WO2018036272A1

WO2018036272A1 - News content pushing method, electronic device, and computer readable storage medium

Info

Publication number: WO2018036272A1
Application number: PCT/CN2017/091258
Authority: WO
Inventors: 倪博溢; 窦宏辰; 马文利
Original assignee: 上海壹账通金融科技有限公司
Priority date: 2016-08-22
Filing date: 2017-06-30
Publication date: 2018-03-01
Also published as: CN106372113B; CN106372113A

Abstract

A news content pushing method comprises: when a user visits a news server to read news content by means of a browser system of a client, a news content monitoring module of the client analyzes and records attribute data of the news content read by the user according to a preset analysis model, and sends the recorded attribute data of the news content to a control server in real time or at regular time (S10); the control server analyzes the received attribute data of the news content corresponding to the user according to a preset analysis rule, so as to obtain a reading tag corresponding to the user, the reading tag comprising a preferred news type (S20); the control server obtains news content associated to the reading tag corresponding to the user from at least one news server in real time or at regular time (S30); and the control server pushes the obtained news content to the client of the user (S40). Also disclosed is an electronic device in which a news content pushing system is stored. In this way, the control server can specify a news customer group, and can push news content in a targeted way according to reading habits of users, and accordingly the phenomena of the repetition of news content and the occurrence of news content copyright disputes are avoided.

Description

Push method of news content, electronic device and computer readable storage medium

Priority claim

This application is based on the priority of the Paris Convention, which is entitled to the Chinese Patent Application No. CN201610704731.3, entitled "Pushing Method and System for News Content", filed on August 22, 2016, the entire contents of which are incorporated by reference. The method is incorporated in the present application.

Technical field

The present invention relates to the field of communications technologies, and in particular, to a method for pushing news content, an electronic device, and a computer readable storage medium.

Background technique

Most of the information sections of the existing mobile device app are simply sorted, edited, and forwarded by grabbing news source messages. The shortcomings of this existing method are as follows: 1. The news customer group is not clear and the targeting is not strong; second, the repeated news content, and direct copying will bring copyright problems.

Summary of the invention

The main object of the present invention is to provide a method for pushing news content, an electronic device, and a computer readable storage medium, which are aimed at solving the technical problem that the news customer group is unclear, the targeting is not strong, and the news content is duplicated and the copyright dispute is easy to occur.

In order to achieve the above object, a first aspect of the present invention provides a method for pushing a news content, where the method for pushing the news content includes:

A. When the user accesses the news server to read the news content through the browser system of the client, the news content monitoring module of the client analyzes and records the attribute data of the news content read by the user according to the predetermined analysis model, and the real-time or timing will be The attribute data of the recorded news content is sent to the control server;

B. The control server analyzes the received attribute data of the news content corresponding to the user according to the predetermined analysis rule to analyze the reading label corresponding to the user, and the reading label includes a preferred news category;

C. The control server acquires news content associated with the reading tag corresponding to the user from at least one news server in real time or at a time;

D. The control server pushes the obtained news content to the client of the user.

A second aspect of the present application provides an electronic device, including a processing device, a storage device, and a news content recommendation system, where the news content recommendation system is stored in the storage device, including at least one computer readable instruction, the at least one computer A read command can be executed by the processing device to:

A. When the user accesses the news server through the client's browser system to read the news content, the attribute data of the news content read by the user is analyzed and recorded according to a predetermined analysis model;

B. Performing attribute data of the news content corresponding to the user according to a predetermined analysis rule Parsing to analyze the reading tag corresponding to the user, the reading tag including a preferred news category;

C. acquiring news content associated with the reading tag corresponding to the user from at least one news server in real time or at a time;

D. Push the obtained news content to the client of the user.

A third aspect of the present application provides a computer readable storage medium having stored thereon at least one computer readable instruction executable by a processing device to:

B. The attribute data of the news content corresponding to the user is analyzed according to a predetermined analysis rule to analyze the reading label corresponding to the user, and the reading label includes a preferred news category;

D. Push the obtained news content to the client of the user.

The push method, the electronic device and the medium of the news content provided by the present invention analyze and record the attribute data of the news content read by the user according to a predetermined analysis model when the user accesses the news server through the browser system of the client to read the news content. And analyzing the attribute data of the news content corresponding to the user according to the predetermined analysis rule to analyze the reading label corresponding to the user, and acquiring the reading label corresponding to the user from the at least one news server in real time or timing. The news content, and the obtained news content is pushed to the client of the user. It realizes the ability to clarify the news customer base and push the news content to the user according to the user's reading habits, while avoiding the duplication of news content and the phenomenon of copyright disputes of news content.

DRAWINGS

1 is a schematic diagram of an application environment of a preferred embodiment of a method for pushing news content according to the present invention;

2 is a schematic flow chart of a first embodiment of a method for pushing news content according to the present invention;

3 is a schematic flow chart of a second embodiment of a method for pushing news content according to the present invention;

4 is a schematic flow chart of a third embodiment of a method for pushing news content according to the present invention;

FIG. 5 is a schematic flowchart of a detailed step of pushing a news content in a fourth embodiment of a method for pushing news content according to the present invention; FIG.

