Channel provider automatic settlement processing method and system

Abstract

The invention provides a channel provider automatic settlement processing method and system, and relates to the technical field of data processing, and the method comprises the steps: obtaining standard sales data; obtaining a rebate rule parameter, configuring a corresponding weight value for each field, and performing field structure adjustment and weight binding on the rebate rule parameter; according to each sales record in the standard sales data, rule items whose matching relation with the current sales record is not empty are acquired as an evaluable set, and field matching scoring processing is performed on each rule item; screening the target rule item with the highest score, extracting a rebate coefficient of the target rule item, and performing product calculation on the rebate coefficient and the sales quantity of the corresponding sales record to obtain a rebate amount; performing normalization calculation according to the distribution range of the maximum score value and other score values to generate a confidence score; according to all the sales records, generating a settlement entry set with a rebate amount and a confidence score; according to the invention, the accuracy of automatic settlement processing of a channel provider is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method and system for automated settlement processing of channel partners. Background Art

[0002] In the prior art, the settlement processing of channel partners usually relies on the enterprise's internal financial system or ERP system. The system summarizes based on basic data such as the sales orders, delivery notes, and payment records of channel partners, and generates the amount due for channel partners through preset settlement cycles and calculation rules. In this process, enterprises usually set fixed rebate ratios or rebate conditions, and complete data classification and summarization through automatic scripts. For example, the system applies corresponding calculation templates according to elements such as the level of channel partners and product types, and outputs settlement details and summary reports. After the final result is confirmed by financial personnel, a settlement statement is generated and payment is executed.

[0003] In the quarterly promotion scenario of home appliance products, channel partners often need to upload their terminal sales data so that the enterprise can calculate rebates according to the actual sales volume. Since the promotion policies often include cross - rules for product models and time periods, such as "the rebate rate for selling product model A from January to March 2025 is 8%, and 5% at other times", and existing systems often only support single - rule matching. When the data uploaded by channel partners contains sales records of multiple models and different time periods, the system cannot accurately distinguish the applicable rule scope, resulting in incorrect calculation of some rebate amounts. For example, the same product sold in January and April may be uniformly applied a rebate rate of 5%, which causes channel partners to question the accuracy of the settlement and requires manual intervention by finance to correct, reducing the settlement efficiency and data credibility. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for automated settlement processing of channel partners, aiming to solve the problems mentioned in the background art.

[0005] To solve the above - mentioned technical problems, the technical solution of the present invention is as follows:

[0006] In a first aspect, a method for automated settlement processing of channel partners, the method includes:

[0007] Obtain the original sales data, and perform field detection and time sorting processing on the original sales data to obtain standard sales data;

[0008] Obtain the rebate rule parameters, configure corresponding weight values for each field according to the field information in the rebate rule parameters, and perform field structure adjustment and weight binding on the rebate rule parameters to obtain a weight rule data set, where the rebate rule parameters include a rebate rule number, an applicable time range, an applicable product model, applicable channel information, and a rebate coefficient;

[0009] For each sales record in the standard sales data, obtain the rule items with non-empty matching relationships with the current sales record from the weight rule dataset as the evaluable set, and perform field matching score processing on each rule item to obtain a rule adaptation score set;

[0010] According to the rule adaptation score set, filter the target rule item with the highest score, extract the rebate coefficient in the target rule item, and perform a multiplication calculation with the sales quantity of the corresponding sales record to obtain the rebate amount corresponding to the sales record;

[0011] According to the distribution range of the maximum score value and other score values in the rule adaptation score set, perform normalization calculation to generate the corresponding confidence score;

[0012] According to all sales records, generate a settlement entry set with rebate amounts and confidence scores, and merge the settlement entry set to obtain the complete settlement detail data.

[0013] Preferably, according to the field information in the rebate rule parameters, configure corresponding weight values for each field, including:

[0014] Extract the applicable time range, applicable product model, and applicable channel information fields in the rebate rule parameters to form a field information set;

[0015] According to the field stability, hit frequency, and distribution fluctuation degree of each field in the historical sales records in the field information set, calculate the field importance index;

[0016] According to the field importance index, combined with the distribution characteristics of the field in different product types or sales channels, set the corresponding weight adjustment factor for each field;

[0017] Perform a multiplication process on the field importance index and the corresponding weight adjustment factor to obtain a field score value set;

[0018] Perform normalization processing on the field score value set to generate a field weight value set, including the time field weight value, model field weight value, and channel field weight value.

[0019] Preferably, perform field structure adjustment and weight binding on the rebate rule parameters to obtain a weight rule dataset, including:

[0020] According to the field weight value set, match each field weight value with the corresponding field in the rebate rule parameters one by one, and perform marker enhancement processing on the matching results to generate weighted field records;

[0021] Combine and bind the weighted field records with their corresponding rebate rule numbers and rebate coefficients to construct a unified rule structure entry;

[0022] Construct the rule key-value combinations for all rule structure entries in the preset field order for indexing identification, and generate the weighted rule dataset.

[0023] Preferably, for each sales record in the standard sales data, obtain the rule items with non-empty matching relationships with the current sales record from the weighted rule dataset as the evaluable set, and perform field matching score processing on each rule item to obtain the rule adaptation score set, including:

[0024] Extract the time field, model field, and channel field of each sales record in the standard sales data to form the current sales field set;

[0025] Traverse and filter all rule items in the weighted rule dataset, identify the rule items whose field values have non-empty intersections or fuzzy similarity relationships with the current sales field set, and generate the evaluable rule set;

[0026] For each rule item in the evaluable rule set, calculate the time coincidence degree score between the current sales field set and its time field, the exact matching score with the model field, and the classification similarity score with the channel field respectively;

[0027] Multiply the time coincidence degree score, the exact matching score, and the classification similarity score by the time field weight value, the model field weight value, and the channel field weight value respectively, and accumulate the product results to obtain the weighted score of the sales record and the rule item;

[0028] Merge the weighted scores calculated for all rule items into a set to generate the rule adaptation score set corresponding to the sales record.

[0029] Preferably, calculate the field importance index according to the field stability, hit frequency, and distribution fluctuation degree of each field in the historical sales records in the field information set, including:

[0030] Based on the historical sales record data, perform time dimension slicing statistics on each field in the field information set, analyze the value change range of the field in consecutive periods, and obtain the stability score of the field;

[0031] Based on the historical sales record data, calculate the frequency proportion of each field value appearing in the sales records to obtain the hit frequency score;

[0032] Based on the historical sales record data, calculate the standard deviation or information entropy of the distribution of each field value to obtain the volatility score of the field;

[0033] Weighted sum the stability score, the hit frequency score, and the volatility score according to the preset ratio to generate the field importance index corresponding to the field.

[0034] Preferably, according to the field importance index and in combination with the distribution characteristics of fields in different product types or sales channels, weight adjustment factors corresponding to each field are set, including:

[0035] Based on historical sales record data, value sets of each field in the field information set under different product types, sales regions or channel types are extracted to form field-business dimension mapping relationship data;

[0036] According to the field-business dimension mapping relationship data, the value distribution density, concentration and distinctiveness of each field under different business dimensions are statistically calculated to obtain a field distribution characteristic index set;

[0037] According to each index in the field distribution characteristic index set and in combination with the field importance index, preference factor evaluation calculation is performed to output the weight adjustment factor of each field.

