Incentive method and system for reverse garbage collection based on bidirectional evaluation and credit score dynamic adjustment

Abstract

The application discloses a kind of based on two-way evaluation and credit score dynamic adjustment's reverse garbage service incentive method and system, this method includes: after order completion, service personnel submits independent overall evaluation classification compliance special evaluation to user;Platform anonymously collects the evaluation of multiple different service personnel to the same user within the set aggregation window, and does not disclose to user during window period. After window ends, according to the consistency analysis of service personnel evaluation credibility weight, the weighted non-compliance report proportion is obtained, and the user compliance confidence level is determined;Again, according to the level, adjust user credit score. When non-compliance confirmed user orders again, according to the weighted non-compliance report proportion and order benchmark service fee to determine additional service subsidies, and show on service personnel order interface. This method can improve the authenticity of classification evaluation, enhance the credit score constraint effect, and improve the service incentive of non-compliant order.

Description

Technical Field

[0001] This application relates to the field of order service incentive technology, specifically to a garbage disposal service incentive method and system based on two-way evaluation and dynamic adjustment of credit scores. Background Technology

[0002] With the continued implementation of urban household waste sorting systems, the quality of waste sorting by residents has become a crucial management issue in community governance and the operation of community service platforms. Existing waste disposal service platforms typically operate through online ordering, service personnel collection and disposal, and mutual evaluation upon order completion. They also use mechanisms such as credit scores and ranking systems to regulate user and service personnel behavior. In actual service, service personnel can directly observe whether users' waste sorting is compliant, whether the packaging is standardized, and whether secondary sorting is needed when collecting waste; therefore, their evaluation data has significant on-site and management value.

[0003] However, existing two-way evaluation mechanisms often mix service quality evaluations and user behavior evaluations. Evaluation results are typically added to the credit score and displayed to the recipient immediately after the order is completed. If service personnel truthfully report non-compliant user classification, they may be affected by low-score reviews or complaints, leading to damage to their credit score, order ranking, and subsequent earnings. This can result in reluctance, fear, or compromise in their evaluations, distorting the data related to waste sorting. Furthermore, individual order evaluations are heavily influenced by service scenarios, individual judgment differences, and chance factors, lacking aggregated verification of independent evaluations from multiple service personnel, making it difficult to establish stable and reliable judgments on user classification compliance.

[0004] Furthermore, existing credit score adjustments typically involve direct increases or decreases based on instant ratings, failing to differentiate between various scenarios such as compliant and reliable, questionable and under observation, and confirmed non-compliance. They also fail to differentiate treatment based on the credibility and degree of non-compliance of reviews. For users with consistently non-standard waste sorting practices, service personnel often incur additional sorting and handling costs, but platform order compensation fails to effectively link this extra labor, resulting in insufficient incentive for service personnel to provide truthful reviews and accept such orders. Therefore, it is necessary to improve the review collection, credit score adjustment, and service incentive mechanisms in waste disposal services. Summary of the Invention

[0005] In view of this, this disclosure proposes a method and system for incentivizing garbage disposal services based on two-way evaluation and dynamic adjustment of credit scores.

[0006] According to one aspect of this disclosure, a method for incentivizing garbage disposal services based on two-way evaluation and dynamic adjustment of credit scores is provided, including:

[0007] After a garbage disposal service order is completed, the service personnel submit a specific evaluation of the user's garbage sorting compliance. This specific evaluation of garbage sorting compliance is independent of the service personnel's overall evaluation of the user.

[0008] Within a set aggregation window, multiple different service personnel anonymously collect the category compliance evaluations submitted by the same user, and the category compliance evaluations are not disclosed to the user during the aggregation window period.

[0009] After the aggregation window ends, a weighted consistency analysis is performed on all categorized compliance evaluations received by the same user within the aggregation window, based on the credibility weight of each service personnel's evaluation. This yields a weighted non-compliance report ratio, and the user's compliance confidence level is determined based on the weighted non-compliance report ratio.

[0010] The user's credit score is adjusted according to the compliance confidence level, with different compliance confidence levels corresponding to different credit score adjustment directions and magnitudes;

[0011] When a user with a compliance confidence level of non-compliance confirmation initiates a new service request, the additional service subsidy amount for the order is determined based on the user's weighted non-compliance report ratio and the order's base service fee, and the additional service subsidy is displayed on the service personnel's order acceptance interface.

[0012] In one possible implementation, determining the evaluation credibility weight includes: counting the number of times that the evaluation conclusion of the service personnel is consistent with the majority opinion of other service personnel on the same user in all the category compliance special evaluations submitted by the service personnel within the set historical period, and taking the proportion of the consistent number to the total number of evaluations by the service personnel within the historical period as the evaluation credibility weight of the service personnel.

