Recommending target transaction code setting region

Abstract

Implementations of the present specification disclose a method and a system for recommending a target transaction code setting region. The method includes the following: dividing a target region to obtain multiple sub-regions, where the multiple sub-regions include one or more label sub-regions with known target transaction code setting effects and one or more sample sub-regions with unknown target transaction code setting effects; obtaining an association feature between the multiple sub-regions; obtaining predicted effect values of setting a target transaction code in the one or more sample sub-regions by using a prediction algorithm based on at least estimated effect values of setting a target transaction code in the one or more label sub-regions and the association feature; and determining at least one recommended region for setting a target transaction code from the one or more sample sub-regions based on at least the one or more predicted effect values.

1 .- 20 . (canceled) 
     
     
         21 . A computer-implemented method comprising:
 obtaining, over a network from a user device, a first portion of association data among multiple sub-regions comprising one or more labeled sub-regions with known target transaction code setting effects and one or more sample sub-regions with unknown target transaction code setting effects, the first portion of the association data comprising payment transaction data related to the user device scanning a target transaction code;   obtaining, a second portion of the association data among the multiple sub-regions, wherein a first sub-region corresponds to a first location represented by a first hash value and a second sub-region corresponds to a second location represented by a second hash value;   generating, based on the first and second portions of the association data, an association feature comprising a plurality of associations between the multiple sub-regions based on the association data, wherein the plurality of associations comprises a first association between the first sub-region and the second sub-region;   generating a plurality of distance parameters, wherein the plurality of distance parameters comprises a first distance parameter representing a distance between the first sub-region and the second sub-region, wherein the first distance parameter is calculated based on a first comparison score that represents a degree of similarity between the first hash value and the second hash value;   generating a plurality of weight values corresponding to the association feature, wherein the plurality of weight values comprises a first weight value representing the first association, wherein the first weight value is calculated based on the first distance parameter and a hyperparameter associated with the first sub-region and the second sub-region;   obtaining a predicted effect value of setting the target transaction code in the second sub-region by using the plurality of weight values and the association feature;   determining, based on at least the predicted effect value, a recommended region, wherein the recommended region comprises the second sub-region;   providing the target transaction code to the user device located within the recommended region;   receiving, from the user device, in response to providing the target transaction code, (i) information indicative of completion of a transaction within the recommended region and (ii) subsequent payment transaction data corresponding to the transaction; and   updating the association feature based on the subsequent payment transaction data.   
     
     
         22 . The computer-implemented method of  claim 21 , comprising:
 obtaining an estimated effect value of at least one sample sub-region; and   updating at least one of the plurality of weight values and the association feature based on at least the estimated effect value of the sample sub-region.   
     
     
         23 . The computer-implemented method of  claim 22 , wherein updating at least one of the plurality of weight values and the association feature based on at least the estimated effect value of the sample sub-region comprises:
 updating at least one of the plurality of weight values and the association feature based on a difference between the estimated effect value of the sample sub-region and a predicted effect value of the sample sub-region.   
     
     
         24 . The computer-implemented method of  claim 22 , wherein updating at least one of the plurality of weight values and the association feature based on at least the estimated effect value of the sample sub-region comprises:
 determining the estimated effect value is greater than a predetermined threshold to a label sub-region; and   updating at least one of the plurality of weight values and the association feature based on determining the estimated effect value is greater than the predetermined threshold to the label sub-region.   
     
     
         25 . The computer-implemented method of  claim 21 , wherein the target transaction code comprises at least one or more of a red packet code, a collection code, a promo code, and a redeem code. 
     
     
         26 . The computer-implemented method of  claim 21 , wherein the label sub-regions comprise a region in which the target transaction code has been set. 
     
     
         27 . The method of  claim 21 , comprising:
 obtaining target transaction code usage data of a label sub-region, wherein the target transaction code usage data comprises a first quantity of merchants conducting offline network payment transactions using the target transaction code in the label sub-region, a first ratio of a quantity of offline network payment transactions using the target transaction code to a total quantity of transactions for each of the first quantity of merchants in the label sub-region, and a second ratio of a quantity of users conducting offline network payment transactions using the target transaction code to a total quantity of users in the label sub-region; and   determining an estimated effect value based on the first quantity, the first ratio, and the second ratio.   
     
