Application in the system for supplementing and updating important information of electricity customers

Abstract

This invention discloses a system for supplementing and updating important information of electricity customers, belonging to the field of power information technology. The invention includes an intelligent sensing module, an adaptive updating module, an information fusion and mining module, and a secure interaction module. The intelligent sensing module connects sensors, smart meters, and network monitoring systems via IoT technology to collect environmental and electricity consumption parameters in real time, analyze electricity consumption behavior patterns, and provide data support for judging changes in customer information, achieving comprehensive perception of customer electricity consumption and environmental impact. This invention utilizes IoT technology in collaboration with sensors, smart meters, and network monitoring systems to collect environmental and electricity consumption parameters in real time. Through a formula for predicting changes in electrical equipment load, it can accurately analyze the impact of environmental factors on the load of electrical equipment, providing a basis for power allocation in advance and avoiding power supply imbalances caused by information lag.

Description

Technical Field

[0001] This invention relates to the field of power information technology, specifically to a system for supplementing and updating important information of electricity customers. Background Technology

[0002] In the power industry, customer information management is crucial for power companies to provide high-quality services and ensure the stable operation of the power system. Traditional customer information management methods rely primarily on manual operation and simple database records. Regarding information collection, basic information is typically registered once when a customer opens an account, with a lack of effective automated mechanisms for subsequent information updates. For example, important information such as changes in address or contact information often requires customers to proactively contact the power company for corrections. However, many customers may fail to update this information in a timely manner due to negligence or cumbersome procedures, leading to discrepancies between the customer information held by the power company and the actual situation. This untimely information update can cause numerous problems in actual operations, such as inaccurate delivery of electricity bills, affecting customer payments and potentially resulting in power outages due to unpaid bills; and during power outage repairs, the inability to contact customers promptly delays repair time, causing inconvenience to customers and reducing the efficiency and quality of the power company's services.

[0003] In the traditional model, the accuracy of customer information is difficult to guarantee. Manual data entry is prone to errors, and there is a lack of effective review and verification mechanisms for important information (such as changes in customer electricity load). Furthermore, with the diversification of the power business, power companies acquire customer information from multiple channels, including marketing systems, customer service feedback, and on-site surveys. However, this information is scattered across different subsystems, making effective integration and unified management impossible. Inconsistent data formats and standards between subsystems lead to serious issues of information duplication, conflict, and redundancy. For example, customer electricity usage type information in the marketing system may not match data in the meter data collection system, preventing power companies from obtaining accurate and complete information when performing electricity billing and power allocation, severely impacting the scientific accuracy and effectiveness of business decisions.

[0004] Existing electricity customer information management systems are struggling to keep up with increasingly complex customer situations and frequent information changes. They lack effective triggering mechanisms to proactively detect changes in customer information, relying instead on passively waiting for customer feedback or periodic manual checks, resulting in delayed information updates. Furthermore, the lack of a scientific and reasonable evaluation system to determine which information needs prioritizing updates and their necessity is problematic. For example, when a corporate customer adds large-scale production equipment, leading to a significant increase in electricity load, the existing system may fail to detect and accurately assess its impact on power supply and billing, thus hindering timely adjustments to relevant business parameters and service strategies. Additionally, information security and customer privacy protection measures are inadequate during customer interactions, resulting in low customer participation and trust in information updates, thus impeding the smooth implementation of the update process. In conclusion, traditional electricity customer information management methods can no longer meet the needs of the modern power industry, urgently requiring a more intelligent, efficient, accurate, and secure information update system.

[0005] To address the aforementioned shortcomings, a technical solution is provided. Summary of the Invention

[0006] The purpose of this invention is to solve the problems of untimely updates, low accuracy, difficulty in integration, and lack of effective triggering and evaluation mechanisms in traditional electricity customer information management. At the same time, there are problems of insufficient security and privacy protection, low customer participation and trust in the information interaction process. Therefore, this invention proposes a system for supplementing and updating important information of electricity customers.

[0007] The objective of this invention can be achieved through the following technical solutions:

[0008] Applications include systems for supplementing and updating important information about electricity customers, including:

[0009] The intelligent sensing module is used to connect sensors with smart meters and network monitoring systems through Internet of Things (IoT) technology, collect environmental and electricity parameters in real time, analyze electricity consumption behavior patterns, provide data support for judging changes in customer information, and achieve comprehensive perception of customer electricity consumption and environmental impact.

[0010] The adaptive update module is used to automatically determine and execute customer information updates based on information fusion and mining results and predefined strategies, while dynamically adjusting relevant business system parameters and models to ensure timely and accurate information and enable power services to adapt to changes in customer information.

[0011] The information fusion and mining module is used to integrate data from the intelligent sensing module with information from traditional channels. It uses data fusion algorithms and machine learning algorithms to mine hidden relationships and patterns in customer information, providing a basis for accurately assessing information update needs.