[0013] In one possible implementation, when the cumulative number of categorized compliance evaluations by service personnel does not reach the set minimum evaluation threshold, the evaluation credibility weight takes a default value; after reaching the minimum evaluation threshold, the evaluation credibility weight is calculated according to the proportion of consistent evaluations within the historical period, and is recalculated and updated at the end of each aggregation window.

[0014] In one possible implementation, the compliance confidence level includes three levels: compliant and credible, questionable and under observation, and non-compliance confirmed. The threshold for classifying the three levels is determined through a trial operation period: during the trial operation period, classification compliance evaluation data is collected but credit score adjustments are not performed. After the trial operation period ends, the weighted non-compliance report ratio of each user is compared with the results of manual on-site verification, and the weighted non-compliance report ratio value that makes the classification judgment accuracy rate and misjudgment rate reach the set level is selected as the level classification threshold.

[0015] In one possible implementation, adjusting the user's credit score based on the compliance confidence level includes: when the compliance confidence level is "compliant and trustworthy," determining a compliance reward coefficient based on the number of consecutive windows in which the user has obtained a compliance and trustworthy level, and using the product of the compliance reward coefficient and the single adjustment benchmark score as a positive adjustment amount for the credit score; when the compliance confidence level is "questionable and pending observation," not adjusting the credit score in the current window, and deducting the credit score when two consecutive aggregation windows are both "questionable and pending observation"; when the compliance confidence level is "non-compliance confirmed," using the product of the non-compliance deduction coefficient, the weighted non-compliance reporting ratio, and the single adjustment benchmark score as a negative adjustment amount for the credit score.

[0016] In one possible implementation, the non-compliance deduction coefficient is determined based on manual sampling data during the trial operation period: the average number of window periods from the initial confirmation of non-compliance to the improvement of classification behavior of non-compliant users is statistically analyzed, and the non-compliance deduction coefficient value that causes continuous deductions to reduce the credit score to a set threshold within the average number of window periods is calculated in reverse.

[0017] In one possible implementation, the additional service subsidy is funded by the user's additional service fee: the platform automatically adds an additional service fee to the service orders of users whose compliance confidence level is non-compliant confirmation, and the amount of the additional service fee is equal to the amount of the additional service subsidy. The user can view the additional service fee on the order page.

[0018] In one possible implementation, after the aggregation window ends, the proportion of each service personnel whose classification compliance evaluation conclusions in the window are consistent with the direction of the final determined compliance confidence level is counted. When the proportion exceeds a set threshold, an additional positive adjustment amount is added to the credit score of the service personnel.

[0019] In one possible implementation, when the number of service personnel participating in the evaluation of the same user within the aggregation window does not reach the set minimum number, the consistency analysis result of the aggregation window is not included in the credit score adjustment, and the classification compliance special evaluation data within the window is merged into the next aggregation window for weighted consistency analysis again.

[0020] According to another aspect of this disclosure, a garbage disposal service incentive system based on two-way evaluation and dynamic adjustment of credit scores is provided, comprising:

[0021] The special evaluation receiving module is used for service personnel to submit a special evaluation of classification compliance to users after the garbage disposal service order is completed. The special evaluation of classification compliance is independent of the service personnel's overall evaluation of users.

[0022] An anonymous aggregation module is used to anonymously collect the classification compliance evaluations submitted by multiple different service personnel to the same user within a set aggregation window. The classification compliance evaluations are not disclosed to the user during the aggregation window.

[0023] The compliance analysis module is used to perform a weighted consistency analysis on all categorized compliance evaluations received by the same user within the aggregation window after the aggregation window ends, based on the credibility weight of each service personnel's evaluation, to obtain the weighted non-compliance report ratio, and to determine the user's compliance confidence level based on the weighted non-compliance report ratio.

[0024] The credit score adjustment module is used to adjust the user's credit score according to the compliance confidence level. Different compliance confidence levels correspond to different credit score adjustment directions and adjustment ranges.

[0025] The subsidy determination and display module is used to determine the additional service subsidy amount for a new service request when a user with a compliance confidence level of non-compliance confirmation initiates a new service request, based on the user's weighted non-compliance report ratio and the order's base service fee, and to display the additional service subsidy in the service personnel's order acceptance interface.

[0026] This application separates the overall user evaluation and the specific evaluation of waste sorting compliance in the garbage disposal service, enabling waste sorting behavior to be collected and judged independently, preventing it from being masked by ordinary service ratings. The specific evaluation of waste sorting compliance is collected anonymously and disclosed with a delay within the aggregation window, reducing service personnel's concerns about receiving low scores for truthfully reporting users' non-compliant sorting, thus improving the authenticity of the evaluation data. After the aggregation window ends, this invention determines the evaluation credibility weight based on the consistency of service personnel's historical evaluations and performs a weighted consistency analysis on the evaluations of multiple service personnel for the same user, which can reduce the impact of single evaluation bias and individual abnormal evaluations on the judgment results, forming a more reliable compliance confidence level. Furthermore, this invention differentiates and adjusts the user's credit score based on the compliance confidence level, and when a user with non-compliance is confirmed to place a subsequent order, it links the degree of non-compliance with additional service subsidies, so that the additional sorting costs caused by non-standard sorting can be reflected in the order incentive, thereby taking into account user behavior constraints, service personnel's enthusiasm for accepting orders, and platform governance effectiveness.

