application is proposed.

[0004] Therefore, the technical problem solved by the present application is how to solve the technical problems of low electricity management efficiency, inaccurate electricity prediction and difficult-to-understand electricity warning.

[0005] To solve the above technical problems, the present application provides the following technical solutions: using an RPA platform and a prediction model, designing a process to automatically log in to a marketing system, querying user information records, predicting future electricity consumption trends of users, calculating user ladder electricity prices, and comparing them with standard electricity prices to determine whether to send a warning reminder to users; storing electricity data, saving electricity data in a user information table in a database, and using a prediction model, an optimization model and an evaluation model to process user electricity data, visualizing user electricity information and issuing a warning reminder;

[0006] Periodic code review and performance optimization are performed, and an intelligent error handling mechanism is designed, and a data backup and fast rollback scheme is implemented.

[0007] As a preferred scheme of the resident ladder electricity price intelligent management method based on RPA, the user information record table should include user number, user name, user mobile phone number, user email, user address, user electricity type, user electricity consumption, user electricity cost, and user ladder electricity price.

[0008] As a preferred scheme of the resident ladder electricity price intelligent management method based on RPA, the design process of automatically logging in to the marketing system includes dividing the entire business process into five sub-processes, including user information reading, system login, data query, data processing and data storage; each sub-process is used as an independent module and is called in the main process.

[0009] Correlate the sub-process with the main process to generate a.dgrpa program package file;

[0010] Read the user list from the user information record table under the specified directory, open the user information record table using the Excel operation component provided by the RPA platform, read the data of all rows and columns, and store them into a two-dimensional array variable;

[0011] Simulate user operation using RPA to log in to the marketing system.

[0012] As a preferred scheme of the RPA-based resident tiered electricity price intelligent management method, the designed process automatically logs in to the marketing system, which further includes an integrated deep learning model to automatically identify and solve the slider verification code; the deep learning model is an image processing model based on convolutional neural network and regression analysis, and is expressed as:

[0013] Z [l] =W [l] A [l-1] +b [l]

[0014] A [l] =g [l] (Z [l] )

[0015]

[0016] Wherein, Z [l] is the linear output of the lth layer; W [l] is the weight matrix of the lth layer; A [l-1] is the activation output of the (l-1)th layer; b [l] is the bias vector of the lth layer; g [l] is the activation function of the lth layer; is the predicted value; W [L] is the weight matrix of the last layer; A [L-1] is the activation output of the second last layer; b [L] is the bias vector of the last layer.

[0017] As a preferred scheme of the RPA-based resident tiered electricity price intelligent management method, the query of the user's electricity and electricity charge information includes obtaining the user whose electricity type is resident life, whose tiered type is annual tier, and whose metering point executes the electricity price name of urban residents one household one meter less than 1 kilovolt, and using the database tool MySQL to store and manage the user information;

[0018] Use OCR and image recognition technology to identify the slider verification code to realize the slider verification code login;

[0019] In the marketing system opens the electric quantity electricity fee query page, uses XPath and CSS selector to capture webpage element, constructs mouse click event, triggers menu button click, and sets the query condition of the electric quantity query, sequentially sets the user number as the query basis, the electricity fee year month start, the electricity fee year month stop, and the user number as the query basis;

[0020] The electric quantity data is queried according to the user number, the user information table is traversed and circulates, the input box text with id yhbhIptBtn_input is set to a single user number, and the mouse click query button is operated;

[0021] The abnormal handling and retry mechanism are used to handle the appearance and disappearance of the query result waiting box element, the user number in the input box is compared with the user number in the query result, if they are consistent, the next step is performed, if they are inconsistent, the previous step is rolled back, if the user number cannot be captured in the query result, it indicates that the user suspends electricity in the electricity calculation time period, the metering electricity fee meter is zero, and the next step is continued; the metering electric quantity element text attribute is read and stored in the user information table.

