CN-122019852-A - Transaction policy recommendation method, device, computer equipment and storage medium

CN122019852ACN 122019852 ACN122019852 ACN 122019852ACN-122019852-A

Abstract

The application relates to a transaction strategy recommendation method, a transaction strategy recommendation device, computer equipment and a storage medium. The method comprises the steps of determining a standardized score of a user evaluation index based on enterprise operation capacity, upstream coordination capacity and downstream touchdown capacity of a target transaction enterprise where a target user is located, determining weighted average of the user evaluation index according to expert scores, determining comprehensive index weight of the user evaluation index according to the weighted average, determining a first dimension evaluation score of the target user in the enterprise operation capacity dimension, a second dimension evaluation score of the target user in the upstream coordination capacity dimension and a third dimension evaluation score of the target user in the downstream touchdown capacity dimension according to the comprehensive index weight and the standardized score, determining a target label of the target user, and recommending transaction strategies to the target user based on the target label. According to the scheme, different tag users can be distinguished accurately, and pertinence and effectiveness of policy recommendation are improved.

Inventors

DONG LIANG
WANG JIANFEI
LIANG TIANWEI
ZHOU ZHANMIN
JIANG FENGYU

Assignees

浙江中烟工业有限责任公司

Dates

Publication Date: 20260512
Application Date: 20260130

Claims (10)

1. A transaction policy recommendation method, comprising: Acquiring a user evaluation index of a target user, and determining a standardized score of the user evaluation index; Obtaining expert scores of the user evaluation indexes, and determining weighted average scores of the user evaluation indexes according to the expert scores; Determining the comprehensive index weight of the user evaluation index according to the weighted average score; Determining a first dimension evaluation score of the target user in an enterprise operation capability dimension, a second dimension evaluation score in an upstream collaborative capability dimension and a third dimension evaluation score in a downstream touchability dimension according to the comprehensive index weight and the standardized score; Determining a target label of the target user according to the first dimension evaluation score, the second dimension evaluation score, the third dimension evaluation score and the evaluation score sorting threshold, and recommending the transaction strategy to the target user based on the target label.
2. The method of claim 1, wherein determining a normalized score for the user rating index comprises: Dividing the user evaluation index into a numerical index and a classification index; Carrying out standardization processing on the numerical index through a Z-score standardization algorithm to determine an index score of the numerical index; And carrying out standardization processing on the classified indexes through a single-heat coding technology, determining index scores of the classified indexes, and taking the index scores of the numerical indexes and the index scores of the classified indexes as the standardization scores of the user evaluation indexes.
3. The method of claim 2, wherein determining the composite index weight of the user evaluation index based on the weighted average score comprises: Determining a first index weight of the user evaluation index according to the weighted average score by a range normalization method; Determining a second index weight of the user evaluation index through a data driving algorithm; and taking the product of the first index weight and the second index weight as the comprehensive index weight of the user evaluation index.
4. A method according to claim 3, wherein determining the second index weight of the user evaluation index by a data driven algorithm comprises: Determining an index sample ratio of a standardized score corresponding to the user evaluation index through a data driving algorithm; Determining the information entropy of the standardized score according to the index sample ratio; determining a difference coefficient of the standardized score according to the information entropy; and carrying out normalization processing on the difference coefficient, and determining a second index weight of the user evaluation index.
5. The method of claim 1, wherein determining the target label for the target user based on the first dimension rating score, the second dimension rating score, the third dimension rating score, and a rating score ranking threshold comprises: determining a user tag of the target user according to the first dimension evaluation score, the second dimension evaluation score, the third dimension evaluation score and an evaluation score ordering threshold; determining an initial contour coefficient of the target user according to the user tag by a contour coefficient method; determining an invalid tag from the user tags according to the initial profile coefficients, and taking a target user corresponding to the invalid tag as a user to be verified; Based on user codes, acquiring label classification results of operation and maintenance personnel on the user to be verified, and determining label accuracy according to the label classification results and user labels corresponding to the user to be verified; and if the label accuracy is smaller than a preset accuracy threshold, adjusting the user label of the target user by adopting a grid search method, and determining the target label of the target user.
6. The method of claim 5, wherein if the tag accuracy is less than a preset accuracy threshold, adjusting the user tag of the target user by using a grid search method to determine the target tag of the target user comprises: Determining a threshold searching range and a threshold adjustment step size, and determining a candidate threshold value based on the threshold searching range and the threshold step size; Determining candidate labels of the target users based on the candidate threshold by adopting a grid search method; According to the user tag, determining an updated contour coefficient of the target user, and determining the verification accuracy of the candidate tag; Determining an optimal score threshold from the candidate thresholds according to the updated contour coefficients and the verification accuracy; and adjusting the user label of the target user based on the optimal score threshold, the first dimension evaluation score, the second dimension evaluation score and the third dimension evaluation score, and determining the target label of the target user.
7. The method as recited in claim 1, further comprising: The user code of the target user is used as a core associated key, and the heterogeneous data in the heterogeneous data source is subjected to data cleaning based on the core associated key through a data associated algorithm to determine effective user data, wherein the heterogeneous data source comprises a transaction management database, a terminal information database and a public number user information database; And generating a user view of the target user according to the effective user data.
8. A transaction policy recommending apparatus, characterized in that the transaction policy recommending apparatus comprises: The standardized score determining module is used for acquiring the user evaluation index of the target user and determining the standardized score of the user evaluation index; The weighted average determining module is used for obtaining expert scores of the user evaluation indexes and determining weighted average scores of the user evaluation indexes according to the expert scores; The comprehensive index weight determining module is used for determining the comprehensive index weight of the user evaluation index according to the weighted average score; The evaluation score determining module is used for determining a first dimension evaluation score of the target user in the enterprise operation capability dimension, a second dimension evaluation score in the upstream coordination capability dimension and a third dimension evaluation score in the downstream touchdown capability dimension according to the comprehensive index weight and the standardized score; And the transaction strategy recommendation module is used for determining a target label of the target user according to the first dimension evaluation score, the second dimension evaluation score, the third dimension evaluation score and the evaluation score sorting threshold value and recommending the transaction strategy for the target user based on the target label.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any one of claims 1 to 7.