[0027] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0028] The accompanying drawings, which are included in and form part of this specification, illustrate exemplary embodiments, features, and aspects of this disclosure together with the specification and serve to explain the principles of this disclosure.

[0029] Figure 1 A flowchart is shown for a garbage disposal service incentive method based on two-way evaluation and dynamic adjustment of credit scores, according to an embodiment of the present disclosure.

[0030] Figure 2 A flowchart of weighted consistency analysis according to an embodiment of this disclosure is shown.

[0031] Figure 3 This diagram illustrates the structure of a garbage disposal service incentive system based on two-way evaluation and dynamic adjustment of credit scores, according to an embodiment of the present disclosure.

[0032] Figure 4 A schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0033] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. Like reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise. The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0034] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant regions.

[0035] This embodiment provides an incentive method for garbage disposal services based on two-way evaluation and dynamic adjustment of credit scores, applicable to online platforms operating household waste disposal services. The platform has two registered roles: users and service personnel. Users initiate garbage disposal service requests through the client, and the platform assigns the order to a service personnel. After each service is completed, both the user and the service personnel evaluate each other, and each holds a credit score, which is updated sequentially based on the evaluation results. The city where the platform is located has implemented a mandatory household waste sorting system, allowing service personnel to directly observe the sorting status of the garbage disposed of by users when collecting it. The platform uses a rotation allocation rule to assign service personnel, with the same user being served by different service personnel in multiple consecutive services; based on a typical service frequency of 3 to 7 times per week, a user typically receives services from at least 3 different service personnel within 7 days.

[0036] According to an embodiment of this disclosure, a user submits a garbage disposal service request through a client, the request including the user's address, appointment time, and garbage description information. The platform selects a service provider from candidates based on their geographical location, current order load, and credit score. The service provider arrives at the user's residence to collect the garbage, transports it to the designated disposal point, and confirms the order completion through the client. After the order is completed, the platform pushes an evaluation portal to both parties: the user rates the service provider's overall service from 1 to 5 points, which is a positive evaluation score and is immediately added to the service provider's credit score according to the platform's general scoring rules; the service provider's evaluation of the user is divided into two parts: an overall evaluation score, also from 1 to 5 points, which is immediately added to the user's credit score; and a specific evaluation on classification compliance, which is processed separately as described below.

[0037] The implementation process of the method described in this application will be described in detail below with reference to specific embodiments. It should be noted that this embodiment is only used to explain this application and is not intended to limit the scope of protection of this application. Conventional adjustments or substitutions of each step by those skilled in the art without departing from the concept of this application should be included in the scope of protection of this application.

[0038] Figure 1 A flowchart illustrating an incentive method for garbage disposal services based on two-way evaluation and dynamic adjustment of credit scores, according to an embodiment of this disclosure, is shown. Figure 1 As shown, the method may include:

[0039] In step S11, after the garbage disposal service order is completed, the service personnel submit a special evaluation on classification compliance to the user. The special evaluation on classification compliance is independent of the service personnel's overall evaluation of the user.

[0040] In one embodiment, after each garbage disposal service, service personnel must complete a specific evaluation of waste sorting compliance in addition to submitting an overall user rating. This specific evaluation is independent of the overall rating, does not affect the immediate scoring process of the overall rating, and is not combined with the overall rating. The specific evaluation includes three dimensions: the first dimension is the degree of compliance, with options for "compliant," "partially compliant," and "non-compliant"; the second dimension is the standardization of garbage packaging, with options for "standardized" and "non-standardized"; and the third dimension is whether the service personnel needed to perform secondary sorting of the garbage during the service, with options for "yes" and "no." The degree of compliance is determined based on the household waste sorting standards published by the city where the platform is located, and service personnel receive standardized training on these standards after joining the platform.

[0041] In step S12, within a set aggregation window, multiple different service personnel anonymously collect the classification compliance evaluations submitted by the same user. The classification compliance evaluations are not disclosed to the user during the aggregation window.

[0042] In one embodiment, the classification compliance evaluation adopts anonymized collection and delayed disclosure. Specifically, after a service provider submits a classification compliance evaluation, the user cannot view the content of the evaluation or know its source. The platform sets an aggregation window for each user, which is a continuous time interval. All classification compliance evaluations collected within this interval are processed uniformly after the window ends. The duration of the aggregation window is configurable, for example, set to 7 days. Within the 7-day window period, the same user typically receives services from more than 3 different service providers, resulting in multiple classification compliance evaluations from independent sources.