6 is a schematic flowchart of a detailed step of pushing a news content in a fifth embodiment of a method for pushing news content according to the present invention;

7 is a schematic diagram of functional modules of a first embodiment of a push system for news content according to the present invention;

8 is a schematic diagram of a refinement function module of a news content monitoring module in a push system of a news content according to the present invention;

9 is a schematic diagram of a refinement function module of a push module in a second embodiment of a push content system of the present invention;

10 is a schematic diagram of a refinement function module of a push module in a fourth embodiment of a push content system of the present invention;

11 is a refinement function model of a push module in a fifth embodiment of a push content system of the present invention; Block diagram.

The implementation, functional features, and advantages of the present invention will be further described in conjunction with the embodiments.

detailed description

It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Referring to FIG. 1 , it is a schematic diagram of an application environment of a preferred embodiment of the news content pushing method of the present invention. The application environment diagram includes an electronic device 1 and a client 2. The electronic device 1 can perform data interaction with the client 2 through a suitable technology such as a network or a near field communication technology.

Client 2 includes, but is not limited to, any electronic product that can interact with a user through a keyboard, mouse, remote control, touch pad, or voice control device, such as a personal computer, a tablet, a smart phone, or an individual. Digital Assistant (PDA), game console, Internet Protocol Television (IPTV), smart wearable device, etc.

The electronic device 1 is an apparatus capable of automatically performing numerical calculation and/or information processing in accordance with an instruction set or stored in advance. The electronic device 1 may be a computer, a single network server, a server group composed of multiple network servers, or a cloud-based cloud composed of a large number of hosts or network servers, where cloud computing is a type of distributed computing, A super virtual computer consisting of a loosely coupled set of computers.

In the present embodiment, the electronic device 1 includes, but is not limited to, a storage device 11, a processing device 12, and a network interface 13 that are communicably connected to each other through a system bus. It should be noted that FIG. 1 only shows the electronic device 1 having the components 11-13, but it should be understood that not all illustrated components are required to be implemented, and more or fewer components may be implemented instead.

The storage device 11 includes a memory and at least one type of readable storage medium. The memory provides a cache for the operation of the electronic device 1; the readable storage medium may be a non-volatile storage medium such as a flash memory, a hard disk, a multimedia card, a card type memory, or the like. In some embodiments, the readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1; in other embodiments, the non-volatile storage medium may also be external to the electronic device 1. A storage device, such as a plug-in hard disk equipped with an electronic device 1, a smart memory card (SMC), a Secure Digital (SD) card, a flash card, or the like. In this embodiment, the readable storage medium of the storage device 11 is generally used to store an operating system installed in the electronic device 1 and various types of application software, such as program code of the push system 10 of the news content in an embodiment of the present application. Further, the storage device 11 can also be used to temporarily store various types of data that have been output or are to be output.

Processing device 12 may, in some embodiments, include one or more microprocessors, microcontrollers, digital processors, and the like. The processing device 12 is generally used to control the operation of the electronic device 1, for example, to perform control and processing related to data interaction or communication with the terminal device 2. In the present embodiment, the processing device 12 is configured to execute program code or processing data stored in the storage device 11, such as the push system 10 that runs the news content, and the like.

The network interface 13 may comprise a wireless network interface or a wired network interface, which is typically used to establish a communication connection between the electronic device 1 and other electronic devices. In this embodiment, the network interface 13 is mainly used to connect the electronic device 1 with one or more clients 2, and establish a data transmission channel and a communication connection between the electronic device 1 and one or more clients 2.

The push system 10 of news content includes at least one computer readable instructions stored in the storage device 11, the at least one computer readable instructions being executable by the processing device 12 to implement a method of pushing news content of various embodiments of the present application. As described later, the at least one computer readable instruction can be classified into different logic modules depending on the functions implemented by its various parts.

In an embodiment, when the push system 10 of the news content is executed by the processing device 12, the following operations are first performed: first, when receiving the user accessing the news server through the browser system of the client 2, reading the news content, according to the predetermined analysis The attribute data of the news content read by the user is analyzed and recorded; and then the attribute data of the news content corresponding to the user is analyzed according to a predetermined analysis rule to analyze the reading label corresponding to the user (the reading label includes the preferred news category) Finally, the news content associated with the reading tag corresponding to the user is obtained from at least one news server in real time or at a time, and the obtained news content is pushed to the client 2 to implement targeted pushing according to the reading habits of the user of the client 2. News content to the user.

The push system 10 of the news content is communicatively connected with a plurality of social servers, and determines other users who belong to the same social group as the user of the client 2, and pushes the obtained news content to the user of the client 2, and/or This user belongs to other users of the same social group. In an embodiment, the push system 10 of news content is stored in the storage device 11 and includes at least one computer readable instructions stored in the storage device 11, the at least one computer readable instructions being executable by the processing device 12 to implement A method of pushing news content of various embodiments of the present application. As described later, the at least one computer readable instruction can be classified into different logic modules depending on the functions implemented by its various parts.

The invention provides a method for pushing news content. Referring to FIG. 2, FIG. 2 is a schematic flowchart diagram of a first embodiment of a method for pushing news content according to the present invention. The method for pushing news content according to the present invention includes the following steps:

Step S10, when the user accesses the news server to read the news content through the browser system of the client, the news content monitoring module of the client analyzes and records the attribute data of the news content read by the user according to the predetermined analysis model, and performs real-time or timing. Transmitting the attribute data of the recorded news content to the control server;

In this embodiment, the client can be a mobile phone, a tablet, a notebook, and all terminals that can be networked. The client's news content monitoring module can monitor whether the browser is running in real time or at a time and whether the browser is accessing the news server and whether to obtain news content on the news server while the browser is running. When the news content monitoring module detects that the browser obtains the news content on the news server, the news content monitoring module records the attribute data of the news content.

