WO2018036272A1 - 新闻内容的推送方法、电子装置及计算机可读存储介质 - Google Patents
新闻内容的推送方法、电子装置及计算机可读存储介质 Download PDFInfo
- Publication number
- WO2018036272A1 WO2018036272A1 PCT/CN2017/091258 CN2017091258W WO2018036272A1 WO 2018036272 A1 WO2018036272 A1 WO 2018036272A1 CN 2017091258 W CN2017091258 W CN 2017091258W WO 2018036272 A1 WO2018036272 A1 WO 2018036272A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- news
- news content
- content
- user
- preset
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
- G06F16/337—Profile generation, learning or modification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
Definitions
- 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.
- 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.
- a first aspect of the present invention provides a method for pushing a news content, where the method for pushing the news content includes:
- 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;
- 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;
- 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;
- 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:
- the attribute data of the news content read by the user is analyzed and recorded according to a predetermined analysis model
- 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:
- the attribute data of the news content read by the user is analyzed and recorded according to a predetermined analysis model
- 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;
- 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.
- FIG. 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
- FIG. 2 is a schematic flow chart of a first embodiment of a method for pushing news content according to the present invention
- FIG. 3 is a schematic flow chart of a second embodiment of a method for pushing news content according to the present invention.
- FIG. 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.
- FIG. 7 is a schematic diagram of functional modules of a first embodiment of a push system for news content according to the present invention.
- FIG. 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.
- FIG. 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.
- FIG. 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.
- FIG. 11 is a refinement function model of a push module in a fifth embodiment of a push content system of the present invention.
- 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.
- IPTV Internet Protocol Television
- 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.
- 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.
- 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.
- SMC smart memory card
- SD Secure Digital
- 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.
- 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.
- 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.
- the at least one computer readable instruction can be classified into different logic modules depending on the functions implemented by its various parts.
- the push system 10 of the news content when 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.
- 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.
- the at least one computer readable instruction can be classified into different logic modules depending on the functions implemented by its various parts.
- 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;
- 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.
- the predetermined analysis model is a logistic regression model
- the training process of the logistic regression model is as follows:
- the preset number can be set large enough to ensure the accuracy of the analysis.
- 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.
- 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.
- 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.
- the “Nanjing Yangtze River Bridge” can be divided into: “Nanjing City/Yangtze River/ Bridge.”
- 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.”
- 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.
- 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;
- reading labels can be sports, entertainment, real estate, and the like.
- the predetermined analysis rule may include:
- 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
- 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.
