Sorting text report categories

Patent metadata

Field	Value
Publication number	US-10915706-B2
Application number	US-202016888605-A
Country	US
Kind code	B2
Filing date	May 29, 2020
Priority date	Feb 5, 2018
Publication date	Feb 9, 2021
Grant date	Feb 9, 2021

Abstract

A computer-implemented method includes: receiving, by a computing device, a text report request from a user device associated with a user; obtaining a behavior history and personal information of the user; inputting the behavior history and the personal information of the user into a model, to obtain a plurality of personalized evaluation results, each personalized evaluation result corresponding to a respective text report category of a plurality of text report categories, in which each personalized evaluation result indicates a predicted relevance of the corresponding text report category to a problem faced by the user, and in which the model includes a classification model trained using one or more supervised learning techniques on a plurality of user behavior history samples and a plurality of personal information samples; and determining an order in which the plurality of text report categories are to be presented to the user.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving, by a computing device, a text report request from a user device associated with a user;
obtaining a behavior history and personal information of the user;
inputting the behavior history and the personal information of the user into a model, to obtain, as an output of the model, a plurality of personalized evaluation results, each personalized evaluation result corresponding to a respective text report category of a plurality of text report categories,
wherein each personalized evaluation result indicates a predicted relevance of the corresponding text report category to a problem faced by the user, and
wherein the model comprises a classification model trained using one or more supervised learning techniques on a plurality of user behavior history samples and a plurality of personal information samples, each sample associated with a respective label indicating a category of a text report selected by a user corresponding to the sample;

determining that a predetermined first number of text report categories of the plurality of text report categories are each selected more frequently than each other text report category by all users during a first predetermined time period;
determining that a predetermined second number of text report categories of the plurality of text report categories, excluding the predetermined first number of text report categories, are selected more frequently than each other text report category, except for the predetermined first number of text report categories, by users in a particular region during a second predetermined time period; and
determining, based on the plurality of personalized evaluation results, an order in which the plurality of text report categories are to be presented to the user, comprising sorting the plurality of text report categories in an order in which
the predetermined first number of text report categories are ordered in descending order based on respective quantities of user selections,
the predetermined second number of text report categories are ordered after the predetermined first number of text report categories, in descending order based on respective quantities of user selections, and
remaining text report categories of the plurality of text report categories are ordered in descending order after the predetermined second number of text report categories, sorted in an order based on respective personalized evaluation results corresponding to each remaining text report category.

2. The computer-implemented method of claim 1 , wherein the model comprises at least one of a multinomial classification model and N binary classification models, where N is a quantity of the plurality of text report categories.

3. The computer-implemented method of claim 1 , wherein the model is a personalized model trained based on one or more text report categories previously selected by the user.

4. The computer-implemented method of claim 1 , wherein the behavior history of the user comprises at least one of a browsing history of the user, a chat history of the user, and a function use history of the user; and
wherein the personal information of the user comprises at least one of geographical location information of the user device, a personalized user label of the user, and an IP address of the user device.

5. The computer-implemented method of claim 1 , comprising:
determining a number of times each text report category of the plurality of text report categories is selected during the first predetermined time period; and
determining the order in which the plurality of text report categories are to be presented to the user based on the determined number of times each text report category is selected during the first predetermined time period.

6. The computer-implemented method of claim 1 , comprising:
determining a number of times each text report category is selected by users in the particular region during the second predetermined time period; and
determining the order in which the plurality of text report categories are to be presented to the user based on the determined number of times each text report category is selected by users in the particular region during the second predetermined time period.

7. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:
receiving, by a computing device, a text report request from a user device associated with a user;
obtaining a behavior history and personal information of the user;
inputting the behavior history and the personal information of the user into a model, to obtain, as an output of the model, a plurality of personalized evaluation results, each personalized evaluation result corresponding to a respective text report category of a plurality of text report categories,
wherein each personalized evaluation result indicates a predicted relevance of the corresponding text report category to a problem faced by the user, and
wherein the model comprises a classification model trained using one or more supervised learning techniques on a plurality of user behavior history samples and a plurality of personal information samples, each sample associated with a respective label indicating a category of a text report selected by a user corresponding to the sample;

determining that a predetermined first number of text report categories of the plurality of text report categories are each selected more frequently than each other text report category by all users during a first predetermined time period;
determining that a predetermined second number of text report categories of the plurality of text report categories, excluding the predetermined first number of text report categories, are selected more frequently than each other text report category, except for the predetermined first number of text report categories, by users in a particular region during a second predetermined time period; and
determining, based on the plurality of personalized evaluation results, an order in which the plurality of text report categories are to be presented to the user, comprising sorting the plurality of text report categories in an order in which
the predetermined first number of text report categories are ordered in descending order based on respective quantities of user selections,
the predetermined second number of text report categories are ordered after the predetermined first number of text report categories, in descending order based on respective quantities of user selections, and
remaining text report categories of the plurality of text report categories are ordered in descending order after the predetermined second number of text report categories, sorted in an order based on respective personalized evaluation results corresponding to each remaining text report category.

8. The non-transitory, computer-readable medium of claim 7 , wherein the model comprises at least one of a multinomial classification model and N binary classification models, where N is a quantity of the plurality of text report categories.

9. The non-transitory, computer-readable medium of claim 7 , wherein the model is a personalized model trained based on one or more text report categories previously selected by the user.

10. The non-transitory, computer-readable medium of claim 7 , wherein the behavior history of the user comprises at least one of a browsing history of the user, a chat history of the user, and a function use history of the user; and
wherein the personal information of the user comprises at least one of geographical location information of the user device, a personalize

Assignees

• Advanced New Technologies Co Ltd

Inventors

• Jin Hong
• Wang Weiqiang

Classifications

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06Q30/0609

  Qualifying participants for shopping transactions (payment transaction verification G06Q20/401) · CPC title

• G06Q30/016

  After-sales · CPC title

• G06F40/279 Primary

  Recognition of textual entities · CPC title

• G06N20/20

  Ensemble learning · CPC title