Intelligent short message electricity marketing application system

By using data collection, analysis and visual display modules in the smart SMS power marketing application system, a personalized energy-saving suggestions model is built, which solves the accuracy of data analysis and user classification, improves the pertinence and user experience of energy-saving suggestions, and realizes the realization of energy-saving suggestions. In-depth exploration and prediction of users' electricity consumption behavior has been improved, and the overall quality and efficiency of power marketing services have been improved.

CN119027273APending Publication Date: 2024-11-26BEIJING HUITONG JINCAI INFORMATION TECH
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411077886.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The smart SMS power marketing application system has low accuracy in data analysis and user classification, insufficient personalization of energy-saving suggestions, and limited user experience and interactivity, resulting in low user acceptance.

Method used

Using data acquisition module, data analysis module, energy-saving suggestions module and visual display module, electricity consumption data is collected through smart electricity meters, data characteristics are extracted using real-time analysis platform, electricity consumption data is predicted, personalized energy-saving suggestions model is constructed, and the power consumption is transmitted through SMS and Closed-loop feedback mechanism optimization model.

Benefits of technology

It has achieved in-depth exploration and accurate prediction of users' electricity consumption behavior, provided customized energy-saving solutions, improved the quality and efficiency of power marketing services, and enhanced user experience and system self-optimization capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure HDA0004982874890000011
    Figure HDA0004982874890000011
  • Figure HDA0004982874890000021
    Figure HDA0004982874890000021
Patent Text Reader

Abstract

The invention discloses an intelligent short message power marketing application system, and relates to the technical field of power marketing, and the system comprises a data collection module which is used for collecting historical power consumption data of a user and transmitting the historical power consumption data to a central database for preprocessing; the data analysis module is used for extracting and associating data features based on a real-time analysis platform, predicting power consumption data and classifying users; and the energy-saving suggestion module is used for constructing an energy-saving suggestion model, generating personalized energy-saving suggestions, generating short messages and sending the short messages to the user. Through a real-time analysis platform, deep mining of user power consumption characteristics, accurate extraction and association of user power consumption data characteristics, accurate prediction of future power consumption trend by using a prediction model, construction of a personalized energy-saving model, provision of a customized energy-saving scheme, and timely sending of the scheme to the user through a short message, the user is assisted to save cost, and through a closed-loop feedback mechanism, the energy-saving effect of the user is improved. The self-optimization and continuous improvement of the system are ensured, and the overall quality and efficiency of the power marketing service are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power marketing, and in particular to a smart short message power marketing application system. Background Art

[0002] In today's information age, competition in the power market is becoming increasingly fierce. Innovation in power marketing methods has become the key to improving the competitiveness of enterprises. Traditional power marketing systems mainly rely on manual operations and simple data analysis. With the rapid development of technologies such as the Internet, big data, and artificial intelligence, the smart SMS power marketing application system has emerged, bringing revolutionary changes to the power industry.

[0003] In recent years, the research and development of smart SMS electricity marketing application systems has achieved remarkable results, but there are still some technical bottlenecks in practical applications. In terms of data analysis and user classification, the accuracy of electricity consumption data prediction is not high, and the user classification effect is not good. The existing technology needs to be improved in establishing an efficient real-time analysis platform. In terms of generating and pushing energy-saving suggestions, the existing technology does not analyze users' electricity consumption behaviors and habits comprehensively, and the proposed energy-saving suggestions lack pertinence and practicality, and user acceptance is low. In terms of visual display and feedback adjustment, the interactivity and user experience of the existing system have certain limitations, which have a certain impact on the continuous optimization of the energy-saving suggestion model. Summary of the invention

[0004] In view of the problems existing in the above-mentioned existing smart SMS power marketing application system, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that the data analysis module lacks advanced algorithm support, the energy-saving suggestion module is not personalized enough, the solution for providing customized energy-saving solutions based on the actual electricity demand of users needs to be improved, and there are many problems in the single function of the visualization module.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a smart SMS power marketing application system, which includes:

[0007] Data collection module, used to collect users' historical electricity consumption data and transmit it to the central database for pre-processing;

[0008] Data analysis module, used to extract and correlate data features based on the real-time analysis platform, predict electricity consumption data and classify users;

[0009] Energy-saving suggestion module, used to build energy-saving suggestion model, generate personalized energy-saving suggestions and send SMS to users;

[0010] The visualization module is used to collect user feedback and adjust the energy-saving suggestion model, and collect all data for visualization.