[0038] Preferably, for each rule item in the evaluable rule set, the time coincidence score between the current sales field set and its time field, the exact match score with the model field, and the classification similarity score with the channel field are calculated respectively, including:

[0039] Perform an interval intersection calculation on the time field in the current sales field set and the rule item time interval, and divide the number of intersection days by the total number of days in the rule time interval to obtain the time coincidence score;

[0040] Perform a character-level exact comparison on the product model field in the sales field set and the rule item model field. If they are exactly the same, a full score is given; if there is a partial match, the score is reduced according to the similarity to obtain the exact match score;

[0041] Perform category mapping or label similarity calculation on the channel field in the sales field set and the rule item channel field, and correspond the similarity value to the scoring criterion of the channel field to output the classification similarity score.

[0042] In a second aspect, a channel partner automated settlement processing system, the system includes:

[0043] A sales data acquisition module, configured to acquire original sales data and perform field detection and time sorting processing on the original sales data to obtain standard sales data;

[0044] A rebate rule management module, configured to acquire rebate rule parameters, configure corresponding weight values for each field according to the field information in the rebate rule parameters, perform field structure adjustment and weight binding on the rebate rule parameters, and generate a weight rule data set;

[0045] The rule matching and scoring module is used to obtain the rule items that have a non-empty matching relationship with the current sales record from the weighted rule data set as an evaluable set according to each sales record in the standard sales data, and perform field matching scoring processing on each rule item to generate a rule adaptation score set;

[0046] A rebate calculation module is used to filter the target rule item with the highest score according to the rule adaptation score set, extract the rebate coefficient in the target rule item, and multiply the rebate coefficient by the sales quantity of the corresponding sales record to generate the rebate amount;

[0047] A confidence calculation module is used to perform normalization calculation based on the maximum score value and the distribution range of other score values ​​in the rule adaptation score set to generate a corresponding confidence score;

[0048] The settlement generation module is used to generate a set of settlement items with rebate amounts and confidence scores based on all sales records, and merge the set of settlement items to generate complete settlement detail data.

[0049] The above solution of the present invention includes at least the following beneficial effects:

[0050] By constructing a multi-field weighted matching mechanism, the problem of inaccurate adaptation caused by the rebate rules in the prior art only supporting single condition matching can be solved. The system constructs a multi-dimensional rule adaptation path based on the combination of time fields, model fields and channel fields, and introduces field matching scoring and field weighting mechanisms to make the matching process of rebate rules more refined and logically transparent. Unlike the existing system that can only select the "hit means match" processing logic, the present invention can achieve the pros and cons scoring between different rule items, thereby selecting the rule item with the best score for rebate calculation, significantly improving the rationality and accuracy of the match.

[0051] Furthermore, for the "model-time crossover" rebate strategy commonly seen in home appliance promotions, the present invention quantifies the matching strength between sales records and rules through field overlap scoring and confidence generation mechanisms, which can not only automatically identify the optimal rebate rule item corresponding to the sales record, but also determine the credibility of the matching result through confidence scoring. This scoring model avoids the hidden risk of incorrect matching of rebate amounts. When the confidence score is low, it can be marked in advance or a manual review mechanism can be triggered, fundamentally reducing the settlement error rate and subsequent correction costs.

[0052] In addition, by combining the weight configuration mechanism and the field importance analysis model, the present invention can dynamically generate field weights based on historical sales behavior data, enabling the rebate decision-making process to not only rely on rule settings but also possess data-driven capabilities. Especially when facing complex rebate policies for different channels and product types, the system can automatically adjust the field influence, achieving "multiple perspectives for the same rule" intelligent judgment and effectively coping with the complexity of rebate calculation brought about by the flexible and changeable promotion strategies. Generally speaking, the automated settlement processing solution provided by the present invention can reduce manual intervention, improve the intelligent level of rebate accounting and the maintainability of the system, and is applicable to the high-efficiency settlement requirements in large-scale channel rebate scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is a flowchart of a method for automated settlement processing of channel merchants provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0055] As Figure 1 shown, an embodiment of the present invention proposes a method for automated settlement processing of channel merchants, the method comprising:

[0056] S100. Obtain original sales data, and perform field detection and time sorting processing on the original sales data to obtain standard sales data;

[0057] S200. Obtain rebate rule parameters, configure corresponding weight values for each field according to the field information in the rebate rule parameters, and perform field structure adjustment and weight binding on the rebate rule parameters to obtain a weight rule data set, where the rebate rule parameters include a rebate rule number, an applicable time range, an applicable product model, applicable channel information, and a rebate coefficient;

[0058] S300. According to each sales record in the standard sales data, obtain the rule items with non-empty matching relationships with the current sales record from the weight rule data set as an evaluable set, and perform field matching score processing on each rule item to obtain a rule adaptation score set;

[0059] S400. According to the rule adaptation score set, screen the target rule item with the highest score, extract the rebate coefficient in the target rule item, and perform a multiplication calculation on the rebate coefficient and the sales quantity of the corresponding sales record to obtain the rebate amount corresponding to the sales record;

[0060] S500. Calculate the normalization based on the distribution range between the maximum score value and other score values in the rule adaptation score set, and generate the corresponding confidence score.

[0061] S600. Generate a settlement entry set with rebate amounts and confidence scores based on all sales records, and merge the settlement entry set to obtain the complete settlement detail data.

[0062] In the embodiment of the present invention, by constructing a complete set of automated settlement processing methods for channel merchants, it is possible to achieve automatic matching and rebate calculation between a large amount of sales data and rebate rules, significantly reduce the intensity of manual review, and improve the accuracy and traceability of rebate accounting. First, by obtaining the original sales data and performing field detection and time sorting operations, it is ensured that all sales records are complete and have time series consistency, avoiding rule matching deviations caused by missing or disordered data. Based on the preprocessed standard sales data, the system introduces rebate rule parameters as the settlement basis, including rebate rule numbers, applicable time ranges, applicable product models, applicable channel information, and rebate coefficients. By standardizing the structure of such parameters and configuring field weights, a structured and evaluable weight rule data set is formed, providing a data basis for the subsequent scoring mechanism.

[0063] In the actual calculation process, for each sales record, the system selects the rule items in the weight rule data set whose all field values have a matching relationship with it as the evaluable set, avoiding full traversal and improving the matching efficiency. On this basis, through the matching calculation between the time field, model field, and channel field, and combining the weight values of each field, a weighted summation operation is performed to output the rule adaptation score set between the sales record and each rule item. The score set is not only used to select the target rule item with the highest score as the final settlement basis, but also generates a confidence score through score normalization processing to measure the credibility of the matching result. The confidence score provides an audit reference for the subsequent settlement process. When the confidence level is low, it can guide the system or manual operation to perform backtracking correction on the result. Finally, the system combines the rebate amounts and confidence scores corresponding to all sales records to generate a settlement entry set, and performs a merging operation to output the standardized settlement detail data, providing a clearly structured data output result for subsequent payment, financial reconciliation, or system docking.