- the reading label may further include a preferred reading period
- the predetermined analysis rule may further include:
- 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,
- 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 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
- 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 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.
- 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,
- 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 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
- the user determines that the time period is the reading time of the user's preference for all news categories.
- 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
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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;
- the predetermined parsing rule includes:
- 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;
- 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".
- 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.
- 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.
- 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.
- 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 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.
- the predetermined parsing rule includes:
- 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;
- 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".
- 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.
- 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
- 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.
- 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;
- 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.
- 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 preset number can be set large enough to ensure the accuracy of the analysis.
- 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.
- 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 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.
- 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 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.
- the “Nanjing Yangtze River Bridge” can be divided into: “Nanjing City/Yangtze River/ Bridge.”
- 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 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.
- 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;
- reading labels can be sports, entertainment, real estate, and the like.
- the predetermined analysis rule may include:
- the second preset time is greater than the first A 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
- 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.
- the reading label may further include a preferred reading period
- the predetermined analysis rule may further include:
- 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,
- 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 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
- 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 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.
- 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,
- 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 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
- the user determines that the time period is the reading time of the user's preference for all news categories.
- 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
- 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 is, for example, the last 85 days, the time period may be, for example, 8:30 to 9:30, 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 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 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.
- 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.
- 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.
- 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.
- 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 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.
- 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.
- 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.
- 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.
- 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;
- the predetermined parsing rule includes:
- 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;