[0011] As a preferred solution of the smart SMS electricity marketing application system described in the present invention, wherein: the collection of historical electricity consumption data of users refers to determining the target data source, and collecting historical electricity consumption data of users by installing smart meters at the user end. The historical electricity consumption data includes user information, daily electricity consumption, peak electricity consumption time, commonly used electrical appliances, electricity consumption frequency, weather conditions and electricity prices.

[0012] As a preferred solution of the smart SMS electricity marketing application system described in the present invention, the transmission to the central database for preprocessing refers to transmitting the collected historical electricity consumption data to the central database via the HTTPS data transmission protocol and performing preprocessing, including cleaning noise and outliers in the data and filling missing data using interpolation.

[0013] As a preferred solution of the smart SMS electricity marketing application system described in the present invention, the method of extracting data features and correlating them based on a real-time analysis platform refers to utilizing an offline analysis based on batch processing and a real-time analysis platform based on stream processing to extract all data features from historical electricity consumption data, using the Pearson correlation coefficient to quantify the correlation between all data features in the historical electricity consumption data and electricity consumption, identifying the associated features that affect the user's electricity consumption behavior, including weather conditions, time, and electricity prices, integrating the associated features with the historical electricity consumption data to form an associated feature set.

[0014] As a preferred solution of the smart SMS electricity marketing application system described in the present invention, wherein: the predicting of electricity consumption data and classification of users refers to selecting an ARIMA model, training the ARIMA model using an associated feature set, and adjusting the ARIMA model parameters through cross-validation;

[0015] By collecting users' electricity consumption data in real time and integrating it with related features, a new set of related features is formed;

[0016] Import the new associated feature set into the trained ARIMA model to obtain the predicted electricity consumption data, analyze the deviation between the predicted electricity consumption data and the actual electricity consumption data, and adjust the ARIMA model parameters according to the deviation;

[0017] The Logistic regression model is selected to predict the probability of users’ response to electricity price changes;

[0018] Use the associated feature set as the training set to train the Logistic regression model;

[0019] Import the predicted electricity consumption data into the trained Logistic regression model to obtain the predicted probability of users' response to electricity price changes;

[0020] According to the predicted response probability, set the thresholds of different response groups, divide the user response groups into high response groups, medium response groups, low response groups and non-response groups, and design differentiated incentives for different response groups;

[0021] Real-time monitoring of the user's electricity consumption data and current electricity price changes, matching the current response probability with the set response group interval. If the current response probability deviates from the interval, it means that the electricity consumption behavior is abnormal;

[0022] Conduct a detailed analysis of abnormal electricity usage behavior to determine the specific circumstances of the abnormal electricity usage behavior, including electricity theft, leakage, and equipment failure.

[0023] As a preferred solution of the smart SMS electricity marketing application system described in the present invention, wherein: the construction of the energy-saving suggestion model and the generation of personalized energy-saving suggestions refer to extracting features from the user's historical electricity consumption data and predicted electricity consumption data and performing standardization and normalization processing;

[0024] Divide the extracted features into training set and validation set;

[0025] Select a neural network model to build an energy-saving suggestion model, and initialize the parameters of the energy-saving suggestion model, including the number of neurons in the input layer, hidden layer, and output layer;

[0026] The input layer is the extracted features;

[0027] The hidden layer processes nonlinear combinations of features;

[0028] The output layer is personalized energy-saving suggestions;

[0029] Use the training set for training and adjust the weights and biases of the energy-saving recommendation model through the back-propagation algorithm;

[0030] Real-time electricity usage data is input into the trained energy-saving recommendation model, and personalized energy-saving recommendations are output through the model. The energy-saving recommendations include adjusting electricity usage time, replacing high-efficiency appliances, and optimizing electricity usage habits.

[0031] As a preferred solution of the smart SMS power marketing application system described in the present invention, wherein: the generating SMS to send to the user means extracting the suggestion content from the personalized energy-saving suggestions according to different response groups of users, and designing the SMS template, including greetings, guide words, energy-saving suggestions, energy-saving reasons and feedback forms;

[0032] The feedback form includes user ID, feedback time, text comments, satisfaction rating and suggested improvement points. Users fill in the feedback form through the link in the SMS.