[0012] The secure interaction module is used to follow the authorization mechanism in the collection and updating of customer information to ensure information security. At the same time, it collects customer opinions and calculates satisfaction through multiple channels to improve service and enhance customer trust and interaction.

[0013] Furthermore, the execution process of the intelligent sensing module is as follows:

[0014] Utilizing IoT technology, it connects to sensors installed around the customer's electrical equipment; the sensors collect environmental and power consumption parameters in real time, and through data analysis, it determines the potential impact of environmental factors on electrical equipment and the customer's power consumption habits; through the formula: Where ΔP represents the estimated load change of the electrical equipment, and k is the temperature coefficient of the equipment load. It is the rate of change of ambient temperature. It is the rate of change of current of electrical equipment; by monitoring the changes in ambient temperature and equipment current in real time, this formula is used to predict the changes in the load of electrical equipment, providing a basis for the dispatching of the power system and the updating of customer information in advance.

[0015] By working in conjunction with smart meters and the power company's network monitoring system, we analyze customers' electricity consumption patterns; identify peak and off-peak hours, frequency of use, and power consumption variations; and combine this with network access data to infer changes in customers' lifestyles or production patterns; using the formula: Where S ij x represents the similarity of electricity consumption patterns between customer i and customer j within a preset time period. ik and x jk These are the electricity consumption characteristic values ​​of customer i and customer j at time point k, respectively. and It is the average value of the electricity consumption characteristics of the corresponding customer within the time period, where n is the number of time points; by calculating the similarity of electricity consumption behavior patterns among customers, customer groups with an absolute value of similarity difference less than a threshold are selected for analyzing the electricity consumption trend of the group, and when the deviation of a customer's electricity consumption behavior from the group pattern is greater than a preset deviation, information changes are detected in a timely manner, thereby triggering the information update process.

[0016] Furthermore, the specific operation steps of the information fusion and mining module are as follows:

[0017] The data obtained from the intelligent sensing module will be integrated with information from traditional channels, including customer account registration information and customer service feedback records. Data fusion algorithms will be used to standardize data from different formats and sources, eliminating data conflicts and redundancy.

[0018] When fusing information from different sources, the differences in credibility among the sources are analyzed, and the accurate information fusion is obtained through the following formula: Where F represents the fused information value, w i This is the credibility weight of the i-th information source, which is pre-set based on factors such as the reliability and accuracy of the information source. I i It is the information value provided by the i-th information source, including sensor measurement values, customer registration information values, etc., and m is the number of information sources;

[0019] Machine learning algorithms are used to perform in-depth analysis of the fused information to uncover hidden relationships and patterns within customer information.

[0020] Furthermore, the specific operation steps of the adaptive update module are as follows:

[0021] Based on the results of information fusion and mining, and combined with a predefined update strategy, the system automatically determines whether customer information needs to be updated and, if so, what the updates should entail. Specifically, it quantitatively compares the differences between the currently collected information and the existing information, and, in conjunction with attribute importance weights, assesses the necessity of the information update using the formula: Where U represents the information update necessity index, a j C is the importance weight of the j-th information attribute. j It is the value of the i-th attribute in the currently collected customer information. U is the original value of the attribute in the customer information database, and p is the number of information attributes. When U exceeds the preset update necessity index threshold, it is determined that the customer information needs to be updated.

[0022] The importance weight 'a' of information attributes j The settings are based on the impact of power business needs and customer information on the service;

[0023] Following the decision update, an automatic information update operation is executed, synchronizing the updated information to the power company's customer information database. Simultaneously, based on the nature and scope of the updated content, the parameters and models of relevant business systems are dynamically adjusted to adapt to the new customer information status. After the customer electricity consumption information is updated, the unit price parameters in the electricity billing system are dynamically adjusted according to the following formula. Where P new This is the adjusted electricity price per unit, P. old This is the original electricity price per unit, β is the adjustment coefficient, and ΔE is the change in the customer's electricity consumption. old This is the customer's original electricity consumption;

[0024] This formula makes electricity bill calculations more consistent with customers' actual electricity consumption, ensuring that the power company's billing is accurate and reasonable, while also allowing customers to clearly understand the relationship between changes in electricity costs and information updates.

[0025] Furthermore, the importance weight 'a' of the information attribute in the adaptive update module j The specific steps for analysis are as follows:

[0026] Importance weight of information attribute a j Through comprehensive analysis of influencing parameters, including:

[0027] The accuracy of information is affected by parameters including historical data accuracy score and data source reliability score. The historical data accuracy score is calculated by multiplying the ratio of the number of accurate records of the information attribute data to the total number of records within a preset time period by 100 to obtain a score between 0 and 100, which is recorded as the historical accuracy value. The data source reliability score is assigned a value based on the reliability of the information source channel and is recorded as the trust value. After normalizing the obtained historical accuracy value and trust value, the historical accuracy value and trust value are used as two legs of a right triangle, and the other side of the triangle is connected. A triangular pyramid model is built using this triangle and a preset height. The volume of the triangular pyramid model is calculated and recorded as the reliability judgment value. This reliability judgment value is used as the standard for measuring the accuracy of information.