     
         28 . The computer-implemented method of  claim 21 , wherein the association data comprises at least one second quantity, and the second quantity is a quantity of common users conducting offline network payment transactions in two sub-regions within a first predetermined time period; and
 generating the association feature based on the association data comprises:
 determining whether the second quantity is greater than a first predetermined threshold; and 
 if the second quantity is greater than the first predetermined threshold, determining an association relationship between the two sub-regions related to the second quantity to construct an association map, and determining the association map as the association feature between the multiple sub-regions. 
   
     
     
         29 . The computer-implemented method of  claim 21 , wherein obtaining the predicted effect value of setting the target transaction code in the second sub-region comprises using a graph propagation algorithm. 
     
     
         30 . The computer-implemented method of  claim 21 , wherein the association data comprises at least one second quantity, and the second quantity is a quantity of common users conducting offline network payment transactions in two sub-regions within a first predetermined time period; and
 generating the association feature between the multiple sub-regions based on the association data comprises:
 determining, based on the second quantity, whether there is an association between the two sub-regions related to the second quantity and association strength to construct an association map, and determining the association map as the association feature between the multiple sub-regions, wherein the association strength is positively correlated with the second quantity. 
   
     
     
         31 . The computer-implemented method of  claim 30 , comprising:
 determining a label sub-region associated with a sample sub-region based on the association map; and   determining a predicted effect value of setting the target transaction code in the sample sub-region based on an estimated effect value of the label sub-region associated with the sample sub-region and association strength associated with the sample sub-region.   
     
     
         32 . The computer-implemented method of  claim 21 , wherein determining based on at least the predicted effect value, the recommended region, wherein the recommended region comprises the second sub-region comprises:
 determining whether a predicted effect value of a sample sub-region in which no target transaction code has been set is greater than a second predetermined threshold;   determining that the predicted effect value of the sample sub-region is greater than the second predetermined threshold; and   responsive to determining that the predicted effect value of the sample sub-region is greater than the second predetermined threshold, determining the sample sub-region in which no target transaction code has been set as the recommended region for setting the target transaction code.   
     
     
         33 . The computer-implemented method of  claim 21 , wherein determining based on at least the predicted effect value, the recommended region, wherein the recommended region comprises the second sub-region comprises:
 obtaining feature data of the one or more sample sub-regions and a predetermined condition corresponding to the feature data, wherein the feature data comprises:
 a third quantity of users conducting offline network payment transactions within a second predetermined time period in a sample sub-region, 
 a fourth quantity of merchants conducting offline network payment transactions within the second predetermined time period in the sample sub-region, 
 a third ratio comparing the fourth quantity of merchants conducting offline network payment transactions within the second predetermined time period in the sample sub-region to a total quantity of merchants in the sample sub-region, or 
 a type of a point of interest corresponding to the sample sub-region; 
   determining a predicted effect value of the sample sub-region is greater than a second predetermined threshold and at least one type of feature data satisfies the predetermined condition; and   responsive to determining the predicted effect value of the sample sub-region is greater than the second predetermined threshold and the at least one type of feature data satisfies the predetermined condition, determining the sample sub-region as the recommended region for setting the target transaction code.   
     
     
         34 . The computer-implemented method of  claim 33 , wherein the predetermined condition comprises at least one or more of:
 the third quantity of users is greater than a third predetermined threshold;   the fourth quantity of merchants is greater than a fourth predetermined threshold;   the third ratio is greater than a fifth predetermined threshold; and   the type of the point of interest is the same as at least one predetermined type of a point of interest.   
     
     
         35 . The computer-implemented method of  claim 21 , comprising:
 combining adjacent recommended regions.   
     