[0033] Relevant personnel shall review the content of the SMS and adjust and optimize it based on the review opinions;

[0034] Determine the time to send SMS based on the user's peak electricity consumption period;

[0035] Use SMS queuing mechanism to send energy-saving reminder SMS messages to the non-responding groups first according to different response groups of users;

[0036] Track SMS sending records in real time, record sending results, and conduct statistical analysis on the sending results, including SMS sending success rate and user feedback rate;

[0037] If the SMS fails to be sent, it will be resent.

[0038] As a preferred solution of the smart SMS power marketing application system described in the present invention, wherein: collecting user feedback refers to collecting feedback information from each user, using natural language processing technology to perform sentiment analysis on text comments, and obtaining sentiment evaluation;

[0039] Calculate the distribution of user satisfaction scores and find out the main factors affecting user satisfaction;

[0040] Use correlation analysis to identify effective and ineffective energy-saving suggestions and determine user acceptance and feedback trends.

[0041] As a preferred solution of the smart SMS power marketing application system described in the present invention, wherein: the adjustment of the energy-saving suggestion model refers to establishing a feedback database to store the feedback information of each user, including user ID, feedback time, emotional evaluation, suggested improvement points and main factors affecting satisfaction;

[0042] Integrate the user feedback results with the training set of the energy-saving suggestion model to form a new training set;

[0043] Retrain the energy-saving recommendation model using the new training set, select the gradient descent algorithm for optimization, and obtain the adjusted energy-saving recommendations;

[0044] Use the validation set to validate the optimized energy-saving recommendation model;

[0045] Store and deploy the verified energy-saving recommendation models to the production environment;

[0046] Improved SMS copy with adjusted energy saving suggestions.

[0047] As a preferred solution of the smart SMS power marketing application system described in the present invention, wherein: the collection of all data for visual display refers to designing a visual user interface to display the real-time SMS sending status, the user's emotional evaluation of energy-saving suggestions, and the real-time user's electricity consumption data on the main operation panel;

[0048] It provides historical electricity consumption data query function and energy-saving suggestion editing interface, allowing operation management personnel to adjust and edit the content of energy-saving suggestions, supports batch operations, and displays the changes in electricity consumption after the implementation of energy-saving suggestions, using comparison charts to display energy-saving effects.

[0049] The beneficial effects of the present invention are: through the real-time analysis platform, deeply explore the user's electricity consumption characteristics, accurately extract and associate the user's electricity consumption data characteristics, use the prediction model to accurately predict the future electricity consumption trend, build a personalized energy-saving model, provide customized energy-saving solutions and send them to users in time via text messages, help users save costs, and ensure system self-optimization and continuous improvement through a closed-loop feedback mechanism, thereby improving the overall quality and efficiency of power marketing services. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0051] Figure 1 This is a structural diagram of a smart SMS power marketing application system.

[0052] Figure 2 The figure is a flow chart of a smart SMS power marketing application system. DETAILED DESCRIPTION

[0053] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0055] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0056] Example 1

[0057] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and which provides a smart SMS power marketing application system, a smart SMS power marketing application system comprising:

[0058] S1, data collection module, used to collect users' historical electricity consumption data and transmit it to the central database for preprocessing;

[0059] Specifically, collecting users' historical electricity consumption data means determining the target data source and collecting users' historical electricity consumption data by installing smart meters at the user end. The historical electricity consumption data includes user information, daily electricity consumption, peak electricity consumption time, commonly used electrical appliances, electricity consumption frequency, weather conditions and electricity prices.

[0060] By installing smart meters at the user end, the system determines the target data source and collects the user's historical electricity consumption data. These data cover multi-dimensional information such as user information, daily electricity consumption, peak electricity consumption time, usage of common electrical appliances, electricity consumption frequency, and related weather conditions and electricity prices, providing a detailed data basis for subsequent data analysis and energy-saving recommendations.

[0061] Furthermore, transmission to a central database for preprocessing means transmitting the collected historical electricity consumption data to a central database via an HTTPS data transmission protocol and performing preprocessing, including cleaning noise and outliers in the data and filling in missing data using interpolation methods.