[0022] As a preferred scheme of the RPA-based intelligent management method for resident step-by-step electricity price, wherein: the prediction model uses a neural network prediction model to predict and analyze the electricity consumption of the user in the next three months, represented as:

[0023] y=f(Wx+b)

[0024]

[0025]

[0026]

[0027] Where y is the prediction result of the output layer, x is the current month of the input layer, W is the connection weight matrix, b is the bias vector, f is the activation function, L is the loss function, is the true result, and alpha is the learning rate;

[0028] The optimization model uses a linear programming optimization model to optimize and manage the electricity distribution and scheduling of the user, thereby reducing the electricity cost and improving the power efficiency, and the linear programming optimization model is represented as:

[0029]

[0030]

[0031] y i1 ≤1000,i=1,2,...,12

[0032] y i2≤1000, i = 1, 2,..., 12

[0033] y i3 ≥0, i = 1, 2,..., 12

[0034]

[0035]

[0036] x ij ≤C / 4, i = 1, 2,..., 12; j = 1, 2, 3, 4

[0037] x ij ≥0, i = 1, 2,..., 12; j = 1, 2, 3, 4

[0038] Where x is the decision variable, representing the user's electricity consumption in different time periods and different ladder intervals; p is the electricity price coefficient, representing the user's electricity price in different time periods; y is the decision variable, representing the user's electricity consumption in different ladder intervals; q is the electricity price coefficient, representing the user's electricity price in different ladder intervals; T is the total demand, representing the user's total electricity consumption in a year; S is the total supply, representing the user's total supply in a year; C is the total capacity, representing the user's total capacity in a year.

[0039] The analytic hierarchy process evaluation model is used to evaluate and feedback the user's electricity consumption and energy saving effect. The formula of the analytic hierarchy process evaluation model is as follows:

[0040] S = W0W1A1 + W0W2A2 + W0W3A3

[0041] Where S is the comprehensive evaluation value of the user's electricity consumption and energy saving effect; W0 is the weight vector of each criterion for the total target; W1, W2, W3 are the weight vectors of each scheme under the three criteria of electricity cost, power efficiency and energy saving awareness; A1, A2, A3 are the evaluation vectors of the original scheme and the optimized scheme under the three criteria of electricity cost, power efficiency and energy saving awareness; CI is the consistency index of the judgment matrix; CR is the consistency ratio of the judgment matrix.

[0042] As a preferred scheme of the RPA-based resident ladder electricity price intelligent management method, a code review component is used to check syntax errors, logical errors, redundant code in the RPA script, and to modify or delete them. A performance optimization component provided by the RPA platform is used to analyze the running time, resource occupation and error rate index of the RPA process, and to optimize or adjust them;

[0043] An exception handling component is used to capture exceptions occurring in the RPA process and handle them according to the exception type and severity;

[0044] A data backup component is used to periodically backup user information records and other related data to a secure location;

[0045] A quick rollback component is used to quickly recover to the last normal running state when a serious error or data corruption occurs in the RPA process.

[0046] Another object of the present application is to provide an RPA-based resident step electricity price intelligent management method system that can automatically log in to the marketing system, query user electricity and electricity information, and predict future electricity consumption trends through the RPA platform module; use a neural network prediction model to predict and analyze user electricity consumption in the next three months; and use a linear programming optimization model to optimize and manage user electricity distribution and scheduling.

[0047] To solve the above technical problems, the present application provides the following technical solutions: an internal and external network exchange platform service detection system, including an RPA platform module, a prediction model module, an optimization model module, an evaluation model module, a data storage module, a code review and performance optimization module, and a data backup and quick rollback module;

[0048] The RPA platform module is used to automatically execute various tasks, including automatically logging in to the marketing system, querying user electricity and electricity information, and predicting future electricity consumption trends;

[0049] The prediction model module uses a neural network prediction model to predict and analyze user electricity consumption in the next three months;

[0050] The optimization model module uses a linear programming optimization model to optimize and manage user electricity distribution and scheduling, thereby reducing electricity costs and improving power efficiency;

[0051] The evaluation model module uses an analytic hierarchy process evaluation model to evaluate and feedback user electricity consumption and energy saving effects;

[0052] The data storage module is responsible for storing electricity data and saving electricity data in the user information table in the database;

[0053] The code review and performance optimization module regularly performs code review and performance optimization, and designs an intelligent error handling mechanism;

[0054] The data backup and quick rollback module implements a data backup and quick rollback scheme, and quickly recovers to the last normal running state when a serious error or data corruption occurs in the RPA process.

