Information pushing method and device

Patent metadata

Field	Value
Publication number	US-11252245-B2
Application number	US-201916509410-A
Country	US
Kind code	B2
Filing date	Jul 11, 2019
Priority date	May 18, 2017
Publication date	Feb 15, 2022
Grant date	Feb 15, 2022

Abstract

Embodiments can include an information pushing method and device. An embodiment of the method can include: receiving an information stream data acquisition request sent by a terminal, wherein the information stream data acquisition request comprises query information; performing a query according to the query information to obtain first information stream data; acquiring at least one of a search record or a browsing record of an account associated with the terminal with respect to a predetermined time period; determining, based on the at least one of the search record or the browsing record, a keyword; determining second information stream data located in a preset information stream data set and matching the key word; generating, based on the first information stream data and the determined second information stream data, data to be pushed; and pushing to the terminal the data to be pushed. The embodiment can achieve targeted information pushing.

First claim

What is claimed is:

1. A method for pushing information, the method comprising:
in response to an information stream data acquisition request sent by a terminal, performing a query to obtain first information stream data;
obtaining an alternative word set based on at least one of search statement in a search record or content of a browsed page in a browsing record;
for each alternative word in the alternative word set:
determining second information stream data and a preset attribute value corresponding to the second information stream data matching the alternative word;
calculating a product of the preset attribute value corresponding to the alternative word and a first probability corresponding to the alternative word;
obtaining a first score corresponding to the alternative word by weighted summation on the preset attribute value, the first probability, and the product; and
selecting, from the alternative word set, a predetermined number of alternative words as keywords according to an order of the first scores from high to low;

determining, in a preset information stream data set, second information stream data matching the selected keywords;
in response to a number of the determined second information stream data matching the selected keywords being greater than a preset number, executing following operations for each piece of the determined second information stream data matching the selected keywords:
acquiring another preset attribute value corresponding to the second information stream data matching the selected keywords;
determining respectively, on a basis of a pre-trained second probability determination model, a second probability of receiving a request sent by the terminal for visiting a page pointed to by the second information stream data matching the selected keywords, wherein the second probability determination model is used to characterize a corresponding relationship between the second probability and at least one of following information items: an account information of an account associated with the terminal, a device type of the terminal, type information of a browser used by the terminal, or feature information of the second information stream data matching the selected keywords; and
determining a second score of the second information stream data matching the selected keywords based on the other acquired preset attribute value and the second probability;

selecting, from the determined second information stream data matching the selected keywords, the preset number of the second information stream data matching the selected keywords according to an order of the second scores from high to low;
aggregating the first information stream data and the selected second information stream data to generate to-be-pushed data; and
pushing the to-be-pushed data to the terminal.

2. The method according to claim 1 , wherein:
the first probability is determined, on a basis of a pre-trained first probability determination model, which is used to characterize a corresponding relationship between the first probability and at least one of following information items: the account information of an account associated with the terminal, the device type of the terminal, the browser type of the browser used by the terminal, the alternative word, information of an industry to which the alternative word belongs, or a source of the alternative word.

3. The method according to claim 2 , wherein obtaining the alternative word set comprises:
performing at least one of statistical analysis or semantic parsing on the at least one of the search statement or the content, to extract at least one core word;
expanding each core word in the at least one core word to obtain an expanded word, wherein the expanded word comprises at least one of the following: a synonym of the core word, a near-synonym of the core word, or an associated word of the core word; and
determining the core word and the obtained expanded word as the selected keywords.

4. An apparatus for pushing information, the apparatus comprising:
at least one processor; and
a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
in response to an information stream data acquisition request sent by a terminal, performing a query to obtain first information stream data;
obtaining an alternative word set based on at least one of search statement in a search record or content of a browsed page in a browsing record;
for each alternative word in the alternative word set:
determining second information stream data and a preset attribute value corresponding to the second information stream data matching the alternative word;
calculating a product of the preset attribute value corresponding to the alternative word and a first probability corresponding to the alternative word;
obtaining a first score corresponding to the alternative word by weighted summation on the preset attribute value, the first probability, and the product; and
selecting, from the alternative word set, a predetermined number of alternative words as keywords according to an order of the first scores from high to low;

determining, in a preset information stream data set, second information stream data matching the selected keywords;
in response to a number of the determined second information stream data matching the selected keywords being greater than a preset number, executing following operations for each piece of the determined second information stream data matching the selected keywords:
acquiring another preset attribute value corresponding to the second information stream data matching the selected keywords;
determining respectively, on a basis of a pre-trained second probability determination model, a second probability of receiving a request sent by the terminal for visiting a page pointed to by the second information stream data matching the selected keywords, wherein the second probability determination model is used to characterize a corresponding relationship between the second probability and at least one of following information items: an account information of an account associated with the terminal, a device type of the terminal, type information of a browser used by the terminal, or feature information of the second information stream data matching the selected keywords; and
determining a second score of the second information stream data matching the selected keywords based on the other acquired preset attribute value and the second probability;

selecting, from the determined second information stream data matching the selected keywords, the preset number of the second information stream data matching the selected keywords according to an order of the second scores from high to low;
aggregating the first information stream data and the selected second information stream data to generate to-be-pushed data; and
pushing the to-be-pushed data to the terminal.

5. The apparatus according to claim 4 , wherein:
the first probability is determined, on a basis of a pre-trained first probability determination model, which is used to characterize a corresponding relationship between the first probability and at least one of following information items: the account information of an account associated with the terminal, the device type of the terminal, the browser type of the browser used by the terminal, the alternative word, information of an industry to which the alternative word belongs, or a source of the alternative word.

6. The apparatus according to claim 5 , wherein obtaining the alternative word set comprises:
performing at least one of statistical analysis or semantic parsing on the at least one of the searc

Assignees

• Baidu online network technology beijing co ltd

Inventors

• Shi Xuyong
• Han Cong
• He Dengwu
• Wang Luguang
• Wang Xiufei
• Liang Renpeng
• Yang Jiajun
• Liu Guoqing
• Yang Cheng
• Jiang Zhimin

Classifications

• H04L67/55 Primary

  Push-based network services · CPC title

• G06F16/953

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

• G06F16/951

  Indexing; Web crawling techniques · CPC title

• H04L41/145

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

• H04L41/142

  using statistical or mathematical methods · CPC title