Modeling distribution of digital components over a network

Patent metadata

Field	Value
Publication number	US-10917310-B2
Application number	US-201916666658-A
Country	US
Kind code	B2
Filing date	Oct 29, 2019
Priority date	Apr 1, 2019
Publication date	Feb 9, 2021
Grant date	Feb 9, 2021

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a content platform that receives a request to provide a digital component. The request includes information about users to which the digital component is directed. Futurized queries are obtained from serving logs of a serving system that is configured to execute an existing digital component using serving code that directs digital content to the set of users. The futurized queries are loaded as data structures in memory of a forecasting system. The system uses an instruction set derived from the serving code to determine that similarity between the particular futurized query and the request exceeds a threshold similarity. The system then generates a forecast output as a response to the request based on futurized queries that exceed the threshold similarity. The forecast output includes data describing future provision of the digital component.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving a request to provide a digital component to a set of users, wherein the request includes information about the set of users to which the digital components is directed;
obtaining, based on the received request, a plurality of futurized queries from historical serving logs of a serving system that is configured to provide an existing digital component using serving code that directs the existing digital component to the set of users;
for each futurized query of the plurality of futurized queries:
loading the futurized query as a data structure in a memory of the forecasting system;
determining, by a forecasting system, a measure of similarity between the request and at least the futurized query based on an instruction set of the forecasting system that is derived from the serving code; and

determining, for a particular futurized query, that the measure of similarity indicates similarity between the particular futurized query and the request exceeds a threshold similarity;
generating, by the forecasting system and based on the particular futurized query, a forecast output as a response to the request, wherein the forecast output includes data describing future provision of the digital component; and
determining a quantity of users to which the digital component will be directed by the serving system.

2. The method of claim 1 , wherein determining a quantity of users to which the digital component will be directed comprises:
determining the quantity of users to which the digital component will be directed based on a quantity of particular futurized queries for which a respective measure of similarity indicates similarity between each of the particular futurized queries and the request exceeds a threshold similarity.

3. The method of claim 1 , wherein serving code of the serving system includes a set of pre-defined reversible data structures and the method further comprises:
deriving the instruction set of the forecasting system using the set of pre-defined reversible data structures included in the serving code of the serving system.

4. The method of claim 3 , wherein the method further comprises:
filtering the plurality of futurized queries against information about the set of users in the request, wherein the plurality of futurized queries is filtered using a filtering logic in the instruction set of the forecasting system, the filtering logic being derived from the set of pre-defined reversible data structures.

5. The method of claim 4 , wherein the method further comprises:
generating a targeting representation of the digital component in response to processing information about the set of users in the request against the plurality of futurized queries, wherein the targeting representation is generated using a targeting logic in the instruction set of the forecasting system, the targeting logic being derived from the set of pre-defined reversible data structures.

6. The method of claim 5 , wherein the targeting representation of the digital component comprises information describing a demographic attribute of the quantity of users, geographic region that includes the quantity of users, and a timeframe for providing the digital component.

7. The method of claim 5 , wherein the targeting representation of the digital component comprises an eligibility value that controls transmission of the digital component.

8. The method of claim 5 , wherein:
i) the set of pre-defined reversible data structures is configured to provide filtering functions of the serving system; and
ii) the filtering logic of the forecasting system is configured to emulate, at the forecasting system, filtering functions performed by the serving system when the serving system serves the digital component.

9. The method of claim 8 , wherein:
i) the set of pre-defined reversible data structures is configured to provide targeting functions of the serving system; and
ii) the targeting logic of the forecasting system is configured to emulate, at the forecasting system, targeting functions performed by the serving system when the serving system serves the digital component.

10. The method of claim 1 , wherein the method further comprises:
generating, by the forecasting system, a respective similarity score based on the determined measure of similarity for each futurized query, wherein the respective similarity score is generated for each futurized query obtained from the historical serving logs.

11. The method of claim 10 , wherein the respective similarity score indicates a match between a plurality of first parameters of the request and a plurality of second parameters of the particular futurized query obtained from the historical serving logs.

12. A system comprising:
one or more processing devices; and
one or more non-transitory machine-readable storage devices storing instructions that are executable by the one or more processing devices to cause performance of operations comprising:
receiving a request to provide a digital component to a set of users, wherein the request includes information about the set of users to which the digital component is directed;
obtaining, based on the received request, a plurality of futurized queries from historical serving logs of a serving system that is configured to provide an existing digital component using serving code that directs the existing digital component to the set of users;
for each futurized query of the plurality of futurized queries:
loading the futurized query as a data structure in a memory of the forecasting system;
determining, by a forecasting system, a measure of similarity between the request and at least the futurized query based on an instruction set of the forecasting system that is derived from the serving code; and

determining, for a particular futurized query, that the measure of similarity indicates similarity between the particular futurized query and the request exceeds a threshold similarity;
generating, by the forecasting system and based on the particular futurized query, a forecast output as a response to the request, wherein the forecast output includes data describing future provision of the digital component; and
determining a quantity of users to which the digital component will be directed by the serving system.

13. The system of claim 12 , wherein determining a quantity of users to which the digital component will be directed comprises:
determining the quantity of users to which the digital component will be directed, based on a quantity of particular futurized queries for which a respective measure of similarity indicates similarity between each of the particular futurized queries and the request exceeds a threshold similarity.

14. The system of claim 12 , wherein serving code of the serving system includes a set of pre-defined reversible data structures and the operations further comprise:
deriving the instruction set of the forecasting system using the set of pre-defined reversible data structures included in the serving code of the serving system.

15. The system of claim 14 , wherein the operations further comprise:
filtering the plurality of futurized queries against information about the set of users in the request, wherein the plurality of futurized queries is filtered using a filtering logic in the instruction set of the forecasting system, the filtering logic being derived from the set of pre-defined reversible data structures.

16. The system of claim 15 , wherein the operations further comprise:
generating a targeting represent

Assignees

• Google Llc

Inventors

• So Chiu Wah Kelvin
• Ocwieja Jakub
• Jurca Radu
• Hasan Md Mahbubul
• Svonava Daniel
• Manjunatha Mahesh Keralapura
• Fan David
• Liu Yao
• Xiong Xi
• Dragus Andrei
• Vemuri Vinay Vyas
• Wang Shen
• Liu Muruo

Classifications

• G06Q30/0251 Primary

  Targeted advertisements · CPC title

• H04L41/145 Primary

  involving simulating, designing, planning or modelling of a network · CPC title

• G06F16/953

  Querying, e.g. by the use of web search engines · CPC title

• G06Q30/0242

  Determining effectiveness of advertisements · CPC title

• G06F30/20

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title