- 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 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.
- 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.
- 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.
- 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.
- 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;
- the predetermined parsing rule includes:
- 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;
- 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".
- 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.
- Extensible content can be content associated with related frequency news content.
- 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.
- 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 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.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Information Transfer Between Computers (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
一种新闻内容的推送方法,包括:在用户通过客户端的浏览器系统访问新闻服务器阅读新闻内容时,所述客户端的新闻内容监控模块按照预先确定的分析模型分析并记录该用户阅读的新闻内容的属性数据,并实时或者定时将记录的新闻内容的属性数据发送给控制服务器(S10);所述控制服务器根据预先确定的分析规则对接收的该用户对应的新闻内容的属性数据进行分析,以分析出该用户对应的阅读标签,所述阅读标签包括偏好的新闻类别(S20);所述控制服务器实时或定时从至少一个新闻服务器获取与该用户对应的阅读标签关联的新闻内容(S30);所述控制服务器将获取的新闻内容推送给该用户的客户端(S40)。还公开了一种存储有新闻内容推送系统的电子装置。使得控制服务器能够明确新闻客户群,并根据用户的阅读习惯有针对性的推送新闻内容,避免了新闻内容的重复及新闻内容版权纠纷的现象产生。
Description
优先权申明
本申请基于巴黎公约申明享有2016年8月22日递交的申请号为CN201610704731.3、名称为“新闻内容的推送方法及系统”中国专利申请的优先权,该中国专利申请的整体内容以参考的方式结合在本申请中。
本发明涉及通信技术领域,尤其涉及一种新闻内容的推送方法、电子装置及计算机可读存储介质。
现有的移动设备app的资讯板块多是通过抓取新闻源消息,加以简单分类、编辑后转发。这种现有方式的缺陷在于:一、新闻客户群不明确、针对性不强;二、新闻内容重复,以及直接复制会带来版权问题。
发明内容
本发明的主要目的在于提供一种新闻内容的推送方法、电子装置及计算机可读存储介质,旨在解决新闻客户群不明确、针对性不强以及新闻内容重复、容易产生版权纠纷的技术问题。
为实现上述目的,本发明第一方面提供一种新闻内容的推送方法,所述新闻内容的推送方法包括:
A、在用户通过客户端的浏览器系统访问新闻服务器阅读新闻内容时,所述客户端的新闻内容监控模块按照预先确定的分析模型分析并记录该用户阅读的新闻内容的属性数据,并实时或者定时将记录的新闻内容的属性数据发送给控制服务器;
B、所述控制服务器根据预先确定的分析规则对接收的该用户对应的新闻内容的属性数据进行分析,以分析出该用户对应的阅读标签,所述阅读标签包括偏好的新闻类别;
C、所述控制服务器实时或者定时从至少一个新闻服务器获取与该用户对应的阅读标签关联的新闻内容;
D、所述控制服务器将获取的新闻内容推送给该用户的所述客户端。
本申请第二方面提供一种电子装置,包括处理设备、存储设备及新闻的内容推荐系统,该新闻的内容推荐系统存储于该存储设备中,包括至少一个计算机可读指令,该至少一个计算机可读指令可被所述处理设备执行,以实现以下操作:
A、在用户通过客户端的浏览器系统访问新闻服务器阅读新闻内容时,按照预先确定的分析模型分析并记录该用户阅读的新闻内容的属性数据;
B、根据预先确定的分析规则对该用户对应的新闻内容的属性数据进行分
析,以分析出该用户对应的阅读标签,所述阅读标签包括偏好的新闻类别;
C、实时或者定时从至少一个新闻服务器获取与该用户对应的阅读标签关联的新闻内容;
D、将获取的新闻内容推送给该用户的所述客户端。
本申请第三方面提供一种计算机可读存储介质,其上存储有至少一个可被处理设备执行以实现以下操作的计算机可读指令:
A、在用户通过客户端的浏览器系统访问新闻服务器阅读新闻内容时,按照预先确定的分析模型分析并记录该用户阅读的新闻内容的属性数据;
B、根据预先确定的分析规则对该用户对应的新闻内容的属性数据进行分析,以分析出该用户对应的阅读标签,所述阅读标签包括偏好的新闻类别;
C、实时或者定时从至少一个新闻服务器获取与该用户对应的阅读标签关联的新闻内容;
D、将获取的新闻内容推送给该用户的所述客户端。
本发明提供的新闻内容的推送方法、电子装置及介质,通过在用户通过客户端的浏览器系统访问新闻服务器阅读新闻内容时,按照预先确定的分析模型分析并记录该用户阅读的新闻内容的属性数据,根据预先确定的分析规则对接收的该用户对应的新闻内容的属性数据进行分析,以分析出该用户对应的阅读标签,实时或者定时从至少一个新闻服务器获取与该用户对应的阅读标签关联的新闻内容,并将获取的新闻内容推送给该用户的所述客户端。实现了能够明确新闻客户群,并根据用户的阅读习惯有针对性的推送新闻内容给用户,同时避免了新闻内容的重复,及新闻内容版权纠纷的现象产生。
图1为本发明新闻内容的推送方法的较佳实施例的应用环境示意图;
图2为本发明新闻内容的推送方法第一实施例的流程示意图;
图3为本发明新闻内容的推送方法第二实施例的流程示意图;
图4为本发明新闻内容的推送方法第三实施例的流程示意图;
图5为本发明新闻内容的推送方法第四实施例中新闻内容推送步骤的细化流程示意图;
图6为本发明新闻内容的推送方法第五实施例中新闻内容推送步骤的细化流程示意图;
图7为本发明新闻内容的推送系统第一实施例的功能模块示意图;
图8为本发明新闻内容的推送系统中新闻内容监控模块的细化功能模块示意图;
图9为本发明新闻内容的推送系统第二实施例中推送模块的细化功能模块示意图;
图10为本发明新闻内容的推送系统第四实施例中推送模块的细化功能模块示意图;
图11为本发明新闻内容的推送系统第五实施例中推送模块的细化功能模
块示意图。
本发明目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。
参阅图1所示,是本发明新闻内容推送方法的较佳实施例的应用环境示意图。应用环境示意图包括电子装置1及客户端2。电子装置1可以通过网络、近场通信技术等适合的技术与客户端2进行数据交互。
客户端2包括,但不限于,任何一种可与用户通过键盘、鼠标、遥控器、触摸板或者声控设备等方式进行人机交互的电子产品,例如,个人计算机、平板电脑、智能手机、个人数字助理(Personal Digital Assistant,PDA),游戏机、交互式网络电视(Internet Protocol Television,IPTV)、智能式穿戴式设备等。
电子装置1是一种能够按照事先设定或者存储的指令,自动进行数值计算和/或信息处理的设备。电子装置1可以是计算机、也可以是单个网络服务器、多个网络服务器组成的服务器组或者基于云计算的由大量主机或者网络服务器构成的云,其中云计算是分布式计算的一种,由一群松散耦合的计算机集组成的一个超级虚拟计算机。
在本实施例中,电子装置1包括,但不仅限于,可通过系统总线相互通信连接的存储设备11、处理设备12、及网络接口13。需要指出的是,图1仅示出了具有组件11-13的电子装置1,但是应理解的是,并不要求实施所有示出的组件,可以替代的实施更多或者更少的组件。
其中,存储设备11包括内存及至少一种类型的可读存储介质。内存为电子装置1的运行提供缓存;可读存储介质可为如闪存、硬盘、多媒体卡、卡型存储器等的非易失性存储介质。在一些实施例中,可读存储介质可以是电子装置1的内部存储单元,例如该电子装置1的硬盘;在另一些实施例中,该非易失性存储介质也可以是电子装置1的外部存储设备,例如电子装置1上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。本实施例中,存储设备11的可读存储介质通常用于存储安装于电子装置1的操作系统和各类应用软件,例如本申请一实施例中的新闻内容的推送系统10的程序代码等。此外,存储设备11还可以用于暂时地存储已经输出或者将要输出的各类数据。
处理设备12在一些实施例中可以包括一个或者多个微处理器、微控制器、数字处理器等。该处理设备12通常用于控制电子装置1的运行,例如执行与终端设备2进行数据交互或者通信相关的控制和处理等。在本实施例中,处理设备12用于运行存储设备11中存储的程序代码或者处理数据,例如运行新闻内容的推送系统10等。
网络接口13可包括无线网络接口或有线网络接口,该网络接口13通常用于在电子装置1与其他电子设备之间建立通信连接。本实施例中,网络接口13主要用于将电子装置1与一个或多个客户端2相连,在电子装置1与一个或多个客户端2之间建立数据传输通道和通信连接。