[0043] The purpose of anonymous collection and delayed disclosure is to address the issue that, in the existing two-way rating system, if service personnel truthfully report user classification non-compliance, users are likely to respond with low scores, damaging the service personnel's credit score. To avoid this consequence, service personnel generally do not provide truthful evaluations on classification issues, thus distorting the evaluation data. Delayed disclosure prevents users from pointing any specific classification compliance evaluation to a particular service personnel during the entire aggregation window, thereby structurally eliminating the correlation between retaliatory negative reviews.

[0044] In step S13, after the aggregation window ends, a weighted consistency analysis is performed on all categorized compliance evaluations received by the same user within the aggregation window, based on the evaluation credibility weight of each service personnel, to obtain the weighted non-compliance report ratio, and the user's compliance confidence level is determined based on the weighted non-compliance report ratio.

[0045] After the aggregation window ends, the platform performs a weighted consistency analysis on all category compliance-specific evaluations received by the same user within that window. The basic logic of the analysis is that multiple unrelated service personnel independently provide evaluations in different service sessions, and the reliability of the evaluation conclusions is determined by statistically analyzing the consistency between these evaluations.

[0046] Figure 2 A flowchart of weighted consistency analysis according to an embodiment of this disclosure is shown, such as Figure 2 As shown, in step S1301, the evaluation credibility weight of each service personnel participating in the evaluation is determined. Before the weighted consistency analysis, the evaluation credibility weight of each service personnel participating in the evaluation is determined first. The evaluation credibility weight reflects the degree of agreement between a service personnel's judgment and that of other service personnel regarding classification compliance evaluation.

[0047] Specifically, the consistency rate is calculated as the number of times a service provider's evaluation conclusion aligns with the majority opinion of other service providers within the same aggregation window for the same user across all categorized compliance evaluations submitted within a defined historical period (e.g., the past 30 days). Here, "majority opinion" refers to the evaluation conclusions given by more than half of the service providers within the window, indicating either compliance or non-compliance. The proportion of these consistent evaluations to the total number of evaluations submitted by the service provider within that historical period is defined as the consistency rate, denoted as . , This is a dimensionless ratio, ranging from 0 to 1. Weighting for evaluating credibility. Directly take the numerical value of the consistency rate of the evaluation, that is

[0048]

[0049] For example, if service personnel A submitted classification compliance evaluations for 15 different users in the past 30 days, and the conclusions of 12 of these evaluations were consistent with the majority opinion of other service personnel during the same window period, then... Correspondingly .

[0050] When a service provider's cumulative number of compliance-specific evaluations falls below the set minimum evaluation threshold, historical data is insufficient to reflect their evaluation preferences, and the evaluation credibility weight defaults to 1.0. The minimum evaluation threshold is configurable, for example, 10 times. Once this threshold is reached, the evaluation credibility weight is calculated as described above, and recalculated and updated at the end of each aggregation window based on the latest historical data.

[0051] By introducing a weighted evaluation credibility, if a service provider consistently reports non-compliance to most users and their judgments remain inconsistent with those of other service providers, their evaluation consistency rate will naturally be lower, and their weight in subsequent summaries will be reduced, thereby decreasing the impact of individual biased evaluations on the overall conclusion.

[0052] In step S1302, after determining the credibility weight of each evaluator's evaluation, all the categorized compliance evaluations received by the user in the current aggregation window are weighted and summarized to calculate the weighted non-compliance report ratio.

[0053] Among them, the weighted non-compliance reporting ratio It reflects the degree of non-compliance of the user's classification after the summarization of multi-source evaluations, and the value ranges from 0 to 1, which is a dimensionless ratio.

[0054] In the specific calculation, reports selected as "non-compliant" or "partially compliant" in the compliance level dimension are considered non-compliant reports, and the corresponding indicator variables... The value is 1; selecting "Compliance" is considered a compliance report. The value is 0. The formula for calculating the weighted non-compliance reporting ratio is:

[0055]

[0056] in This represents the total number of service personnel currently participating in the evaluation of this user within the aggregation window. For service personnel The evaluation credibility weight, This is the indicator variable corresponding to the service personnel. The numerator is the sum of the credibility weights of the evaluations of all evaluators who reported non-compliance, and the denominator is the sum of the credibility weights of the evaluations of all evaluators.

[0057] As an example, a user received services from four service providers within an aggregated window, with their rating credibility weights of 0.9, 0.8, 1.0, and 0.7, respectively. The first and third service providers reported that the user's classification was non-compliant. , The 2nd and 4th place reports were compliant. , Substituting into the above formula, .

