Power supply service evaluation method and system based on dynamic weight adjustment

Abstract

The invention belongs to the field of power supply service evaluation, and provides a power supply service evaluation method and system based on dynamic weight adjustment, and the method comprises the steps: collecting the score of a user for a power supply service, and carrying out the correlation storage of the score and user information; dividing the score into a preset time period according to time, and counting an average score of all users in each time period; determining an environmental influence factor according to the power supply state in the preset time period; determining the dynamic weight of the user in the current time period according to the average score, the environmental impact factor and the basic weight of the user; calculating a weighted score of each user according to the dynamic weights and scores of the users; calculating a total score of the power supply service according to the weighted score of each user; and updating the basic weight for each user according to the dynamic weight after combination in each time period.

Description

Technical Field

[0001] The present invention belongs to the field of power supply service evaluation, and particularly relates to a power supply service evaluation method and system based on dynamic weight adjustment. Background Art

[0002] With the development of social economy and the acceleration of urbanization, power supply service, as an important part of public infrastructure, its service quality is directly related to user satisfaction and the social image of power enterprises. In the prior art, power supply service units generally evaluate service quality by collecting user feedback information, user satisfaction questionnaires, and regular evaluation reports. However, the existing power supply service evaluation methods generally have the following technical problems: First of all, user scores are not weighted, and the scores of all users are usually regarded as equivalent, having the same impact on the final evaluation result, and unable to effectively reflect the authenticity and credibility of user scores. For example, some users may give extremely high or low scores due to personal emotions, non-service factors, or malicious score brushing behaviors, resulting in distorted evaluation results.

[0003] Secondly, the existing methods lack a dynamic management mechanism for scoring behaviors. There are significant differences in user scoring behaviors at different time periods. Especially when power supply services are affected by environmental factors (such as power outages, natural disasters, equipment failures), user scores fluctuate more severely, and the existing systems are difficult to effectively buffer the interference of the external environment on the evaluation results, resulting in unfair scoring of service personnel or units under uncontrollable conditions.

[0004] In addition, the prior art fails to achieve dynamic adjustment and adaptive update of the influence of user scores, and is unable to optimize the weights according to the long-term scoring behaviors of users, resulting in ineffective utilization of historical scoring behaviors and lack of in-depth mining and management of scoring trends.

[0005] Furthermore, the current power supply service evaluation methods fail to combine with actual business situations, such as key indicators like seasonal changes, peak and valley periods of business handling, complaint volume, business volume, etc., to dynamically adjust evaluation weights. For example, in the off-season of business, users expect higher service quality, but the existing systems are unable to increase the proportion of service quality in the evaluation, making it difficult to accurately reflect the actual service performance.

[0006] In summary, the existing power supply service evaluation technologies have problems such as distorted scoring results, lack of scoring weight management, poor anti-interference ability, and lack of adaptive adjustment ability. There is an urgent need for a power supply service evaluation method based on dynamic weight adjustment to achieve scientific management of scoring behaviors, effective buffering of the external environment, and dynamic optimization of user weights, so as to improve the objectivity, fairness, and reliability of evaluation results and enhance the technical level of power supply service quality management. Summary of the Invention

[0007] To solve the problems in the prior art, the present invention provides a power supply service evaluation method based on dynamic weight adjustment, which includes the following steps: Collect the scores of users on the power supply service and store the scores in association with the user information; Divide the scores by time into preset time periods, and count the average scores of all users in each time period; Determine the environmental impact factor according to the power supply status within the preset time period; Determine the dynamic weight of the user in the current time period according to the average score, the environmental impact factor, and the basic weight of the user; Calculate the weighted score of each user according to the dynamic weight of the user and their score; Calculate the total score of the power supply service according to the weighted scores of each user; Update the basic weight for each user according to the dynamic weight after combining each time period.

[0008] Further, the determination of the environmental impact factor includes the following steps: Collect the power supply status information within the preset time period; Perform standardization processing on the power supply status information, and perform weighted calculation according to the set weights of each index to obtain the initial value of the environmental impact factor for the time period; Perform gain adjustment on the initial value of the environmental impact factor according to the business busy degree of the time period to obtain the adjusted environmental impact factor.

[0009] Further, the method for determining the dynamic weight includes: , wherein, represents the dynamic weight, represents the basic weight of the user, represents the highest score that the user can give, represents the environmental impact factor, represents the average score, represents the user 's score.