新闻内容的推送系统10包括至少一个存储在存储设备11中的计算机可读指令,该至少一个计算机可读指令可被处理设备12执行,以实现本申请各实施例的新闻内容的推送方法。如后续所述,该至少一个计算机可读指令依据其各部分所实现的功能不同,可被划为不同的逻辑模块。
在一实施例中,新闻内容的推送系统10被处理设备12执行时,实现以下操作:首先在接收到用户通过客户端2的浏览器系统访问新闻服务器阅读新闻内容时,按照预先确定的分析默写分析并记录该用户阅读的新闻内容的属性数据;然后根据预先确定的分析规则对该用户对应的新闻内容的属性数据进行分析,以分析出该用户对应的阅读标签(阅读标签包括偏好的新闻类别);最后实时或者定时从至少一个新闻服务器获取与该用户对应的阅读标签关联的新闻内容,将获取的新闻内容推送给客户端2,实现根据客户端2的用户的阅读习惯有针对性的推送新闻内容给该用户。
其中,新闻内容的推送系统10与多个社交服务器通信连接,确定出与客户端2的用户属于同一社交群组的其他用户,将获取的新闻内容推送给客户端2的用户,及/或与该用户属于同一社交群组的其他用户。在一实施例中,新闻内容的推送系统10存储在存储设备11中,包括至少一个存储在存储设备11中的计算机可读指令,该至少一个计算机可读指令可被处理设备12执行,以实现本申请各实施例的新闻内容的推送方法。如后续所述,该至少一个计算机可读指令依据其各部分所实现的功能不同,可被划为不同的逻辑模块。
本发明提供一种新闻内容的推送方法。参照图2,图2为本发明新闻内容的推送方法第一实施例的流程示意图,本发明提出的新闻内容的推送方法包括以下步骤:
步骤S10,在用户通过客户端的浏览器系统访问新闻服务器阅读新闻内容时,所述客户端的新闻内容监控模块按照预先确定的分析模型分析并记录该用户阅读的新闻内容的属性数据,并实时或者定时将记录的新闻内容的属性数据发送给控制服务器;
在本实施例中,客户端可以为手机、平板电脑、笔记本以及所有可以联网的终端等。客户端的新闻内容监控模块可以实时或定时监测浏览器是否处于运行状态以及在浏览器处于运行状态时,浏览器是否在访问新闻服务器,以及是否获取新闻服务器上的新闻内容。在新闻内容监控模块监测到浏览器获取新闻服务器上的新闻内容时,则新闻内容监控模块记录该新闻内容的属性数据。
可选的,预先确定的分析模型为逻辑回归模型,所述逻辑回归模型的训练过程如下:
E、获取预设数量的新闻样本数据,并采用人工方式对该用户阅读的新闻进行分类,以获得各个分类对应的新闻样本数据集合,或者,通过预设的关键词搜集新闻,以获得各个预设关键词对应的新闻样本数据集合;
可选的,预设数量可以设置的足够大,以确保分析的准确性。例如,预设数量可以设置为50万份。预设的关键词例如可以为美元加息、人民币汇率、房价调控等,具体可以根据实际需要进行设置。
F、从各个所述新闻样本数据集合中提取出第一预设比例的新闻样本数据作为训练集,并将各个所述新闻样本数据集合中剩余的新闻样本数据作为测试集;
第一预设比例可以根据实际需要进行设置,例如可以设置为70%。因此,则将剩余的30%的新闻样本数据作为测试集。
G、对训练集和测试集中的各个新闻样本进行分词处理;
例如,对各个新闻样本的新闻文本,由一个词库作为基础,以词频为标准,获得最有可能的一个分词方案,如可以将“南京市长江大桥”,划分为:“南京市/长江/大桥”。
H、对分词处理后的新闻文本特征提取,以提取出各个新闻文本中各个分词按照在文本中的预设类型特征,并将各个新闻文本对应的预设类型特征转化成所述逻辑回归模型的训练参数;
预设类型特征例如可以为词频、词序等特征。训练参数例如可以为数字或者数列,常见的训练参数转化方法包括TF-IDF(词频-逆文档频率)方法,即将每个词赋予一个维度,每篇文章在这个维度上的值是“该词出现在本文中的概率”/“出现该词的文章频率”。
I、将训练集中的各个新闻文本对应的训练参数输入到所述逻辑回归模型中进行训练,以生成待用于进行新闻内容的属性数据分析的逻辑回归模型;
J、将测试集中的各个新闻文本对应的训练参数输入到生成的逻辑回归模型中以进行测试,若测试的准确率大于等于预设阈值,则结束训练,或者,若测试的准确率小于预设阈值,则增加新闻样本数据,并重新执行步骤F、G、H、I和J,直到测试的准确率大于等于预设阈值。
预设阈值的大小可以根据实际需要进行设置,例如可以为95%。
本实施例提供的预先确定的分析模型,能够准确的进行新闻内容的属性数据分析,准确性和可靠性较高。
步骤S20,所述控制服务器根据预先确定的分析规则对接收的该用户对应的新闻内容的属性数据进行分析,以分析出该用户对应的阅读标签,所述阅读标签包括偏好的新闻类别;
例如,阅读标签可以为体育、娱乐、房产等。
在本实施例中,预先确定的分析规则可以包括:
若第一预设时间内,该用户针对一个新闻类别下的新闻内容的阅读次数大于第一预设阈值,则确定该新闻类别为偏好的新闻类别;
若第二预设时间内,该用户针对一个新闻类别下的新闻内容的阅读次数
大于第二预设阈值,则确定该新闻类别为偏好的新闻类别,所述第二预设时间大于所述第一预设时间。
第一预设时间例如可以为最近7天内。新闻类别例如可以为体育类新闻。第一预设阈值例如可以为10次。即,在用户在最近7天内若阅读体育类新闻的次数大于10次,则认为体育新闻类别为该用户偏好的新闻类别。
第二预设时间例如可以为最近90天内,新闻类别例如可以为体育类新闻,第二预设阈值例如可以为30次。即,在用户在最近90天内阅读体育类新闻的次数大于30次,则认为体育新闻类别为该用户偏好的新闻类别。
进一步的,基于上述,所述阅读标签还可以包括偏好的阅读时间段,所述预先确定的分析规则还可以包括:
若第三预设时间内,该用户在一个时间段,针对一个新闻类别下的新闻内容的阅读次数大于第三预设阈值,则确定该时间段是该用户针对该新闻类别的偏好的阅读时间段,所述第三预设时间与所述第一预设时间相同或者不同;第三预设时间例如可以为最近6天,时间段例如可以为8:30—9:30,新闻类别例如可以为体育新闻类别,第三预设阈值例如可以为4次。即,若用户在最近6天内的8:30—9:30的时间段内,累计阅读体育新闻类别的次数大于4次,则认为时间段8:30—9:30为该用户针对体育新闻类别的偏好的阅读时间段。
若第四预设时间内,该用户在一个时间段,针对所有新闻类别下的新闻内容的阅读次数大于第四预设阈值,则确定该时间段是该用户针对所有新闻类别的偏好的阅读时间段,所述第四预设时间与所述第一预设时间相同或者不同;第四预设时间例如可以为最近5天,时间段例如可以为8:30—9:30,第四预设阈值例如可以为8次。即,若用户在最近5天内的8:30—9:30的时间段内,累计阅读所有新闻类别的次数大于8次,则认为时间段8:30—9:30为该用户针对所有新闻类别的偏好的阅读时间段。
若第五预设时间内,该用户在一个时间段,针对一个新闻类别下的新闻内容的阅读次数大于第五预设阈值,则确定该时间段是该用户针对该新闻类别的偏好的阅读时间段,所述第五预设时间与所述第二预设时间相同或者不同;第五预设时间例如可以为最近80天,时间段例如可以为8:30—9:30,新闻类别例如可以为体育新闻类别,第五预设阈值例如可以为14次。即,若用户在最近80天内的8:30—9:30的时间段内,累计阅读体育新闻类别的次数大于14次,则认为时间段8:30—9:30为该用户针对体育新闻类别的偏好的阅读时间段。
若第六预设时间内,该用户在一个时间段,针对所有新闻类别下的新闻内容的阅读次数大于第六预设阈值,则确定该时间段是该用户针对所有新闻类别的偏好的阅读时间段,所述第六预设时间与所述第二预设时间相同或者不同。第六预设时间例如可以为最近85天,时间段例如可以为8:30—9:30,第六预设阈值例如可以为28次。即,若用户在最近85天内的8:30—9:30的时间段内,累计阅读所有新闻类别的次数大于28次,则认为时间段8:30—9:30
为该用户针对所有新闻类别的偏好的阅读时间段。
步骤S30,所述控制服务器实时或者定时从至少一个新闻服务器获取与该用户对应的阅读标签关联的新闻内容;
步骤S40,所述控制服务器将获取的新闻内容推送给该用户的所述客户端。
例如,若该用户对应的阅读标签表明偏好的新闻类别为体育,则所述控制服务器实时或者定时从至少一个新闻服务器获取属于体育类别且还未被推送给该用户的新闻内容,并将获取的新闻内容推送至客户端。
本发明提供的新闻内容的推送方法,通过在用户通过客户端的浏览器系统访问新闻服务器阅读新闻内容时,客户端的新闻内容监控模块按照预先确定的分析模型分析并记录该用户阅读的新闻内容的属性数据,并实时或者定时将记录的新闻内容的属性数据发送给控制服务器,然后控制服务器根据预先确定的分析规则对接收的该用户对应的新闻内容的属性数据进行分析,以分析出该用户对应的阅读标签,所述阅读标签包括偏好的新闻类别,然后控制服务器实时或者定时从至少一个新闻服务器获取与该用户对应的阅读标签关联的新闻内容,并将获取的新闻内容推送给该用户的所述客户端,从而使得控制服务器能够明确新闻客户群,并根据用户的阅读习惯有针对性的推送新闻内容,避免了新闻内容的重复,避免了新闻内容版权纠纷的现象产生。
进一步的,基于本发明新闻内容的推送方法的第一实施例,本发明还提出了新闻内容的推送方法的第二实施例,参照图3,图3为本发明新闻内容的推送方法第二实施例的流程示意图,在本实施例中,与第一实施例不同的是,所述步骤S40替换为:
步骤S401,所述控制服务器与多个社交服务器通信连接,确定出与该用户属于同一社交群组的其他用户;
步骤S402,所述控制服务器将获取的新闻内容推送给该用户的所述客户端,及/或,推送给确定出的其他用户的客户端。
在本实施例中,社交服务器例如可以为微信服务器、QQ服务器、微博服务器等。若该用户的微信群中有一个足球群,则该足球群中的其他用户均可以称之为与该用户属于同一社交群组的其他用户。若该用户偏好的新闻类别为体育新闻类别,则该足球群中的其他用户很可能偏好的新闻类别也为体育新闻类别。因此,可以将服务器获取的与体育阅读标签关联的新闻内容推送给该用户的客户端,并同时推送给确定出的足球群中的其他用户的客户端。
本实施例通过确定用户的社交群组的其他用户,并根据该用户的阅读习惯向其社交群组的其他用户推送新闻内容,从而进一步扩大了新闻客户群,更有效地实现了根据用户的阅读习惯有针对性的推送新闻内容。