[0064] Among them, obtain the original sales data, and perform field detection and time sorting on the original sales data, specifically including: collecting the original sales data from the upload of channel partners or the enterprise internal sales system, and the original sales data includes at least multiple fields such as sales time, product model, channel code, sales quantity, etc. Considering the diverse sources and inconsistent formats of the original data, the system needs to perform preliminary verification and processing on data integrity and field consistency. The field detection process is mainly used to identify records with missing fields, empty field values or abnormal data formats, and eliminate, repair or mark them. After passing the detection, the system sorts all records in ascending or descending order according to the sales time field to ensure that the time sequence can be accurately referenced and cross-matching errors can be avoided during the subsequent rule matching process. After completing the above operations, the sorted data is saved as standard sales data for subsequent rule adaptation and rebate calculation.

[0065] Among them, obtain the rebate rule parameters, specifically including: extracting the set rebate rule content from the rebate policy management system, and the rebate rule parameters include fields such as rule number, applicable time range, applicable product model, applicable channel information, and rebate coefficient. These parameters are usually formulated in advance by the marketing or finance department and configured according to the promotion cycle, product category or channel level. The system will perform rule validity period verification during the extraction process to ensure that expired or ineffective rules will not be misused in the current calculation process. In the specific implementation, the system can also establish an index according to the rule number for quick retrieval in the subsequent sales record and rule matching link. This step ensures that the logical basic data for rebate calculation has timeliness and integrity, and can support subsequent field comparison and rebate amount calculation operations.

[0066] Among them, according to the rule adaptation score set, select the target rule item with the highest score, extract the rebate coefficient in the target rule item, and multiply the rebate coefficient by the sales quantity of the corresponding sales record to obtain the rebate amount corresponding to the sales record, specifically including: The system first sorts the rule adaptation score set formed by each sales record in the scoring process, and selects the rule item with the highest score as the optimal adaptation rule corresponding to this record. The rebate coefficient in the target rule item is the rebate ratio coefficient that should be used for this sales record under the current rule structure. The system multiplies the rebate coefficient by the sales quantity recorded in the sales record to calculate the rebate amount corresponding to the sales record. For example, in a certain sales record, if the rebate coefficient of the target rule item is 7% and the sales quantity is 150 units, the system calculates the rebate amount as the result of 150 multiplied by 7%, which is the rebate value for this record. This step ensures that the calculation of the rebate amount is based on the optimal rule option formed by the scoring mechanism, and maintains the consistency and logical closed-loop between the numerical result and the original sales volume data.

[0067] Among them, according to the distribution range of the maximum score value and other score values in the rule adaptation score set, a normalization calculation is performed to generate a corresponding confidence score, which specifically includes: After the system obtains all the rule adaptation scores of a certain sales record, it uses the highest score value in the set as the core reference value, and at the same time calculates the minimum score value in the set and the overall interval span. Subsequently, the system calculates its credibility level according to the position ratio of the maximum value in the overall score distribution and outputs a confidence score. This confidence score is used to measure the matching rationality degree between the current target rule item and the sales record. For example, when a certain sales record shows a medium matching level and the scores are close under multiple rule items, the confidence score generated by the system will be low to indicate that the certainty of this rebate calculation in the subsequent decision-making process is weak; while when there is a score significantly higher than other items, the confidence score will be close to full marks, thus reflecting a high-confidence rule adaptation result. The confidence score can be used as a reference for marking, grading or manual intervention in the subsequent settlement review link.

[0068] Among them, according to all sales records, a settlement entry set with rebate amounts and confidence scores is generated, and the settlement entry set is merged to obtain complete settlement detail data, which specifically includes: The system binds the rebate amount and confidence score corresponding to each sales record to generate a settlement entry with structured fields. The settlement entry can include field information such as sales record number, rebate amount, matched rule number, confidence score, settlement status, etc. The system performs a statistical summary operation on all settlement entries, classifies and merges them according to channel trademark, product dimension or cycle dimension, and outputs the final settlement detail data. For example, multiple sales records generated by a certain channel merchant within a quarter will be merged by the system according to the sales time to form the rebate details of this channel merchant for this quarter. This detail can be directly called by the financial system for payment application, or output as a reconciliation statement, audit interface or channel external settlement document. This processing method not only improves the integrity and output efficiency of the rebate detail structure, but also provides a unified settlement interface support for multi-dimensional business integration.

[0069] In a preferred embodiment of the present invention, corresponding weight values are configured for each field according to the field information in the rebate rule parameters, including:

[0070] Extract the applicable time range, applicable product model and applicable channel information fields in the rebate rule parameters to form a field information set;

[0071] Calculate the field importance index according to the field stability, hit frequency and distribution fluctuation degree of each field in the historical sales records in the field information set;

[0072] According to the field importance index, combined with the distribution characteristics of the field in different product types or sales channels, set the corresponding weight adjustment factor for each field;

[0073] Multiply the field importance index by the corresponding weight adjustment factor to obtain a set of field score values;

[0074] Normalize the set of field score values to generate a set of field weight values, including the time field weight value, the model field weight value, and the channel field weight value.

[0075] In the embodiment of the present invention, in order to make the fields of the rebate rule have differentiability and weight difference in the matching process, by introducing a field weight configuration mechanism, the flexibility and intelligence of rule screening are effectively improved. Specifically, the system extracts fields such as the applicable time range, applicable product model, and applicable channel information from the rebate rule parameters to form a unified set of field information. By combining historical sales records, the performance characteristics of each field in the actual sales data are statistically analyzed to generate a field importance index. The analysis content includes: the value change frequency of the field in different time periods to evaluate the stability of the field; the frequency of the field being referenced in all sales records to judge the hit rate; the distribution breadth and deviation degree of the field value to reflect its volatility. The above three indicators are quantified numerically and a preset ratio is set for weighted fusion to form a scoring result reflecting the overall importance of the field.

[0076] Furthermore, considering that the importance of different fields varies under different product types or channel strategies, the system uses the value characteristics of the fields in each business dimension as the source of adjustment factors. By extracting the distribution characteristics of the fields in different product classifications and channel scenarios, weight adjustment factors related to the field matching strategy are generated and multiplied by the field importance index. The product result represents the score value that the field should have in the current business environment, that is, the set of field score values. To facilitate the subsequent weighted calculation by the scoring module, the system normalizes all score values and finally generates a set of field weight values for actual rule matching calculation. This processing mechanism avoids the rigidity problem of fixed weight configuration, realizes the coupling of field importance and business context, and effectively enhances the accuracy of rebate calculation and the intelligence of rule adaptation.

[0077] In a preferred embodiment of the present invention, the field structure of the rebate rule parameters is adjusted and weights are bound to obtain a weight rule data set, including:

[0078] According to the set of field weight values, match each field weight value with the corresponding field in the rebate rule parameters one by one, and perform marker enhancement processing on the matching results to generate weighted field records;

[0079] Combine and bind the weighted field records with their corresponding rebate rule numbers and rebate coefficients to construct a unified rule structure entry;

[0080] Construct rule key-value combinations for all rule structure entries in the preset field order for indexing identification, and generate a weighted rule data set.

[0081] In the embodiment of the present invention, aiming at the problems of complex structure and diverse data formats of rebate rule parameters, a method of field structure adjustment and weight binding is provided, enabling the rule parameters to have a unified data structure and field weight information, which is convenient for subsequent scoring and rule call processing. In this implementation, the system first reads the generated set of field weight values, and matches the weight values in the set with the corresponding time field, model field, and channel field in the rebate rule parameters one by one. After the matching is completed, the weight value is attached to each field and marked enhancement processing is performed, so that the original field not only has the original semantics, but also has the importance weight information when participating in scoring, thus forming a weighted field record.