[0010] Further, the calculation of the weighted score of each user according to the dynamic weight of the user and their score includes: , wherein, represents the score of the user , represents the dynamic weight, represents the weighted score.

[0011] Further, updating the base weight for each user according to the dynamic weight after combination in each time period includes one of the following strategies: Update strategy one: , Update strategy two: , Update strategy three: If , then trigger the update; Update method: , Otherwise, keep the original base weight unchanged; Update strategy four: , Wherein: represents the new base weight; represents the base weight of the previous time period; represents the smoothing coefficient; represents the number of time periods that the user has participated in the evaluation cumulatively; represents the dynamic weight in the 𝑡-th time period; represents the highest score that the user can give; represents the preset update trigger threshold; represents the historical weight decay coefficient; represents the system preset neutral weight reference value.

[0012] The present invention also provides a power supply service evaluation system based on dynamic weight adjustment, including the following modules: An acquisition module, configured to acquire the scores of users on the power supply service and store the scores in association with user information; A statistics module, configured to divide the scores into preset time periods according to time and statistically calculate the average score of all users in each time period; A first determination module, configured to determine an environmental impact factor according to the power supply state within a preset time period; A second determination module, configured to determine the dynamic weight of the user in the current time period according to the average score, the environmental impact factor, and the base weight of the user; A first calculation module, configured to calculate the weighted score of each user according to the dynamic weight of the user and his score; A second calculation module, configured to calculate the total score of the power supply service according to the weighted scores of each user; An update module, configured to update the base weight for each user according to the dynamic weight after combination in each time period.

[0013] Further, the first determination module includes the following sub-modules: The second acquisition module is used to acquire the power supply status information within the preset time period; The weighted calculation module is used to perform standardization processing on the power supply status information and perform weighted calculation according to the set weights of each index to obtain the initial value of the environmental impact factor for the time period; The adjustment module is used to perform gain adjustment on the initial value of the environmental impact factor according to the business busy degree of the time period to obtain the adjusted environmental impact factor.

[0014] Furthermore, the dynamic weight is determined using the following formula: , where, represents the dynamic weight, represents the basic weight of the user, represents the highest score that the user can give, represents the environmental impact factor, represents the average score, represents the user 's score.

[0015] Furthermore, the calculation of the weighted score of each user according to the user's dynamic weight and his score includes: , where, represents the score of the user , represents the dynamic weight, represents the weighted score.

[0016] Furthermore, the update of the basic weight for each user according to the dynamic weight in each combined time period includes one of the following strategies: Update strategy one: , Update strategy two: , Update strategy three: If , then trigger the update; Update method: , Otherwise, keep the original basic weight unchanged; Update strategy four: , where: represents the new basic weight; represents the basic weight of the previous time period; represents the smoothing coefficient; Indicates the number of time periods that the user has participated in the evaluation cumulatively; Indicates the dynamic weight within the \(t\) -th time period; Indicates the highest score that the user can give; Indicates the preset update trigger threshold; Indicates the historical weight decay coefficient; Indicates the system - preset neutral weight reference value.

[0017] The present invention provides a power supply service evaluation method and system based on dynamic weight adjustment. By introducing a dynamic weight calculation mechanism for user scores, an adjustment strategy for environmental impact factors, and an adaptive update mechanism for user base weights, a scientific evaluation of the power supply service quality is achieved. Compared with the prior art, it has the following beneficial effects: The present invention dynamically calculates the weight of the user score according to the deviation between the user score and the average score of the time period. If the score is higher than the average score, its weight is reduced; if the score is lower than the average score, its weight is increased, effectively weakening the influence of high - score cheating behavior on the evaluation result, strengthening the weight of low - score feedback, and ensuring that the evaluation result truly reflects the power supply service level.

[0018] The present invention quantifies the power supply status (such as power outage frequency, number of complaints, business volume, etc.) by introducing environmental impact factors. When the external environment is abnormal, it appropriately adjusts the contribution of the score deviation term to the weight, buffers the score anomaly caused by environmental fluctuations, and prevents service personnel or units from being dragged down by score anomalies under uncontrollable conditions.

[0019] After each evaluation cycle ends, the system dynamically updates the user's base weight according to the user's current dynamic weight, dynamically adjusts the influence of the user score in subsequent cycles, suppresses the long - term score weight of users with abnormal scores, and increases the weight of users with stable scores, realizing the long - term adaptive optimization of the system for scoring behavior.