进一步的,基于本发明新闻内容的推送方法的第一或第二实施例,本发明还提出了新闻内容的推送方法的第三实施例,参照图4,图4为本发明新闻内容的推送方法第三实施例的流程示意图,在本实施例中,与第一或第二实施例不同的是,于所述步骤S20之后,该方法包括:
步骤S50,所述控制服务器实时或者定时按照预先确定的阅读标签和业务类型的关联关系,确定出与该用户对应的阅读标签关联的业务,并将确定出的业务推送给该用户的所述客户端。
在本实施例中,例如,理财类标签可以对应设置金融产品业务,若用户的阅读标签为理财类标签,则该用户的理财类标签相关联的业务为金融产品业务,可以将该金融产品业务推送给用户的客户端。
本实施例通过根据用户的阅读习惯向用户推送关联的业务,从而进一步扩大了推送数据的范围,并给用户带来了便利,也给商家带来了经济效益。
进一步的,基于本发明新闻内容的推送方法的第一至第三任一实施例,本发明还提出了新闻内容的推送方法的第四实施例,参照图5,图5为本发明新闻内容的推送方法第四实施例中新闻内容推送步骤的细化流程示意图,在本实施例中,与第一至第三实施例不同的是,所述步骤S40包括:
步骤S403,所述控制服务器根据预先确定的解析规则,对获取的新闻内容进行解析,以解析出各个原始新闻内容,及与各个原始新闻内容关联的延伸新闻内容;
在本实施例中,可选的,所述预先确定的解析规则包括:
若多个新闻内容对应同一个标题信息,则将发布时间最早的新闻内容作为原始新闻内容,并将各个所述其他新闻内容作为与该新闻内容关联的延伸新闻内容;
若一个新闻内容的标题信息出现在至少一个其他新闻内容的预先确定的位置,所述预先确定的位置的内容格式是第一预设格式,且该新闻内容的标题信息与各个所述其他新闻内容的标题信息不一致,则确定该新闻内容为原始新闻内容,而将各个所述其他新闻内容作为与该新闻内容关联的延伸新闻内容;在本实施例中,预先确定的位置例如可以为第一段位置。第一预设格式例如可以为“原标题:XXX”。
在各个延伸新闻内容中,确定出预设位置的第二预设格式的内容,并将确定出的第二预设格式的内容作为对应的延伸性内容。预设位置例如可以为正文的第一段及第二段。第二预设格式例如可以为包括“XXX援引XXX报道XXX”、“据XX报道”、“XXX E地点F月G日电(例如,中新网重庆4月21日电)”等字段的格式。
延伸新闻内容例如可以为对原始新闻内容进行论述的相关评论新闻内容。
步骤S404,所述控制服务器对各个原始新闻内容关联的延伸新闻内容按照发布时间的先后顺序进行排序;
步骤S405,所述控制服务器在各个原始新闻内容页面的预设位置,将关联的所有延伸新闻内容的标题及/或链接网址按照对应的排序顺序插入;预设位置例如可以设置为页面最下方的空白位置。
步骤S406,所述控制服务器将各个带有关联的延伸新闻内容的标题及/或链接网址的原始新闻内容发送给该用户的所述客户端。
本实施例通过进一步根据用户的阅读习惯确定原始新闻内容以及与原始新闻内容关联的延伸新闻内容,从而进一步扩大了推送数据的范围,使得推送的新闻内容更加丰富,更加符合用户的阅读习惯。
进一步的,基于本发明新闻内容的推送方法的第一至第三任一实施例,本发明还提出了新闻内容的推送方法的第五实施例,参照图6,图6为本发明新闻内容的推送方法第五实施例中新闻内容推送步骤的细化流程示意图,在本实施例中,与第一至第三实施例不同的是,所述步骤S40包括:
步骤S407,所述控制服务器根据预先确定的解析规则,对获取的新闻内容进行解析,以解析出各个原始新闻内容,及与各个原始新闻内容关联的延伸新闻内容,及各个延伸新闻内容中的延伸性内容;
在本实施例中,可选的,所述预先确定的解析规则包括:
若多个新闻内容对应同一个标题信息,则将发布时间最早的新闻内容作为原始新闻内容,并将各个所述其他新闻内容作为与该新闻内容关联的延伸新闻内容;
若一个新闻内容的标题信息出现在至少一个其他新闻内容的预先确定的位置,所述预先确定的位置的内容格式是第一预设格式,且该新闻内容的标题信息与各个所述其他新闻内容的标题信息不一致,则确定该新闻内容为原始新闻内容,而将各个所述其他新闻内容作为与该新闻内容关联的延伸新闻内容;在本实施例中,预先确定的位置例如可以为第一段位置。第一预设格式例如可以为“原标题:XXX”。
在各个延伸新闻内容中,确定出预设位置的第二预设格式的内容,并将确定出的第二预设格式的内容作为对应的延伸性内容。预设位置例如可以为正文的第一段及第二段。第二预设格式例如可以为包括“XXX援引XXX报道XXX”、“据XX报道”、“XXX E地点F月G日电(例如,中新网重庆4月21日电)”等字段的格式。
延伸新闻内容例如可以为对原始新闻内容进行论述的相关评论新闻内容。延伸性内容可以为与相关频率新闻内容关联的内容。
步骤S408,所述控制服务器对各个原始新闻内容关联的延伸新闻内容按照发布时间的先后顺序进行排序;
步骤S409,所述控制服务器在各个原始新闻内容页面的预设位置,将关联的所有延伸新闻内容的延伸性内容按照对应的排序顺序插入;预设位置例如可以设置为页面最下方的空白位置。
步骤S410,所述控制服务器将各个带有关联的延伸新闻内容的延伸性内容的原始新闻内容发送给该用户的所述客户端。
本实施例通过进一步根据用户的阅读习惯确定原始新闻内容以及与原始新闻内容关联的延伸新闻内容的延伸性内容,从而进一步扩大了推送数据的范围,使得推送的新闻内容更加丰富,更加符合用户的阅读习惯。
本发明进一步提供一种新闻内容的推送系统。参照图7,图7为本发明新闻内容的推送系统第一实施例的功能模块示意图,本发明提供的新闻内容的
推送系统包括客户端100和控制服务器200,所述客户端100包括新闻内容监控模块110,所述控制服务器200包括分析模块210、获取模块220和推送模块230;
所述新闻内容监控模块110用于在用户通过客户端的浏览器系统访问新闻服务器阅读新闻内容时,按照预先确定的分析模型分析并记录该用户阅读的新闻内容的属性数据,并实时或者定时将记录的新闻内容的属性数据发送给控制服务器;
在本实施例中,客户端可以为手机、平板电脑、笔记本以及所有可以联网的终端等。客户端的新闻内容监控模块可以实时或定时监测浏览器是否处于运行状态以及在浏览器处于运行状态时,浏览器是否在访问新闻服务器,以及是否获取新闻服务器上的新闻内容。在新闻内容监控模块监测到浏览器获取新闻服务器上的新闻内容时,则新闻内容监控模块记录该新闻内容的属性数据。
可选的,所述预先确定的分析模型为逻辑回归模型,参照图8,图8为本发明新闻内容的推送系统中新闻内容监控模块的细化功能模块示意图,所述新闻内容监控模块110包括:
新闻样本获取单元111,用于获取预设数量的新闻样本数据,并采用人工方式对该用户阅读的新闻进行分类,以获得各个分类对应的新闻样本数据集合,或者,通过预设的关键词搜集新闻,以获得各个预设关键词对应的新闻样本数据集合;
可选的,预设数量可以设置的足够大,以确保分析的准确性。例如,预设数量可以设置为50万份。预设的关键词例如可以为美元加息、人民币汇率、房价调控等,具体可以根据实际需要进行设置。
训练集提取单元112,用于从各个所述新闻样本数据集合中提取出第一预设比例的新闻样本数据作为训练集,并将各个所述新闻样本数据集合中剩余的新闻样本数据作为测试集;
第一预设比例可以根据实际需要进行设置,例如可以设置为70%。因此,则将剩余的30%的新闻样本数据作为测试集。
分词处理单元113,用于对训练集和测试集中的各个新闻样本进行分词处理;
例如,对各个新闻样本的新闻文本,由一个词库作为基础,以词频为标准,获得最有可能的一个分词方案,如可以将“南京市长江大桥”,划分为:“南京市/长江/大桥”。
训练参数生成单元114,用于对分词处理后的新闻文本特征提取,以提取出各个新闻文本中各个分词按照在文本中的预设类型特征,并将各个新闻文本对应的预设类型特征转化成所述逻辑回归模型的训练参数;
预设类型特征例如可以为词频、词序等特征。训练参数例如可以为数字或者数列,常见的训练参数转化方法包括TF-IDF(词频-逆文档频率)方法,即将每个词赋予一个维度,每篇文章在这个维度上的值是“该词出现在本文
中的概率”/“出现该词的文章频率”。
回归模型生成单元115,用于将训练集中的各个新闻文本对应的训练参数输入到所述逻辑回归模型中进行训练,以生成待用于进行新闻内容的属性数据分析的逻辑回归模型;
测试单元116,用于将测试集中的各个新闻文本对应的训练参数输入到生成的逻辑回归模型中以进行测试,若测试的准确率大于等于预设阈值,则结束训练,或者,若测试的准确率小于预设阈值,则增加新闻样本数据,并返回调用所述新闻样本获取单元111、训练集提取单元112、分词处理单元113、训练参数生成单元114以及回归模型生成单元115,直到测试的准确率大于等于预设阈值。
预设阈值的大小可以根据实际需要进行设置,例如可以为95%。
本实施例提供的预先确定的分析模型,能够准确的进行新闻内容的属性数据分析,准确性和可靠性较高。
所述分析模块210用于根据预先确定的分析规则对接收的该用户对应的新闻内容的属性数据进行分析,以分析出该用户对应的阅读标签,所述阅读标签包括偏好的新闻类别;
例如,阅读标签可以为体育、娱乐、房产等。
在本实施例中,预先确定的分析规则可以包括:
若第一预设时间内,该用户针对一个新闻类别下的新闻内容的阅读次数大于第一预设阈值,则确定该新闻类别为偏好的新闻类别;
若第二预设时间内,该用户针对一个新闻类别下的新闻内容的阅读次数大于第二预设阈值,则确定该新闻类别为偏好的新闻类别,所述第二预设时间大于所述第一预设时间。
第一预设时间例如可以为最近7天内。新闻类别例如可以为体育类新闻。第一预设阈值例如可以为10次。即,在用户在最近7天内若阅读体育类新闻的次数大于10次,则认为体育新闻类别为该用户偏好的新闻类别。
第二预设时间例如可以为最近90天内,新闻类别例如可以为体育类新闻,第二预设阈值例如可以为30次。即,在用户在最近90天内阅读体育类新闻的次数大于30次,则认为体育新闻类别为该用户偏好的新闻类别。
进一步的,基于上述,所述阅读标签还可以包括偏好的阅读时间段,所述预先确定的分析规则还可以包括:
若第三预设时间内,该用户在一个时间段,针对一个新闻类别下的新闻内容的阅读次数大于第三预设阈值,则确定该时间段是该用户针对该新闻类别的偏好的阅读时间段,所述第三预设时间与所述第一预设时间相同或者不同;第三预设时间例如可以为最近6天,时间段例如可以为8:30—9:30,新闻类别例如可以为体育新闻类别,第三预设阈值例如可以为4次。即,若用户在最近6天内的8:30—9:30的时间段内,累计阅读体育新闻类别的次数大于4次,则认为时间段8:30—9:30为该用户针对体育新闻类别的偏好的阅读时间段。
若第四预设时间内,该用户在一个时间段,针对所有新闻类别下的新闻内容的阅读次数大于第四预设阈值,则确定该时间段是该用户针对所有新闻类别的偏好的阅读时间段,所述第四预设时间与所述第一预设时间相同或者不同;第四预设时间例如可以为最近5天,时间段例如可以为8:30—9:30,第四预设阈值例如可以为8次。即,若用户在最近5天内的8:30—9:30的时间段内,累计阅读所有新闻类别的次数大于8次,则认为时间段8:30—9:30为该用户针对所有新闻类别的偏好的阅读时间段。
若第五预设时间内,该用户在一个时间段,针对一个新闻类别下的新闻内容的阅读次数大于第五预设阈值,则确定该时间段是该用户针对该新闻类别的偏好的阅读时间段,所述第五预设时间与所述第二预设时间相同或者不同;第五预设时间例如可以为最近80天,时间段例如可以为8:30—9:30,新闻类别例如可以为体育新闻类别,第五预设阈值例如可以为14次。即,若用户在最近80天内的8:30—9:30的时间段内,累计阅读体育新闻类别的次数大于14次,则认为时间段8:30—9:30为该用户针对体育新闻类别的偏好的阅读时间段。
若第六预设时间内,该用户在一个时间段,针对所有新闻类别下的新闻内容的阅读次数大于第六预设阈值,则确定该时间段是该用户针对所有新闻类别的偏好的阅读时间段,所述第六预设时间与所述第二预设时间相同或者不同。第六预设时间例如可以为最近85天,时间段例如可以为8:30—9:30,第六预设阈值例如可以为28次。即,若用户在最近85天内的8:30—9:30的时间段内,累计阅读所有新闻类别的次数大于28次,则认为时间段8:30—9:30为该用户针对所有新闻类别的偏好的阅读时间段。
所述获取模块220用于实时或者定时从至少一个新闻服务器获取与该用户对应的阅读标签关联的新闻内容;
所述推送模块230用于将获取的新闻内容推送给该用户的所述客户端。
例如,若该用户对应的阅读标签表明偏好的新闻类别为体育,则所述控制服务器实时或者定时从至少一个新闻服务器获取属于体育类别且还未被推送给该用户的新闻内容,并将获取的新闻内容推送至客户端。
本发明提供的新闻内容的推送系统,通过在用户通过客户端的浏览器系统访问新闻服务器阅读新闻内容时,客户端的新闻内容监控模块按照预先确定的分析模型分析并记录该用户阅读的新闻内容的属性数据,并实时或者定时将记录的新闻内容的属性数据发送给控制服务器,然后控制服务器根据预先确定的分析规则对接收的该用户对应的新闻内容的属性数据进行分析,以分析出该用户对应的阅读标签,所述阅读标签包括偏好的新闻类别,然后控制服务器实时或者定时从至少一个新闻服务器获取与该用户对应的阅读标签关联的新闻内容,并将获取的新闻内容推送给该用户的所述客户端,从而使得控制服务器能够明确新闻客户群,并根据用户的阅读习惯有针对性的推送新闻内容,避免了新闻内容的重复,避免了新闻内容版权纠纷的现象产生。
进一步的,基于本发明新闻内容的推送系统的第一实施例,本发明还提
出了新闻内容的推送系统的第二实施例,参照图9,图9为本发明新闻内容的推送系统第二实施例中推送模块的细化功能模块示意图,在本实施例中,与第一实施例不同的是,所述推送模块230包括:
确定单元2311,用于与多个社交服务器通信连接,确定出与该用户属于同一社交群组的其他用户;
第一推送单元2312,用于将获取的新闻内容推送给该用户的所述客户端,及/或,推送给确定出的其他用户的客户端。
在本实施例中,社交服务器例如可以为微信服务器、QQ服务器、微博服务器等。若该用户的微信群中有一个足球群,则该足球群中的其他用户均可以称之为与该用户属于同一社交群组的其他用户。若该用户偏好的新闻类别为体育新闻类别,则该足球群中的其他用户很可能偏好的新闻类别也为体育新闻类别。因此,可以将服务器获取的与体育阅读标签关联的新闻内容推送给该用户的客户端,并同时推送给确定出的足球群中的其他用户的客户端。
本实施例通过确定用户的社交群组的其他用户,并根据该用户的阅读习惯向其社交群组的其他用户推送新闻内容,从而进一步扩大了新闻客户群,更有效地实现了根据用户的阅读习惯有针对性的推送新闻内容。
进一步的,基于本发明新闻内容的推送系统的第一或第二实施例,本发明还提出了新闻内容的推送系统的第三实施例,在本实施例中,与第一或第二实施例不同的是,所述推送模块230还用于实时或者定时按照预先确定的阅读标签和业务类型的关联关系,确定出与该用户对应的阅读标签关联的业务,并将确定出的业务推送给该用户的所述客户端。
在本实施例中,例如,理财类标签可以对应设置金融产品业务,若用户的阅读标签为理财类标签,则该用户的理财类标签相关联的业务为金融产品业务,可以将该金融产品业务推送给用户的客户端。
本实施例通过根据用户的阅读习惯向用户推送关联的业务,从而进一步扩大了推送数据的范围,并给用户带来了便利,也给商家带来了经济效益。
进一步的,基于本发明新闻内容的推送系统的第一至第三任一实施例,本发明还提出了新闻内容的推送系统的第四实施例,参照图10,图10为本发明新闻内容的推送系统第四实施例中推送模块的细化功能模块示意图,在本实施例中,与第一至第三实施例不同的是,所述推送模块230包括:
第一解析单元232,用于根据预先确定的解析规则,对获取的新闻内容进行解析,以解析出各个原始新闻内容,及与各个原始新闻内容关联的延伸新闻内容;
在本实施例中,可选的,所述预先确定的解析规则包括:
若多个新闻内容对应同一个标题信息,则将发布时间最早的新闻内容作为原始新闻内容,并将各个所述其他新闻内容作为与该新闻内容关联的延伸新闻内容;
若一个新闻内容的标题信息出现在至少一个其他新闻内容的预先确定的
位置,所述预先确定的位置的内容格式是第一预设格式,且该新闻内容的标题信息与各个所述其他新闻内容的标题信息不一致,则确定该新闻内容为原始新闻内容,而将各个所述其他新闻内容作为与该新闻内容关联的延伸新闻内容;在本实施例中,预先确定的位置例如可以为第一段位置。第一预设格式例如可以为“原标题:XXX”。
在各个延伸新闻内容中,确定出预设位置的第二预设格式的内容,并将确定出的第二预设格式的内容作为对应的延伸性内容。预设位置例如可以为正文的第一段及第二段。第二预设格式例如可以为包括“XXX援引XXX报道XXX”、“据XX报道”、“XXX E地点F月G日电(例如,中新网重庆4月21日电)”等字段的格式。
延伸新闻内容例如可以为对原始新闻内容进行论述的相关评论新闻内容。
第一排序单元233,用于对各个原始新闻内容关联的延伸新闻内容按照发布时间的先后顺序进行排序;
第一插入单元234,用于在各个原始新闻内容页面的预设位置,将关联的所有延伸新闻内容的标题及/或链接网址按照对应的排序顺序插入;预设位置例如可以设置为页面最下方的空白位置。
第二推送单元235,用于将各个带有关联的延伸新闻内容的标题及/或链接网址的原始新闻内容发送给该用户的所述客户端。
本实施例通过进一步根据用户的阅读习惯确定原始新闻内容以及与原始新闻内容关联的延伸新闻内容,从而进一步扩大了推送数据的范围,使得推送的新闻内容更加丰富,更加符合用户的阅读习惯。
进一步的,基于本发明新闻内容的推送系统的第一至第三任一实施例,本发明还提出了新闻内容的推送系统的第五实施例,参照图11,图11为本发明新闻内容的推送系统第五实施例中推送模块的细化功能模块示意图,在本实施例中,与第一至第三实施例不同的是,所述推送模块230包括:
第二解析单元236,用于根据预先确定的解析规则,对获取的新闻内容进行解析,以解析出各个原始新闻内容,及与各个原始新闻内容关联的延伸新闻内容,及各个延伸新闻内容中的延伸性内容;
在本实施例中,可选的,所述预先确定的解析规则包括:
若多个新闻内容对应同一个标题信息,则将发布时间最早的新闻内容作为原始新闻内容,并将各个所述其他新闻内容作为与该新闻内容关联的延伸新闻内容;
若一个新闻内容的标题信息出现在至少一个其他新闻内容的预先确定的位置,所述预先确定的位置的内容格式是第一预设格式,且该新闻内容的标题信息与各个所述其他新闻内容的标题信息不一致,则确定该新闻内容为原始新闻内容,而将各个所述其他新闻内容作为与该新闻内容关联的延伸新闻内容;在本实施例中,预先确定的位置例如可以为第一段位置。第一预设格式例如可以为“原标题:XXX”。
在各个延伸新闻内容中,确定出预设位置的第二预设格式的内容,并将确定出的第二预设格式的内容作为对应的延伸性内容。预设位置例如可以为正文的第一段及第二段。第二预设格式例如可以为包括“XXX援引XXX报道XXX”、“据XX报道”、“XXX E地点F月G日电(例如,中新网重庆4月21日电)”等字段的格式。
延伸新闻内容例如可以为对原始新闻内容进行论述的相关评论新闻内容。延伸性内容可以为与相关频率新闻内容关联的内容。
第二排序单元237,用于对各个原始新闻内容关联的延伸新闻内容按照发布时间的先后顺序进行排序;
第二插入单元238,用于在各个原始新闻内容页面的预设位置,将关联的所有延伸新闻内容的延伸性内容按照对应的排序顺序插入;预设位置例如可以设置为页面最下方的空白位置。
第三推送单元239,用于将各个带有关联的延伸新闻内容的延伸性内容的原始新闻内容发送给该用户的所述客户端。
本实施例通过进一步根据用户的阅读习惯确定原始新闻内容以及与原始新闻内容关联的延伸新闻内容的延伸性内容,从而进一步扩大了推送数据的范围,使得推送的新闻内容更加丰富,更加符合用户的阅读习惯。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
上述本发明实施例序号仅仅为了描述,不代表实施例的优劣。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本发明各个实施例所述的方法。
以上仅为本发明的优选实施例,并非因此限制本发明的专利范围,凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本发明的专利保护范围内。