[0028] The parameters for business relevance include the degree of direct business relevance and the degree of business process dependence. The degree of direct business relevance is assigned a value based on the correlation assessment of the information attribute. If the information attribute directly affects core power businesses, including electricity billing and power distribution, a value of 10 is assigned; if it has an indirect impact, a value of 5 is assigned; and if it has no impact, a value of 1 is assigned, recorded as the relevance value ax. The degree of business process dependence is determined by statistically analyzing the frequency of the information attribute's use in the business process, recorded as the frequency assessment value po. The obtained relevance value ax and frequency assessment value po are normalized and then substituted into the following formula: To obtain the correlation value GVD, where To correct the coefficients, the final correlation value GVD is used as the standard to measure the closeness of the correlation between information attributes and business.

[0029] Information change sensitivity parameters include change frequency and change impact range. Change frequency is obtained by dividing the number of changes of the information attribute within a preset time period by the total monitoring time to get the average number of changes per month. The frequency score is then assigned based on the range of changes. The change impact range is assessed based on the impact of information changes on the power company's services and quantified by the number of departments or business links affected. The change impact range is denoted as change shadow value. The obtained frequency score and change shadow value are labeled as gf and by, respectively. After normalization, they are substituted into the following formula: XMZ=gf×λ1+by×λ2 to obtain the information sensitivity value XMZ, where λ1 and λ2 are the preset weight coefficients of the frequency score and change shadow value, respectively. The obtained information sensitivity value XMZ is used as the standard for measuring information change sensitivity parameters.

[0030] Customer privacy importance parameters, including the level of privacy leakage risk, are assessed based on the nature of the information attributes and the degree of harm caused by the leakage. They are divided into three levels: high, medium, and low, with values ​​of 10, 6, and 2 respectively, and are recorded as customer weight values. These customer weight values ​​are used as the standard for measuring the importance of customer privacy parameters.

[0031] The calculated accuracy score XCF, correlation score GVD, sensitivity score XMZ, and customer weight score GZZ are then normalized and substituted into the following formula: TGR=XCF×ν1+GVD×ν2+XMZ×ν3+GZZ×ν4 to obtain the comprehensive score TGR, where ν1, ν2, ν3, and ν4 are the preset weight coefficients of the accuracy score XCF, correlation score GVD, sensitivity score XMZ, and customer weight score GZZ, respectively. This comprehensive score is used as the importance weight 'a' for measuring the information attribute. j Standards;

[0032] The obtained comprehensive score TGR is compared with several preset comprehensive score intervals. Each of the several comprehensive score intervals corresponds to a different importance weight of the information attribute. When the comprehensive score interval to which the comprehensive score TGR belongs is determined, the importance weight of that information attribute is determined.

[0033] Furthermore, the specific operation steps of the secure interaction module are as follows:

[0034] During the collection and updating of customer authorization information, the security risks of information exchange are continuously assessed using the following formula: Where R represents the security risk value of customer information during the interaction process, b k It is the weight of the k-th safety risk factor, L k q represents the risk level of the kth safety risk factor, which is determined through real-time monitoring or pre-assessment, and q represents the number of safety risk factors.

[0035] If R exceeds the set security threshold, the system will automatically take corresponding security enhancement measures to ensure the security of customer information;

[0036] During the collection and updating of customer information, the customer authorization mechanism is followed, and secure communication protocols and encryption technologies are used to ensure that customers are clearly aware of and authorize the scope of information collection and updating when they interact with the system using mobile terminals or other devices.

[0037] Before and after information is updated, provide feedback to customers on the update status through various means such as SMS, APP push, and email, informing them which information has been updated, the basis for the update, and the possible impact on their electricity service.

[0038] At the same time, establish customer feedback channels to facilitate customers to raise questions or objections about information updates, respond and handle them in a timely manner, and collect customer feedback to calculate customer satisfaction.

[0039] Furthermore, the specific steps for collecting customer feedback and calculating customer satisfaction in the secure interaction module are as follows:

[0040] Through the formula: Where S represents customer satisfaction feedback, s l N is the score corresponding to the l-th feedback evaluation level. l is the number of the i-th type of feedback received, and r is the number of feedback rating levels;

[0041] By calculating customer feedback satisfaction, we can quantitatively understand customers' satisfaction with the information update process and results.

[0042] Based on the satisfaction results, we will make targeted improvements to service processes and optimize information update strategies to enhance customer experience.