[0055] A computer device comprises a memory and a processor, the memory stores a computer program, characterized in that the processor implements the steps of the RPA-based resident tiered electricity price intelligent management method when executing the computer program.

[0056] A computer readable storage medium having a computer program stored thereon, characterized in that the computer program implements the steps of the RPA-based resident tiered electricity price intelligent management method when executed by a processor.

[0057] The beneficial effects of the present application are: improving the management efficiency of resident tiered electricity price, reducing the management cost. By accurately predicting the future electricity consumption trend of the user, helping the user to make electricity plan in advance, avoiding unnecessary electricity cost. By optimizing the electricity distribution and scheduling of the user, reducing the electricity cost, improving the power efficiency. By evaluating and feeding back the electricity consumption and energy saving effect of the user, improving the energy saving awareness of the residents. BRIEF DESCRIPTION OF DRAWINGS

[0058] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. Among them:

[0059] Figure 1 The flow chart of the RPA-based resident tiered electricity price intelligent management method provided by an embodiment of the present application.

[0060] Figure 2 The processing flow chart of the RPA-based resident tiered electricity price intelligent management method provided by an embodiment of the present application.

[0061] Figure 3 The processing process chart of the RPA-based resident tiered electricity price intelligent management method provided by an embodiment of the present application.

[0062] Figure 4 The processing process chart of the RPA-based resident tiered electricity price intelligent management method provided by an embodiment of the present application.

[0063] Figure 5 The processing result chart of the RPA-based resident tiered electricity price intelligent management method provided by an embodiment of the present application.

[0064] Figure 6 The structural schematic diagram of the RPA-based resident tiered electricity price intelligent management system provided by an embodiment of the present application. DETAILED DESCRIPTION

[0065] In order to make the above objectives, characteristics and advantages of the present application more obvious and comprehensible, the specific embodiments of the present application will be described in detail below with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all the other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present application.

[0066] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. The present application, however, can be practiced in a variety of ways beyond the specific details set forth herein without departing from the scope of the present application, and it is understood that the application is not limited in this respect.

[0067] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. The "in one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an embodiment that is independent of or selected from other embodiments.

[0068] The present application is described in detail in conjunction with the schematic drawings. In the detailed description of the embodiments of the present application, the sectional view of the device structure is partially enlarged without the general proportion for the convenience of description, and the schematic drawings are only examples, which should not limit the scope of protection of the present application herein. In addition, the three-dimensional spatial dimensions of length, width and depth should be included in actual manufacturing.

[0069] Meanwhile, in the description of the present application, it should be noted that the terms "upper, lower, inner and outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first, second or third" are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0070] In the present application, unless otherwise explicitly specified and limited, the terms "mounting, connecting, connection" should be understood broadly, for example: it can be fixed connection, detachable connection or integral connection; it can also be mechanical connection, electrical connection or direct connection, it can also be indirectly connected through an intermediate medium, or it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0071] Example 1

[0072] Reference Figure 1For an embodiment of the present application, an RPA-based resident step electricity price intelligent management method is provided, comprising:

[0073] S1: using an RPA platform and a prediction model, designing a process to automatically log in to a marketing system, querying user information records, and predicting future electricity consumption trends of users;

[0074] Further, the user information record table should include user number, user name, user mobile phone number, user email, user address, user electricity type, user electricity consumption, user electricity cost, and user step electricity price.

[0075] S2: calculating the user step electricity price and comparing it with the standard electricity price to determine whether to send a warning reminder to the user;

[0076] Further, the designed process to automatically log in to the marketing system includes dividing the entire business process into five sub-processes, including user information reading, system login, data query, data processing, and data storage; each sub-process is an independent module and is called in the main process.

[0077] Associate the sub-process with the main process to generate a.dgrpa program package file.

[0078] Read the user list from the user information record table in the specified directory, use the Excel operation component provided by the RPA platform to open the user information record table, read the data of all rows and columns, and store it in a two-dimensional array variable.

[0079] Use RPA to simulate user operations to log in to the marketing system.