Optionally, the predetermined analysis model is a logistic regression model, and the training process of the logistic regression model is as follows:

E. Obtain a preset number of news sample data, and manually classify the news read by the user to obtain a news sample data set corresponding to each category, or collect news through preset keywords to obtain each pre- Set a news sample data set corresponding to the keyword;

Optionally, the preset number can be set large enough to ensure the accuracy of the analysis. For example, the preset number can be set to 500,000 copies. The preset keywords can be, for example, a US dollar interest rate increase, a RMB exchange rate, a house price adjustment, etc., which can be set according to actual needs.

F. Extracting, from each of the news sample data sets, a first preset proportion of news sample data as a training set, and using the remaining news sample data in each of the news sample data sets as a test set;

The first preset ratio can be set according to actual needs, for example, can be set to 70%. Therefore, the remaining 30% of the news sample data is used as a test set.

G. Perform word segmentation on each news sample in the training set and the test set;

For example, the news texts of various news samples are based on a thesaurus, with the word frequency as the standard, and the most likely one word segmentation scheme is obtained. For example, the “Nanjing Yangtze River Bridge” can be divided into: “Nanjing City/Yangtze River/ Bridge."

H. extracting the feature of the news text after the word segmentation, extracting the feature of each word segment in each news text according to the preset type in the text, and converting the preset type feature corresponding to each news text into the logistic regression model Training parameters

The preset type features may be, for example, features such as word frequency, word order, and the like. The training parameters can be, for example, numbers or series. Common training parameter conversion methods include TF-IDF (word frequency-inverse document frequency) method, which assigns each word to a dimension, and the value of each article in this dimension is "the word appears. The probability in this article "/" the frequency of the article in which the word appears."

I. Input training parameters corresponding to each news text in the training set into the logistic regression model for training to generate a logistic regression model to be used for attribute data analysis of the news content;

J. The training parameters corresponding to each news text in the test set are input into the generated logistic regression model for testing. If the accuracy of the test is greater than or equal to the preset threshold, the training is ended, or if the accuracy of the test is less than the preset. Threshold, then increase the news sample data, and re-execute steps F, G, H, I, and J until the accuracy of the test is greater than or equal to the preset threshold.

The preset threshold can be set according to actual needs, for example, it can be 95%.

The predetermined analysis model provided in this embodiment can accurately perform attribute data analysis of news content, and has high accuracy and reliability.

In step S20, the control server analyzes the received attribute data of the news content corresponding to the user according to the predetermined analysis rule to analyze the reading label corresponding to the user, and the reading label includes a preferred news category;

For example, reading labels can be sports, entertainment, real estate, and the like.

In this embodiment, the predetermined analysis rule may include:

If the number of times the user reads the news content under one news category is greater than the first preset threshold in the first preset time, determining that the news category is a preferred news category;

If the user selects the number of times of news content under a news category for the second preset time If the second preset threshold is greater, the news category is determined to be a preferred news category, and the second preset time is greater than the first preset time.

The first preset time can be, for example, the last 7 days. The news category can be, for example, sports news. The first preset threshold may be, for example, 10 times. That is, if the user reads the sports news more than 10 times in the last 7 days, the sports news category is considered to be the news category preferred by the user.

The second preset time may be, for example, the last 90 days, the news category may be, for example, sports news, and the second preset threshold may be, for example, 30 times. That is, when the user reads the sports news more than 30 times in the last 90 days, the sports news category is considered to be the news category preferred by the user.

Further, based on the foregoing, the reading label may further include a preferred reading period, and the predetermined analysis rule may further include:

If the number of readings of the news content under one news category is greater than the third preset threshold in the third preset time, the user determines that the time period is the reading time of the user's preference for the news category. The third preset time is the same as or different from the first preset time; the third preset time may be, for example, the last 6 days, and the time period may be, for example, 8:30-9:30, and the news category may be, for example, For the sports news category, the third preset threshold may be, for example, 4 times. That is, if the user has read the sports news category more than 4 times in the period from 8:30 to 9:30 in the last 6 days, it is considered that the time period is 8:30-9:30 for the user for the sports news category. The preferred reading time period.

If, during the fourth preset time, the user reads the news content under all news categories for a time period greater than a fourth preset threshold, determining that the time period is a reading time of the user's preference for all news categories The fourth preset time is the same as or different from the first preset time; the fourth preset time may be, for example, the last 5 days, and the time period may be, for example, 8:30-9:30, the fourth preset The threshold can be, for example, 8 times. That is, if the user has read all the news categories more than 8 times in the period from 8:30 to 9:30 in the last 5 days, it is considered that the time period is 8:30-9:30 for the user for all news categories. The preferred reading time period.

If the number of readings of the news content under one news category is greater than the fifth preset threshold in the fifth preset time, the user determines that the time period is the reading time of the user's preference for the news category. The fifth preset time is the same as or different from the second preset time; the fifth preset time may be, for example, the last 80 days, and the time period may be, for example, 8:30-9:30, and the news category may be, for example, For the sports news category, the fifth preset threshold may be, for example, 14 times. That is, if the user has repeatedly read the sports news category more than 14 times in the period of 8:30-9:30 in the last 80 days, it is considered that the time period is 8:30-9:30 for the user for the sports news category. The preferred reading time period.