[0082] Subsequently, the system combines the weighted field record with its affiliated rebate rule number and rebate coefficient to generate a rule structure entry with a unified structure. Each entry contains field values, field weights, and settlement elements at the same time, and has complete semantics and scoring functions. After all the rule item structures are completed, the system combines the field values in the set field order (such as time → model → channel) to generate keys for subsequent rule indexing and calling, thereby forming a weighted rule data set. This data set has a standardized structure, can efficiently support the filtering, scoring, and decision-making logic execution in the matching process, and also provides a unified data interface for system maintenance.

[0083] Among them, according to the set of field weight values, the weight values of each field are matched with the corresponding fields in the rebate rule parameters one by one, and the marking enhancement process is performed on the matching results to generate a weighted field record, which specifically includes: the system reads the respective weights of the time field, product model field, and channel field from the generated set of field weight values, and matches these weights to the corresponding fields in the rebate rule parameters respectively. For example, if a certain rebate rule applies to the first quarter of 2025, Class A products, and the first-level distribution channel, the system attaches the corresponding weights of the time field, model field, and channel field to the parameter fields of this rule, making it no longer static text, but a structured field with weight attributes.

[0084] During the tag enhancement process, the system explicitly expresses the relationship between the field and its corresponding weight through structural identification or data tags to ensure that the numerical contribution of the field can be correctly identified during subsequent scoring calculations. For example, field weights can be encoded into structure entries as field attributes, or a triple of "field name-field value-field weight" can be defined through a key-value pair structure to support subsequent weighted matching processing. This enhancement operation ensures that the rebate rule field has the complete semantic expression required to participate in the scoring calculation, effectively eliminating the operation interruption or deviation caused by the lack of field weights in the scoring process.

[0085] Among them, the weighted field record is combined and bound with its corresponding rebate rule number and rebate coefficient to construct a unified rule structure entry, specifically including: after the field tag enhancement is completed, the system combines the field value and field weight in each rebate rule with the rebate rule number and rebate coefficient of the rule item itself to generate a complete and unified data entry. This rule structure entry has both field matching information and rebate calculation parameters, and is a key reference unit in the subsequent sales record scoring and rebate amount calculation process.

[0086] To ensure the structural consistency and easy indexing of entries, the system arranges the fields in a predefined field order and encapsulates them using a unified data model or structured object. For example, a rule structure entry can be organized in the order of "rule number → time field (including weight) → model field (including weight) → channel field (including weight) → rebate coefficient" and stored in the system as a standard object for subsequent calls and comparisons. This step not only ensures the consistency and integrity of the rebate rule data, but also helps to improve the calculation efficiency and result traceability of rule matching and evaluation.

[0087] Among them, all rule structure entries are constructed into rule key value combinations according to the preset field order, which are used for index identification and generating weight rule data sets, specifically including: the system connects or combines the field values ​​of all generated unified rule structure entries according to the set field priority order to form a unique rule key value identifier. The key value identifier can be generated by string concatenation, hash calculation or encoding mapping, and is used to quickly retrieve matching rules in the sales record scoring stage to avoid repeated traversal of the entire rule data set.

[0088] For example, if the field order is set to "time→model→channel", the system will sequentially concatenate the time period identifier, product model code, and channel category identifier of a rule to form a rule key value, such as "2025Q1_A001_D1", and then use the key value as the primary index field of the rule structure entry. The system builds a weighted rule data set that supports fast query by establishing a mapping relationship between the key value and the rule structure entry.

[0089] The rule dataset can build an index table by key-value, supporting advanced matching operations such as fuzzy query, prefix matching, or similarity calculation. In practical applications, this structure significantly improves the retrieval efficiency in the process of large-scale rule matching, especially suitable for complex business scenarios with hundreds or even thousands of rebate rules, and can effectively reduce the latency and resource consumption in the scoring process.

[0090] In a preferred embodiment of the present invention, for each sales record in the standard sales data, rule items with non-empty matching relationships with the current sales record are obtained from the weight rule dataset as an evaluable set, and field matching score processing is performed on each rule item to obtain a rule adaptation score set, including:

[0091] Extract the time field, model field, and channel field of each sales record in the standard sales data to form the current sales field set;

[0092] Traverse and filter all rule items in the weight rule dataset to identify rule items whose field values have a non-empty intersection or fuzzy similarity relationship with the current sales field set, and generate an evaluable rule set;

[0093] For each rule item in the evaluable rule set, calculate the time coincidence degree score between the current sales field set and its time field, the exact matching score with the model field, and the classification similarity score with the channel field respectively;

[0094] Multiply the time coincidence degree score, exact matching score, and classification similarity score by the time field weight value, model field weight value, and channel field weight value respectively, and accumulate the product results to obtain the weighted score of the sales record and the rule item;

[0095] Merge the weighted scores calculated for all rule items into a set to generate the rule adaptation score set corresponding to the sales record.

[0096] In the embodiment of the present invention, in order to improve the matching accuracy and scoring efficiency between sales records and rebate rules, by constructing a step-by-step field scoring process, the system can calculate the association strength between sales records and rule items in a structured manner and provide quantitative support for rebate calculation. For each standard sales data record, the system first extracts the time field, model field, and channel field it contains to form the current sales field set. This field set serves as the input source for subsequent matching and scoring.

[0097] The system analyzes each rule item in the weight rule dataset one by one. By comparing the time, model, and channel field values of each rule, it identifies rule items that have a non-empty intersection, partial overlap, or fuzzy matching relationship with the current sales field set. The eligible rule items are marked as the evaluable rule set. The limitation of this set effectively reduces the consumption of computing resources and avoids the interference of invalid rules on the scoring results.

[0098] In the scoring stage, the system performs scoring operations on each rule item in the evaluable set separately. The time field is processed using the interval intersection method. By calculating the proportion of the overlapping days between the sales time and the rule application time range, it outputs the time coincidence score. The model field uses the exact matching strategy, comparing the field strings character by character. When they are exactly the same, it assigns a full score; when there is partial matching, it reduces the score proportionally according to the similarity degree. The channel field evaluates the generic proximity between fields through a preset channel label system or mapping rules and outputs the classification similarity score. The above three scoring values respectively represent the proximity between the sales record and the rule item in three key dimensions.

[0099] In the score calculation stage, the system multiplies the time coincidence score, exact matching score, and classification similarity score by the field weight values respectively, reflecting the contribution of each field score to the overall score. All the product results are summed up to form the weighted score between this sales record and the current rule item. After merging the weighted scores corresponding to all evaluable rule items, it constitutes the rule adaptation score set for this sales record. This set not only reflects the matching quality between multiple rules and sales data but also provides the original scoring basis for subsequent rebate calculation and confidence generation, enhancing the accuracy, transparency, and adjustability of the system in the rule adaptation process.

[0100] Among them, traversing and screening all rule items in the weight rule dataset to identify rule items whose field values have a non-empty intersection or fuzzy similarity relationship with the current sales field set and generating the evaluable rule set specifically includes: When processing each standard sales record, the system first extracts the time field, product model field, and channel field from the record to form the current sales field set. The system uses this field set as the input and compares the field values with all rule items in the weight rule dataset one by one. During the comparison process, the system first judges whether there is an obvious intersection between the current sales field set and the rule item field values, that is, whether the field values are the same or included in the applicable range of the rule item, such as the coincidence of time periods or the model belonging to the same category.