[0043] Compared with the prior art, the beneficial effects of the present invention are:

[0044] (1) This invention utilizes Internet of Things (IoT) technology in collaboration with sensors, smart meters, and network monitoring systems to collect environmental and electricity parameters in real time. Through the formula for predicting changes in the load of electrical equipment, it can accurately analyze the impact of environmental factors on the load of electrical equipment, providing a basis for power allocation in advance and avoiding power supply imbalances caused by information lag. At the same time, the calculation of similarity of electricity behavior patterns can accurately identify changes in customers' electricity consumption habits, promptly detect information changes such as the addition of new household appliances or adjustments in enterprise production, quickly trigger the update process, and ensure the timeliness of information. The information fusion and mining module integrates multi-source information and uses data fusion algorithms and machine learning algorithms to deeply mine the hidden patterns of customer information, providing an accurate basis for assessing information update needs and effectively solving the problems of low accuracy and untimely updates in traditional information management.

[0045] (2) In terms of power service optimization, the adaptive update module automatically judges and executes information updates based on the fusion and mining results, dynamically adjusts the parameters of the business system, and adjusts the unit price according to the unit price adjustment formula of the electricity billing system to make the electricity billing fit the actual electricity consumption, ensuring reasonable and accurate billing and enhancing customers' trust in the power company's billing; it optimizes the power dispatch and other business systems according to the updated content, improves the adaptability of power services to changes in customer information, ensures stable and reliable power supply, and improves service efficiency and quality; the secure interaction module follows a strict authorization mechanism in information collection and updating, adopts secure communication protocols and encryption technology to ensure information security and privacy, monitors interaction security in real time through a security risk assessment formula, takes timely enhancement measures to enhance customer trust, and at the same time, provides feedback on the update status through multiple channels and calculates satisfaction, optimizes service processes and update strategies based on customer opinions, strengthens interaction with customers, and improves customer satisfaction and loyalty;

[0046] (3) This invention has a positive impact on the overall operational efficiency of the power system. Through intelligent sensing and adaptive updating functions, power companies can rationally allocate resources according to real-time changes in customer electricity consumption, avoid resource waste or shortage, reduce operating costs, and improve the efficiency and stability of power grid operation. Information fusion and mining provide forward-looking decision support for power grid planning, help to plan infrastructure construction in advance, and optimize long-term resource allocation. In addition, the system's comprehensive perception and timely updating of customer information helps to identify risks and potential fault hazards of electrical equipment in advance, reduce the incidence of power accidents, and ensure the safe operation of the power system. Accurate information analysis provides a scientific basis for various decisions of the power company, enhances market competitiveness, promotes the sustainable development of the power industry, and adapts to the ever-growing and changing needs of social and economic development for power services. Attached Figure Description

[0047] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0048] Figure 1 This is the overall system block diagram of the present invention. Detailed Implementation

[0049] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] It should be understood that the terms “comprising” and “including” used in this disclosure and claims indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0051] It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure. As used in this disclosure and claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this disclosure and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations.

[0052] like Figure 1 As shown, the system for supplementing and updating important information of electricity customers includes an intelligent sensing module, an adaptive update module, an information fusion and mining module, and a secure interaction module.

[0053] The intelligent sensing module is used to connect sensors with smart meters and network monitoring systems through Internet of Things (IoT) technology, collect environmental and electricity parameters in real time, analyze electricity consumption behavior patterns, provide data support for judging changes in customer information, and achieve comprehensive perception of customer electricity consumption and environmental impact.

[0054] Utilizing IoT technology, it connects to sensors (such as temperature sensors, humidity sensors, current and voltage sensors) installed around the customer's electrical equipment. These sensors collect environmental and power consumption parameters in real time, and through data analysis, determine the potential impact of environmental factors on electrical equipment and the customer's power consumption habits; through the formula: Where ΔP represents the estimated load change of the electrical equipment (unit: kilowatt), and k is the equipment load temperature coefficient (different equipment types have different coefficient values, which need to be determined in advance through experiments or empirical data). It is the rate of change of ambient temperature (unit: degrees Celsius / minute). It is the rate of change of current in electrical equipment; by monitoring changes in ambient temperature and equipment current in real time, this formula is used to predict changes in the load of electrical equipment, providing a basis for power system dispatching and customer information updates in advance.