[0020] The present invention combines seasonal changes and peak - valley cycles of business handling, and dynamically adjusts the evaluation weight configuration according to key indicators such as business volume and service quality. For example, during the off - peak season of business, it appropriately increases the evaluation proportion of service quality, reflects higher service expectations of users, and improves the sensitivity and accuracy of the evaluation result to the actual power supply service performance.

[0021] In summary, the present invention constructs a power supply service evaluation system with intelligent adaptation ability through dynamic scoring management and self - learning weight optimization mechanism, provides a high - quality and quantifiable service quality evaluation basis for power enterprises, and promotes the continuous improvement and optimization of power supply services. Brief Description of the Drawings

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0023] Figure 1 is the flowchart of the method of the present invention. Detailed implementation manners

[0024] Next, in combination with the drawings and specific implementation manners, a preferred description of the invention will be given.

[0025] As Figure 1 shown, this embodiment describes a power supply service evaluation method based on dynamic weight adjustment. By periodically collecting user rating data and combining the power supply status to determine the environmental impact factor, according to the deviation between the user rating and the average score, the dynamic weight of the user rating is adjusted in real time, and then the rating is weighted to ensure that the evaluation result is more objective and fair, effectively suppressing the influence of abnormal ratings or score-padding behaviors on the accuracy of the power supply service evaluation, thereby improving the scientificity and accuracy of the power supply service quality monitoring.

[0026] In the present invention, the power supply service evaluation refers to a quantitative or qualitative comprehensive evaluation of the service quality, business handling efficiency, customer satisfaction, business complexity handling ability, etc. of the power service entity (such as a power supply company, service personnel or relevant business department) in the process of providing power services. This evaluation objectively reflects the overall quality of the power supply service by collecting the feedback information of users on the power supply service, especially the rating data, and combining the actual business processing indicators.

[0027] The power supply service evaluation includes a data-based evaluation of the service level shown by the power supply enterprise in links such as power supply, business acceptance, customer service, emergency response, and fault handling. The evaluation data at least includes user rating information, business processing information, and auxiliary information related to the power supply status, and is used to reflect the service performance and customer satisfaction of the power supply service unit or personnel within a preset period.

[0028] Step S10, collect the ratings of users on the power supply service and store the ratings in association with the user information.

[0029] After the power supply service is completed or ends stage by stage, feedback information made by users on the power supply service is collected through a preset service evaluation system. The feedback information includes, but is not limited to, numerical scores, text evaluations, service satisfaction level selections, service time period selections, service type identifications, and other information. Among them, the numerical score is a quantitative score given by users to the power supply service quality based on subjective evaluations. The score has a limited scoring range, preferably in the form of an integer or decimal between 1 and 10.

[0030] The user information includes, but is not limited to, user identity identification, user account information, power consumption address information, service request numbers, scoring timestamps, terminal device identifications, etc. The system correlates the scoring data submitted by users with the corresponding user information to form data pairs that can be used for subsequent statistical analysis, and stores the data pairs in a preset data storage module to support subsequent operations such as time division, introduction of environmental factors, and weight calculation.

[0031] The collection method of the score can be in forms such as manual input, mobile terminal submission, web interactive submission, or voice recognition conversion. The score collection system can be configured with a data verification module to verify the integrity and legality of the scoring data to ensure the accurate collection of the scoring data.

[0032] By associatively storing the user scores with the user information, the structured management of the scoring data is realized, ensuring the traceability and integrity of the data in subsequent processing links, and providing reliable data support for dynamic weight adjustment and power supply service quality evaluation.

[0033] Step S20: Divide the scores by time into preset time periods, and statistically calculate the average score of all users within each time period.

[0034] After collecting the user scoring data and completing the associative storage with the user information, according to the set time division rule, the scoring data is assigned to the corresponding time intervals, and statistical processing is performed on all user scoring data within each time interval to obtain the average score within that time period for subsequent dynamic weight calculation.

[0035] Specifically, the time division rule is an evaluation cycle division strategy preset by the system. Preferably, it is divided by units of days, weeks, months, or quarters, and the time division granularity can also be adaptively adjusted according to business requirements or service fluctuations. The time period is adjacent and non-overlapping time intervals for chronological sorting and batch processing of the scoring data.

[0036] Within each time period, the system extracts all user scores belonging to that time period , and calculates the average score within this time period based on the following mathematical formula : , wherein, represents the total number of users participating in the scoring within the current time period, represents the score submitted by the user.