[0101] If the exact matching condition is not met, the system further performs fuzzy matching processing. For example, if there are similar prefixes or suffixes in the product model field, or the channel field belongs to the same channel branch in the category mapping table, the system can consider that there is a similarity relationship between the fields. During this process, the system sets matching strategies according to the field types respectively. For example, it performs interval overlap judgment on time fields, conducts string similarity comparison on model fields, and invokes channel classification mapping rules for channel fields.

[0102] Any rule item that identifies at least one field with an effective intersection or a similarity exceeding the preset threshold during the above process is added to the set of evaluable rules for the current sales record. This set serves as the input set for subsequent score calculation and rebate selection, ensuring that the scoring mechanism focuses on relevant rule items, improving calculation efficiency, and reducing waste of system resources caused by irrelevant rules participating in scoring.

[0103] In a preferred embodiment of the present invention, according to the field stability, hit frequency, and distribution fluctuation degree of each field in the historical sales record in the field information set, a field importance index is calculated, including:

[0104] Based on the historical sales record data, each field in the field information set is segmented and statistically analyzed in the time dimension, and the value change range of the field in consecutive periods is analyzed to obtain the stability score of the field;

[0105] Based on the historical sales record data, the frequency proportion of each field value appearing in the sales record is calculated to obtain the hit frequency score;

[0106] Based on the historical sales record data, the standard deviation or information entropy of the distribution of each field value is calculated to obtain the volatility score of the field;

[0107] The stability score, hit frequency score, and volatility score are weighted and summed according to a preset ratio to generate the field importance index corresponding to the field.

[0108] In an embodiment of the present invention, to improve the scientificity and discrimination of field weights during the rule matching process, the system introduces a method for calculating field importance indexes based on historical sales records. This method respectively performs stability, hit frequency, and volatility analyses on the time fields, model fields, and channel fields extracted from the rebate rule parameters to ensure that the field weights have sufficient historical data support.

[0109] In the data analysis phase, the system first segments historical sales records by time period, for example, statistically analyzing the value changes of each field on a monthly or quarterly basis. For each field, the system calculates the amplitude of the value change within consecutive periods. A small change indicates a high stability of the field value, and the system assigns it a higher score. Stable fields can usually reflect channel characteristics or product sales patterns more reliably, and thus have more reference value in rebate judgment.

[0110] In the process of hit frequency scoring, the system counts the frequency of each field value appearing in the historical records, and uses the proportion of this frequency to the total number of records as the scoring basis. A high frequency indicates the universality of the field for sales behavior, and the score is relatively high. The system also identifies those field values that appear in only a very small number of records to reduce their scores and minimize the impact of noise.

[0111] In terms of volatility assessment, the system uses standard deviation or information entropy algorithms to analyze the discreteness of field values in the sample distribution. The more concentrated and regular the field values are, the higher the score; the wider and more discrete the distribution is, the lower the score. The above three scores respectively represent the stability degree, coverage degree and predictability of the field in historical data.

[0112] The system weights and sums up the stability score, hit frequency score and volatility score according to a preset ratio (such as 3:2:1) to generate the field importance index for each field. This index is directly used in the subsequent setting of the weight adjustment factor, laying a data foundation for the reasonable generation of the final weight value of the field.

[0113] Among them, for each rule item in the evaluable rule set, the system calculates the time coincidence score between the current sales field set and its time field, specifically including: the system extracts the sales time field of the sales record and makes an interval comparison with the applicable time range defined in the rule item. If the sales time is completely within the effective time period of the rule, the system determines that the time is completely matched and assigns a high-level score. If the sales time only partially overlaps with the rule time interval, the system sets a scoring level according to the proportion of the overlapping days in the total rule time period. If the sales time is completely earlier than or later than the rule time period, the score is the lowest or no score is given.

[0114] For example, if the date of a sales record is April 5, 2025, and the time range of the rule item is from April 1, 2025 to April 30, 2025, the system will determine that it is completely covered and give a full score; if the sales date is March 31, which is only adjacent to but does not overlap with the rule time period, no score is given. This score ensures the basic screening role of the time field in rule adaptation, especially applicable to scenarios where the rebate policy is strongly bound to the promotion time.

[0115] Among them, for each rule item in the evaluable rule set, the exact match score between the current sales field set and its product model field is calculated respectively, specifically including: The system first performs a character-level comparison between the model field in the sales record and the model field in the rule item. When the characters of the two are exactly the same, it is considered a perfect match, and the system gives a full score; if there are some character differences but there is structural similarity, such as belonging to the same product series or having the same prefix, the system gives a secondary score through the set similarity rules.

[0116] In specific implementation, the system can determine whether there is a derivative relationship between product models. For example, if "A123-B" and "A123-C" are classified as products of the same series, then in the case of incomplete match, an intermediate-level match score can still be given according to the principle of the same series. This strategy is applicable to scenarios where product model naming is not unified or there is simplified processing of data reported by sales terminals, and can maintain the accuracy of score determination while ensuring the flexibility of matching.

[0117] Among them, for each rule item in the evaluable rule set, the classification similarity score between the current sales field set and its channel field is calculated respectively, specifically including: The system first extracts the channel field value from the sales record and maps it to a standard channel category label according to the predefined channel classification table. The system then compares this label with the label to which the channel field in the rule item belongs to judge its similarity degree in the channel hierarchy tree or classification mapping structure.

[0118] If the sales channel and the rule channel belong to exactly the same label, such as both being "direct sales - first-level distribution", the score is the highest level; if there is a superior - subordinate relationship or they belong to the same major category (such as "direct sales channel" and "direct sales - second-level distribution"), a relatively high but not full score is set according to the similarity relationship level; if they do not belong to the same major category, the score is relatively low or considered a mismatch. This method supports flexible adaptation under a complex channel system through the structured processing of channel labels, effectively solving the limitation that traditional systems cannot handle the problem of cross-level similarity of channels.

[0119] Among them, the time coincidence score, the exact match score, and the classification similarity score are respectively multiplied by the time field weight value, the model field weight value, and the channel field weight value, and the product results are accumulated to obtain the weighted score of this sales record and this rule item, specifically including: After the system obtains the score results of each field, it respectively calls the weight value of the corresponding field in the field weight value set and multiplies each score value by the corresponding weight value. The above product represents the contribution value of this field to the overall score.

[0120] After the contribution values of all fields are calculated, they are summed up uniformly to form the final weighted score between the current sales record and a certain rule item. This score reflects the overall adaptation degree between the current rule item and the sales record, and is the core decision-making basis for subsequent screening of the optimal rebate rule item. By introducing field weight control in this step, it not only reflects the importance differences of different fields to the scoring model, but also makes the scoring mechanism adjustable and interpretable, avoiding one-sided impacts on the final result caused by scoring in different dimensions.

[0121] In a preferred embodiment of the present invention, according to the field importance index, combined with the distribution characteristics of the field in different product types or sales channels, a weight adjustment factor corresponding to each field is set, including:

[0122] Based on the historical sales record data, the value sets of each field in the field information set under different product types, sales regions or channel types are extracted to form the field-business dimension mapping relationship data;

[0123] According to the field-business dimension mapping relationship data, the value distribution density, concentration and discrimination of each field under different business dimensions are statistically calculated to obtain the field distribution characteristic index set;

[0124] According to each index in the field distribution characteristic index set, combined with the field importance index, the preference factor evaluation calculation is performed to output the weight adjustment factor of each field.