[0055] By working in conjunction with smart meters and the power company's network monitoring system, we analyze customers' electricity consumption patterns; identify peak and off-peak hours, frequency of use, and power variation information; and combine this with network access data (if customers perform business inquiries or other operations through the power company's network platform) to infer changes in customers' lifestyles or production patterns; using the formula: Where S ij x represents the similarity of electricity consumption patterns between customer i and customer j within a preset time period. ik and x jk These are the electricity consumption characteristics (such as power, electricity consumption, etc.) of customer i and customer j at the k-th time point, respectively. and It is the average value of the electricity consumption characteristics of the corresponding customer during the time period, where n is the number of time points;

[0056] By calculating the similarity of electricity consumption patterns among customers, customer groups with similar electricity consumption habits can be identified. This information can be used to analyze the electricity consumption trends of these groups. Furthermore, when the deviation of a customer's electricity consumption behavior from the group pattern exceeds a preset deviation, information changes (such as adjustments in enterprise production or the addition of large appliances to households) can be detected in a timely manner, thereby triggering an information update process.

[0057] The information fusion and mining module is used to integrate data from the intelligent sensing module with information from traditional channels. It uses data fusion algorithms and machine learning algorithms to mine hidden relationships and patterns in customer information, providing a basis for accurately assessing information update needs and ensuring the integrity and in-depth utilization of information.

[0058] Data acquired from the intelligent sensing module will be integrated with information from traditional channels, including customer account registration information and customer service feedback records. A data fusion algorithm will be used to standardize data from different formats and sources, eliminating data conflicts and redundancy. When integrating information from different sources, considering the varying credibility of each source, the following formula will be used to obtain more accurate and reliable integrated information: Where F represents the fused information value, w i This is the credibility weight of the i-th information source, which is pre-set based on factors such as the reliability and accuracy of the information source. I i It is the information value provided by the i-th information source, including sensor measurement values, customer registration information values, etc., and m is the number of information sources;

[0059] Machine learning algorithms (such as cluster analysis and association rule mining) are used to deeply mine the fused information. This uncovers hidden relationships and patterns in customer information. For example, it is found that certain types of enterprise customers often exhibit specific changes in electricity consumption parameters and equipment purchase behaviors before expanding their production scale, thus allowing for the prediction of potentially significant changes in customer information in advance.

[0060] The adaptive update module is used to automatically determine and execute customer information updates based on the results of information fusion and mining and predefined strategies. At the same time, it dynamically adjusts the relevant business system parameters and models to ensure that the information is timely and accurate, so that the power service can adapt to changes in customer information.

[0061] Based on the results of information fusion and mining, and combined with predefined update strategies (which can be flexibly adjusted according to different types of customers and business scenarios), the system automatically determines whether customer information needs to be updated and what the updates should include. Specifically, it quantitatively compares the differences between the currently collected information and the original information, and, combined with attribute importance weights, accurately assesses the necessity of information updates using the formula: Where U represents the information update necessity index, a j C is the importance weight of the j-th information attribute. j It is the value of the i-th attribute in the currently collected customer information. U is the original value of the attribute in the customer information database, and p is the number of information attributes. When U exceeds the preset update necessity index threshold, it is determined that the customer information needs to be updated.

[0062] The importance weight 'a' of information attributes j Based on the impact of electricity business demand and customer information on service, the following impact parameters are determined through comprehensive analysis:

[0063] The accuracy of information is affected by parameters including historical data accuracy score and data source reliability score. The historical data accuracy score is obtained by multiplying the ratio of the number of accurate records of the information attribute data to the total number of records in the past period by 100 to get a score between 0 and 100, which is recorded as the historical accuracy value. The data source reliability score is assigned according to the reliability of the information source channel and recorded as the trust value. After normalizing the obtained historical accuracy value and trust value, the historical accuracy value and trust value are used as two legs of a right triangle, and the other side of the triangle is connected. A triangular pyramid model is built with this triangle and a preset height. The volume of the triangular pyramid model is calculated and recorded as the reliability judgment value. This reliability judgment value is used as the standard for measuring the accuracy of information.

[0064] The parameters for business relevance include the degree of direct business relevance and the degree of business process dependence. The degree of direct business relevance is assigned a value based on the correlation assessment of the information attribute. If the information attribute directly affects core power businesses, including electricity billing and power distribution, a value of 10 is assigned; if it has an indirect impact, a value of 5 is assigned; and if it has no impact, a value of 1 is assigned, recorded as the relevance value ax. The degree of business process dependence is determined by statistically analyzing the frequency of the information attribute's use in the business process, recorded as the frequency assessment value po. The obtained relevance value ax and frequency assessment value po are normalized and then substituted into the following formula: To obtain the correlation value GVD, where To correct the coefficient, the value is set between 2 and 6, and the final correlation value GVD is used as the standard to measure the closeness of the correlation between information attributes and business.

[0065] Information change sensitivity parameters include change frequency and change impact range. Change frequency is obtained by dividing the number of changes of the information attribute within a preset time period by the total monitoring time to get the average number of changes per month. The frequency score is then assigned based on the range of changes. The change impact range is assessed based on the impact of information changes on the power company's services and quantified by the number of departments or business links affected. The change impact range is denoted as change shadow value. The obtained frequency score and change shadow value are labeled as gf and by, respectively. After normalization, they are substituted into the following formula: XMZ=gf×λ1+by×λ2 to obtain the information sensitivity value XMZ, where λ1 and λ2 are the preset weight coefficients of the frequency score and change shadow value, respectively. The obtained information sensitivity value XMZ is used as the standard for measuring information change sensitivity parameters.