[0037] The average score, as the statistical result of the current time period, will be used to adjust the dynamic weights of each user to determine the overall evaluation criteria for the scoring behavior within this time period.

[0038] In addition, the system can optimize and adjust the division granularity of time periods and the statistical method of average scores according to the user activity, the number of scores, and the score volatility within different time periods, so as to improve the flexibility of data processing and the evaluation accuracy. The specific optimization and adjustment methods are as follows: Based on the evaluation of user activity, the system counts the number of active users within each preset time period. An active user refers to a user who submits at least one score within this time period; if the number of active users is higher than the first threshold , the system will divide this time period into smaller granularity sub-time periods; if the number of active users is lower than the second threshold , the system will merge the current time period with the adjacent time period to form a larger granularity time interval.

[0039] Based on the judgment of the number of scores, the system records the total number of scores within each time period ; when the total number of scores exceeds the preset score number threshold , the system preferentially uses the median or weighted average method to calculate the average score to reduce the impact of extreme scores; if the number of scores is small, the system maintains the traditional arithmetic average calculation method or performs weighted smoothing processing based on historical score data.

[0040] According to the analysis of score volatility, the system calculates the variance or standard deviation of scores within each time period, denoted as or ; if the score volatility is greater than the volatility threshold , the system introduces robust statistical methods, such as calculating the average after removing the highest and lowest 5% of the scores, or using the weighted moving average method, to reduce the impact of score anomalies on the average score.

[0041] According to the adaptive adjustment of time granularity, the system, after comprehensively considering the number of active users , the total number of scores and the score volatility , dynamically adjusts the division granularity of time periods according to the following rules: If and , the current time period is divided into multiple sub - time periods; If and , it is merged with the adjacent time period to extend the time interval; The time period division result is fed back to the data processing module to optimize the subsequent scoring statistics and weight adjustment processes in real - time.

[0042] Furthermore, according to the scoring distribution characteristics, the average value calculation method is dynamically selected, specifically including arithmetic mean, weighted mean, trimmed mean, median, etc. The weighting coefficient can be set according to the user's historical scoring weights to ensure that the evaluation results are more authentic and reliable.

[0043] Through the above - mentioned optimization process, the system realizes an adaptive adjustment mechanism for time period division and average score statistical methods, improves the processing ability of the power supply service evaluation system in the case of diverse user scoring behaviors and fluctuating business handling, enhances the resistance to abnormal scoring behaviors, and ensures that the evaluation results have statistical stability, computational robustness, and application universality.

[0044] Step S30, determine the environmental impact factor according to the power supply state within the preset time period.

[0045] Within each time period, the system analyzes the objective power supply environment by collecting status information related to power supply services, quantifies the environmental factors that may affect the user's scoring mood and actual service experience, and generates an environmental impact factor 𝑘 for weight adjustment accordingly. This factor is used to suppress the scoring deviation caused by abnormal environments and enhance the fairness and robustness of the scoring results.

[0046] Specifically, the power supply state includes but is not limited to the following information: The number of planned power outages in the power supply area during this time period ; The number of unplanned power outages or fault - related power outages ; The average power outage duration of users ; The grid load rate ; The number of customer service complaints ; The total number of business transactions accepted by the power supply unit ; Whether this time period is during a business peak or a special period (such as holidays, bad weather periods).

[0047] Based on the power supply state parameters, the system determines the environmental impact factor according to the following calculation steps : Standardize each parameter and denote the normalized value as: , , , , , , Among them, the denominator of each index is the set maximum allowable value or the historical maximum value, which is used for normalization processing.

[0048] Let the weight coefficients of each parameter be Satisfy , then calculate the initial value of the environmental impact factor : , If this time period is during the business peak period or an emergency, then perform a gain adjustment on : , Among them, Is the adjustment factor, and the value range is , reflecting the buffering degree of the score fluctuation in special situations.

[0049] The value range of the finally obtained environmental impact factor 𝑘 is restricted to: , Among them, Is 1, Can be set to MaxScore (such as 10) to avoid excessive adjustment affecting the score calculation.

[0050] Through the above calculation, the environmental impact factor 𝑘 can comprehensively reflect the power supply environment stability and business pressure level in the current time period, effectively suppress the abnormal score fluctuation caused by the deterioration of the power supply state, make the dynamic weight adjustment more reasonable, and improve the adaptability and accuracy of the power supply service evaluation system in a complex power supply environment.