If the number of readings of the news content under all the news categories is greater than the sixth preset threshold in the sixth preset time, the user determines that the time period is the reading time of the user's preference for all news categories. And the sixth preset time is the same as or different from the second preset time. The sixth preset time may be, for example, the last 85 days, the time period may be, for example, 8:30 to 9:30, and the sixth preset threshold may be, for example, 28 times. That is, if the user has read all the news categories more than 28 times in the period of 8:30-9:30 in the last 85 days, the time period is 8:30-9:30. The reading period for the user's preferences for all news categories.

Step S30, the control server acquires news content associated with the reading tag corresponding to the user from at least one news server in real time or at a time;

Step S40, the control server pushes the obtained news content to the client of the user.

For example, if the corresponding reading tag of the user indicates that the preferred news category is sports, the control server acquires news content belonging to the sports category and has not been pushed to the user from at least one news server in real time or at a time, and will acquire News content is pushed to the client.

The method for pushing news content provided by the present invention, when the user accesses the news server through the browser system of the client to read the news content, the news content monitoring module of the client analyzes and records the attribute of the news content read by the user according to the predetermined analysis model. Data, and real-time or timingly, the attribute data of the recorded news content is sent to the control server, and then the control server analyzes the received attribute data of the news content corresponding to the user according to the predetermined analysis rule to analyze the corresponding content of the user. Reading a tag, the reading tag includes a preferred news category, and then controlling the server to obtain news content associated with the reading tag corresponding to the user from at least one news server in real time or timing, and pushing the obtained news content to the user The client, so that the control server can clear the news customer group, and according to the user's reading habits, the news content is pushed in a targeted manner, avoiding the duplication of the news content, and avoiding the phenomenon of copyright disputes of the news content.

Further, based on the first embodiment of the push method of the news content of the present invention, the present invention also proposes a second embodiment of the push method of the news content. Referring to FIG. 3, FIG. 3 is a second implementation of the push method of the news content according to the present invention. A schematic flowchart of an example, in this embodiment, different from the first embodiment, the step S40 is replaced by:

Step S401, the control server is in communication connection with a plurality of social servers, and determines other users belonging to the same social group as the user;

Step S402, the control server pushes the obtained news content to the client of the user, and/or pushes the determined client of the other user.

In this embodiment, the social server may be, for example, a WeChat server, a QQ server, a Weibo server, or the like. If there is a soccer group in the user's WeChat group, then other users in the soccer group may be referred to as other users belonging to the same social group as the user. If the news category preferred by the user is a sports news category, the news category that other users in the soccer group are likely to prefer is also a sports news category. Therefore, the news content associated with the sports reading tag acquired by the server can be pushed to the client of the user, and simultaneously pushed to the client of the other users in the determined soccer group.

This embodiment further expands the news customer group by determining other users of the user's social group and pushing news content to other users of the social group according to the user's reading habits, and more effectively realizes reading according to the user. It is customary to push news content in a targeted manner.

Further, based on the first or second embodiment of the push method of the news content of the present invention, the present invention also proposes a third embodiment of the push method of the news content, with reference to FIG. 4, FIG. 4 is a push method of the news content of the present invention. The flow chart of the third embodiment is different from the first or second embodiment in the present embodiment. After the step S20, the method includes:

In step S50, the control server determines the service associated with the read tag corresponding to the user according to the association relationship between the read tag and the service type in real time or timing, and pushes the determined service to the client of the user. end.

In this embodiment, for example, the financial label can be configured to correspond to the financial product service. If the user's reading label is a financial label, the business associated with the financial label of the user is a financial product service, and the financial product service can be used. Push to the client's client.

In this embodiment, the related service is pushed to the user according to the reading habit of the user, thereby further expanding the range of the push data, and bringing convenience to the user, and also bringing economic benefits to the merchant.

Further, based on any one of the first to third embodiments of the push method of the news content of the present invention, the present invention further provides a fourth embodiment of the push method of the news content, with reference to FIG. 5, which is the news content of the present invention. In the present embodiment, the step S40 is different from the first to third embodiments in that the step S40 includes:

Step S403, the control server parses the acquired news content according to a predetermined parsing rule, to parse out each original news content, and extended news content associated with each original news content;

In this embodiment, optionally, the predetermined parsing rule includes:

If the plurality of news contents correspond to the same title information, the news content with the earliest release time is used as the original news content, and each of the other news contents is used as the extended news content associated with the news content;

If the title information of a news content appears in a predetermined position of at least one other news content, the content format of the predetermined location is a first preset format, and the title information of the news content and each of the other news content If the title information is inconsistent, the news content is determined to be the original news content, and each of the other news content is used as the extended news content associated with the news content; in this embodiment, the predetermined location may be, for example, the first segment. position. The first preset format may be, for example, "original title: XXX".

In each extended news content, the content of the second preset format of the preset location is determined, and the determined content of the second preset format is used as the corresponding extended content. The preset position may be, for example, the first segment and the second segment of the body. The second preset format may be, for example, a format including "XXX refers to XXX report XXX", "reported according to XX", and "XXX E location F month G (for example, Zhongxin.com Chongqing April 21st)" .

The extended news content may, for example, be related commentary news content that discusses the original news content.