[0066] Customer privacy importance parameters, including the level of privacy leakage risk, are assessed based on the nature of the information attributes and the degree of harm that may be caused once leaked. They are divided into three levels: high, medium, and low, with values ​​of 10, 6, and 2 respectively, and are recorded as customer weight values. These customer weight values ​​are used as the standard for measuring the importance of customer privacy parameters.

[0067] The calculated accuracy score XCF, correlation score GVD, sensitivity score XMZ, and customer weight score GZZ are then normalized and substituted into the following formula: TGR=XCF×ν1+GVD×ν2+XMZ×ν3+GZZ×ν4 to obtain the comprehensive score TGR, where ν1, ν2, ν3, and ν4 are the preset weight coefficients of the accuracy score XCF, correlation score GVD, sensitivity score XMZ, and customer weight score GZZ, respectively. This comprehensive score is used as the importance weight 'a' for measuring the information attribute. j The standard is to compare the obtained comprehensive score value TGR with several preset comprehensive score value intervals. Each of the several comprehensive score value intervals corresponds to a different importance weight of the information attribute. When the comprehensive score value interval to which the comprehensive score value TGR belongs is determined, the importance weight of that information attribute is determined.

[0068] After a decision is updated, an information update operation is automatically performed, synchronizing the updated information to the power company's customer information database. Simultaneously, it can dynamically adjust the parameters and models of relevant business systems (such as the power dispatch system and electricity billing system) based on the nature and scope of the updated content to adapt to the new customer information status. For example, after customer electricity consumption information is updated (e.g., electricity consumption increases significantly due to new equipment), the unit price parameter in the electricity billing system is dynamically adjusted according to the following formula. Where P new This is the adjusted electricity price per unit, P. old This is the original electricity price per unit, β is the adjustment coefficient (determined based on the power company's pricing strategy and cost factors), ΔE is the change in customer electricity consumption (calculated based on updated electricity consumption information), and E oldThis is the customer's original electricity consumption; this formula makes electricity bill calculation more consistent with the customer's actual electricity consumption, ensuring that the power company's billing is accurate and reasonable, and also allowing customers to clearly understand the relationship between changes in electricity costs and information updates.

[0069] The secure interaction module is used to follow the authorization mechanism in the collection and updating of customer information, ensure information security, and collect customer opinions to calculate satisfaction through multi-channel feedback on updates, promote service optimization, and enhance customer trust and interaction.

[0070] During the collection and updating of customer authorization information, the security risks of information exchange are continuously assessed using the following formula: Where R represents the security risk value of customer information during the interaction process, b k This is the weight of the k-th security risk factor (such as the weight of factors like communication protocol security and data encryption strength, set according to industry standards and expert experience), L k R represents the risk level of the k-th security risk factor (determined through real-time monitoring or pre-assessment, ranging from 1 to 5, where 1 represents low risk and 5 represents high risk), and q represents the number of security risk factors. If R exceeds the set security threshold, the system automatically takes corresponding security enhancement measures (such as upgrading encryption algorithms, prompting customers to re-authorize, etc.) to ensure customer information security, prevent information leakage and malicious tampering, and enhance customer trust in the system. During the collection and updating of customer information, the system adheres to the customer authorization mechanism, using secure communication protocols (such as HTTPS) and encryption technology to ensure that customers clearly understand and authorize the scope of information collection and updates when interacting with the system using mobile terminals or other devices.

[0071] Before and after information updates, promptly inform customers of the updates. Use various methods such as SMS, app push notifications, and emails to inform customers which information has been updated, the basis for the updates, and the potential impact on their electricity service. Simultaneously, establish customer feedback channels to facilitate customer inquiries or objections regarding information updates. The system can respond and handle these in a timely manner. Customer satisfaction is calculated by collecting customer feedback using the formula: Where S represents customer satisfaction feedback, s l This refers to the score corresponding to the l-th feedback evaluation level (specifically, 5 points for very satisfied, 4 points for satisfied, 3 points for dissatisfied, etc.), N l denoted as the number of the i-th type of feedback received, and r as the number of feedback rating levels; by calculating customer feedback satisfaction, we can quantitatively understand the degree of customer satisfaction with the information update process and results; based on the satisfaction results, we can improve service processes and optimize information update strategies in a targeted manner, enhance customer experience, and further strengthen positive interactive relationships with customers.