[0062] After the collected historical electricity consumption data was securely transmitted to the central database via the HTTPS data transmission protocol, a series of preprocessing operations were performed, including cleaning the data to remove noise and outliers, and using interpolation to fill in missing data, ensuring the quality and integrity of the data and providing a reliable data source for subsequent analysis.

[0063] S2, data analysis module, used to extract and associate data features based on the real-time analysis platform, predict electricity consumption data and classify users;

[0064] Specifically, extracting data features and correlating them based on a real-time analysis platform means using a batch-based offline analysis and a stream-based real-time analysis platform to extract all data features from historical electricity consumption data, using the Pearson correlation coefficient to quantify the correlation between all data features and electricity consumption in the historical electricity consumption data, identifying correlated features that affect user electricity consumption behavior, including weather conditions, time, and electricity prices, and integrating the correlated features with historical electricity consumption data to form a correlated feature set.

[0065] Using a real-time analysis platform that combines batch processing and stream processing, all features in the historical electricity consumption data were extracted and quantified. The correlation between them and electricity consumption was analyzed using the Pearson correlation coefficient, thereby identifying key associated features that affect electricity consumption behavior, such as weather conditions, time, and electricity prices. These features were integrated with historical electricity consumption data to form a comprehensive set of associated features to support more in-depth data analysis and prediction of user electricity consumption behavior.

[0066] Furthermore, predicting electricity consumption data and classifying users means selecting an ARIMA model, training the ARIMA model using a set of associated features, and adjusting the ARIMA model parameters through cross-validation;

[0067] By collecting users' electricity consumption data in real time and integrating it with related features, a new set of related features is formed;

[0068] Import the new associated feature set into the trained ARIMA model to obtain the predicted electricity consumption data, analyze the deviation between the predicted electricity consumption data and the actual electricity consumption data, and adjust the ARIMA model parameters according to the deviation;

[0069] The Logistic regression model is selected to predict the probability of users’ response to electricity price changes;

[0070] Use the associated feature set as the training set to train the Logistic regression model;

[0071] Import the predicted electricity consumption data into the trained Logistic regression model to obtain the predicted probability of users' response to electricity price changes;

[0072] According to the predicted response probability, set the thresholds of different response groups, divide the user response groups into high response groups, medium response groups, low response groups and non-response groups, and design differentiated incentives for different response groups;

[0073] Real-time monitoring of the user's electricity consumption data and current electricity price changes, matching the current response probability with the set response group interval. If the current response probability deviates from the interval, it means that the electricity consumption behavior is abnormal;

[0074] Conduct a detailed analysis of abnormal electricity usage behavior to determine the specific circumstances of the abnormal electricity usage behavior, including electricity theft, leakage, and equipment failure.

[0075] The ARIMA model is selected, and the model is trained using the associated feature set. The model parameters are optimized through cross-validation to ensure the accuracy of the prediction. The new associated feature set is input into the trained ARIMA model to obtain the predicted value of the electricity consumption data, and the model parameters are further adjusted by comparing the deviation between the predicted value and the actual value. The Logistic regression model is used to predict the user's response probability to the change in electricity price. The associated feature set is used as training data, and then the user's response probability is obtained based on the predicted electricity consumption data. By setting different thresholds, the system divides users into high-response, medium-response, low-response and non-response groups, and customized differentiated incentives for each group. The real-time monitoring mechanism is used to track the user's electricity consumption data and electricity price changes. By comparing the current response probability with the preset response group interval, the system can promptly detect abnormal electricity consumption behavior. For abnormal electricity consumption behavior, the system will conduct a detailed analysis to determine whether there are problems such as electricity theft, leakage or equipment failure, thereby providing power companies with accurate user insights and effective risk management methods, which not only improves the personalization level of power marketing, but also enhances the operating efficiency and reliability of the power system.