Step S404, the control server sorts the extended news content associated with each original news content according to the order of the publishing time;

Step S405, the control server inserts the title of the associated extended news content and/or the link URL in the corresponding sorting order in the preset position of each original news content page; the preset location may be set, for example, at the bottom of the page. Blank location.

Step S406, the control server sends the original news content of each title and/or link URL with the associated extended news content to the client of the user.

In this embodiment, the original news content and the extended news content associated with the original news content are further determined according to the reading habit of the user, thereby further expanding the range of the push data, so that the pushed news content is more abundant and more in line with the user's reading habits.

Further, based on any one of the first to third embodiments of the push method of the news content of the present invention, the present invention further provides a fifth embodiment of the push method of the news content, with reference to FIG. 6, which is the news content of the present invention. In the present embodiment, the step S40 is different from the first to third embodiments in that the step S40 includes:

Step S407, the control server parses the acquired news content according to a predetermined parsing rule to parse out each original news content, and extended news content associated with each original news content, and an extension in each extended news content. Sexual content

In this embodiment, optionally, the predetermined parsing rule includes:

The extended news content may, for example, be related commentary news content that discusses the original news content. Extensible content can be content associated with related frequency news content.

Step S408, the control server sorts the extended news content associated with each original news content according to the order of the publishing time;

In step S409, the control server inserts the extended content of the associated extended news content in the corresponding sorting order in the preset position of each original news content page; the preset location may be set, for example, as a blank position at the bottom of the page.

Step S410, the control server sends the original news content of each extended content with the associated extended news content to the client of the user.

The embodiment further expands the scope of the push data by further determining the original news content and the extended content of the extended news content associated with the original news content according to the reading habit of the user, so that the pushed news content is richer and more in line with the user. reading habit.

The present invention further provides a push system for news content. Referring to FIG. 7, FIG. 7 is a schematic diagram of functional modules of a first embodiment of a push content system for a news content according to the present invention. The push system includes a client 100 and a control server 200, the client 100 includes a news content monitoring module 110, the control server 200 includes an analysis module 210, an acquisition module 220, and a push module 230;

The news content monitoring module 110 is configured to analyze and record attribute data of the news content read by the user according to a predetermined analysis model when the user accesses the news server to read the news content through the browser system of the client, and record the data in real time or at a time. The attribute data of the news content is sent to the control server;

Optionally, the predetermined analysis model is a logistic regression model. Referring to FIG. 8, FIG. 8 is a schematic diagram of a refinement function module of a news content monitoring module in a push content system of the present invention, where the news content monitoring module 110 includes :

The news sample obtaining unit 111 is configured to obtain a preset quantity of news sample data, and manually classify the news read by the user to obtain a news sample data set corresponding to each category, or collect the preset keyword. News to obtain a news sample data set corresponding to each preset keyword;

The training set extracting unit 112 is configured to extract a first preset proportion of news sample data from each of the news sample data sets as a training set, and use the remaining news sample data in each of the news sample data sets as a test set. ;

The word segmentation processing unit 113 is configured to perform word segmentation processing on each news sample in the training set and the test set;

The training parameter generating unit 114 is configured to extract the feature of the news text after the word segmentation, to extract the preset type features of each participle in each news text according to the text, and convert the preset type features corresponding to each news text into Training parameters of the logistic regression model;

The preset type features may be, for example, features such as word frequency, word order, and the like. The training parameters can be, for example, numbers or series. Common training parameter conversion methods include TF-IDF (word frequency-inverse document frequency) method, which assigns each word to a dimension, and the value of each article in this dimension is "the word appears. In this article Probability in /" "The frequency of the article in which the word appears."

The regression model generating unit 115 is configured to input training parameters corresponding to each news text in the training set into the logistic regression model for training, to generate a logistic regression model to be used for performing attribute data analysis of the news content;

The testing unit 116 is configured to input the training parameters corresponding to each news text in the test set into the generated logistic regression model for testing, and if the accuracy of the test is greater than or equal to the preset threshold, end the training, or if the test is accurate If the rate is less than the preset threshold, the news sample data is added, and the news sample acquisition unit 111, the training set extraction unit 112, the word segmentation processing unit 113, the training parameter generation unit 114, and the regression model generation unit 115 are returned to the test until the test is accurate. The rate is greater than or equal to the preset threshold.

The analyzing module 210 is configured to analyze, according to a predetermined analysis rule, the attribute data of the news content corresponding to the user, to analyze the reading label corresponding to the user, where the reading label includes a preferred news category;

In this embodiment, the predetermined analysis rule may include:

If the number of times the user reads the news content under one news category is greater than the second preset threshold in the second preset time, determining that the news category is a preferred news category, the second preset time is greater than the first A preset time.

If the number of readings of the news content under all the news categories is greater than the sixth preset threshold in the sixth preset time, the user determines that the time period is the reading time of the user's preference for all news categories. And the sixth preset time is the same as or different from the second preset time. The sixth preset time may be, for example, the last 85 days, the time period may be, for example, 8:30 to 9:30, and the sixth preset threshold may be, for example, 28 times. That is, if the user has read all the news categories more than 28 times in the period of 8:30-9:30 in the last 85 days, it is considered that the time period is 8:30-9:30 for the user for all news categories. The preferred reading time period.

The obtaining module 220 is configured to acquire news content associated with a reading tag corresponding to the user from at least one news server in real time or at a time;

The push module 230 is configured to push the obtained news content to the client of the user.