[0125] In the embodiment of the present invention, to further improve the adaptability of the field weight to the actual business strategy, the system introduces a setting mechanism for the weight adjustment factor on the basis of the field importance index. This mechanism comprehensively considers the distribution characteristics of the field under different business dimensions, dynamically adjusts the field scoring, and enhances the scenario generalization ability of the scoring model.

[0126] The system first extracts all the value situations of each field in different product types, sales regions and channel types from the historical sales records, and conducts business dimension classification and analysis on them. For example, the product model field may play a more decisive role in the high-end product series, while its influence is weaker in low-price promotional products. The system forms distribution characteristic parameters describing the performance differences of the field in each business context by identifying the occurrence frequency, distribution concentration and category discrimination ability of the field values in different dimensions.

[0127] Then, the system performs adjustment analysis on the above distribution characteristic parameters and combines them with the field importance index. For example, if a certain field has a high importance score in history and also has a high distribution density in the current product line, the system assigns a higher adjustment factor value to it. If the field has a high score, but its values are sparse or mixed in a certain business dimension, the system reduces its scoring impact to avoid matching deviations.

[0128] The system performs a weighted or product operation on the adjustment factor and the field importance index to generate a weight adjustment factor for each field, and applies it to the importance index to obtain a score correction value. These correction values form a set of field score values for the next step of normalization to generate the final weight value. This mechanism ensures that the system scoring strategy has business awareness, inherits the data-driven characteristics, reflects business flexibility, and improves the practicality and accuracy of the rebate rule adaptation model.

[0129] Among them, based on the historical sales record data, the value sets of each field in the field information set under different product types, sales regions or channel types are extracted to form the field-business dimension mapping relationship data, specifically including: The system first cleans and clusters the historical sales records, and extracts the specific value records of the time field, product model field and channel field under different business attributes (such as product classification, regional code or channel level). The system summarizes the frequencies, value types and ownership relationships of these fields in different business dimensions to form the mapping between the fields and business dimensions.

[0130] In the specific implementation, taking the product model field as an example, the system will record the specific values of this field in different product lines such as high-end, basic, and entry-level, and count its coverage ratio in each category. Similarly, the channel field will be mapped to multiple categories such as direct sales, distribution, and platform. The above data is not directly used for scoring, but as the basic data structure for downstream analysis of the field distribution characteristics, to reveal the usage characteristics of the field under different business conditions. This mapping relationship not only helps the system understand in which business dimensions a certain field is active, but also provides data support for field scoring.

[0131] Among them, according to the field-business dimension mapping relationship data, the value distribution density, concentration and discrimination of each field in different business dimensions are statistically analyzed to obtain a set of field distribution characteristic indicators, specifically including: The system performs three types of statistical analyses on each field separately from the field-dimension mapping data constructed in the first step.

[0132] First, the distribution density reflects whether the field values are widely present in each business dimension. The system calculates the occurrence frequency of the field in each dimension and compares it with the total amount of sales records in that dimension to quantify the coverage degree of the field. For example, if a certain field value exists in multiple product types, the density score will be higher.

[0133] Secondly, the concentration is used to evaluate whether the field values are concentrated in a few specific dimensions. The system analyzes the frequency distribution of the field values in all dimensions and gives a concentration score by judging the proportion of the main values concentrated in a few dimensions. The higher the concentration, the stronger the focusing characteristic of the field in business.

[0134] Finally, the discriminative reflection field value reflects the discriminative ability of the business dimension. The system determines whether a field helps to distinguish different business scenarios by analyzing the distribution range of the field in each dimension, that is, the proportional gap between the most frequent and the least frequent dimensions of the field. For example, if a certain channel field appears frequently in the direct sales channel and rarely in the third-party platform, its discriminative score is relatively high. These distribution feature scores will be used as the parameter basis for generating the weight adjustment factor subsequently.

[0135] Among them, according to each index in the field distribution feature index set, combined with the importance index of the field, the preference factor evaluation calculation is performed to output the weight adjustment factor of each field, specifically including: The system separately takes the distribution density, concentration, and discriminative score values obtained in the previous step for each field, and combines the importance index value obtained by the field in the historical sales record, and calculates the weight adjustment factor through a comprehensive scoring model. This calculation model can be a linear weighted structure, a segmented evaluation strategy, or a fusion function set according to empirical rules, so as to reflect the actual importance degree of the field in the current business context.

[0136] When the system conducts comprehensive analysis, it will set corresponding adjustment weights for each distribution feature to control its proportion in the overall score. For example, in some businesses, more attention is paid to the discrimination ability of the field, and the system will correspondingly increase the weight of the discriminative score; if more attention is paid to whether the field is widely applicable to multiple dimensions, the influence proportion of the distribution density score is increased. Finally, the system combines the adjusted three scoring results with the importance index of the field to generate the weight adjustment factor of the field. This factor will further act on the field score value in the weight generation module to achieve dynamic adjustment for different business characteristics.

[0137] For example, in a certain implementation scenario, the importance score of the model number field is relatively high, but its distribution density in different product types is too low. The system sets the generated adjustment factor to be slightly lower than the original score, so as to suppress the excessive influence of this field on the scoring model. This strategy realizes the organic integration of historical data-driven and business strategy guidance, making the field weight configuration highly flexible and adaptable to the business.

[0138] In a preferred embodiment of the present invention, the calculation formula of the weight adjustment factor is: ;

[0139] Wherein: is the weight adjustment factor of the field ; is the importance index of the field , which is derived from the above-mentioned weighted scoring; is the distribution density score; is the distribution concentration score; is the discrimination score; and and are the adjustment coefficients corresponding to the three feature scores respectively, which can be set by the system or learned through training; is the field the number of values in all business dimensions, which comes from the field and business mapping data; is the field in the business dimension the number of occurrences, which is obtained by statistics; is the business dimension the total number of sales records under it, which is used for normalization to solve the dimensional problem; is the total number constant of all business dimensions, the number of dimensions; is the field the total number of occurrences in all business dimensions, which is used to calculate the relative frequency of the field; is the entropy normalization denominator, which ensures that the concentration score is between [0,1]; and are the maximum and minimum proportions of the field in each dimension, which are used to distinguish the distribution differences of fields;

[0140] In the above calculation formulas, the base of the logarithm not shown is e, that is, it is defaulted to the natural logarithm.

[0141] In the embodiment of the present invention, the system first extracts the value situations of each field in different product types, sales regions or channel types based on historical sales records, and forms the mapping relationship between the field and the business dimension. On this basis, the distribution density, distribution concentration and discrimination characteristics of the field in each dimension are calculated respectively. The three types of characteristics are respectively normalized and quantified into score values. The distribution density measures the broadness of the field in each dimension; the concentration reflects whether the field values are concentrated in a few dimensions; the discrimination measures the performance differences of the field between different dimensions. These statistical characteristics are integrated through formulas and embedded in the field weight adjustment process, so that the field score is no longer determined by static rules, but dynamically floats based on data performance.