[0076] S3, energy-saving suggestion module, used to build an energy-saving suggestion model, generate personalized energy-saving suggestions and send them to users via SMS;

[0077] Specifically, building an energy-saving suggestion model and generating personalized energy-saving suggestions means extracting features from the user's historical electricity consumption data and predicted electricity consumption data and performing standardization and normalization processing;

[0078] Divide the extracted features into training set and validation set;

[0079] Select a neural network model to build an energy-saving suggestion model, and initialize the parameters of the energy-saving suggestion model, including the number of neurons in the input layer, hidden layer, and output layer;

[0080] The input layer is the extracted features;

[0081] The hidden layer processes nonlinear combinations of features;

[0082] The output layer is personalized energy-saving suggestions;

[0083] Use the training set for training and adjust the weights and biases of the energy-saving recommendation model through the back-propagation algorithm;

[0084] Real-time electricity usage data is input into the trained energy-saving recommendation model, and personalized energy-saving recommendations are output through the model. The energy-saving recommendations include adjusting electricity usage time, replacing high-efficiency appliances, and optimizing electricity usage habits.

[0085] A neural network model is used to construct the model, and the parameters of the input layer, hidden layer and output layer are initialized. The input layer receives the extracted features, the hidden layer performs nonlinear combination processing of the features, and the output layer generates personalized energy-saving suggestions. The model is trained through the training set, and the model weights and biases are adjusted using the back propagation algorithm. Finally, the electricity consumption data of new users is input into the trained model, and personalized energy-saving suggestions including adjusting electricity consumption time, replacing high-efficiency appliances and optimizing electricity consumption habits are output to promote the improvement of users' energy-saving behavior.

[0086] Furthermore, generating SMS messages to send to users means extracting suggestion contents from personalized energy-saving suggestions according to different response groups of users, and designing SMS templates, including greetings, introductory words, energy-saving suggestions, energy-saving reasons, and feedback forms;

[0087] The feedback form includes user ID, feedback time, text comments, satisfaction rating and suggested improvement points. Users fill in the feedback form through the link in the SMS.

[0088] Relevant personnel shall review the content of the SMS and adjust and optimize it based on the review opinions;

[0089] Determine the time to send SMS based on the user's peak electricity consumption period;

[0090] Use SMS queuing mechanism to send energy-saving reminder SMS messages to the non-responding groups first according to different response groups of users;

[0091] Track SMS sending records in real time, record sending results, and conduct statistical analysis on the sending results, including SMS sending success rate and user feedback rate;

[0092] If the SMS fails to be sent, it will be resent.

[0093] According to the different response groups of users, content is extracted from personalized energy-saving suggestions, and SMS templates are designed that include greetings, introductory words, energy-saving suggestions, energy-saving reasons and feedback forms. Users fill in the feedback form through the link in the SMS, recording the user ID, feedback time, text comments, satisfaction score and suggested improvement points. The SMS content is reviewed by professionals before sending and adjusted and optimized based on the opinions. The sending time is determined according to the user's peak electricity consumption period. Through the SMS queuing mechanism, energy-saving reminder SMS are sent preferentially to non-response groups. The SMS sending records are tracked in real time, the sending success rate and user feedback rate are statistically analyzed, and the SMS is resent in case of sending failure to ensure the timeliness and effectiveness of information transmission.

[0094] S4, visualization module, is used to collect user feedback and adjust the energy-saving suggestion model, and collect all data for visualization;

[0095] Specifically, collecting user feedback means collecting feedback information from each user, using natural language processing technology to perform sentiment analysis on text comments, and obtaining sentiment evaluations;

[0096] Calculate the distribution of user satisfaction scores and find out the main factors affecting user satisfaction;

[0097] Use correlation analysis to identify effective and ineffective energy-saving suggestions and determine user acceptance and feedback trends.

[0098] Use natural language processing technology to perform sentiment analysis on text reviews, derive sentiment evaluations, and calculate the distribution of user satisfaction scores to find out the main factors affecting user satisfaction. Through correlation analysis, the system identifies effective and ineffective energy-saving suggestions, determines user acceptance and feedback trends, and thus provides data support for the continuous improvement and optimization of the system.

[0099] Furthermore, adjusting the energy-saving suggestion model refers to establishing a feedback database to store each user's feedback information, including user ID, feedback time, emotional evaluation, suggested improvement points, and main factors affecting satisfaction;

[0100] Integrate the user feedback results with the training set of the energy-saving suggestion model to form a new training set;

[0101] Retrain the energy-saving recommendation model using the new training set, select the gradient descent algorithm for optimization, and obtain the adjusted energy-saving recommendations;

[0102] Use the validation set to validate the optimized energy-saving recommendation model;

[0103] Store and deploy the verified energy-saving recommendation models to the production environment;

[0104] Improved SMS copy with adjusted energy saving suggestions.