The push content system of the news content provided by the present invention, when the user accesses the news server through the browser system of the client to read the news content, the news content monitoring module of the client analyzes and records the attribute of the news content read by the user according to the predetermined analysis model. Data, and real-time or timingly, the attribute data of the recorded news content is sent to the control server, and then the control server analyzes the received attribute data of the news content corresponding to the user according to the predetermined analysis rule to analyze the corresponding content of the user. Reading a tag, the reading tag includes a preferred news category, and then controlling the server to obtain news content associated with the reading tag corresponding to the user from at least one news server in real time or timing, and pushing the obtained news content to the user The client, so that the control server can clear the news customer group, and according to the user's reading habits, the news content is pushed in a targeted manner, avoiding the duplication of the news content, and avoiding the phenomenon of copyright disputes of the news content.

Further, based on the first embodiment of the push system of the news content of the present invention, the present invention also provides The second embodiment of the push system of the news content, with reference to FIG. 9, is a schematic diagram of the refinement function module of the push module in the second embodiment of the push system of the news content of the present invention. In this embodiment, The embodiment is different, the push module 230 includes:

a determining unit 2311, configured to communicate with a plurality of social servers, and determine other users that belong to the same social group as the user;

The first pushing unit 2312 is configured to push the obtained news content to the client of the user, and/or to the client of the determined other user.

Further, based on the first or second embodiment of the push system of the news content of the present invention, the present invention also proposes a third embodiment of the push system of the news content, in the present embodiment, with the first or second embodiment The difference is that the push module 230 is further configured to determine, according to a predetermined association relationship between the read tag and the service type, the service associated with the read tag corresponding to the user, and push the determined service to the real-time or timing. The client of the user.

Further, according to any one of the first to third embodiments of the push system of the news content of the present invention, the present invention further provides a fourth embodiment of the push system of the news content, with reference to FIG. 10, which is the news content of the present invention. In the fourth embodiment, the push module 230 includes:

The first parsing unit 232 is configured to parse the obtained news content according to a predetermined parsing rule to parse each original news content and extended news content associated with each original news content;

In this embodiment, optionally, the predetermined parsing rule includes:

If the title information of a news content appears in a predetermined one of at least one other news content Position, the content format of the predetermined location is a first preset format, and the title information of the news content is inconsistent with the title information of each of the other news content, determining that the news content is the original news content, and each The other news content is extended news content associated with the news content; in the embodiment, the predetermined location may be, for example, a first segment location. The first preset format may be, for example, "original title: XXX".

The first sorting unit 233 is configured to sort the extended news content associated with each original news content according to the order of the publishing time;

The first insertion unit 234 is configured to insert, in a preset position of each original news content page, the title and/or the link URL of the associated extended news content in a corresponding sorting order; the preset position may be set, for example, at the bottom of the page. The blank location.

The second pushing unit 235 is configured to send the original news content of each title and/or link URL with the associated extended news content to the client of the user.

Further, according to any one of the first to third embodiments of the push system of the news content of the present invention, the present invention further provides a fifth embodiment of the push system of the news content, with reference to FIG. 11, which is the news content of the present invention. In the embodiment, in the embodiment, the push module 230 includes:

The second parsing unit 236 is configured to parse the obtained news content according to a predetermined parsing rule to parse each original news content, and extended news content associated with each original news content, and each extended news content Extensible content;

In this embodiment, optionally, the predetermined parsing rule includes:

The second sorting unit 237 is configured to sort the extended news content associated with each original news content according to the order of the publishing time;

The second insertion unit 238 is configured to insert, in a preset position of each original news content page, the extended content of the associated extended news content in a corresponding sorting order; the preset position may be set, for example, to a blank position at the bottom of the page. .

The third pushing unit 239 is configured to send the original news content of each extended content with the associated extended news content to the client of the user.

It is to be understood that the term "comprises", "comprising", or any other variants thereof, is intended to encompass a non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes those elements. It also includes other elements that are not explicitly listed, or elements that are inherent to such a process, method, article, or device. An element that is defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in the process, method, item, or device that comprises the element.

The serial numbers of the embodiments of the present invention are merely for the description, and do not represent the advantages and disadvantages of the embodiments.

Through the description of the above embodiments, those skilled in the art can clearly understand that the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better. Implementation. Based on such understanding, the technical solution of the present invention, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk, The optical disc includes a number of instructions for causing a terminal device (which may be a cell phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present invention.

The above are only the preferred embodiments of the present invention, and are not intended to limit the scope of the invention, and the equivalent structure or equivalent process transformations made by the description of the present invention and the drawings are directly or indirectly applied to other related technical fields. The same is included in the scope of patent protection of the present invention.