[0058] In some embodiments, when the number of service personnel participating in the evaluation of the same user within an aggregation window does not reach the set minimum number (e.g., 3), the number of independent evaluation sources is too small, and the reliability of the consistency analysis is insufficient. In this case, the consistency analysis results of the aggregation window are not included in the subsequent credit score adjustment. The platform merges the classification compliance special evaluation data collected in the window into the next aggregation window, and performs a weighted consistency analysis again together with the newly collected evaluation data in the next window.

[0059] In step S1303, based on the weighted non-compliance reporting ratio The value of this value categorizes the user's compliance status in the current aggregation window into three compliance confidence levels. The compliance confidence level is a graded assessment of a user's compliance level in waste sorting within an aggregation window, divided into three levels: credible compliance, questionable and awaiting observation, and confirmed non-compliance.

[0060] In one embodiment, the thresholds for the three levels are determined through a trial operation period. Specifically, before officially launching the credit score adjustment function, the platform runs a trial operation period (e.g., 2 months), during which only classification compliance evaluation data is collected but credit score adjustments are not performed. After the trial operation period, the platform calculates the weighted non-compliance reporting ratio for all users. Statistical analysis was conducted on the distribution of users, and a certain percentage of users were randomly selected for on-site manual verification. This involved city sanitation management departments or platform operators conducting on-site inspections of their waste sorting practices. The results of the manual verification were then compared with those of the corresponding users. The values ​​were compared, and the classification accuracy and misclassification rate were used as evaluation indicators to select values ​​that brought both indicators to an acceptable level. The value is used as the threshold for classifying grades.

[0061] As an example, the calibrated threshold is set as follows: The compliance confidence level is determined to be compliant and trustworthy. It was initially determined to be questionable and require further observation; If deemed non-compliant, the platform may periodically review and adjust the above thresholds based on feedback from subsequent manual spot checks during operation.

[0062] In step S14, the user's credit score is adjusted according to the compliance confidence level. Different compliance confidence levels correspond to different credit score adjustment directions and adjustment ranges.

[0063] Once the compliance and trust level is determined, the platform will adjust the user's credit score accordingly. Different compliance and trust levels correspond to different adjustment directions and magnitudes. Specifically, the following three situations will be handled.

[0064] When the compliance confidence level is "compliant and trustworthy," the user's credit score is increased by a positive adjustment factor. Positive adjustment factor The calculation involves two parameters: the single-adjustment baseline score. and compliance reward coefficient . The value is determined by the platform based on the total score range of the credit scoring system. For example, when the maximum credit score is 1000 points, It can be set to 5 points. This is a dimensionless coefficient, based on the number of consecutive window periods during which the user obtains a compliance and trustworthiness level. Segmented value retrieval: hour ; hour ; hour The positive adjustment amount is:

[0065]

[0066] in Dimensionless The unit is cents. The unit is points. For example, if a user has been judged as compliant and trustworthy for 4 consecutive windows, then... , Points. The more consecutive compliance windows a user has, the higher the reward coefficient; users with consistently good category performance will receive increasing point rewards.

[0067] When the compliance confidence level is "Questionable and Under Observation," the current aggregation window will not adjust the user's credit score. The platform records the number of consecutive windows during which the user is in the "Questionable and Under Observation" status. If two consecutive aggregation windows determine the user to be in the "Questionable and Under Observation" status, a small deduction will be made at the end of the second window. At the same time, the platform sends a category improvement reminder to the user.

[0068] When the compliance confidence level is changed to non-compliance confirmation, the user's credit score will be reduced by a negative adjustment amount. The calculation method is as follows:

[0069]

[0070] in For non-compliant deduction coefficients; This represents the weighted proportion of non-compliance reports for the current window. This is the baseline score for a single adjustment, in points. The unit is minutes.

[0071] Among them, non-compliant deduction coefficient The value ranges from 1.0 to 3.0, and its determination method is as follows: Based on the manual sampling data during the trial operation period, the platform calculates the average number of window periods (i.e., the average improvement period) experienced by non-compliant users from the initial confirmation of non-compliance to the improvement of their classification behavior. Then, it calculates in reverse the deductions to reduce the credit score of typical non-compliant users to a set threshold within the average improvement period. Specifically, assuming an average improvement cycle of four windows, users face additional service fees when their credit score falls below a certain threshold. The platform uses this as a target constraint, substituting a typical value for the non-compliance ratio into the above formula, and setting the cumulative deduction over four windows equal to the difference between the initial score and the threshold score. This allows us to solve for... After trial operation and standardization, Version 2.0 is acceptable.

