Prioritizing topics of interest determined from product evaluations

Patent metadata

Field	Value
Publication number	US-2017337594-A1
Application number	US-201615281807-A
Country	US
Kind code	A1
Filing date	Sep 30, 2016
Priority date	May 18, 2016
Publication date	Nov 23, 2017
Grant date	—

Abstract

A measurement of an effect of a topic on an aggregate of numerical information related to a set of evaluations of a specific product can be produced. A subset of the set of the evaluations can be determined. The subset can be defined by inclusion of textual information about the topic. The specific product can be a good, a service, an application, the like, or any combination thereof. An aggregate of the numerical information related to the subset can be determined. Based on the aggregate of the numerical information related to the subset, the measurement of the effect of the topic on the aggregate of the numerical information related to the set can be calculated. The measurement can be included in a file to be transmitted to a computer system to be used to control operations performed by the computer system to produce a modification to the specific product.

First claim

1 . A method for producing a measurement of an effect of a first topic on an aggregate of numerical information related to a set of evaluations of a specific product, comprising:
determining, by a first computer system, a subset of the set of the evaluations, the subset defined by inclusion of textual information about the first topic, the set being stored in records in an electronic database, the specific product being at least one of a good, a service, or an application software product; determining, by the first computer system, an aggregate of the numerical information related to the subset; calculating, by the first computer system and based on the aggregate of the numerical information related to the subset, the measurement of the effect of the first topic on the aggregate of the numerical information related to the set; and including, by the first computer system, the measurement in a file to be transmitted to a second computer system to be used to control operations performed by the second computer system to produce a modification to the specific product.

2 . The method of claim 1 , wherein the numerical information comprises at least one of:
at least one score included in at least one of the evaluations of the specific product, an amount of money expended, related to the specific product, from a first account related to the at least one of the evaluations of the specific product, an amount of time expended accessing, from a second account related to the at least one of the evaluations of the specific product, a web site of a provider of the specific product, or a number of followers of a social media account related to the at least one of the evaluations of the specific product.

3 . The method of claim 1 , wherein:
the first computer system comprises a digital distribution platform; the specific product comprises the application software product; the second computer system comprises an application development system; and the modification comprises an upgrade instruction.

4 . The method of claim 1 , further comprising transmitting, from the first computer system to the second computer system, the file.

5 . The method of claim 1 , wherein the calculating the measurement of the effect of the first topic comprises multiplying a difference by a quotient, the difference being the aggregate of the numerical information related to the set subtracted from the aggregate of the numerical information related to the subset, the quotient being a count of a number of the evaluations included in the subset divided by a count of a number of the evaluations included in the set.

6 . The method of claim 1 , wherein the determining the aggregate of the numerical information related to the subset comprises:
obtaining, from the records for the subset, the numerical information related to the subset; and calculating an average of the numerical information related to the subset.

7 . The method of claim 1 , further comprising determining, by the first computer system, the first topic.

8 . The method of claim 7 , wherein the determining the first topic is performed using a term frequency-inverse document frequency technique.

9 . The method of claim 7 , wherein the determining the first topic is performed using at least one of an unsupervised automatic document classification technique or a supervised automatic document classification technique.

10 . The method of claim 7 , wherein the determining the first topic comprises:
identifying a pattern included in the textual information of the evaluations included in the set of the evaluations, the pattern being a pattern in parts of speech, the pattern including a noun and an adjective; calculating a count of a number of occurrences of the noun in the pattern in the set of the evaluations; assigning a numerical value to the adjective in the pattern, the numerical value related to a strength of an opinion associated with the adjective; and selecting the first topic based on the count of the number of occurrences of the noun in the pattern and the numerical value assigned to the adjective in the pattern.

11 . The method of claim 10 , wherein the pattern includes at least one of a first pattern or a second pattern, the first pattern having the adjective followed by the noun, the second pattern having the noun followed by a verb followed by the adjective.

12 . The method of claim 10 , wherein:
the pattern comprises a plurality of patterns, each of the plurality of patterns including a corresponding noun and a corresponding adjective, the calculating is performed for each corresponding noun, the assigning is performed for each corresponding adjective, and further comprising producing a cluster of nouns, the cluster defined by a same subject described by the nouns, wherein the selecting the first topic is based on the cluster of the nouns.

13 . The method of claim 10 , wherein the determining the first topic further comprises:
calculating a product of the count of the numerical occurrences of the noun in the pattern multiplied by a first weight multiplied by the numerical value assigned to the adjective in the pattern multiplied by a second weight; and determining whether an absolute value of the product is greater than a threshold, wherein the selecting the first topic comprises identifying the noun in the pattern as the first topic in response to the absolute value being greater than the threshold.

14 . The method of claim 1 , wherein the specific product is included in a category of products.

15 . The method of claim 14 , further comprising determining, by the first computer system, the products included in the category.

16 . The method of claim 14 , further comprising receiving, by the first computer system and from the second computer system, a signal, the signal having information that identifies the products included in the category.

17 . The method of claim 14 , further comprising:
producing, by the first computer system, a measurement of an effect of a second topic on the aggregate of the numerical information related to the set of the evaluations; and including, by the first computer system, the measurement of the effect of the second topic in the file to be transmitted to the second computer system to be used to control the operations performed by the second computer system to produce the modification to the specific product.

18 . The method of claim 17 , wherein the second topic is predefined.

19 . The method of claim 17 , further comprising determining, by the first computer system, words related to the second topic using at least one of an unsupervised automatic document classification technique or a supervised automatic document classification technique.

20 . The method of claim 17 , wherein the category is associated with a set of evaluations of the products included in the category, and further comprising:
determining, by the first computer system, a subset of the set of the evaluations of the products included in the category, the subset of the set of the evaluations of the products included in the category defined by inclusion of textual information about the second topic; determining, by the first computer system, an aggregate of the numerical information related to the subset of the set of the evaluations of the products included in the category; determining, by the first computer system, an aggregate of the numerical information related to a sub-subset of the subset of the set of the evaluations of the product

Assignees

• Google Inc

Inventors

• Hurley Fergus
• Mazzawi Hanna
• Gaillard Olivier

Classifications

• G06F40/253

  Grammatical analysis; Style critique · CPC title

• G06Q30/0282 Primary

  Rating or review of business operators or products · CPC title

• G06F40/211

  Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars · CPC title

• G06Q30/02

  Marketing; Price estimation or determination; Fundraising · CPC title

• G06Q10/06

  Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling · CPC title