Claims

A method for pushing news content, characterized in that the method for pushing news content comprises:

A. When the user accesses the news server to read the news content through the browser system of the client, the news content monitoring module of the client analyzes and records the attribute data of the news content read by the user according to the predetermined analysis model, and the real-time or timing will be The attribute data of the recorded news content is sent to the control server;

B. The control server analyzes the received attribute data of the news content corresponding to the user according to the predetermined analysis rule to analyze the reading label corresponding to the user, and the reading label includes a preferred news category;

C. The control server acquires news content associated with the reading tag corresponding to the user from at least one news server in real time or at a time;

D. The control server pushes the obtained news content to the client of the user.
The method for pushing news content according to claim 1, wherein the step D is replaced by:

The control server is in communication with a plurality of social servers to determine other users belonging to the same social group as the user;

The control server pushes the obtained news content to the client of the user, and/or pushes the determined client of the other user.
The method for pushing a news content according to claim 1, wherein after the step B, the method further comprises:

The control server determines the service associated with the reading tag corresponding to the user according to the association relationship between the read tag and the service type in real time or timing, and pushes the determined service to the client of the user.
The method for pushing news content according to any one of claims 1 to 3, wherein the predetermined analysis model is a logistic regression model, and the training process of the logistic regression model is as follows:

E. Obtain a preset number of news sample data, and manually classify the news read by the user to obtain a news sample data set corresponding to each category, or collect news through preset keywords to obtain each pre- Set a news sample data set corresponding to the keyword;

F. Extracting, from each of the news sample data sets, a first preset proportion of news sample data as a training set, and using the remaining news sample data in each of the news sample data sets as a test set;

G. Perform word segmentation on each news sample in the training set and the test set;

H. extracting the feature of the news text after the word segmentation, extracting the feature of each word segment in each news text according to the preset type in the text, and converting the preset type feature corresponding to each news text into the logistic regression model Training parameters

I. Input training parameters corresponding to each news text in the training set to the logistic regression model Training to generate a logistic regression model to be used for attribute data analysis of news content;

J. The training parameters corresponding to each news text in the test set are input into the generated logistic regression model for testing. If the accuracy of the test is greater than or equal to the preset threshold, the training is ended, or if the accuracy of the test is less than the preset. Threshold, then increase the news sample data, and re-execute steps F, G, H, I, and J until the accuracy of the test is greater than or equal to the preset threshold.
The method for pushing news content according to any one of claims 1 to 3, wherein the predetermined analysis rule comprises:

If the number of times the user reads the news content under one news category is greater than the first preset threshold in the first preset time, determining that the news category is a preferred news category;

If the number of times the user reads the news content under one news category is greater than the second preset threshold in the second preset time, determining that the news category is a preferred news category, the second preset time is greater than the first A preset time.
The method for pushing a news content according to claim 5, wherein the reading tag further comprises a preferred reading time period, the predetermined analysis rule further comprising:

If the number of readings of the news content under one news category is greater than the third preset threshold in the third preset time, the user determines that the time period is the reading time of the user's preference for the news category. The third preset time is the same as or different from the first preset time;

If, during the fourth preset time, the user reads the news content under all news categories for a time period greater than a fourth preset threshold, determining that the time period is a reading time of the user's preference for all news categories a segment, the fourth preset time being the same as or different from the first preset time;

If the number of readings of the news content under one news category is greater than the fifth preset threshold in the fifth preset time, the user determines that the time period is the reading time of the user's preference for the news category. a segment, the fifth preset time being the same as or different from the second preset time;

If the number of readings of the news content under all the news categories is greater than the sixth preset threshold in the sixth preset time, the user determines that the time period is the reading time of the user's preference for all news categories. And the sixth preset time is the same as or different from the second preset time.
The method for pushing a news content according to claim 1, wherein the step D comprises:

The control server parses the acquired news content according to a predetermined parsing rule to parse each original news content and extended news content associated with each original news content;

The control server sorts the extended news content associated with each original news content according to the order of the publishing time;

The control server inserts, in a preset position of each original news content page, a title and/or a link URL of all associated extended news content in a corresponding sorting order;

The control server will each have a title and/or link URL of the associated extended news content The original news content is sent to the client of the user.
The method for pushing a news content according to claim 1, wherein the step D comprises:

The control server parses the obtained news content according to a predetermined parsing rule to parse each original news content, and extended news content associated with each original news content, and extended content in each extended news content;

The control server sorts the extended news content associated with each original news content according to the order of the publishing time;

The control server inserts, in a preset position of each original news content page, the extended content of all the extended news content that is associated according to the corresponding sorting order;

The control server sends the original news content of each of the extended content with associated extended news content to the client of the user.
The method for pushing news content according to claim 7 or 8, wherein the predetermined parsing rule comprises:

If the plurality of news contents correspond to the same title information, the news content with the earliest release time is used as the original news content, and each of the other news contents is used as the extended news content associated with the news content;

If the title information of a news content appears in a predetermined position of at least one other news content, the content format of the predetermined location is a first preset format, and the title information of the news content and each of the other news content If the title information is inconsistent, the news content is determined to be the original news content, and each of the other news content is used as the extended news content associated with the news content;

In each extended news content, the content of the second preset format of the preset location is determined, and the determined content of the second preset format is used as the corresponding extended content.
An electronic device comprising a processing device, a storage device storing a push system of news content, the push system of the news content comprising at least one computer readable instruction, the at least one computer readable instruction being readable by the processing device Execute to do the following:

A. When the user accesses the news server through the client's browser system to read the news content, the attribute data of the news content read by the user is analyzed and recorded according to a predetermined analysis model;

B. The attribute data of the news content corresponding to the user is analyzed according to a predetermined analysis rule to analyze the reading label corresponding to the user, and the reading label includes a preferred news category;

C. acquiring news content associated with the reading tag corresponding to the user from at least one news server in real time or at a time;

D. Push the obtained news content to the client of the user.
The electronic device according to claim 10, wherein said at least one computer readable instruction is executable by said processing device, and said step of implementing said operation D is replaced by:

Communicating with a plurality of social servers to determine other users belonging to the same social group as the user;

Pushing the obtained news content to the client of the user, and/or pushing it to the determined one Clients of other users.
The electronic device of claim 10, wherein the at least one computer readable instruction is executable by the processing device and further configured to:

The service associated with the reading tag corresponding to the user is determined in real time or periodically according to the relationship between the predetermined reading tag and the service type, and the determined service is pushed to the client of the user.
The electronic device according to any one of claims 10 to 12, wherein the predetermined analysis model is a logistic regression model, the at least one computer readable instruction being executable by the processing device, Do the following:

E. Obtain a preset number of news sample data, and manually classify the news read by the user to obtain a news sample data set corresponding to each category, or collect news through preset keywords to obtain each pre- Set a news sample data set corresponding to the keyword;

F. Extracting, from each of the news sample data sets, a first preset proportion of news sample data as a training set, and using the remaining news sample data in each of the news sample data sets as a test set;

G. Perform word segmentation on each news sample in the training set and the test set;

H. extracting the feature of the news text after the word segmentation, extracting the feature of each word segment in each news text according to the preset type in the text, and converting the preset type feature corresponding to each news text into the logistic regression model Training parameters

I. Input training parameters corresponding to each news text in the training set into the logistic regression model for training to generate a logistic regression model to be used for attribute data analysis of the news content;

J. The training parameters corresponding to each news text in the test set are input into the generated logistic regression model for testing. If the accuracy of the test is greater than or equal to the preset threshold, the training is ended, or if the accuracy of the test is less than the preset. Threshold, then increase the news sample data, and re-execute steps F, G, H, I, and J until the accuracy of the test is greater than or equal to the preset threshold.
The electronic device according to any one of claims 10 to 12, wherein the predetermined analysis rule comprises:

If the number of times the user reads the news content under one news category is greater than the first preset threshold in the first preset time, determining that the news category is a preferred news category;

If the number of times the user reads the news content under one news category is greater than the second preset threshold in the second preset time, determining that the news category is a preferred news category, the second preset time is greater than the first A preset time.
The electronic device of claim 14, wherein the reading tag further comprises a preferred reading time period, the predetermined analysis rule further comprising:

If the number of readings of the news content under one news category is greater than the third preset threshold in the third preset time, the user determines that the time period is the reading time of the user's preference for the news category. The third preset time is the same as or different from the first preset time;

If the user is in a time period for the fourth preset time, for all news categories The reading time of the content is greater than the fourth preset threshold, determining that the time period is a reading time period of the user's preference for all news categories, and the fourth preset time is the same as or different from the first preset time;

If the number of readings of the news content under one news category is greater than the fifth preset threshold in the fifth preset time, the user determines that the time period is the reading time of the user's preference for the news category. a segment, the fifth preset time being the same as or different from the second preset time;

If the number of readings of the news content under all the news categories is greater than the sixth preset threshold in the sixth preset time, the user determines that the time period is the reading time of the user's preference for all news categories. And the sixth preset time is the same as or different from the second preset time.
The electronic device of claim 10, wherein the at least one computer readable instruction is executable by the processing device and further configured to:

Parsing the obtained news content according to a predetermined parsing rule to parse out the original news content and the extended news content associated with each original news content;

The extended news content associated with each original news content is sorted in the order of publication time;

In the preset position of each original news content page, insert the title and/or the link URL of all the extended news content associated in the corresponding sort order;

The original news content with the title and/or link URL of the associated extended news content is sent to the client of the user.
The electronic device of claim 10, wherein the at least one computer readable instruction is executable by the processing device and further configured to:

The obtained news content is parsed according to a predetermined parsing rule to parse each original news content, and extended news content associated with each original news content, and extended content in each extended news content;

The extended news content associated with each original news content is sorted in the order of publication time;

Inserting, in a preset position of each original news content page, the extended content of the associated extended news content in a corresponding sorting order;

The original news content of each of the extended content with associated extended news content is sent to the client of the user.
The electronic device according to claim 16 or 17, wherein the predetermined resolution rule comprises:

If the plurality of news contents correspond to the same title information, the news content with the earliest release time is used as the original news content, and each of the other news contents is used as the extended news content associated with the news content;

If the title information of a news content appears in a predetermined position of at least one other news content, the content format of the predetermined location is a first preset format, and the subject matter of the news content The title information is inconsistent with the title information of each of the other news contents, and then the news content is determined to be the original news content, and each of the other news contents is used as the extended news content associated with the news content;

In each extended news content, the content of the second preset format of the preset location is determined, and the determined content of the second preset format is used as the corresponding extended content.
A computer readable storage medium having stored thereon at least one computer readable instruction executable by a processing device to:

A. When the user accesses the news server through the client's browser system to read the news content, the attribute data of the news content read by the user is analyzed and recorded according to a predetermined analysis model;

B. The attribute data of the news content corresponding to the user is analyzed according to a predetermined analysis rule to analyze the reading label corresponding to the user, and the reading label includes a preferred news category;

C. acquiring news content associated with the reading tag corresponding to the user from at least one news server in real time or at a time;

D. Push the obtained news content to the client of the user.
A medium according to claim 19, wherein said computer readable instructions storing at least one step executable by said processing device to implement the push method of news content according to any of claims 1 to 9 is stored.