[0051] Exemplarily, taking February 2025 as the evaluation time period, due to frequent power outages for grid upgrade and transformation in a certain area, the power supply service environment is poor, and user complaints have increased significantly. The power supply state data collected by the system during this time period is shown in Table 1: Table 1 Power supply state data Item Value Normalized Maximum (Reference) Normalized Result Planned Power Outage Times 9 times 10 times 0.9 Unplanned Power Outage Times 6 times 10 times 0.6 Average Power Outage Duration 3 hours 4 hours 0.75 Grid Load Rate 90% 100% 0.9 Number of Customer Complaints 180 items 200 items 0.9 Total Business Volume Accepted 800 cases 1000 cases 0.8 The weight coefficients are: , , , In February, which is the peak period for power transformation, the adjustment factor , then: , Step S40: Determine the dynamic weight of the user for the current time period according to the average score, the environmental impact factor, and the user's basic weight.

[0052] The system retrieves the user's ratings submitted within the current time period from the database and obtains the average value of all users' ratings during this time period , as well as the user's basic weight stored in the previous cycle .

[0053] The system normalizes the user's basic weight by the maximum score MaxScore to eliminate the influence of the scoring standard difference on the weight calculation and obtain the normalized basic weight: , The system uses the following formula to determine the user's dynamic weight in the current time period : , where: The first term is the contribution of the basic weight; The second term is the contribution of the scoring deviation. After being adjusted by the environmental impact factor , it controls the influence range of the scoring deviation on the weight.

[0054] In this step, by comprehensively considering the user's scoring behavior and the system's global statistical data, the scoring influence of each user is dynamically adjusted to avoid unreasonable deviations in the evaluation results caused by a single score. Its core calculation mechanism is based on the following principles: The user's basic weight reflects the stability and authority of the user's historical ratings and is the historical dependence factor of the dynamic weight. The system normalizes it to ensure unified influence under different scoring systems.

[0055] The difference between the user's score and the average score of the time period measures the deviation degree of the individual's scoring behavior. This difference is adjusted by the environmental impact factor to prevent the amplification effect of large score fluctuations on the results.

[0056] The environmental impact factor \(k\) reflects the interference of the external environment of power supply services on user ratings. The worse the environment, the larger \(k\), thus reducing the weight contribution of the rating deviation term and realizing the buffering and isolation of the external environment from the evaluation system.

[0057] Step S50: Calculate the weighted rating of each user based on the user's dynamic weight and their rating.

[0058] After calculating the dynamic weight of the user for the current time period, the system operates this dynamic weight with the user's original rating to obtain the weighted rating of the user in the power supply service evaluation system, which is used to reflect the actual contribution value of the user's rating to the service evaluation result.

[0059] Specifically, the weighted rating reflects the actual influence of the user's rating after weight correction, which is used to eliminate the influence brought by rating deviation and ensure the fairness and authenticity of the final rating result. The system adopts the following weighted calculation method: Let the original rating of user be , the dynamic weight be , and the weighted rating be , then: Among them, if the weighted rating exceeds the maximum rating value MaxScore, then take MaxScore as the upper limit of the weighted rating of this user to prevent rating distortion.

[0060] In this step, when the user's rating is high and the weight is positive, the weighted rating is appropriately increased to encourage positive rating behavior; when the user's rating is low and the weight is negative, the weighted rating is appropriately decreased to weaken the impact of malicious or abnormally low ratings on the evaluation result; the weighted rating does not exceed the preset maximum value to ensure the rationality of the rating and the stability of the result; the system realizes the quantification of the user's rating contribution through the weighted rating and improves the credibility of the service evaluation.

[0061] Step S60: Calculate the total score of the power supply service based on the weighted rating of each user.

[0062] After completing the calculation of the weighted ratings of each user, the system summarizes and processes the weighted rating data of all users to quantitatively reflect the overall service quality level of the power supply service object (such as service personnel, service units or business departments) within the preset evaluation period. The total score can be used as a reference basis for power supply service performance evaluation, user satisfaction management and service improvement.

[0063] The system obtains the weighted rating data of all valid users within the current evaluation period, denoted as , where is the total number of users participating in the evaluation, is the weighted score of user \(i\), which is obtained by dynamically adjusting the original score of the user and has been capped according to the set upper limit.