Claims (20)
- 一种新闻内容的推送方法,其特征在于,所述新闻内容的推送方法包括:A、在用户通过客户端的浏览器系统访问新闻服务器阅读新闻内容时,所述客户端的新闻内容监控模块按照预先确定的分析模型分析并记录该用户阅读的新闻内容的属性数据,并实时或者定时将记录的新闻内容的属性数据发送给控制服务器;B、所述控制服务器根据预先确定的分析规则对接收的该用户对应的新闻内容的属性数据进行分析,以分析出该用户对应的阅读标签,所述阅读标签包括偏好的新闻类别;C、所述控制服务器实时或者定时从至少一个新闻服务器获取与该用户对应的阅读标签关联的新闻内容;D、所述控制服务器将获取的新闻内容推送给该用户的所述客户端。
- 如权利要求1所述的新闻内容的推送方法,其特征在于,所述步骤D替换为:所述控制服务器与多个社交服务器通信连接,确定出与该用户属于同一社交群组的其他用户;所述控制服务器将获取的新闻内容推送给该用户的所述客户端,及/或,推送给确定出的其他用户的客户端。
- 如权利要求1所述的新闻内容的推送方法,其特征在于,于所述步骤B之后,该方法还包括:所述控制服务器实时或者定时按照预先确定的阅读标签和业务类型的关联关系,确定出与该用户对应的阅读标签关联的业务,并将确定出的业务推送给该用户的所述客户端。
- 如权利要求1至3任一项所述的新闻内容的推送方法,其特征在于,所述预先确定的分析模型为逻辑回归模型,所述逻辑回归模型的训练过程如下:E、获取预设数量的新闻样本数据,并采用人工方式对该用户阅读的新闻进行分类,以获得各个分类对应的新闻样本数据集合,或者,通过预设的关键词搜集新闻,以获得各个预设关键词对应的新闻样本数据集合;F、从各个所述新闻样本数据集合中提取出第一预设比例的新闻样本数据作为训练集,并将各个所述新闻样本数据集合中剩余的新闻样本数据作为测试集;G、对训练集和测试集中的各个新闻样本进行分词处理;H、对分词处理后的新闻文本特征提取,以提取出各个新闻文本中各个分词按照在文本中的预设类型特征,并将各个新闻文本对应的预设类型特征转化成所述逻辑回归模型的训练参数;I、将训练集中的各个新闻文本对应的训练参数输入到所述逻辑回归模型 中进行训练,以生成待用于进行新闻内容的属性数据分析的逻辑回归模型;J、将测试集中的各个新闻文本对应的训练参数输入到生成的逻辑回归模型中以进行测试,若测试的准确率大于等于预设阈值,则结束训练,或者,若测试的准确率小于预设阈值,则增加新闻样本数据,并重新执行步骤F、G、H、I和J,直到测试的准确率大于等于预设阈值。
- 如权利要求1至3任一项所述的新闻内容的推送方法,其特征在于,所述预先确定的分析规则包括:若第一预设时间内,该用户针对一个新闻类别下的新闻内容的阅读次数大于第一预设阈值,则确定该新闻类别为偏好的新闻类别;若第二预设时间内,该用户针对一个新闻类别下的新闻内容的阅读次数大于第二预设阈值,则确定该新闻类别为偏好的新闻类别,所述第二预设时间大于所述第一预设时间。
- 如权利要求5所述的新闻内容的推送方法,其特征在于,所述阅读标签还包括偏好的阅读时间段,所述预先确定的分析规则还包括:若第三预设时间内,该用户在一个时间段,针对一个新闻类别下的新闻内容的阅读次数大于第三预设阈值,则确定该时间段是该用户针对该新闻类别的偏好的阅读时间段,所述第三预设时间与所述第一预设时间相同或者不同;若第四预设时间内,该用户在一个时间段,针对所有新闻类别下的新闻内容的阅读次数大于第四预设阈值,则确定该时间段是该用户针对所有新闻类别的偏好的阅读时间段,所述第四预设时间与所述第一预设时间相同或者不同;若第五预设时间内,该用户在一个时间段,针对一个新闻类别下的新闻内容的阅读次数大于第五预设阈值,则确定该时间段是该用户针对该新闻类别的偏好的阅读时间段,所述第五预设时间与所述第二预设时间相同或者不同;若第六预设时间内,该用户在一个时间段,针对所有新闻类别下的新闻内容的阅读次数大于第六预设阈值,则确定该时间段是该用户针对所有新闻类别的偏好的阅读时间段,所述第六预设时间与所述第二预设时间相同或者不同。
- 如权利要求1所述的新闻内容的推送方法,其特征在于,所述步骤D包括:所述控制服务器根据预先确定的解析规则,对获取的新闻内容进行解析,以解析出各个原始新闻内容,及与各个原始新闻内容关联的延伸新闻内容;所述控制服务器对各个原始新闻内容关联的延伸新闻内容按照发布时间的先后顺序进行排序;所述控制服务器在各个原始新闻内容页面的预设位置,将关联的所有延伸新闻内容的标题及/或链接网址按照对应的排序顺序插入;所述控制服务器将各个带有关联的延伸新闻内容的标题及/或链接网址的 原始新闻内容发送给该用户的所述客户端。
- 如权利要求1所述的新闻内容的推送方法,其特征在于,所述步骤D包括:所述控制服务器根据预先确定的解析规则,对获取的新闻内容进行解析,以解析出各个原始新闻内容,及与各个原始新闻内容关联的延伸新闻内容,及各个延伸新闻内容中的延伸性内容;所述控制服务器对各个原始新闻内容关联的延伸新闻内容按照发布时间的先后顺序进行排序;所述控制服务器在各个原始新闻内容页面的预设位置,将关联的所有延伸新闻内容的延伸性内容按照对应的排序顺序插入;所述控制服务器将各个带有关联的延伸新闻内容的延伸性内容的原始新闻内容发送给该用户的所述客户端。
- 如权利要求7或8所述的新闻内容的推送方法,其特征在于,所述预先确定的解析规则包括:若多个新闻内容对应同一个标题信息,则将发布时间最早的新闻内容作为原始新闻内容,并将各个所述其他新闻内容作为与该新闻内容关联的延伸新闻内容;若一个新闻内容的标题信息出现在至少一个其他新闻内容的预先确定的位置,所述预先确定的位置的内容格式是第一预设格式,且该新闻内容的标题信息与各个所述其他新闻内容的标题信息不一致,则确定该新闻内容为原始新闻内容,而将各个所述其他新闻内容作为与该新闻内容关联的延伸新闻内容;在各个延伸新闻内容中,确定出预设位置的第二预设格式的内容,并将确定出的第二预设格式的内容作为对应的延伸性内容。
- 一种电子装置,包括处理设备、存储设备,该存储设备存储有新闻内容的推送系统,该新闻内容的推送系统包括至少一个计算机可读指令,该至少一个计算机可读指令可被所述处理设备执行,以实现以下操作:A、在用户通过客户端的浏览器系统访问新闻服务器阅读新闻内容时,按照预先确定的分析模型分析并记录该用户阅读的新闻内容的属性数据;B、根据预先确定的分析规则对该用户对应的新闻内容的属性数据进行分析,以分析出该用户对应的阅读标签,所述阅读标签包括偏好的新闻类别;C、实时或者定时从至少一个新闻服务器获取与该用户对应的阅读标签关联的新闻内容;D、将获取的新闻内容推送给该用户的所述客户端。
- 如权利要求10所述的电子装置,其特征在于,所述至少一个计算机可读指令可被所述处理设备执行,实现所述操作D的步骤替换为:与多个社交服务器通信连接,确定出与该用户属于同一社交群组的其他用户;将获取的新闻内容推送给该用户的所述客户端,及/或,推送给确定出的 其他用户的客户端。
- 如权利要求10所述的电子装置,其特征在于,所述至少一个计算机可读指令可被所述处理设备执行,还用于实现以下操作:实时或者定时按照预先确定的阅读标签和业务类型的关联关系,确定出与该用户对应的阅读标签关联的业务,并将确定出的业务推送给该用户的所述客户端。
- 如权利要求10至12任一项所述的电子装置,其特征在于,所述预先确定的分析模型为逻辑回归模型,所述至少一个计算机可读指令可被所述处理设备执行,还用于实现以下操作:E、获取预设数量的新闻样本数据,并采用人工方式对该用户阅读的新闻进行分类,以获得各个分类对应的新闻样本数据集合,或者,通过预设的关键词搜集新闻,以获得各个预设关键词对应的新闻样本数据集合;F、从各个所述新闻样本数据集合中提取出第一预设比例的新闻样本数据作为训练集,并将各个所述新闻样本数据集合中剩余的新闻样本数据作为测试集;G、对训练集和测试集中的各个新闻样本进行分词处理;H、对分词处理后的新闻文本特征提取,以提取出各个新闻文本中各个分词按照在文本中的预设类型特征,并将各个新闻文本对应的预设类型特征转化成所述逻辑回归模型的训练参数;I、将训练集中的各个新闻文本对应的训练参数输入到所述逻辑回归模型中进行训练,以生成待用于进行新闻内容的属性数据分析的逻辑回归模型;J、将测试集中的各个新闻文本对应的训练参数输入到生成的逻辑回归模型中以进行测试,若测试的准确率大于等于预设阈值,则结束训练,或者,若测试的准确率小于预设阈值,则增加新闻样本数据,并重新执行步骤F、G、H、I和J,直到测试的准确率大于等于预设阈值。
- 如权利要求10至12任一项所述的电子装置,其特征在于,所述预先确定的分析规则包括:若第一预设时间内,该用户针对一个新闻类别下的新闻内容的阅读次数大于第一预设阈值,则确定该新闻类别为偏好的新闻类别;若第二预设时间内,该用户针对一个新闻类别下的新闻内容的阅读次数大于第二预设阈值,则确定该新闻类别为偏好的新闻类别,所述第二预设时间大于所述第一预设时间。
- 如权利要求14所述的电子装置,其特征在于,所述阅读标签还包括偏好的阅读时间段,所述预先确定的分析规则还包括:若第三预设时间内,该用户在一个时间段,针对一个新闻类别下的新闻内容的阅读次数大于第三预设阈值,则确定该时间段是该用户针对该新闻类别的偏好的阅读时间段,所述第三预设时间与所述第一预设时间相同或者不同;若第四预设时间内,该用户在一个时间段,针对所有新闻类别下的新闻 内容的阅读次数大于第四预设阈值,则确定该时间段是该用户针对所有新闻类别的偏好的阅读时间段,所述第四预设时间与所述第一预设时间相同或者不同;若第五预设时间内,该用户在一个时间段,针对一个新闻类别下的新闻内容的阅读次数大于第五预设阈值,则确定该时间段是该用户针对该新闻类别的偏好的阅读时间段,所述第五预设时间与所述第二预设时间相同或者不同;若第六预设时间内,该用户在一个时间段,针对所有新闻类别下的新闻内容的阅读次数大于第六预设阈值,则确定该时间段是该用户针对所有新闻类别的偏好的阅读时间段,所述第六预设时间与所述第二预设时间相同或者不同。