Description

Transaction policy recommendation method, device, computer equipment and storage medium Technical Field The present application relates to the field of computer technologies, and in particular, to a transaction policy recommendation method, a transaction policy recommendation device, a computer device, and a storage medium. Background The operation capability and the brand cultivation capability of the cigarette retail users serving as key connection nodes between two transaction parties are directly related to market expression and brand growth of products. When the retail users are classified, the commonly adopted simple retail user classification method based on historical sales volume or user scale has the problems of single evaluation dimension, subjective layering standard, homogeneous operation strategy, serious data island and delayed dynamic update, while in the prior art, more user evaluation indexes are tried to be introduced for researching user evaluation, but the defects of random user evaluation index selection, weight setting dependence experience, lack of systematic theoretical model and objective weight determination method are often existed, and the accuracy of the user classification result is lower. Therefore, how to improve the classification efficiency and classification accuracy of the retail users, so as to recommend reasonable transaction strategies for the retail users is a problem to be solved. Disclosure of Invention Based on the foregoing, it is necessary to provide a method, an apparatus, a computer device and a storage medium for recommending a reasonable transaction policy for a retail user by improving the classification efficiency and classification accuracy of the retail user. In a first aspect, the present application provides a transaction policy recommendation method, the method comprising: Acquiring a user evaluation index of a target user, and determining a standardized score of the user evaluation index; Obtaining expert scores of the user evaluation indexes, and determining weighted average scores of the user evaluation indexes according to the expert scores; Determining the comprehensive index weight of the user evaluation index according to the weighted average score; Determining a first dimension evaluation score of the target user in an enterprise operation capability dimension, a second dimension evaluation score in an upstream collaborative capability dimension and a third dimension evaluation score in a downstream touchability dimension according to the comprehensive index weight and the standardized score; Determining a target label of the target user according to the first dimension evaluation score, the second dimension evaluation score, the third dimension evaluation score and the evaluation score sorting threshold, and recommending the transaction strategy to the target user based on the target label. In one embodiment, determining the normalized score for the user rating index comprises: Dividing the user evaluation index into a numerical index and a classification index; Carrying out standardization processing on the numerical index through a Z-score standardization algorithm to determine an index score of the numerical index; And carrying out standardization processing on the classified indexes through a single-heat coding technology, determining index scores of the classified indexes, and taking the index scores of the numerical indexes and the index scores of the classified indexes as the standardization scores of the user evaluation indexes. In one embodiment, determining the comprehensive index weight of the user evaluation index according to the weighted average score includes: Determining a first index weight of the user evaluation index according to the weighted average score by a range normalization method; Determining a second index weight of the user evaluation index through a data driving algorithm; and taking the product of the first index weight and the second index weight as the comprehensive index weight of the user evaluation index. In one embodiment, determining, by a data driven algorithm, the second index weight of the user evaluation index includes: Determining an index sample ratio of a standardized score corresponding to the user evaluation index through a data driving algorithm; Determining the information entropy of the standardized score according to the index sample ratio; determining a difference coefficient of the standardized score according to the information entropy; and carrying out normalization processing on the difference coefficient, and determining a second index weight of the user evaluation index. In one embodiment, determining the target tag of the target user according to the first, second, third, and rating score ranking thresholds comprises: determining a user tag of the target user according to the first dimension evaluation score, the second dimension evaluation score, the third dimension evaluation score