[0064] In an alternative approach, the system calculates the total score of the power supply service using the arithmetic mean method , and the formula is as follows: , In an alternative approach, according to actual requirements, the system can set higher weights for the scores of some users and calculate the total score using the weighted average method: , where, is the weighted coefficient of user \(i\), which is used to enhance the influence of the scores of key users.

[0065] Exemplarily: During a certain period, the highest score MaxScore = 10; the average score of the time period ; the basic weight of the user ; environmental impact factor: normal environment: k = 1, off-season (less handling volume, increased business quality weight, k = 2) Table 2 User score data User User Rating Description User A 9 High score, satisfied, slightly on the high side User B 4 Low score, dissatisfied, emotional fluctuation User C 7 Equal to the average score, neutral User D 8 Slightly higher score, relatively positive User E 5 Lower score, may have an emotional low rating User F 6 Slightly lower than the average, normal fluctuation Table 3 When the dynamic weight (k = 1) User Calculation Process Dynamic Weight User A 0.05 + (7-9) / 10 = 0.05 - 0.2 -0.15 User B 0.05 + (7-4) / 10 = 0.05 + 0.3 0.35 User C 0.05 + 0 = 0.05 0.05 User D 0.05 + (7-8) / 10 = 0.05 - 0.1 -0.05 User E 0.05 + (7-5) / 10 = 0.05 + 0.2 0.25 User F 0.05 + (7-6) / 10 = 0.05 + 0.1 0.15 Table 4 When the dynamic weight (k = 2, off-season of business) User Calculation Process Dynamic Weight User A 0.05 + (7-9) / 20 = 0.05 - 0.1 -0.05 User B 0.05 + (7-4) / 20 = 0.05 + 0.15 0.2 User C 0.05 + 0 = 0.05 0.05 User D 0.05 + (7-8) / 20 = 0.05 - 0.05 0 User E 0.05 + (7-5) / 20 = 0.05 + 0.1 0.15 User F 0.05 + (7-6) / 20 = 0.05 + 0.05 0.10 Table 5 If there is no dynamic weight (traditional method) User Original Rating Weighted Rating = Original Rating User A 9 9 User B 4 4 User C 7 7 User D 8 8 User E 5 5 User F 6 6 Total score = (9 + 4 + 7 + 8 + 5 + 6) / 6 = 6.5 With dynamic weight, when k = 1 User Calculation Weighted Rating User A 9 × 0.85 = 7.65 7.65 User B 4 × 1.35 = 5.4 5.4 User C 7 × 1.05 = 7.35 7.35 User D 8 × 0.95 = 7.6 7.6 User E 5 × 1.25 = 6.25 6.25 User F 6 × 1.15 = 6.9 6.9 Total score ≈ (7.65 + 5.4 + 7.35 + 7.6 + 6.25 + 6.9) / 6 ≈ 6.86 Table 6 When there is dynamic weight + environmental factor (k = 2, off-season of business) User Calculation Weighted Rating User A 9 × 0.95 = 8.55 8.55 User B 4 × 1.2 = 4.8 4.8 User C 7 × 1.05 = 7.35 7.35 User D 8 × 1 = 8 8 User E 5 × 1.15 = 5.75 5.75 User F 6 × 1.1 = 6.6 6.6 Total score ≈ (8.55 + 4.8 + 7.35 + 8 + 5.75 + 6.6) / 6 ≈ 6.84 Table 7 Comparison of several evaluation methods Evaluation Method Total Score Contribution of High-Score Users Impact of Low-Score Users Explanation of System Advantages No Dynamic Weight (Traditional) 6.5 Unadjusted Directly Pulled Down Easily affected by low-score cheating, unable to reflect the adjustment function of rating deviation Dynamic Weight, without Environmental Factor 6.86 Weakened Buffered Inhibit high-score cheating, amplify real low scores, and enhance fairness Dynamic Weight + Environmental Factor (Off-Peak Season) 6.84 Partially Buffered Moderately Buffered The weight of business quality in the off-peak season is increased, the system buffers rating fluctuations, and the stability is strong As can be seen from the above examples, in the present invention, the high score weight is weakened to avoid boosting the total score by gaming the system; the low score weight is increased to highlight problem reflection. During the off-peak season of the business, k increases to buffer the scoring deviation and prevent the low scores from concentrating and dragging down the overall evaluation in a harsh environment. The combined action of the dynamic weight and the environmental factor ensures that the total score can truly reflect the service and is resistant to abnormal interference.