[0072] For example, if a user's current aggregation window is determined to be non-compliant, its weighted non-compliance report ratio is... , , Divide, then point. A higher value means that more service personnel agree that the user's classification is non-compliant, and the deduction will be greater accordingly. There is a lower limit to the user's credit score; for example, if a user has 0 points, the score after deduction will not fall below this lower limit.

[0073] Optionally, after each aggregation window concludes, the platform pushes a summary of the compliance assessment results to the user. This summary includes the user's compliance confidence level and credit score change, but does not contain evaluations specific to any particular service provider. Users can understand the assessment status of their categorization behavior based on this summary, but cannot pinpoint the specific evaluation of any particular service provider.

[0074] In step S15, when a user with a compliance confidence level of non-compliance confirmation initiates a new service request, the additional service subsidy amount for the order is determined based on the user's weighted non-compliance report ratio and the order's base service fee, and the additional service subsidy is displayed in the service personnel's order acceptance interface.

[0075] In one embodiment, the compliance confidence level determined through the aforementioned steps not only affects the adjustment of the user's credit score but also influences the remuneration received by the service personnel when serving that user subsequently. When a user with a non-compliant confidence level initiates a new garbage disposal service request, the platform automatically adds an additional service subsidy to the order during the order matching stage. The amount of the additional service subsidy is... The calculation method is as follows:

[0076]

[0077] in This is the subsidy ratio coefficient, ranging from 0.3 to 1.0; The weighted non-compliance report percentage for this user's most recent aggregated window; The starting value for triggering subsidies is the same as the starting threshold for non-compliance confirmation levels, i.e. ; This is the base service fee for this order, in yuan. The unit is yuan.

[0078] Optionally, The method for determining this is as follows: the platform calculates the average time spent by service personnel on additional processing work for non-compliant user orders during the trial operation period, converts this additional work cost into the average hourly wage of the service personnel, and then uses the ratio of this cost to the base service fee as the base price. This serves as a reference starting point. For example, if the extra cleaning takes an average of 5 minutes and the average hourly wage for service personnel is 30 yuan, then the extra work cost is approximately 2.5 yuan; the base service fee is 8 yuan, typically... The difference is approximately 0.1 to 0.4, with 0.3 as the median, and the result is calculated backwards. Rounded down to 1.0. The platform can be periodically reviewed and adjusted based on actual data during its operation.

[0079] For example, the weighted non-compliance reporting ratio of a certain non-compliance confirmation user. Base service fee for orders Yuan, , Additional service subsidies The service personnel see an additional service subsidy and its amount on the order acceptance interface, but the specific value of the user's compliance confidence level or weighted non-compliance report ratio is not displayed. Therefore, the service personnel take the additional compensation into account when making the order acceptance decision, while the user's evaluation data details are protected.

[0080] Optionally, the additional service subsidy is funded by the additional service fee paid by the user. When a user's compliance confidence level is confirmed as non-compliant, the platform will automatically add an additional service fee to the user's next service order. The amount of the additional service fee will be equal to the amount of the additional service subsidy. Users can view the existence and amount of additional service fees on the order page. Users with non-compliant categories face higher service fees, while service personnel are more willing to take on such orders due to the extra subsidies. After users improve their category behavior, their compliance confidence level increases in subsequent aggregation windows, and the additional service fees are subsequently cancelled.

[0081] Optionally, users with a compliance confidence level of compliant and trustworthy can receive a service fee discount on their orders. The discount can be configured, for example, reducing the base service fee by 5% to 10%, with the discount funds borne by the platform's operating costs. This discount complements the positive adjustment of credit scores in the aforementioned steps: credit score adjustment affects the user's long-term credit record and matching priority, while the fee discount provides immediate economic feedback.

[0082] In some embodiments, during continuous operation, to maintain the authenticity of the classification compliance evaluation data, the platform awards additional credit points to service personnel with higher evaluation credibility weights. After each aggregation window ends, a weighted consistency analysis is completed. The platform calculates the proportion of service personnel whose classification compliance evaluation conclusions align with the final determined compliance confidence level among all users who participated in the evaluation within that window. Here, directional consistency refers to two scenarios: the service personnel report compliance and the final compliance confidence level is determined to be credible compliance; or the service personnel report non-compliance and the final compliance confidence level is determined to be confirmed non-compliance. This proportion is defined as the window consistency rate.

[0083] When a service provider's consistency rate at a particular window exceeds a set threshold, the threshold is determined in the same way as the compliance confidence level threshold mentioned earlier. Specifically, it is statistically calibrated based on the consistency rate distribution during the trial operation period, for example, using 0.8. When settling accounts at that window, the platform adds an extra positive adjustment to the service provider's credit score. This positive adjustment is a fixed value, for example... 0.5 times, or 2.5 points. In some embodiments, the platform also displays the service personnel's cumulative rating credibility level (such as high credibility, general credibility) on their personal information page. Service personnel with higher credibility levels are given priority in order matching and sorting, and this priority is used in conjunction with the matching priority of their credit score.