[0080] Further, the designed process to automatically log in to the marketing system also includes integrating a deep learning model to automatically recognize and solve the slider verification code; the deep learning model is an image processing model based on convolutional neural networks and regression analysis, represented as:

[0081] Z [l] =W [l] A [l-1] +b [l]

[0082] A [l] =g [l] (Z [l] )

[0083]

[0084] Where Z [l] is the linear output of the lth layer; W [l] is the weight matrix of the lth layer; A [l-1] is the activation output of the l-1th layer; b[l] is the bias vector of the first layer; g [l] is the activation function of the first layer; is the predicted value; W [L] is the weight matrix of the last layer; A [L-1] is the activation output of the second last layer; b [L] is the bias vector of the last layer.

[0085] Further, the power and electricity fee information of the query user includes obtaining a user whose power consumption type is residential life, whose ladder type is annual ladder, and whose meter execution electricity price name is not more than 1 kilovolt for a household of urban residents, and using a database tool MySQL to store and manage user information;

[0086] The OCR and image recognition technology are used to identify the sliding block verification code, and the sliding block verification code login is realized.

[0087] In the marketing system, the power and electricity fee query page is opened, the web page elements are captured using XPath and CSS selectors, the mouse click event is constructed, the button click of the menu is triggered, and the query conditions of the power query are set, and the user number is set as the query basis, the electricity fee start month, and the electricity fee end month.

[0088] The power data is queried according to the user number, the user information table is traversed and cycled, the input box text with id yhbhIptBtn_input is set to a single user number, and the mouse click query button is operated.

[0089] The exception handling and retry mechanism are used to handle the appearance and disappearance of the query result waiting box element, the user number in the input box is compared with the user number in the query result, if they are consistent, the next step is performed, if they are inconsistent, the previous step is rolled back, and if the user number cannot be captured in the query result, it indicates that the user suspends power consumption in the electricity fee calculation time period, the metering electricity fee is zero, and the next step is continued; the metering power element text attribute is read and stored in the user information table.

[0090] Further, the prediction model uses a neural network prediction model to predict and analyze the power consumption of the user in the next three months, which is represented as:

[0091] y = f(Wx + b)

[0092]

[0093]

[0094]

[0095] where y is the prediction result of the output layer, x is the current month of the input layer, W is the connection weight matrix, b is the bias vector, f is the activation function, L is the loss function, is the true result, and a is the learning rate.

[0096] The optimization model uses a linear programming optimization model to optimize and manage the user's electricity allocation and scheduling, thereby reducing electricity costs and improving power efficiency, and the linear programming optimization model is expressed as:

[0097]

[0098]

[0099] y i1 ≤1000, i = 1, 2,..., 12

[0100] y i2 ≤1000, i = 1, 2,..., 12

[0101] y i3 ≥0, i = 1, 2,..., 12

[0102]

[0103]

[0104] x ij ≤C / 4, i = 1, 2,..., 12; j = 1, 2, 3, 4

[0105] x ij ≥0, i = 1, 2,..., 12; j = 1, 2, 3, 4

[0106] where x is the decision variable, representing the user's electricity consumption in different time periods and different step intervals; p is the electricity price coefficient, representing the user's electricity price in different time periods; y is the decision variable, representing the user's electricity consumption in different step intervals; q is the electricity price coefficient, representing the user's electricity price in different step intervals; T is the total demand, representing the user's total electricity consumption in a year; S is the total supply, representing the user's total supply in a year; C is the total capacity, representing the user's total capacity in a year.

[0107] S3: store electricity data, save the electricity data in the user information table in the database, and use the prediction model, optimization model and evaluation model to process the user electricity data, visualize the user electricity information and issue warning reminders;

[0108] It should be noted that, among them, the objective function represents the total electricity bill that the user needs to pay, which consists of two parts: one is the electricity bill calculated by time period, and the other is the electricity bill calculated by step interval;

[0109] The first constraint condition represents that the total electricity consumption of the user in each month is equal to the sum of the electricity consumption of each step interval;

[0110] The second, third, and fourth constraint conditions represent that the electricity consumption of the user in each month in each step interval must meet the regulations of the step electricity price;

[0111] The fifth constraint condition represents that the total electricity consumption of the user in a year is equal to the given demand T;

[0112] The sixth constraint condition represents that the total electricity consumption of the user in a year does not exceed the given supply S;

[0113] The seventh constraint condition represents that the electricity consumption of the user in each time period does not exceed one-fourth of the given capacity C;

[0114] The eighth constraint condition represents that the electricity consumption of the user in each time period must be non-negative.