[0105] A feedback database is established to store the feedback information of each user, including user ID, feedback time, emotional evaluation, suggested improvement points and main factors affecting satisfaction. The feedback results are integrated with the training set of the energy-saving suggestion model to form a new training set. The system uses the new training set to retrain the energy-saving suggestion model and selects the gradient descent algorithm for optimization to obtain adjusted energy-saving suggestions. After the optimized energy-saving suggestions are verified by the verification set, they are stored and deployed to the production environment. The system can continuously adjust and optimize SMS copy to better meet user needs and improve energy-saving effects.

[0106] In addition, collecting all data for visual display means designing a visual user interface to display the real-time SMS sending status, the user's emotional evaluation of energy-saving suggestions, and the real-time user's electricity consumption data on the main operation panel;

[0107] It provides historical electricity consumption data query function and energy-saving suggestion editing interface, allowing operation management personnel to adjust and edit the content of energy-saving suggestions, supports batch operations, and displays the changes in electricity consumption after the implementation of energy-saving suggestions, using comparison charts to display energy-saving effects.

[0108] By designing a visual user interface, the system displays the SMS sending status, users' emotional evaluation of energy-saving suggestions, and real-time users' electricity consumption data in real time on the main operation panel. The system also provides a historical electricity consumption data query function and an energy-saving suggestion editing interface, allowing operation managers to adjust and edit the content of energy-saving suggestions, and supports batch operations. By comparing charts, the system shows the changes in electricity consumption after the implementation of energy-saving suggestions. The system enables users to intuitively understand the energy-saving effects, thereby improving the transparency of power marketing and user satisfaction.

[0109] Example 2

[0110] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several 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 methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0111] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0112] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0113] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention 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 invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A smart SMS power marketing application system, characterized by: include, Data collection module, used to collect users' historical electricity consumption data and transmit it to the central database for pre-processing; Data analysis module, used to extract and correlate data features based on the real-time analysis platform, predict electricity consumption data and classify users; Energy-saving suggestion module, used to build energy-saving suggestion model, generate personalized energy-saving suggestions and send SMS to users; The visualization module is used to collect user feedback and adjust the energy-saving suggestion model, and collect all data for visualization.

2. The smart SMS power marketing application system as claimed in claim 1, characterized in that: The collecting of the user's historical electricity consumption data refers to determining the target data source, and collecting the user's historical electricity consumption data by installing a smart meter at the user end. The historical electricity consumption data includes user information, daily electricity consumption, peak electricity consumption time, commonly used electrical appliances, electricity consumption frequency, weather conditions and electricity prices.

3. The smart SMS power marketing application system as claimed in claim 2, characterized in that: The transmission to the central database for preprocessing refers to transmitting the collected historical electricity consumption data to the central database via the HTTPS data transmission protocol and performing preprocessing, including cleaning noise and outliers in the data and filling in missing data using interpolation.

4. The smart SMS power marketing application system as claimed in claim 3, characterized in that: The extracting and associating data features based on the real-time analysis platform refers to using a batch-based offline analysis and a stream-based real-time analysis platform to extract all data features in the historical electricity consumption data, using the Pearson correlation coefficient to quantify the correlation between all data features in the historical electricity consumption data and the electricity consumption, identifying the associated features that affect the user's electricity consumption behavior, including weather conditions, time, and electricity prices, and integrating the associated features with the historical electricity consumption data to form an associated feature set.

5. The smart SMS power marketing application system as claimed in claim 4, characterized in that: The predicting of electricity consumption data and classifying users refers to selecting an ARIMA model, training the ARIMA model using an associated feature set, and adjusting the ARIMA model parameters through cross-validation; By collecting users' electricity consumption data in real time and integrating it with related features, a new set of related features is formed; Import the new associated feature set into the trained ARIMA model to obtain the predicted electricity consumption data, analyze the deviation between the predicted electricity consumption data and the actual electricity consumption data, and adjust the ARIMA model parameters according to the deviation; The Logistic regression model is selected to predict the probability of users’ response to electricity price changes; Use the associated feature set as the training set to train the Logistic regression model; Import the predicted electricity consumption data into the trained Logistic regression model to obtain the predicted probability of users' response to electricity price changes; According to the predicted response probability, set the thresholds of different response groups, divide the user response groups into high response groups, medium response groups, low response groups and non-response groups, and design differentiated incentives for different response groups; Real-time monitoring of the user's electricity consumption data and current electricity price changes, matching the current response probability with the set response group interval. If the current response probability deviates from the interval, it means that the electricity consumption behavior is abnormal; Conduct a detailed analysis of abnormal electricity usage behavior to determine the specific circumstances of the abnormal electricity usage behavior, including electricity theft, leakage, and equipment failure.