[0072] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A system for supplementing and updating important information of electricity customers, characterized in that: include: The intelligent sensing module is used to connect sensors with smart meters and network monitoring systems through Internet of Things (IoT) technology, collect environmental and electricity parameters in real time, analyze electricity consumption behavior patterns, provide data support for judging changes in customer information, and achieve comprehensive perception of customer electricity consumption and environmental impact. The adaptive update module is used to automatically determine and execute customer information updates based on information fusion and mining results and predefined strategies, while dynamically adjusting relevant business system parameters and models to ensure timely and accurate information and enable power services to adapt to changes in customer information. The information fusion and mining module is used to integrate data from the intelligent sensing module with information from traditional channels. It uses data fusion algorithms and machine learning algorithms to mine hidden relationships and patterns in customer information, providing a basis for accurately assessing information update needs. The secure interaction module is used to follow the authorization mechanism and ensure information security during customer information collection and updating. At the same time, it collects customer opinions and calculates satisfaction by providing feedback on the update status through multiple channels. The execution process of the intelligent sensing module is as follows: Utilizing IoT technology, it connects to sensors installed around the customer's electrical equipment; the sensors collect environmental and power consumption parameters in real time, and through data analysis, it determines the potential impact of environmental factors on electrical equipment and the customer's power consumption habits; through the formula: ,in This indicates the estimated change in the load of electrical equipment. The equipment load temperature coefficient, It is the rate of change of ambient temperature. It is the rate of change of current in electrical equipment; By monitoring changes in ambient temperature and equipment current in real time, this formula can be used to predict changes in the load of electrical equipment, providing a basis for power system dispatch and customer information updates in advance. By working in conjunction with smart meters and the power company's network monitoring system, we analyze customers' electricity consumption patterns; identify peak and off-peak hours, frequency of use, and power consumption variations; and combine this with network access data to infer changes in customers' lifestyles or production patterns; using the formula: ,in Indicates customer and customers The similarity of electricity consumption behavior patterns within a preset time period. and They are customers and customers In the Electricity consumption characteristics at each point in time, and It is the average value of the electricity consumption characteristics of the corresponding customer during that time period. The number of time points; by calculating the similarity of electricity consumption behavior patterns among customers, customer groups with an absolute value of similarity difference less than a threshold are selected for analyzing the electricity consumption trend of the group, and when the deviation of a customer's electricity consumption behavior from the group pattern is greater than a preset deviation, information changes are detected in a timely manner, thereby triggering the information update process; The specific operation steps of the information fusion and mining module are as follows: The data obtained from the intelligent sensing module will be integrated with information from traditional channels, including customer account registration information and customer service feedback records. Data fusion algorithms will be used to standardize data from different formats and sources, eliminating data conflicts and redundancy. When fusing information from different sources, the differences in credibility among the sources are analyzed, and the accurate information fusion is obtained through the following formula: ,in This represents the fused information value. It is the first The credibility weight of each information source is pre-set based on factors such as the reliability and accuracy of the information source, and , It is the first Information values ​​provided by various information sources, including sensor measurements and customer registration information, The number of information sources; Machine learning algorithms are used to deeply mine the fused information to uncover hidden relationships and patterns in customer information; The specific operation steps of the adaptive update module are as follows: Based on the results of information fusion and mining, and combined with a predefined update strategy, the system automatically determines whether customer information needs to be updated and, if so, what the updates should entail. Specifically, it quantitatively compares the differences between the currently collected information and the existing information, and, in conjunction with attribute importance weights, assesses the necessity of the information update using the formula: ,in This represents the index indicating the necessity of information updates. It is the first The importance weight of each information attribute It is the value of the i-th attribute in the currently collected customer information. This is the original value of this attribute in the customer information database. For the number of information attributes; when When the preset update necessity index threshold is exceeded, it is determined that the customer information needs to be updated; The importance weight of information attributes The settings are based on the impact of power business needs and customer information on the service; Following the decision update, an automatic information update operation is executed, synchronizing the updated information to the power company's customer information database. Simultaneously, based on the nature and scope of the updated content, the parameters and models of relevant business systems are dynamically adjusted to adapt to the new customer information status. After the customer electricity consumption information is updated, the unit price parameters in the electricity billing system are dynamically adjusted according to the following formula. ,in This is the adjusted electricity price per unit. This is the original electricity price per unit. It is an adjustment factor. This is the change in customer electricity consumption. This is the customer's original electricity consumption; This formula makes electricity bill calculations more consistent with customers' actual electricity consumption, ensuring that the power company's billing is accurate and reasonable, while also allowing customers to clearly understand the relationship between changes in electricity costs and information updates.