[0115] The simplex method is used to solve the linear programming optimization model. The simplex method is an algorithm that uses a simplex table to iteratively find the optimal solution. The simplex method can be implemented by the following steps:

[0116] Convert the linear programming optimization model to the standard form, that is, convert all constraint conditions to the form of equations, convert all decision variables to non-negative numbers, and convert the objective function to the form of maximization. This can be achieved by introducing slack variables, surplus variables, artificial variables, etc.

[0117] Construct an initial simplex table, that is, combine the coefficient matrix, constant term, objective function coefficient, etc. in the standard form into a table, where the base variable corresponds to the row mark and the non-base variable corresponds to the column mark.

[0118] Check the optimality condition, that is, check whether there is a positive number in the objective function row of the simplex table. If there is, it means that the current solution is not optimal and needs to continue iteration; if there is not, it means that the current solution is optimal and iteration can be stopped.

[0119] Select the entering base variable and the leaving base variable, that is, select the column corresponding to the largest positive number in the objective function row as the entering base variable, and select the row with the smallest ratio of positive element to constant term in that column as the leaving base variable.

[0120] Perform row transformation, that is, divide the row of the leaving base variable by the element in the column of the leaving base variable to obtain a new pivot element; subtract the product of the row of the leaving base variable and the corresponding column element from other rows to obtain a new simplex table.

[0121] Repeat the third, fourth, fifth step until the optimality condition is met or the iteration cannot continue.

[0122] The analytic hierarchy process evaluation model is used to evaluate and feedback the power consumption and energy saving effect of the user.

[0123] S=W0W1A1+W0W2A2+W0W3A3 Wherein, S is the comprehensive evaluation value of the power consumption and energy saving effect of the user; W0 is the weight vector of each criterion for the total target; W1, W2, W3 are the weight vectors of each scheme under the three criteria of electricity cost, power efficiency and energy saving consciousness; A1, A2, A3 are the evaluation vectors of the original scheme and the optimized scheme under the three criteria of electricity cost, power efficiency and energy saving consciousness; CI is the consistency index of the judgment matrix; CR is the consistency ratio of the judgment matrix.

[0124] S4: Regularly perform code review and performance optimization, and design intelligent error handling mechanism, and implement data backup and fast rollback scheme.

[0125] As a preferred scheme of the RPA-based resident step electricity price intelligent management method, wherein: using the code review component, checking the syntax error, logic error, redundant code in the RPA script, and correcting or deleting. Using the performance optimization component provided by the RPA platform, analyzing the running time, resource occupation, error rate index of the RPA process, and optimizing or adjusting;

[0126] Using the exception handling component, capture the exception occurred in the RPA process, and handle according to the exception type and severity;

[0127] Using the data backup component, regularly backup the user information record table and other related data to a safe place;

[0128] When the RPA process occurs serious error or data damage, the fast rollback component quickly recovers to the last normal running state.

[0129] Embodiment 2

[0130] The second embodiment of the application is different from the previous embodiment:

[0131] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the technical solutions that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0132] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a list of executable instructions for implementing logic functions, which can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus or device, such as a computer-based system, a system including a processor or other system that can fetch the instructions from the instruction execution system, apparatus or device and execute the instructions, or in conjunction with these instructions execution systems, apparatus or devices. For the purpose of this specification, the "computer-readable medium" can be any device that can contain, store, communicate, propagate or transport programs for use by or in connection with an instruction execution system, apparatus or device, or in conjunction with these instruction execution systems, apparatus or devices.

[0133] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection having one or more wires (electrical devices), a portable computer diskette (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium can even be paper or other suitable medium on which the program can be printed, because the program can be electronically obtained, for example, by optical scanning of the paper or other medium, followed by editing, interpreting or otherwise processing, if necessary, in other suitable ways, to be electronically obtained and then stored in the computer memory.

[0134] It should be understood that various parts of the present application can be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, a plurality of steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and as in another embodiment, it can be implemented using any one or a combination of the following technologies known in the art: discrete logic circuit with logic gate circuit for implementing logical functions on data signals, application specific integrated circuit with suitable combination logic gate circuit, programmable gate array (PGA), field programmable gate array (FPGA), etc.