[0084] Optionally, the platform provides an appeal channel. Users who disagree with their compliance confidence level can submit an appeal within a set period (e.g., 3 days) after receiving a summary of the compliance assessment results. Platform operators will conduct a manual review, combining the appeal with photos of junk items taken by service personnel during pickup. The review results will override the automated assessment results, and any changes to the credit score already implemented will be corrected accordingly. This appeal mechanism operates independently of the aforementioned automated process as a supplementary measure.

[0085] Through the above methods, the special evaluation of classification compliance is processed separately from the overall evaluation of service personnel. Anonymous collection and delayed disclosure sever the correspondence between evaluation and retaliation. Multi-source weighted consistency analysis aggregates the independent evaluations of multiple service personnel into a more reliable compliance judgment. The calibrated compliance confidence level generates differentiated adjustments to the user's credit score. At the same time, the compliance status is linked to the service personnel's order-taking incentives through additional service subsidies. While reducing the service personnel's concerns about giving truthful evaluations, classification compliance information is transformed into economic signals, so that the constraint and incentive effect of credit scores on garbage classification behavior is effectively implemented.

[0086] Figure 3 A block diagram is shown of a garbage disposal service incentive system based on two-way evaluation and dynamic adjustment of credit scores, according to an embodiment of this disclosure. Figure 3 As shown, the system includes:

[0087] The special evaluation receiving module 301 is used for the service personnel to submit a special evaluation of classification compliance to the user after the garbage disposal service order is completed. The special evaluation of classification compliance is independent of the service personnel's overall evaluation of the user.

[0088] Anonymous aggregation module 302 is used to anonymously collect the classification compliance special evaluations submitted by multiple different service personnel to the same user within a set aggregation window, and the classification compliance special evaluations are not disclosed to the user during the aggregation window.

[0089] The compliance analysis module 303 is used to perform a weighted consistency analysis on all categorized compliance evaluations received by the same user within the aggregation window after the aggregation window ends, based on the credibility weight of each service personnel's evaluation, to obtain the weighted non-compliance report ratio, and to determine the user's compliance confidence level based on the weighted non-compliance report ratio.

[0090] The credit score adjustment module 304 is used to adjust the user's credit score according to the compliance confidence level. Different compliance confidence levels correspond to different credit score adjustment directions and adjustment ranges.

[0091] The subsidy determination and display module 305 is used to determine the additional service subsidy amount for a new service request when a user with a compliance confidence level of non-compliance confirmation initiates a new service request, based on the user's weighted non-compliance report ratio and the order's base service fee, and to display the additional service subsidy in the service personnel's order acceptance interface.

[0092] In some embodiments, the system provided in this disclosure may have functions or include modules that can be used to execute the methods described in the above method embodiments. The specific implementation of these methods can be referred to the description in the above method embodiments, and for the sake of brevity, they will not be repeated here.

[0093] Figure 4 A block diagram of an electronic device according to an embodiment of the present disclosure is shown. (Refer to...) Figure 4 Electronic devices can be provided as servers or terminal devices. (See reference...) Figure 4 The electronic device includes a processing component 401, which further includes one or more processors, and memory resources represented by memory 402 for storing instructions, such as application programs, that can be executed by the processing component 401. The application programs stored in memory 402 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 401 is configured to execute instructions to perform the methods described above.

[0094] The electronic device may also include a power supply component 403 configured to perform power management of the electronic device, a wired or wireless network interface 404 configured to connect the electronic device to a network, and an input / output interface 405 (I / O interface). The electronic device can operate on an operating system stored in memory 402.

[0095] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 402 including computer program instructions that can be executed by a processing component 401 of an electronic device to perform the above-described method.

[0096] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, and are not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for incentivizing garbage disposal services based on two-way evaluation and dynamic adjustment of credit scores, characterized in that, include: After a garbage disposal service order is completed, the service personnel submit a specific evaluation of the user's garbage sorting compliance. This specific evaluation of garbage sorting compliance is independent of the service personnel's overall evaluation of the user. Within a set aggregation window, multiple different service personnel anonymously collect the category compliance evaluations submitted by the same user, and the category compliance evaluations are not disclosed to the user during the aggregation window period. After the aggregation window ends, a weighted consistency analysis is performed on all categorized compliance evaluations received by the same user within the aggregation window, based on the credibility weight of each service personnel's evaluation. This yields a weighted non-compliance report ratio, and the user's compliance confidence level is determined based on the weighted non-compliance report ratio. The user's credit score is adjusted according to the compliance confidence level, with different compliance confidence levels corresponding to different credit score adjustment directions and magnitudes; When a user with a compliance confidence level of non-compliance confirmation initiates a new service request, the additional service subsidy amount for the order is determined based on the user's weighted non-compliance report ratio and the order's base service fee, and the additional service subsidy is displayed on the service personnel's order acceptance interface.