[0142] By combining the importance indicators of fields with the performance capabilities in business dimensions, a multi-level and multi-factor weight generation mechanism is constructed, which not only reflects the statistical significance of data but also can flexibly adjust its behavioral strategies. During the rebate rule matching process, when the importance of a certain field increases under a certain channel or product dimension, the adjustment factor will increase accordingly, thereby enhancing the role weight of this field in the matching score. Conversely, if the distribution of this field is too sparse or there is a lot of noise, its weight will be suppressed, thus reducing its interference effect in rule screening. This dynamic adjustment strategy can effectively reduce the matching error rate in complex rebate policies and improve the robustness and adaptability of the scoring model.

[0143] Meanwhile, the generation process of the entire weight adjustment factor supports parameter training and business strategy intervention, which can provide an algorithm interface for the future intelligent upgrade of the system and also leave an algorithm space for the iterative optimization of rebate policies, having significant scalability and industrial application prospects. Compared with the traditional method of statically configuring field weights based on empirical values, this scoring formula has stronger generalization ability and dynamic response ability, and is an innovative computing mechanism with both theoretical interpretability and practicality.

[0144] Among them, 、 、 The setting methods are as follows:

[0145] First, the static configuration mode (system setting):

[0146] System administrators or rule designers can manually set the weight ratios of each coefficient based on experience or industry characteristics. For example, if in the enterprise sales strategy, more emphasis is placed on the distribution breadth of a certain field in each business dimension, the α value can be set larger, such as 0.6; if more importance is attached to whether the field can distinguish different business categories, the γ value can be set to 0.5, while other coefficients are appropriately reduced. This mode is suitable for system scenarios with low rule change frequency and rapid deployment requirements.

[0147] Second, the dynamic training mode (model optimization):

[0148] The system can introduce existing rebate historical data as training samples, establish an optimization objective function using target variables (such as settlement accuracy rate, rebate error backtracking rate, etc.), and reverse-adjust the values of α, β, and γ in the scoring model. Through algorithms such as gradient descent, grid search, or Bayesian optimization, iterative learning is carried out to find the optimal coefficient combination. This type of method is suitable for rebate systems with large data volumes, complex models, and frequent rule changes, and can significantly improve the matching quality and automation capabilities.

[0149] Suppose a rebate rule scoring is carried out for an enterprise in the "customized channel promotion" business. In this business scenario, the channel field has strong distinctiveness among different regional branches, while the product models are widely distributed across multiple channels but have limited effects. Based on this experience, the system administrator sets the parameters as follows: = 0.2 (indicating a relatively low importance of distribution density); = 0.3 (indicating a general effect of concentration); = 0.5 (indicating the greatest effect of distinctiveness);

[0150] At this time, if a certain field has obvious discrimination ability in a certain business dimension, even if its coverage is not wide, it will obtain a greater amplified weight in the weight adjustment due to a higher γ value, and ultimately enhance its effect in the overall matching score. On the contrary, in the scenario where the distribution is balanced across all channels and there is no obvious discrimination boundary, the system can appropriately lower the γ value to suppress the intervention of ineffective noise.

[0151] This adjustment coefficient mechanism has the following beneficial effects:

[0152] Supports dual modes of expert knowledge injection and data-driven training;

[0153] Enables the system to flexibly handle the weight differences of fields in different business scenarios;

[0154] Avoids problems of structural rigidity or weight bias in the scoring model when facing the heterogeneity of field distributions;

[0155] Provides interpretability and customization capabilities for the scoring algorithm.

[0156] In a preferred embodiment of the present invention, for each rule item in the evaluable rule set, the time coincidence score between the current sales field set and its time field, the exact match score with the model field, and the classification similarity score with the channel field are calculated respectively, including:

[0157] Perform an interval intersection calculation on the time field in the current sales field set and the rule item time interval, and divide the number of intersection days by the total number of days in the rule time interval to obtain the time coincidence score;

[0158] Perform a character-level exact comparison on the product model field in the sales field set and the rule item model field. If they are exactly the same, a full score is given; if there is a partial match, the score is reduced according to the similarity to obtain the exact match score;

[0159] Perform category mapping or label similarity calculation on the channel field in the sales field set and the rule item channel field, and correspond the similarity value to the scoring criterion of the channel field to output the classification similarity score.

[0160] In the embodiments of the present invention, to improve the interpretability and computability of multi-field scoring between sales records and rule items, the system designs corresponding scoring algorithms for each field, making the matching process have logical rigor and a mathematical basis. Among them, the time field, model field, and channel field are processed by interval scoring, character comparison, and classification similarity evaluation respectively, forming a complete field matching scoring system.

[0161] For the time field, the system calculates the interval intersection of the sales time of the sales record and the applicable time range of the rule item, counts the number of intersection days, and divides it by the total number of days in the time span of the rule item to output a time coincidence score between 0 and 1. This score can quantify the coincidence degree between the sales occurrence time and the rule effective time, taking into account both time granularity and adaptation tolerance.

[0162] For the product model field, the system performs character-level exact comparison. If the model field in the sales record is exactly the same as the rule item, a full score is directly assigned; if there is partial character matching or prefix / suffix overlap, the system uses the edit distance or similarity function to calculate the score value and reduces the score according to the similarity. This strategy not only retains the strict matching standard but also allows fuzzy recognition within a certain range to adapt to model naming differences.

[0163] In the processing of the channel field, the system calls a predefined channel classification table to map the sales field and the rule field to standard category labels, and then generates a classification similarity score based on the category hierarchy relationship or label similarity index. For example, if the two fields belong to the same major channel category but different sub-categories, the system can assign a relatively high but non-full score. All score values are normalized according to the established scoring criteria and output as the input for the next weighted scoring.

[0164] Through the above scoring method, the system provides clear, traceable, and adjustable matching scoring results for each rule item, effectively improving the rule screening accuracy and the transparency of the rebate calculation logic.

[0165] The embodiments of the present invention also provide a channel merchant automated settlement processing system, which includes:

[0166] A sales data acquisition module, used to acquire original sales data, and perform field detection and time sorting processing on the original sales data to obtain standard sales data;

[0167] A rebate rule management module, used to acquire rebate rule parameters, configure corresponding weight values for each field according to the field information in the rebate rule parameters, perform field structure adjustment and weight binding on the rebate rule parameters, and generate a weight rule data set;

[0168] A rule matching and scoring module, which is used to obtain, for each sales record in the standard sales data, the rule items with non-empty matching relationships with the current sales record from the weight rule dataset as the evaluable set, and perform field matching scoring on each rule item to generate a rule adaptation score set;

[0169] A rebate calculation module, which is used to screen the target rule item with the highest score according to the rule adaptation score set, extract the rebate coefficient in the target rule item, and perform a multiplication calculation on the rebate coefficient and the sales quantity of the corresponding sales record to generate a rebate amount;

[0170] A confidence calculation module, which is used to perform normalization calculation according to the distribution range of the maximum score value and other score values in the rule adaptation score set to generate a corresponding confidence score;

[0171] A settlement generation module, which is used to generate a settlement entry set with rebate amounts and confidence scores according to all sales records, and perform a merging process on the settlement entry set to generate complete settlement detail data.