[0135] Embodiment 3

[0136] Referring to Figure 6 For the third embodiment of the present application, the embodiment provides a resident step electricity price intelligent management system based on RPA, including an RPA platform module, a prediction model module, an optimization model module, an evaluation model module, a data storage module, a code review and performance optimization module, and a data backup and fast rollback module.

[0137] The RPA platform module is used to automatically execute various tasks, including automatically logging into the marketing system, querying the user's electricity consumption information, and predicting the user's future electricity consumption trend;

[0138] The prediction model module uses a neural network prediction model to predict and analyze the user's electricity consumption in the next three months;

[0139] The optimization model module uses a linear programming optimization model to optimize and manage the user's electricity distribution and scheduling, thereby reducing electricity costs and improving power efficiency;

[0140] The evaluation model module uses an analytic hierarchy process evaluation model to evaluate and feedback the user's electricity consumption and energy saving effect;

[0141] The data storage module is responsible for storing electricity data, saving electricity data in the user information table in the database;

[0142] The code review and performance optimization module regularly performs code review and performance optimization, and designs an intelligent error handling mechanism;

[0143] The data backup and fast rollback module implements a data backup and fast rollback scheme, and when a serious error or data damage occurs in the RPA process, it quickly recovers to the last normal running state.

[0144] Embodiment 4

[0145] Referring to Figures 2-5 For the fourth embodiment of the present application, a resident step electricity price intelligent management method based on RPA is provided.

[0146] 1、The application is divided into multiple program modules, i.e. multiple sub-processes, and the full-scene process is realized by calling the sub-processes through the main process. The divided sub-processes include: reading a user list, logging into a marketing system, opening a power and electricity fee query page, reading user power and electricity fees, and persistently storing power and electricity fee data. The sub-processes are associated with the main process to generate a project.dgrpa program package file.

[0147] 2、Preparation before running the script: store the user information record table in a specified directory.

[0148] 3、Run the program package file through the Daquan RPA platform

[0149] (1) Start the development platform to display the login interface;

[0150] Click the settings button in the upper right corner to pop up the "connection control center" panel;

[0151] (3) The intranet control center address deployed by the company is: http: / / 10.100.117.99;

[0152] (4) Confirm that the control center address is accurate and log in using the account and password of the control center;

[0153] (5) Chrome Driver configuration. Installation conditions: install the corresponding version of Chrome browser; before installation, you need to turn off the Chrome browser first; installation path: settings > plugin management > Chrome browser extensions > install;

[0154] (6) After installing the development platform, open the Chrome browser and enter: "chrome: / / extensions", or open the extension program page in the upper right corner settings > more tools > extensions; turn on the "developer mode" in the upper right corner, and then click the switch of the element capture plug-in to use it.

[0155] (7) Import and run the prepared program package script.

[0156] 4、Run the script to realize the business process, and the following shows the processing steps:

[0157] (1) Obtain users with residential life as the power consumption type, annual ladder as the ladder type, and "city residents one household one meter not full one kilovolt" as the metering point executed electricity price name, and generate an object array with the unique identification of the user number.

[0158] try:

[0159] _rpa_e13d14_excel = rpa.excel.open(getResourcePath(__file__,"resources","User Information Record Table.xlsx"),visible = False,readonly = True,pass_word = "",wps = True,run_type = 1)

[0160] _rpa_6f1d2a_array_any=_rpa_e13d14_excel.get_sheet("").read("D",skip=1,max=100000)

[0161] (2) Log in to the marketing system and be redirected to 4A authentication. To adapt to different computer resolutions, ① the slider is located by searching for the image and dragged horizontally with the mouse to implement slider verification code login; ② JavaScript is used to manipulate the mousedown, mousemove, and moveup events to implement slider verification code login.

[0162]

[0163]

[0164] Open the electricity consumption and bill inquiry page in the marketing system. Accurately capture elements based on the IDs of input, img, and select elements, construct mouse click events to trigger the button clicks in the menu, and set the query conditions for electricity consumption, namely, querying by user ID, electricity bill start date, and electricity bill end date.

[0165] #-*- Search the page using the global search box and redirect.

