Product delivery system and method

Patent metadata

Field	Value
Publication number	US-10740824-B2
Application number	US-201815922356-A
Country	US
Kind code	B2
Filing date	Mar 15, 2018
Priority date	Mar 15, 2018
Publication date	Aug 11, 2020
Grant date	Aug 11, 2020

Abstract

Systems, methods and computer program products for determining a list of products in response to a client request received from a client device during a request/response session. Occurrence frequency and auxiliary product value information for each auxiliary product set in a list of auxiliary product sets are determined from a tree data structure in response to a client request. A list of candidate auxiliary products for each main product is determined using the occurrence frequency and a service value determined for each auxiliary product set in the list of auxiliary product sets.

First claim

What is claimed is:

1. A server system configured to determine a list of products in response to a client request received from a client device during a request/response session at a given processing time, the client request comprising one or more request parameters, the server system comprising:
one or more processors; and
a memory coupled with the one or more processors, the memory including instructions that, when executed by the one or more processors, cause the system, in response to the client request, to:
determine a list of main products, the list of main products comprising an estimation of one or more of the main products matching the client request, wherein a product provider system further cooperates with an auxiliary product estimation database configured to store historical data related to sets of auxiliary products, wherein each auxiliary product set identifies one or more auxiliary products related to a main product, wherein the historical data comprises data collected from previous request/response sessions, and each previous request/response session is implemented between a client device and a product provider system connected to the auxiliary product estimation database during a predefined time period before the processing time, and wherein the historical data is represented by a tree data structure comprising nodes;
determine, based on the tree data structure, an occurrence frequency and an auxiliary product value information for each auxiliary product set from a list of auxiliary product sets, the list of auxiliary product sets comprising at least one auxiliary product set;
determine, based on the associated auxiliary product value information for each auxiliary product set, a service value for each auxiliary product set of the list of auxiliary product sets;
provide, based on the occurrence frequency and the service value for each auxiliary product set, a list of candidate auxiliary products for each main product for each auxiliary product set of the list of auxiliary product sets;
determine an estimated auxiliary product value information for each auxiliary product set of the list of auxiliary product sets from real-time data; and
update the auxiliary product value information based on the estimated auxiliary product value information for each auxiliary product set of the list of auxiliary product sets.

2. The server system of claim 1 wherein the tree data structure comprises a root node and a plurality of levels, each level of the tree data structure corresponds to a parameter derived from one or more request parameter, each node of a given level of the tree data structure comprises a node value representing a value of the parameter corresponding to the level, the value being assigned to the request parameter in the one or more previous request/response sessions over a time period, the last level of each branch of the tree comprises leaf nodes, and each leaf node corresponds to a given auxiliary product set.

3. The server system of claim 2 wherein each leaf node of the tree data structure corresponding to a given auxiliary product set further comprises a counter value and a value information, the counter value indicates a number of occurrences of the auxiliary product set in the previous request/response sessions, and the instructions, when executed by the one or more processors, further cause the system to:
determine an occurrence frequency of each auxiliary product set of the list of auxiliary product sets using the counter value of the leaf node corresponding to the auxiliary product set in the tree data structure; and
determine the auxiliary product value information for each auxiliary product set of the list of auxiliary product sets from the value information of the leaf node corresponding to the auxiliary product set in the tree data structure.

4. The server system of claim 3 wherein the value information comprised in each leaf node corresponding to a given auxiliary product set comprises a value range defined by a lower threshold and an upper threshold, the lower threshold represents the lower value assigned to the auxiliary product set in a previous request/response session during a predefined time period, and the upper threshold represents the higher value assigned to the auxiliary product set in a previous request/response session during the predefined time period.

5. The server system of claim 4 wherein the instructions, when executed by the one or more processors, further cause the system to:
if the client request comprises a request parameter specifying a given auxiliary product set, the list of auxiliary product sets comprises the auxiliary product set:
browse the tree data structure according to a tree search algorithm to determine a matching node having a path in the tree matching the request parameters of the client request; and
search for a leaf node in a subtree of the matching node that matches the given auxiliary product set and a threshold condition related to a leaf node occurrence frequency,
wherein the leaf node occurrence frequency and the auxiliary product value information of the auxiliary product set are retrieved from the leaf node.

6. The server system of claim 4 wherein the instructions, when executed by the one or more processors, further cause the system to:
if the client request does not comprise a request parameter specifying a given auxiliary product set:
browse the tree data structure according to a tree search algorithm to determine a matching node having a path in the tree matching the request parameters of the client request;
search for all leaf nodes in a subtree of the matching node;
determine a popularity indicator for the auxiliary product set associated with each found leaf node; and
select one or more auxiliary product sets among the auxiliary product sets associated with the found leaf nodes depending on the popularity indicators,
wherein the selected auxiliary product sets are added in the list of auxiliary product sets, and the occurrence frequency and the value information of each auxiliary product set in the list of auxiliary product sets are retrieved from the corresponding leaf node.

7. The server system of claim 6 wherein the popularity indicator for the auxiliary product set associated with each found leaf node is determined using the occurrence frequency associated with the leaf node.

8. The server system of claim 1 wherein the instructions, when executed by the one or more processors, further cause the system to:
integrate the auxiliary product value information of each auxiliary product set of the list of auxiliary product sets to a value of a main product determined by an auxiliary product estimator, depending on an applicability flag.

9. The server system of claim 1 wherein the instructions, when executed by the one or more processors, further cause the system to:
collect learning metadata during a predefined learning period; and
manage the tree data structure using the collected learning metadata.

10. The server system of claim 9 wherein the instructions, when executed by the one or more processors, further cause the system to:
generate a node in the tree data structure in response to a specification of a new value of a parameter corresponding to a level of the tree, in a real-time request/response session; and
set a counter value of the node to the value 1.

11. The server system of claim 9 wherein the instructions, when executed by the one or more processors, further cause the system to:
update a node in the tree data structure each time the value associated with the node is specified in a request/response session for the parameter corresponding to a node level; and
increm

Assignees

• Amadeus Sas

Inventors

• Becker Muriel
• Laperrousaz Vincent
• Pauchet David

Classifications

• G06Q30/0631 Primary

  Recommending goods or services · CPC title

• G06Q30/0283 Primary

  Price estimation or determination · CPC title

• G06Q30/0601

  Electronic shopping [e-shopping] · CPC title

• G06Q30/0254

  based on statistics · CPC title

• G06Q30/0256

  User search · CPC title