2. The method according to claim 1, characterized in that, Determining the evaluation credibility weight includes: counting the number of times that the evaluation conclusion of the service personnel is consistent with the majority opinion of other service personnel on the same user in all the categorized compliance special evaluations submitted by the service personnel within the set historical period, and taking the proportion of the consistent number to the total number of evaluations by the service personnel within the historical period as the evaluation credibility weight of the service personnel.

3. The method according to claim 2, characterized in that, When the cumulative number of categorized compliance evaluations for service personnel does not reach the set minimum evaluation threshold, the evaluation credibility weight takes the default value; after reaching the minimum evaluation threshold, the evaluation credibility weight is calculated according to the proportion of consistent evaluations within the historical period, and is recalculated and updated at the end of each aggregation window.

4. The method according to claim 1, characterized in that, The compliance confidence level includes three levels: compliant and credible, questionable and under observation, and non-compliance confirmed. The threshold for classifying the three levels is determined through the trial operation period: during the trial operation period, special evaluation data on compliance classification is collected but credit score adjustment is not performed. After the trial operation period ends, the weighted non-compliance report ratio of each user is compared with the results of manual on-site verification, and the weighted non-compliance report ratio value that makes the classification judgment accuracy rate and misjudgment rate reach the set level is selected as the level classification threshold.

5. The method according to claim 4, characterized in that, The adjustment of the user's credit score based on the compliance confidence level includes: when the compliance confidence level is "compliant and trustworthy," determining the compliance reward coefficient based on the number of consecutive windows in which the user has obtained the compliance and trustworthy level, and using the product of the compliance reward coefficient and the single adjustment benchmark score as the positive adjustment amount for the credit score; when the compliance confidence level is "questionable and pending observation," the credit score is not adjusted in the current window, and the credit score is deducted when two consecutive aggregation windows are both "questionable and pending observation"; when the compliance confidence level is "non-compliance confirmed," using the product of the non-compliance deduction coefficient, the weighted non-compliance reporting ratio, and the single adjustment benchmark score as the negative adjustment amount for the credit score.

6. The method according to claim 5, characterized in that, The non-compliance deduction coefficient is determined based on the manual sampling data during the trial operation period: the average number of window periods from the initial confirmation of non-compliance to the improvement of the classification behavior of non-compliant users is statistically analyzed, and the non-compliance deduction coefficient value that causes continuous deductions to reduce the credit score to a set threshold within the average number of window periods is calculated in reverse.

7. The method according to claim 1, characterized in that, The additional service subsidy is funded by the user's additional service fee: the platform automatically adds an additional service fee to the service orders of users whose compliance confidence level is non-compliant confirmation. The amount of the additional service fee is equal to the amount of the additional service subsidy. The user can view the additional service fee on the order page.

8. The method according to claim 1, characterized in that, After the aggregation window ends, the proportion of each service personnel whose classification compliance evaluation conclusion in the window is consistent with the direction of the final determined compliance confidence level is calculated. When the proportion exceeds the set threshold, an additional positive adjustment amount is added to the credit score of the service personnel.

9. The method according to claim 1, characterized in that, When the number of service personnel participating in the evaluation of the same user within the aggregation window does not reach the set minimum number, the consistency analysis result of the aggregation window will not be included in the credit score adjustment, and the classification compliance special evaluation data within the window will be merged into the next aggregation window for weighted consistency analysis again.

10. A garbage disposal service incentive system based on two-way evaluation and dynamic adjustment of credit scores, characterized in that, include: The special evaluation receiving module is used for service personnel to submit a special evaluation of classification compliance to users after the garbage disposal service order is completed. The special evaluation of classification compliance is independent of the service personnel's overall evaluation of users. An anonymous aggregation module is used to anonymously collect the classification compliance evaluations submitted by multiple different service personnel to the same user within a set aggregation window. The classification compliance evaluations are not disclosed to the user during the aggregation window. The compliance analysis module is used to perform a weighted consistency analysis on all categorized compliance evaluations received by the same user within the aggregation window after the aggregation window ends, based on the credibility weight of each service personnel's evaluation, to obtain the weighted non-compliance report ratio, and to determine the user's compliance confidence level based on the weighted non-compliance report ratio. The credit score adjustment module is used to adjust the user's credit score according to the compliance confidence level. Different compliance confidence levels correspond to different credit score adjustment directions and adjustment ranges. The subsidy determination and display module is used to determine the additional service subsidy amount for a new service request when a user with a compliance confidence level of non-compliance confirmation initiates a new service request, based on the user's weighted non-compliance report ratio and the order's base service fee, and to display the additional service subsidy in the service personnel's order acceptance interface.

Images