2. The system for supplementing and updating important information of electricity customers according to claim 1, characterized in that, Importance weights of information attributes in the adaptive update module The specific steps for analysis are as follows: Importance weight of information attributes Through comprehensive analysis of influencing parameters, including: The accuracy of information is affected by parameters including historical data accuracy score and data source reliability score. The historical data accuracy score is calculated by multiplying the ratio of the number of accurate records of the information attribute data to the total number of records within a preset time period by 100 to obtain a score between 0 and 100, which is recorded as the historical accuracy value. The data source reliability score is assigned a value based on the reliability of the information source channel and is recorded as the trust value. After normalizing the obtained historical accuracy value and trust value, the historical accuracy value and trust value are used as two legs of a right triangle, and the other side of the triangle is connected. A triangular pyramid model is built using this triangle and a preset height. The volume of the triangular pyramid model is calculated and recorded as the reliability judgment value. This reliability judgment value is used as the standard for measuring the accuracy of information. The parameters for business relevance include the degree of direct business relevance and the degree of business process dependence. The degree of direct business relevance is assigned a value based on the correlation assessment of the information attribute. If the information attribute directly affects core power businesses, including electricity billing and power distribution, a value of 10 is assigned; if it has an indirect impact, a value of 5 is assigned; and if it has no impact, a value of 1 is assigned, recorded as the relevance value ax. The degree of business process dependence is determined by statistically analyzing the frequency of the information attribute's use in the business process, recorded as the frequency assessment value po. The obtained relevance value ax and frequency assessment value po are normalized and then substituted into the following formula: To obtain the correlation value GVD, where To correct the coefficients, the final correlation value GVD is used as the standard to measure the closeness of the correlation between information attributes and business. Information change sensitivity parameters include change frequency and change impact range. Change frequency is calculated by dividing the number of changes of the information attribute within a preset time period by the total monitoring time to obtain the average number of changes per month. A value is then assigned based on the range of changes, denoted as the frequency score. The change impact range is assessed based on the impact of the information change on the power company's services and quantified by the number of affected departments or business processes, denoted as the change shadow value. The obtained frequency score and change shadow value are labeled as gf and by, respectively, and after normalization, are entered into the following formula: To obtain the sensitivity value XMZ, in the formula The preset weighting coefficients for frequency division and shadow value are respectively used, and the obtained information sensitivity value XMZ is used as the standard for measuring the sensitivity parameter of information change. Customer privacy importance parameters, including the level of privacy leakage risk, are assessed based on the nature of the information attributes and the degree of harm caused by the leakage. They are divided into three levels: high, medium, and low, with values ​​of 10, 6, and 2 respectively, and are recorded as customer weight values. These customer weight values ​​are used as the standard for measuring the importance of customer privacy parameters. Then, normalize the calculated accuracy score XCF, correlation score GVD, sensitivity score XMZ, and customer weight score GZZ, and then input them into the following formula: To obtain the comprehensive score TGR, in the formula These are the preset weighting coefficients for the accuracy judgment value (XCF), the correlation judgment value (GVD), the sensitivity value (XMZ), and the customer weight value (GZZ), respectively. This comprehensive score is used as the weight to measure the importance of information attributes. Standards; The obtained comprehensive score TGR is compared with several preset comprehensive score intervals. Each of the several comprehensive score intervals corresponds to a different importance weight of the information attribute. When the comprehensive score interval to which the comprehensive score TGR belongs is determined, the importance weight of that information attribute is determined.

3. The system for supplementing and updating important information of electricity customers according to claim 2, characterized in that, The specific operation steps of the secure interaction module are as follows: During the collection and updating of customer authorization information, the security risks of information exchange are continuously assessed using the following formula: ,in This indicates the security risk value of customer information during the interaction process. It is the first The weight of each security risk factor It is the first The risk level of each safety risk factor is determined through real-time monitoring or pre-assessment. The number of safety risk factors; like If the set security threshold is exceeded, the system will automatically take corresponding security enhancement measures to ensure the security of customer information; In the process of collecting and updating customer information, we follow the customer authorization mechanism and use secure communication protocols and encryption technology to ensure that customers are aware of and authorize the scope of information collection and updating when they interact with the system using mobile terminals. Before and after information is updated, provide feedback to customers on the update status through various means such as SMS, APP push, and email, informing customers which information has been updated, the basis for the update, and the impact on customers' electricity services; At the same time, establish customer feedback channels to facilitate customers to raise questions or objections about information updates, respond and handle them in a timely manner, and collect customer feedback to calculate customer satisfaction.

4. The system for supplementing and updating important information of electricity customers according to claim 3, characterized in that, The specific steps for collecting customer feedback and calculating customer satisfaction in the secure interaction module are as follows: Through the formula: ,in Indicates customer satisfaction feedback. It is the first The scores corresponding to the feedback evaluation levels, It is the number of the first type of feedback received. To provide feedback on the number of evaluation levels; By calculating customer feedback satisfaction, we can quantitatively understand customers' satisfaction with the information update process and results. Based on the satisfaction results, we will make targeted improvements to service processes and optimize information update strategies to enhance customer experience.

Images