[0066] Step S70: After the combination in each time period, update the basic weight for each user according to the dynamic weight.

[0067] After the end of each evaluation period, according to the scoring performance of the user during this time period and the calculated dynamic weight , with a preset weight update strategy, adjust the basic weight of the user so as to dynamically reflect the long-term credibility of the user's scoring behavior and reasonably control its influence in subsequent scoring. The update strategy can be any of the following methods, or based on a multi-strategy fusion.

[0068] Update strategy one: , wherein, represents the smoothing coefficient, which controls the proportion of the historical weight and the current weight, preferably .

[0069] Strategy one can suppress the violent fluctuations caused by short-term scoring anomalies; maintain the long-term continuity of the scoring influence, which is suitable for stable user groups; the system runs smoothly, which is suitable for the evaluation of daily power supply services.

[0070] Update strategy two: , wherein, represents the number of time periods that the user has participated in the evaluation cumulatively; represents the dynamic weight in the 𝑡-th time period.

[0071] Strategy two is suitable for the scenario of continuously tracking the long-term scoring behavior of users and gradually correcting their weights. Each update considers the dynamic weights of the entire historical cycle, reflecting the long-term scoring trend of users; suppressing the interference of abnormal weights in individual time periods and improving the weight stability; suitable for the system environment where users are active for a long time and evaluate frequently.

[0072] Update strategy three: If , then trigger the update; Update method: , Otherwise, keep the original basic weight unchanged.

[0073] wherein, denotes a preset update trigger threshold, preferably 0.2 - 0.3.

[0074] Strategy three is applicable to identifying and dealing with users with sudden changes in scoring behavior or obvious score-padding tendencies. It can quickly respond to abnormal fluctuations in user scores and adjust weights in a timely manner; it is applicable to identifying score-padding behaviors and forcibly correcting the influence of scores; it avoids frequent changes of normal-scoring users and improves the system's anti-attack ability.

[0075] Update strategy four: , wherein, denotes the historical weight decay coefficient, preferably ; denotes the system's preset neutral weight reference value, such as 0.5 - 1.

[0076] Strategy four is applicable to controlling the excessive long-term accumulation of historical weights and preventing old data from dominating the scoring influence for a long time. The historical weights gradually approach the system standard to eliminate long-term accumulated biases; it is applicable to the system's regular reset to maintain the balance of scoring influence; it simplifies data requirements and is applicable to resource-constrained scenarios.

[0077] In another embodiment, the present invention also provides a power supply service evaluation system based on dynamic weight adjustment, including: A collection module, configured to collect users' scores for power supply services and store the scores in association with user information; A statistics module, configured to divide the scores by time into preset time periods and calculate the average score of all users within each time period; A first determination module, configured to determine an environmental impact factor according to the power supply status within a preset time period; A second determination module, configured to determine the dynamic weight of a user for the current time period according to the average score, environmental impact factor, and the user's base weight; A first calculation module, configured to calculate the weighted score of each user according to the user's dynamic weight and their score; A second calculation module, configured to calculate the total score of the power supply service according to the weighted scores of each user; An update module, configured to update the base weight of each user according to the dynamic weight after each time period combination.

[0078] It should be noted that the explanations of the foregoing embodiments of the power supply service evaluation method based on dynamic weight adjustment also apply to the device of the embodiments of the present application, and will not be elaborated here.

[0079] Those of ordinary skill in the art can realize that the units and algorithm steps described in the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0080] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0081] In several embodiments provided in this application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (hereinafter referred to as ROM), random access memories (hereinafter referred to as RAM), magnetic disks, or optical discs that can store program codes.

[0082] The above is only the specific implementation manner of this application. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. The protection scope of this application shall be subject to the protection scope of the claims. For the part of the module structure that is not specifically defined in this invention, the content recorded in the prior art shall prevail. The prior art mentioned in the foregoing background art part and specific embodiment part of this invention can be used as a part of this invention to understand the meaning of some technical features or parameters.

Claims

1. A power supply service evaluation method based on dynamic weight adjustment, characterized in that The method includes the following steps: Collect the scores given by users for power supply services, and store the scores in association with user information; Divide the scores by time into preset time periods, and calculate the average score of all users within each time period; Determine the environmental impact factor according to the power supply status within the preset time period; Determine the dynamic weight of the user in the current time period according to the average score, environmental impact factor, and the basic weight of the user; Calculate the weighted score of each user according to the dynamic weight of the user and their score; Calculate the total score of the power supply service according to the weighted scores of each user; After each time period is combined, update the basic weight for each user according to the dynamic weight.