[0172] It should be noted that this system corresponds to the above method, and all implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0173] An embodiment of the present invention also provides a computing device, including: a processor and a memory storing a computer program. When the computer program is run by the processor, it executes the method as described above. All implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0174] An embodiment of the present invention also provides a computer-readable storage medium storing instructions. When the instructions are run on a computer, the computer is made to execute the method as described above. All implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0175] The above is the preferred embodiment of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. An automated settlement processing method for channel partners, characterized in that, The method includes: Obtaining the original sales data, performing field detection and time sorting processing on the original sales data to obtain the standard sales data; Obtaining the rebate rule parameters, configuring corresponding weight values for each field according to the field information in the rebate rule parameters, and performing field structure adjustment and weight binding on the rebate rule parameters to obtain the weight rule data set. The rebate rule parameters include the rebate rule number, applicable time range, applicable product model, applicable channel information, and rebate coefficient; According to each sales record in the standard sales data, obtaining the rule items with non-empty matching relationships with the current sales record from the weight rule data set as the evaluable set, and performing field matching score processing on each rule item to obtain the rule adaptation score set; According to the rule adaptation score set, screening the target rule item with the highest score, extracting the rebate coefficient in the target rule item, and performing a product calculation on the rebate coefficient and the sales quantity of the corresponding sales record to obtain the rebate amount corresponding to the sales record; Performing normalization calculation according to the distribution range of the maximum score value and other score values in the rule adaptation score set to generate the corresponding confidence score; Generating a settlement entry set with rebate amounts and confidence scores according to all sales records, and merging the settlement entry set to obtain the complete settlement detail data.

2. The automated settlement processing method for a channel partner according to claim 1, wherein, Configuring corresponding weight values for each field according to the field information in the rebate rule parameters, including: Extracting the applicable time range, applicable product model, and applicable channel information fields in the rebate rule parameters to form a field information set; Calculating the field importance index according to the field stability, hit frequency, and distribution fluctuation degree of each field in the historical sales records in the field information set; Setting the corresponding weight adjustment factor for each field according to the field importance index and combining the distribution characteristics of the field in different product types or sales channels; Performing a product process on the field importance index and the corresponding weight adjustment factor to obtain a field score value set; Performing normalization processing on the field score value set to generate a field weight value set, including the time field weight value, model field weight value, and channel field weight value.

3. The automated settlement processing method for a channel partner according to claim 2, wherein Performing field structure adjustment and weight binding on the rebate rule parameters to obtain the weight rule data set, including: According to the field weight value set, matching each field weight value with the corresponding field in the rebate rule parameters one by one, and performing marker enhancement processing on the matching result to generate a weighted field record; Combining and binding the weighted field record with its corresponding rebate rule number and rebate coefficient to construct a unified rule structure entry; Constructing a rule key-value combination in the preset field order for all rule structure entries for index identification to generate the weight rule data set.

4. The automated settlement processing method for a channel partner according to claim 3, wherein According to each sales record in the standard sales data, obtaining the rule items with non-empty matching relationships with the current sales record from the weight rule data set as the evaluable set, and performing field matching score processing on each rule item to obtain the rule adaptation score set, including: Extracting the time field, model field, and channel field of each sales record in the standard sales data to form the current sales field set; Traverse and filter all rule items in the weight rule dataset, identify rule items whose field values have a non-empty intersection or fuzzy similarity relationship with the current sales field set, and generate an evaluable rule set; For each rule item in the evaluable rule set, calculate the time coincidence score between the current sales field set and its time field, the exact match score with the model field, and the classification similarity score with the channel field respectively; Multiply the time coincidence score, the exact match score, and the classification similarity score by the time field weight value, the model field weight value, and the channel field weight value respectively, and accumulate the product results to obtain the weighted score of this sales record and this rule item; Merge the weighted scores calculated for all rule items into a set to generate a rule adaptation score set corresponding to this sales record.

5. The automated settlement processing method for a channel partner according to claim 2, wherein Calculate field importance indicators according to the field stability, hit frequency, and distribution fluctuation degree of each field in the historical sales records in the field information set, including: Based on the historical sales record data, perform time dimension slicing statistics on each field in the field information set, analyze the value change range of the field in consecutive periods, and obtain the stability score of this field; Based on the historical sales record data, calculate the frequency proportion of each field value appearing in the sales records to obtain the hit frequency score; Based on the historical sales record data, calculate the standard deviation or information entropy of the distribution of each field value to obtain the volatility score of the field; Weightedly sum the stability score, the hit frequency score, and the volatility score according to a preset ratio to generate the field importance indicator corresponding to the field.

6. The automated settlement processing method for a channel partner according to claim 5, wherein According to the field importance indicators and combined with the distribution characteristics of the fields in different product types or sales channels, set the weight adjustment factor corresponding to each field, including: Based on the historical sales record data, extract the value sets of each field in the field information set under different product types, sales regions, or channel types to form field-business dimension mapping relationship data; According to the field-business dimension mapping relationship data, statistically calculate the value distribution density, concentration, and distinctiveness of each field under different business dimensions to obtain a set of field distribution characteristic indicators; According to each indicator in the field distribution characteristic indicator set and combined with the importance indicator of the field, perform preference factor evaluation calculation and output the weight adjustment factor of each field.

7. The automated settlement processing method for a channel partner according to claim 4, wherein For each rule item in the evaluable rule set, calculate the time coincidence score between the current sales field set and its time field, the exact match score with the model field, and the classification similarity score with the channel field respectively, including: Perform an interval intersection calculation on the time field in the current sales field set and the rule item time interval, and divide the number of intersection days by the total number of days in the rule time interval to obtain the time coincidence score; Perform a character-level exact comparison on the product model field in the sales field set and the rule item model field. If they are exactly the same, give a full score. If there is a partial match, reduce the score according to the similarity to obtain the exact match score; Perform category mapping or label similarity calculation on the channel field in the sales field set and the rule item channel field, and correspond the similarity value to the scoring criterion of the channel field to output the classification similarity score.

8. An automated settlement processing system for channel partners, characterized in that, Applied to the method described in any one of claims 1 to 7, the system includes: A sales data acquisition module, configured to acquire original sales data, perform field detection and time sorting processing on the original sales data, and obtain standard sales data; A rebate rule management module, configured to acquire rebate rule parameters, configure corresponding weight values for each field according to the field information in the rebate rule parameters, perform field structure adjustment and weight binding on the rebate rule parameters, and generate a weight rule data set; A rule matching and scoring module, configured to, according to each sales record in the standard sales data, obtain rule items with non-empty matching relationships with the current sales record from the weight rule data set as an evaluable set, and perform field matching scoring processing on each rule item to generate a rule adaptation score set; A rebate calculation module, configured to screen the target rule item with the highest score according to the rule adaptation score set, extract the rebate coefficient in the target rule item, and perform a product calculation on the rebate coefficient and the sales quantity of the corresponding sales record to generate a rebate amount; A confidence calculation module, configured to perform normalization calculation according to the distribution range of the maximum score value and other score values in the rule adaptation score set to generate a corresponding confidence score; A settlement generation module, configured to generate a settlement entry set with rebate amounts and confidence scores according to all sales records, and perform a merging process on the settlement entry set to generate complete settlement detail data.

9. A computing device, characterized in that, Including: One or more processors; A storage device for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A program is stored in the computer-readable storage medium, and when the program is executed by a processor, the method described in any one of claims 1 to 7 is implemented.

Images