6. The smart SMS electricity marketing application system as claimed in claim 5, characterized in that: The said constructing an energy-saving suggestion model and generating personalized energy-saving suggestions refers to extracting features from the user's historical electricity consumption data and predicted electricity consumption data and performing standardization and normalization processing; Divide the extracted features into training set and validation set; Select a neural network model to build an energy-saving suggestion model, and initialize the parameters of the energy-saving suggestion model, including the number of neurons in the input layer, hidden layer, and output layer; The input layer is the extracted features; The hidden layer processes nonlinear combinations of features; The output layer is personalized energy-saving suggestions; Use the training set for training and adjust the weights and biases of the energy-saving recommendation model through the back-propagation algorithm; Real-time electricity usage data is input into the trained energy-saving recommendation model, and personalized energy-saving recommendations are output through the model. The energy-saving recommendations include adjusting electricity usage time, replacing high-efficiency appliances, and optimizing electricity usage habits.

7. The smart SMS electricity marketing application system as claimed in claim 6, characterized in that: Generating a text message and sending it to the user means extracting the suggestion content from the personalized energy-saving suggestions according to different response groups of users, and designing a text message template, including a greeting, an introductory message, an energy-saving suggestion, an energy-saving reason, and a feedback form; The feedback form includes user ID, feedback time, text comments, satisfaction rating and suggested improvement points. Users fill in the feedback form through the link in the SMS. Relevant personnel shall review the content of the SMS and adjust and optimize it based on the review opinions; Determine the time to send SMS based on the user's peak electricity consumption period; Use SMS queuing mechanism to send energy-saving reminder SMS messages to the non-responding groups first according to different response groups of users; Track SMS sending records in real time, record sending results, and conduct statistical analysis on the sending results, including SMS sending success rate and user feedback rate; If the SMS fails to be sent, it will be resent.

8. The smart SMS electricity marketing application system as claimed in claim 7, characterized in that: Collecting user feedback refers to collecting feedback information from each user, using natural language processing technology to perform sentiment analysis on text comments, and obtaining sentiment evaluations; Calculate the distribution of user satisfaction scores and find out the main factors affecting user satisfaction; Use correlation analysis to identify effective and ineffective energy-saving suggestions and determine user acceptance and feedback trends.

9. The smart SMS electricity marketing application system as claimed in claim 8, characterized in that: The adjustment of the energy-saving suggestion model refers to establishing a feedback database to store each user's feedback information, including user ID, feedback time, emotional evaluation, suggested improvement points and main factors affecting satisfaction; Integrate the user feedback results with the training set of the energy-saving suggestion model to form a new training set; Retrain the energy-saving recommendation model using the new training set, select the gradient descent algorithm for optimization, and obtain the adjusted energy-saving recommendations; Use the validation set to validate the optimized energy-saving recommendation model; Store and deploy the energy-saving recommendation models that have passed verification into the production environment; Improved SMS copy with adjusted energy saving suggestions.

10. The smart SMS electricity marketing application system according to claim 9, characterized in that: The collecting of all data for visual display refers to designing a visual user interface to display the real-time SMS sending status, the user's emotional evaluation of energy-saving suggestions, and the real-time user's electricity consumption data on the main operation panel; It provides historical electricity consumption data query function and energy-saving suggestion editing interface, allowing operation management personnel to adjust and edit the content of energy-saving suggestions, supports batch operations, and displays the changes in electricity consumption after the implementation of energy-saving suggestions, using comparison charts to display energy-saving effects.

Citation Information

Cited By

  • Energy-saving suggestion generation method and device for household appliance, equipment and medium

    CN119937338A

  • An energy-saving suggestion generation method and device for a household appliance, equipment, and medium

    CN119937338B