Enforcing diversity in ranked relevance results returned from a universal relevance service framework

Abstract

In general, embodiments of the present invention provide systems, methods and computer readable media for a universal relevance service framework for ranking and personalizing items.

1 - 20 . (canceled) 
     
     
         21 . A system, comprising one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to:
 generate a set of filtered lists of promotions by applying one or more filters to a list of promotions;   predict a mix percentage value for an output sorted list in response to adding a promotion from the set of filtered lists of promotions to the output sorted list, wherein the mix percentage value is related to a distribution of attributes of the promotions;   in response to the mix percentage value for an output sorted list satisfying a predetermined mix percentage value, populate the output sorted list using the promotion from the set of filtered lists of promotions; and   transmit, to a user device, one or more promotions from the output sorted list configured for display within an electronic interface of the user device.   
     
     
         22 . The system of  claim 21 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
 determine the one or more filters based on a relevance search request related to the user device.   
     
     
         23 . The system of  claim 21 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
 configure the one or more filters based on the predetermined mix percentage value.   
     
     
         24 . The system of  claim 21 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
 in response to the mix percentage value for the output sorted list not satisfying the predetermined mix percentage value, predict a different mix percentage value for the output sorted list in response to adding a different promotion from the set of filtered lists of promotions to the output sorted list, wherein the different mix percentage value is related to a different distribution of attributes of the promotions.   
     
     
         25 . The system of  claim 24 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
 in response to the different mix percentage value for the output sorted list satisfying the predetermined mix percentage value, populate the output sorted list using the different promotion from the set of filtered lists of promotions.   
     
     
         26 . The system of  claim 21 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
 configure an ordering of promotions within the output sorted list based on the predetermined mix percentage value.   
     
     
         27 . The system of  claim 21 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
 update a machine learning model associated with mix percentage prediction based on one or more features associated with the one or more promotions from the output sorted list.   
     
     
         28 . A computer-implemented method, comprising:
 generating, by a computing device comprising a processor, a set of filtered lists of promotions by applying one or more filters to a list of promotions;   predicting, by the computing device, a mix percentage value for an output sorted list in response to adding a promotion from the set of filtered lists of promotions to the output sorted list, wherein the mix percentage value is related to a distribution of attributes of the promotions;   in response to the mix percentage value for an output sorted list satisfying a predetermined mix percentage value, populating, by the computing device, the output sorted list using the promotion from the set of filtered lists of promotions; and   transmitting, by the computing device and to a user device, one or more promotions from the output sorted list configured for display within an electronic interface of the user device.   
     
     
         29 . The computer-implemented method of  claim 28 , further comprising:
 determining, by the computing device, the one or more filters based on a relevance search request related to the user device.   
     
     
         30 . The computer-implemented method of  claim 28 , further comprising:
 configuring, by the computing device, the one or more filters based on the predetermined mix percentage value.   
     
     
         31 . The computer-implemented method of  claim 28 , further comprising:
 in response to the mix percentage value for the output sorted list not satisfying the predetermined mix percentage value, predicting, by the computing device, a different mix percentage value for the output sorted list in response to adding a different promotion from the set of filtered lists of promotions to the output sorted list, wherein the different mix percentage value is related to a different distribution of attributes of the promotions.   
     
     
         32 . The computer-implemented method of  claim 31 , further comprising:
 in response to the different mix percentage value for the output sorted list satisfying the predetermined mix percentage value, populating, by the computing device, the output sorted list using the different promotion from the set of filtered lists of promotions.   
     
     
         33 . The computer-implemented method of  claim 28 , further comprising:
 configuring, by the computing device, an ordering of promotions within the output sorted list based on the predetermined mix percentage value.   
     
     
         34 . The computer-implemented method of  claim 28 , further comprising:
 updating, by the computing device, a machine learning model associated with mix percentage prediction based on one or more features associated with the one or more promotions from the output sorted list.   
     
     
         35 . A computer program product, stored on a computer readable medium, comprising instructions that when executed by one or more computers cause the one or more computers to:
 generate a set of filtered lists of promotions by applying one or more filters to a list of promotions;   predict a mix percentage value for an output sorted list in response to adding a promotion from the set of filtered lists of promotions to the output sorted list, wherein the mix percentage value is related to a distribution of attributes of the promotions;   in response to the mix percentage value for an output sorted list satisfying a predetermined mix percentage value, populate the output sorted list using the promotion from the set of filtered lists of promotions; and   transmit, to a user device, one or more promotions from the output sorted list configured for display within an electronic interface of the user device.   
     
     
         36 . The computer program product of  claim 35 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:
 determine the one or more filters based on a relevance search request related to the user device.   
     
     
         37 . The computer program product of  claim 35 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:
 configure the one or more filters based on the predetermined mix percentage value.   
     
     
         38 . The computer program product of  claim 35 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:
 in response to the mix percentage value for the output sorted list not satisfying the predetermined mix percentage value, predict a different mix percentage value for the output sorted list in response to adding a different promotion from the set of filtered lists of promotions to the output sorted list, wherein the different mix percentage value is related to a different distribution of attributes of the promotions.   
     
     
         39 . The computer program product of  claim 38 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:
 in response to the different mix percentage value for the output sorted list satisfying the predetermined mix percentage value, populate the output sorted list using the different promotion from the set of filtered lists of promotions.   
     
     
         40 . The computer program product of  claim 35 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:
 configure an ordering of promotions within the output sorted list based on the predetermined mix percentage value.