     
         36 . A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:
 obtaining, over a network from a user device, a first portion of association data among multiple sub-regions comprising one or more labeled sub-regions with known target transaction code setting effects and one or more sample sub-regions with unknown target transaction code setting effects, the first portion of the association data comprising payment transaction data related to the user device scanning a target transaction code;   obtaining, a second portion of the association data among the multiple sub-regions, wherein a first sub-region corresponds to a first location represented by a first hash value and a second sub-region corresponds to a second location represented by a second hash value;   generating, based on the first and second portions of the association data, an association feature comprising a plurality of associations between the multiple sub-regions based on the association data, wherein the plurality of associations comprises a first association between the first sub-region and the second sub-region;   generating a plurality of distance parameters, wherein the plurality of distance parameters comprises a first distance parameter representing a distance between the first sub-region and the second sub-region, wherein the first distance parameter is calculated based on a first comparison score that represents a degree of similarity between the first hash value and the second hash value;   generating a plurality of weight values corresponding to the association feature, wherein the plurality of weight values comprises a first weight value representing the first association, wherein the first weight value is calculated based on the first distance parameter and a hyperparameter associated with the first sub-region and the second sub-region;   obtaining a predicted effect value of setting the target transaction code in the second sub-region by using the plurality of weight values and the association feature;   determining, based on at least the predicted effect value, a recommended region, wherein the recommended region comprises the second sub-region;   providing the target transaction code to the user device located within the recommended region;   receiving, from the user device, in response to providing the target transaction code, (i) information indicative of completion of a transaction within the recommended region and (ii) subsequent payment transaction data corresponding to the transaction; and   updating the association feature based on the subsequent payment transaction data.   
     
     
         37 . The medium of  claim 36 , comprising:
 obtaining an estimated effect value of at least one sample sub-region; and   updating at least one of the plurality of weight values and the association feature based on at least the estimated effect value of the sample sub-region.   
     
     
         38 . The medium of  claim 37 , wherein updating at least one of the plurality of weight values and the association feature based on at least the estimated effect value of the sample sub-region comprises:
 updating at least one of the plurality of weight values and the association feature based on a difference between the estimated effect value of the sample sub-region and a predicted effect value of the sample sub-region.   
     
     
         39 . The medium of  claim 37 , wherein updating at least one of the plurality of weight values and the association feature based on at least the estimated effect value of the sample sub-region comprises:
 determining the estimated effect value is greater than a predetermined threshold to a label sub-region; and   updating at least one of the plurality of weight values and the association feature based on determining the estimated effect value is greater than the predetermined threshold to the label sub-region.   
     
     
         40 . A computer-implemented system, comprising:
 one or more computers; and   one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:   obtaining, over a network from a user device, a first portion of association data among multiple sub-regions comprising one or more labeled sub-regions with known target transaction code setting effects and one or more sample sub-regions with unknown target transaction code setting effects, the first portion of the association data comprising payment transaction data related to the user device scanning a target transaction code;   obtaining, a second portion of the association data among the multiple sub-regions, wherein a first sub-region corresponds to a first location represented by a first hash value and a second sub-region corresponds to a second location represented by a second hash value;   generating, based on the first and second portions of the association data, an association feature comprising a plurality of associations between the multiple sub-regions based on the association data, wherein the plurality of associations comprises a first association between the first sub-region and the second sub-region;   generating a plurality of distance parameters, wherein the plurality of distance parameters comprises a first distance parameter representing a distance between the first sub-region and the second sub-region, wherein the first distance parameter is calculated based on a first comparison score that represents a degree of similarity between the first hash value and the second hash value;   generating a plurality of weight values corresponding to the association feature, wherein the plurality of weight values comprises a first weight value representing the first association, wherein the first weight value is calculated based on the first distance parameter and a hyperparameter associated with the first sub-region and the second sub-region;   obtaining a predicted effect value of setting the target transaction code in the second sub-region by using the plurality of weight values and the association feature;   determining, based on at least the predicted effect value, a recommended region, wherein the recommended region comprises the second sub-region;   providing the target transaction code to the user device located within the recommended region;   receiving, from the user device, in response to providing the target transaction code, (i) information indicative of completion of a transaction within the recommended region and (ii) subsequent payment transaction data corresponding to the transaction; and   updating the association feature based on the subsequent payment transaction data.