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 - 45 . (canceled) 
     
     
         46 . 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:
 receive, via a relevance service application programming interface (API), a relevance search request from a relevance API client of a consumer device associated with a particular consumer, wherein the relevance search request is associated with a product-specific search for one or more products currently available to the particular consumer;   generate a distributed search query based on the relevance search request, wherein the distributed search query comprises at least one document that describes attributes of the product-specific search;   execute the distributed search query based on a user-item relevance score for each item of a set of items that satisfy search query terms associated with the relevance search request, wherein the user-item relevance score is calculated based on one or more user-item attribute vectors, wherein the one or more user-item attribute vectors are generated based on a user-item attribute graph, and wherein the user-item attribute graph describes user-item relationships between one or more personal attributes of the particular consumer and one or more product attributes for a product of the one or more products; generating a ranked list of the set of items based on respective user-item relevance scores; and   transmit, to the consumer device, a response to the relevance search request, the response comprising a ranked list of the set of items based on respective user-item relevance scores.   
     
     
         47 . The system of  claim 46 , 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 a subset of the ranked list of the set of items, wherein the response comprises the subset of the ranked list of the set of items.   
     
     
         48 . The system of  claim 46 , 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:
 employ at least one aggregator node that is operable to execute at least a portion of one or more relevance service processing algorithms associated with the relevance search request.   
     
     
         49 . The system of  claim 46 , 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:
 retrieve, using at least one search index, data that describes the set of items that satisfy the search query terms.   
     
     
         50 . The system of  claim 46 , 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:
 generate one or more user-item attribute vectors based on a combination of the user-item attribute graph and historical data, wherein the historical data describes interactions of a personal attribute space comprising the one or more personal attributes and a product space comprising each product attribute of the one or more product attributes for the product of the one or more products.   
     
     
         51 . The system of  claim 46 , 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:
 execute a distributed search query that comprises a payload associated with at least two different product-specific searches; and   select, for each product of the one or more products, a product-specific model that is associated the product.   
     
     
         52 . The system of  claim 51 , 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:
 select the product-specific model based on a custom selection plugin associated with the product.   
     
     
         53 . The system of  claim 46 , wherein the one or more products comprise one or more promotion offerings. 
     
     
         54 . The system of  claim 46 , wherein the distributed search query comprises one or more search terms that describe at least one promotion attribute associated with the one or more products and at least one customer attribute associated with the particular consumer. 
     
     
         55 . A computer-implemented method, comprising:
 receiving, via a relevance service application programming interface (API), a relevance search request from a relevance API client of a consumer device associated with a particular consumer, wherein the relevance search request is associated with a product-specific search for one or more products currently available to the particular consumer;   generating a distributed search query based on the relevance search request, wherein the distributed search query comprises at least one document that describes attributes of the product-specific search;   executing the distributed search query based on a user-item relevance score for each item of a set of items that satisfy search query terms associated with the relevance search request, wherein the user-item relevance score is calculated based on one or more user-item attribute vectors, wherein the one or more user-item attribute vectors are generated based on a user-item attribute graph, and wherein the user-item attribute graph describes user-item relationships between one or more personal attributes of the particular consumer and one or more product attributes for a product of the one or more products; and   transmitting, via the relevance service API and to the consumer device, a response to the relevance search request comprising a ranked list of the set of items based on respective user-item relevance scores.   
     
     
         56 . The computer-implemented method of  claim 55 , further comprising:
 determining a subset of the ranked list of the set of items; and   providing the subset of the ranked list of the set of items to the relevance service API, wherein the response comprises the subset of the ranked list of the set of items.   
     
     
         57 . The computer-implemented method of  claim 55 , further comprising:
 retrieving, using at least one search index, data that describes the set of items that satisfy the search query terms.   
     
     
         58 . The computer-implemented method of  claim 55 , further comprising:
 selecting, for each product of the one or more products, a product-specific model that is associated the product.   
     
     
         59 . The computer-implemented method of  claim 58 , further comprising:
 selecting the product-specific model based on a custom selection plugin associated with the product.   
     
     
         60 . The computer-implemented method of  claim 55 , further comprising:
 generating the one or more user-item attribute vectors based on a combination of the user-item attribute graph and historical data, wherein the historical data describes interactions of a personal attribute space comprising the one or more personal attributes and a product space comprising each product attribute of the one or more product attributes for the product of the one or more products.   
     
     
         61 . 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:
 receive, via a relevance service application programming interface (API), a relevance search request from a relevance API client of a consumer device associated with a particular consumer, wherein the relevance search request is associated with a product-specific search for one or more products currently available to the particular consumer;   generate a distributed search query based on the relevance search request, wherein the distributed search query comprises at least one document that describes attributes of the product-specific search;   execute the distributed search query based on a user-item relevance score for each item of a set of items that satisfy search query terms associated with the relevance search request, wherein the user-item relevance score is calculated based on one or more user-item attribute vectors, wherein the one or more user-item attribute vectors are generated based on a user-item attribute graph, and wherein the user-item attribute graph describes user-item relationships between one or more personal attributes of the particular consumer and one or more product attributes for a product of the one or more products; generating a ranked list of the set of items based on respective user-item relevance scores; and   transmit, to the consumer device, a response to the relevance search request, the response comprising a ranked list of the set of items based on respective user-item relevance scores.   
     
     
         62 . The computer program product of  claim 61 , wherein the instructions, when executed by the one or more computers, further cause the one or more computers to:
 determine a subset of the ranked list of the set of items; and   provide the subset of the ranked list of the set of items to the relevance service API, wherein the response comprises the subset of the ranked list of the set of items.   
     
     
         63 . The computer program product of  claim 61 , wherein the instructions, when executed by the one or more computers, further cause the one or more computers to:
 retrieve, using at least one search index, data that describes the set of items that satisfy the search query terms.   
     
     
         64 . The computer program product of  claim 61 , wherein the instructions, when executed by the one or more computers, further cause the one or more computers to:
 select, for each product of the one or more products, a product-specific model that is associated the product.   
     
     
         65 . The computer program product of  claim 61 , wherein the instructions, when executed by the one or more computers, further cause the one or more computers to:
 generate the one or more user-item attribute vectors based on a combination of the user-item attribute graph and historical data, wherein the historical data describes interactions of a personal attribute space comprising the one or more personal attributes and a product space comprising each product attribute of the one or more product attributes for the product of the one or more products.