[0166]

[0167]

[0168] (4) Query the power data by user number. Traverse the circular array, set the input box text with id yhbhIptBtn_input to the array content, that is, a single user number, and click the query button with the mouse. ① Wait for the query result. If the query result waiting box element appears and disappears, proceed to the next step. If it does not disappear for a long time, refresh the interface and query again; ② Compare the user number in the input box with the user number in the query result. If they are consistent, proceed to the next step. If they are not consistent, roll back to the previous step. If the user number cannot be captured in the query result, it indicates that the user has suspended electricity during the electricity calculation period, and the metering electricity is zero. Continue to the next step; ③ Read the metering power element text attribute and store it in the object array with the user number as the unique identifier.

[0169]

[0170]

[0171] (5) Persistent storage of power data, storing the object array with the user number as the unique identifier in the user information record table, and judging according to the formula whether the current power data falls in which step power interval.

[0172]

[0173] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application, and they should be covered in the scope of the claims of the present application.

Claims

1. A smart management method for tiered electricity pricing for residential use based on RPA, characterized in that, include: Using an RPA platform and predictive models, a process was designed to automatically log into the marketing system, query user information records, and predict users' future electricity consumption trends. Calculate the tiered electricity price for users and compare it with the standard electricity price to determine whether it is necessary to send a warning reminder to users. The electricity consumption data in the user information table is stored in the database, and the user electricity consumption data is processed using prediction models, optimization models and evaluation models. The user electricity bill information is visualized and early warning reminders are issued. Regularly conduct code reviews and performance optimizations, design intelligent error handling mechanisms, and implement data backup and rapid rollback schemes.

2. The intelligent management method for residential tiered electricity pricing based on RPA as described in claim 1, characterized in that: The user information record table includes user ID, user name, user mobile phone number, user email, user address, user electricity type, user electricity consumption, user electricity cost, and user tiered electricity price.

3. The intelligent management method for residential tiered electricity pricing based on RPA as described in claim 2, characterized in that: The design process of the automated login marketing system includes dividing the entire business process into five sub-processes, which include user information reading, system login, data query, data processing, and data storage; each sub-process is an independent module that is called in the main process. Associate the sub-process with the main process to generate a .dgrpa package file; Read the user list from the user information record table in the specified directory, use the Excel operation component provided by the RPA platform to open the user information record table, read all rows and columns of data, and store them into a two-dimensional array variable; Use RPA to simulate user actions and log into the marketing system.

4. The intelligent management method for residential tiered electricity pricing based on RPA as described in claim 3, characterized in that: The automated login marketing system design process also includes an integrated deep learning model to automatically identify and resolve slider CAPTCHAs; the deep learning model is an image processing model based on convolutional neural networks and regression analysis, represented as follows: Z [l] =W [l] A [l-1] +b [l] A [l] =g [l] (Z [l] ) Among them, Z [l] It is the linear output of the l-th layer; W [l] A is the weight matrix of the l-th layer; [l-1] It is the activation output of layer (l-1); b [l] It is the bias vector of the l-th layer; g [l] It is the activation function of the l-th layer; It is a predicted value; W [L] It is the weight matrix of the last layer; A [L-1] It is the activation output of the second to last layer; b [L] It is the bias vector of the last layer.

5. The intelligent management method for residential tiered electricity pricing based on RPA as described in claim 4, characterized in that: The query of users’ electricity consumption and electricity bill information includes obtaining users whose electricity consumption type is residential, whose tiered electricity type is annual tiered, and whose metering point’s electricity price name is urban residential one-meter-less-1kV, and using the database tool MySQL to store and manage user information. Using OCR and image recognition technology to recognize slider CAPTCHAs, enabling slider CAPTCHA login; Open the electricity and electricity bill query page in the marketing system, use XPath and CSS selectors to capture web page elements, construct mouse click events, trigger the button clicks in the menu, and set the query conditions for electricity consumption, setting them in the following order: user ID as the query basis, electricity bill start date, and electricity bill end date. Query electricity data by user ID, iterate through the user information table, set the text of the input box with id yhbhIptBtn_input to a single user ID, and click the query button with the mouse; The system uses exception handling and retry mechanisms to handle the appearance and disappearance of the query result waiting box element. It compares the user ID in the input box with the user ID in the query result. If they match, it proceeds to the next step; otherwise, it rolls back to the previous step. If the user ID cannot be found in the query result, it means that the user has suspended electricity use during the electricity bill calculation period, and the metered electricity bill is zero, so it continues to the next step. The system reads the text attribute of the metered electricity element and stores it in the user information table.