2. The power supply service evaluation method based on dynamic weight adjustment according to claim 1, wherein The determination of the environmental impact factor includes the following steps: Collect the power supply status information within the preset time period; Perform standardization processing on the power supply status information, and perform weighted calculation according to the set weights of each index to obtain the initial value of the environmental impact factor for the time period; Perform gain adjustment on the initial value of the environmental impact factor according to the business busy degree of the time period to obtain the adjusted environmental impact factor.

3. The power supply service evaluation method based on dynamic weight adjustment according to claim 1, characterized in that The method for determining the dynamic weight includes: ， Among them, represents the dynamic weight, represents the user's basic weight, represents the highest score that the user can give, represents the environmental impact factor, represents the average score, represents the user 's score.

4. The power supply service evaluation method based on dynamic weight adjustment according to claim 1, wherein The calculation of the weighted score of each user according to the dynamic weight of the user and their score includes: ， Among them, represents the user's rating, represents the dynamic weight, represents the weighted rating.

5. The power supply service evaluation method based on dynamic weight adjustment according to claim 1, characterized in that After each time period is combined, updating the basic weight for each user according to the dynamic weight includes one of the following strategies: Update strategy one: ， Update strategy two: ， Update strategy three: If , an update is triggered; Update method: , Otherwise, keep the original basic weight unchanged; Update strategy four: ， Wherein: represents the new base weight; represents the base weight of the previous time period; represents the smoothing coefficient; represents the number of time periods that the user has cumulatively participated in the evaluation; represents the dynamic weight in the 𝑡-th time period; represents the highest score that the user can give; represents the preset update trigger threshold; represents the historical weight decay coefficient; represents the system preset neutral weight reference value.

6. A power supply service evaluation system based on dynamic weight adjustment, characterized in that, The system includes the following modules: A collection module, used to collect the scores given by users for power supply services, and store the scores in association with user information; A statistics module, used to divide the scores by time into preset time periods, and calculate the average score of all users within each time period; A first determination module, used to determine the environmental impact factor according to the power supply status within the preset time period; A second determination module, used to determine the dynamic weight of the user in the current time period according to the average score, environmental impact factor, and the basic weight of the user; A first calculation module, used to calculate the weighted score of each user according to the dynamic weight of the user and their score; A second calculation module, used to calculate the total score of the power supply service according to the weighted scores of each user; An update module, used to update the basic weight for each user according to the dynamic weight after each time period is combined.

7. The power supply service evaluation system based on dynamic weight adjustment according to claim 6, characterized in that The first determination module includes the following sub-modules: A second collection module, used to collect the power supply status information within the preset time period; A weighted calculation module, used to perform standardization processing on the power supply status information, and perform weighted calculation according to the set weights of each index to obtain the initial value of the environmental impact factor for the time period; An adjustment module, used to perform gain adjustment on the initial value of the environmental impact factor according to the business busy degree of the time period to obtain the adjusted environmental impact factor.

8. The power supply service evaluation system based on dynamic weight adjustment according to claim 6, wherein The dynamic weight is determined using the following formula: ， Among them, represents the dynamic weight, represents the user's basic weight, represents the highest score that the user can give, represents the environmental impact factor, represents the average score, represents the user 's score.

9. The power supply service evaluation system based on dynamic weight adjustment according to claim 6, wherein The calculation of the weighted score of each user according to the dynamic weight of the user and their score includes: ， Among them, represents the user 's score, represents the dynamic weight, represents the weighted score.

10. The power supply service evaluation system based on dynamic weight adjustment according to claim 6, wherein After each time period is combined, updating the basic weight for each user according to the dynamic weight includes one of the following strategies: Update strategy one: ， Update Strategy 2: ， Update Strategy 3: If , then trigger an update; Update method: , Otherwise, keep the original base weight unchanged; Update Strategy 4: ， Wherein: represents the new base weight; represents the base weight of the previous time period; represents the smoothing coefficient; represents the number of time periods that the user has cumulatively participated in the evaluation; represents the dynamic weight within the \(t\) -th time period; represents the highest score that the user can give; represents the preset update trigger threshold; represents the historical weight decay coefficient; represents the system - preset neutral weight reference value.

Images