6. The intelligent management method for residential tiered electricity pricing based on RPA as described in claim 5, characterized in that: The prediction model uses a neural network prediction model to predict and analyze the user's electricity consumption over the next three months, as shown below: y = f(Wx + b) Where y is the prediction result of the output layer, x is the current month of the input layer, W is the connection weight matrix, b is the bias vector, f is the activation function, and L is the loss function. This is the actual result, where α is the learning rate; The optimization model uses a linear programming optimization model to optimize and manage the allocation and scheduling of electricity for users, thereby reducing electricity costs and improving power efficiency. The linear programming optimization model is expressed as follows: y i1 ≤1000,i=1,2,...,12 y i2 ≤1000,i=1,2,...,12 y i3 ≥0,i=1,2,...,12 x ij ≤C / 4,i=1,2,...,12;j=1,2,3,4 x ij ≥0,i=1,2,...,12;j=1,2,3,4 Where x is the decision variable, representing the user's electricity consumption in different time periods and different price tiers; p is the electricity price coefficient, representing the user's electricity price in different time periods; y is the decision variable, representing the user's electricity consumption in different price tiers; q is the electricity price coefficient, representing the user's electricity price in different price tiers; and T is the total demand, representing the user's total electricity consumption in one year. S is the total supply, representing the total supply to users within one year; C is the total capacity, representing the total capacity to users within one year. The Analytic Hierarchy Process (AHP) is used to evaluate and provide feedback on users' electricity consumption and energy-saving effects. The formula for the AHP evaluation model is as follows: S=W0W1A1+W0W2A2+W0W3A3 Where S is the comprehensive evaluation value of the user's power consumption and energy-saving effect; W0 is the weight vector of each criterion with respect to the overall goal; W1, W2, and W3 are the weight vectors of each scheme under the three criteria of electricity cost, power efficiency, and energy-saving awareness; A1, A2, and A3 are the evaluation vectors of the original scheme and the optimized scheme under the three criteria of electricity cost, power efficiency, and energy-saving awareness; CI is the consistency index of the judgment matrix; and CR is the consistency ratio of the judgment matrix.

7. The intelligent management method for residential tiered electricity pricing based on RPA as described in claim 6, characterized in that: Use code review components to check for syntax errors, logical errors, and redundant code in RPA scripts, and correct or delete them; use performance optimization components provided by the RPA platform to analyze the runtime, resource consumption, and error rate of the RPA process, and optimize or adjust them. Use exception handling components to capture exceptions that occur in the RPA process and handle them according to the exception type and severity. The data backup component used regularly backs up the user information record table and other related data to a safe location. When a critical error or data corruption occurs in an RPA process, the fast rollback component quickly restores the system to its previous normal operating state.

8. A system employing the RPA-based intelligent management method for residential tiered electricity pricing as described in any one of claims 1 to 7, characterized in that: It includes an RPA platform module, a prediction model module, an optimization model module, an evaluation model module, a data storage module, a code review and performance optimization module, and a data backup and fast rollback module; The RPA platform module is used to automate various tasks, including automatically logging into the marketing system, querying users' electricity consumption and bill information, and predicting users' future electricity consumption trends. The prediction model module uses a neural network prediction model to predict and analyze the user's electricity consumption for the next three months. The optimization model module uses a linear programming optimization model to optimize and manage the user's power allocation and scheduling, thereby reducing electricity costs and improving power efficiency. The evaluation model module uses the analytic hierarchy process (AHP) to evaluate and provide feedback on the user's power consumption and energy-saving effects. The data storage module is responsible for storing power consumption data and saving the power consumption data in the user information table to the database; The code review and performance optimization module performs code reviews and performance optimizations regularly, and is designed with an intelligent error handling mechanism; The data backup and fast rollback module implements a data backup and fast rollback scheme, which can quickly restore the RPA process to the previous normal operating state when a serious error or data corruption occurs.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images