- 如权利要求10所述的电子装置,其特征在于,所述至少一个计算机可读指令可被所述处理设备执行,还用于实现以下操作:根据预先确定的解析规则,对获取的新闻内容进行解析,以解析出各个原始新闻内容,及与各个原始新闻内容关联的延伸新闻内容;对各个原始新闻内容关联的延伸新闻内容按照发布时间的先后顺序进行排序;在各个原始新闻内容页面的预设位置,将关联的所有延伸新闻内容的标题及/或链接网址按照对应的排序顺序插入;将各个带有关联的延伸新闻内容的标题及/或链接网址的原始新闻内容发送给该用户的所述客户端。
- 如权利要求10所述的电子装置,其特征在于,所述至少一个计算机可读指令可被所述处理设备执行,还用于实现以下操作:根据预先确定的解析规则,对获取的新闻内容进行解析,以解析出各个原始新闻内容,及与各个原始新闻内容关联的延伸新闻内容,及各个延伸新闻内容中的延伸性内容;对各个原始新闻内容关联的延伸新闻内容按照发布时间的先后顺序进行排序;在各个原始新闻内容页面的预设位置,将关联的所有延伸新闻内容的延伸性内容按照对应的排序顺序插入;将各个带有关联的延伸新闻内容的延伸性内容的原始新闻内容发送给该用户的所述客户端。
- 如权利要求16或17所述的电子装置,其特征在于,所述预先确定的解析规则包括:若多个新闻内容对应同一个标题信息,则将发布时间最早的新闻内容作为原始新闻内容,并将各个所述其他新闻内容作为与该新闻内容关联的延伸新闻内容;若一个新闻内容的标题信息出现在至少一个其他新闻内容的预先确定的位置,所述预先确定的位置的内容格式是第一预设格式,且该新闻内容的标 题信息与各个所述其他新闻内容的标题信息不一致,则确定该新闻内容为原始新闻内容,而将各个所述其他新闻内容作为与该新闻内容关联的延伸新闻内容;在各个延伸新闻内容中,确定出预设位置的第二预设格式的内容,并将确定出的第二预设格式的内容作为对应的延伸性内容。
- 一种计算机可读存储介质,其上存储有至少一个可被处理设备执行以实现以下操作的计算机可读指令:A、在用户通过客户端的浏览器系统访问新闻服务器阅读新闻内容时,按照预先确定的分析模型分析并记录该用户阅读的新闻内容的属性数据;B、根据预先确定的分析规则对该用户对应的新闻内容的属性数据进行分析,以分析出该用户对应的阅读标签,所述阅读标签包括偏好的新闻类别;C、实时或者定时从至少一个新闻服务器获取与该用户对应的阅读标签关联的新闻内容;D、将获取的新闻内容推送给该用户的所述客户端。
- 根据权利要求19所述的介质,其特征在于,其上存储有至少一个可被处理设备执行以实现权利要求1至9任一所述的新闻内容的推送方法的步骤的计算机可读指令。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610704731.3A CN106372113B (zh) | 2016-08-22 | 2016-08-22 | 新闻内容的推送方法及系统 |
CN201610704731.3 | 2016-08-22 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2018036272A1 true WO2018036272A1 (zh) | 2018-03-01 |
Family
ID=57879426
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2017/091258 WO2018036272A1 (zh) | 2016-08-22 | 2017-06-30 | 新闻内容的推送方法、电子装置及计算机可读存储介质 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106372113B (zh) |
WO (1) | WO2018036272A1 (zh) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110955823A (zh) * | 2018-09-26 | 2020-04-03 | 阿里巴巴集团控股有限公司 | 信息推荐方法、装置 |
CN111159566A (zh) * | 2019-12-31 | 2020-05-15 | 中国银行股份有限公司 | 金融市场产品的资讯推送方法及装置 |
CN111310048A (zh) * | 2020-02-25 | 2020-06-19 | 西安电子科技大学 | 基于多层感知机的新闻推荐方法 |
CN111708879A (zh) * | 2020-05-11 | 2020-09-25 | 北京明略软件系统有限公司 | 针对事件的文本聚合方法、装置及计算机可读存储介质 |
CN111753197A (zh) * | 2020-06-18 | 2020-10-09 | 达而观信息科技(上海)有限公司 | 新闻要素的提取方法、装置、计算机设备和存储介质 |
CN114065038A (zh) * | 2021-11-17 | 2022-02-18 | 中国银行股份有限公司 | 基于大数据的头条资讯推荐方法及装置 |
CN114817730A (zh) * | 2022-05-06 | 2022-07-29 | 李春良 | 一种大数据情境下的资讯活动信息推荐系统及方法 |
CN114840756A (zh) * | 2022-05-06 | 2022-08-02 | 东南大学 | 一种基于关键热点信息的媒体生成推荐系统 |
CN115277835A (zh) * | 2022-08-01 | 2022-11-01 | 网易(杭州)网络有限公司 | 信息推送方法、装置、存储介质及电子设备 |
CN116226539A (zh) * | 2023-05-04 | 2023-06-06 | 浙江保融科技股份有限公司 | 一种自动化内容推荐方法及系统 |
Families Citing this family (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106372113B (zh) * | 2016-08-22 | 2018-03-20 | 上海壹账通金融科技有限公司 | 新闻内容的推送方法及系统 |
CN107038256B (zh) | 2017-05-05 | 2018-06-29 | 平安科技(深圳)有限公司 | 基于数据源的业务定制装置、方法及计算机可读存储介质 |
CN107682385A (zh) * | 2017-05-10 | 2018-02-09 | 平安科技(深圳)有限公司 | 基于线上线下一体化服务的方法及设备、存储介质 |
CN107332905A (zh) * | 2017-06-30 | 2017-11-07 | 广州优视网络科技有限公司 | 信息推送方法、装置及服务器 |
CN107635143B (zh) * | 2017-11-06 | 2020-05-05 | 四川长虹电器股份有限公司 | 基于观看行为预测用户在电视上追剧的方法 |
CN107888679A (zh) * | 2017-11-09 | 2018-04-06 | 广东小天才科技有限公司 | 内容推送方法、内容推送装置及终端 |
CN108427761B (zh) * | 2018-03-21 | 2022-01-14 | 腾讯科技(深圳)有限公司 | 一种新闻事件处理的方法、终端、服务器及存储介质 |
CN108874887A (zh) * | 2018-05-10 | 2018-11-23 | 河海大学常州校区 | 一种基于用户新闻浏览的大数据分析统计系统及方法 |
CN108734348A (zh) * | 2018-05-14 | 2018-11-02 | 广东心里程教育集团有限公司 | 一种自动推送在线课程的方法和系统 |
CN108810095A (zh) * | 2018-05-18 | 2018-11-13 | 歌尔科技有限公司 | 一种新闻推送方法和装置 |
CN109067838B (zh) * | 2018-06-29 | 2021-10-19 | 聚好看科技股份有限公司 | 一种数据的推送方法和装置 |
CN109698975A (zh) * | 2019-01-16 | 2019-04-30 | 上海哔哩哔哩科技有限公司 | 新内容实时播放方法、装置及存储介质 |
CN112445967B (zh) * | 2019-08-30 | 2023-09-26 | 腾讯科技(深圳)有限公司 | 信息推送的方法、装置、可读存储介质及信息推送系统 |
CN111683119A (zh) * | 2020-05-19 | 2020-09-18 | 南京数娱天下网络科技有限公司 | 一种基于云平台的新闻阅读系统 |
CN116074378B (zh) * | 2023-04-06 | 2023-06-16 | 西南石油大学 | 一种互联网信息的推送方法和系统 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101079824A (zh) * | 2006-06-15 | 2007-11-28 | 腾讯科技(深圳)有限公司 | 一种用户兴趣偏好向量生成系统和方法 |
CN101866341A (zh) * | 2009-04-17 | 2010-10-20 | 华为技术有限公司 | 一种信息推送方法、装置及系统 |
US20120124073A1 (en) * | 2010-11-16 | 2012-05-17 | John Nicholas Gross | System & Method For Recommending Content Sources |
CN103389975A (zh) * | 2012-05-07 | 2013-11-13 | 腾讯科技(深圳)有限公司 | 一种新闻推荐方法及系统 |
CN104199874A (zh) * | 2014-08-20 | 2014-12-10 | 哈尔滨工程大学 | 一种基于用户浏览行为的网页推荐方法 |
CN105512326A (zh) * | 2015-12-23 | 2016-04-20 | 成都品果科技有限公司 | 一种图片推荐的方法及系统 |
CN106372113A (zh) * | 2016-08-22 | 2017-02-01 | 上海亿账通互联网科技有限公司 | 新闻内容的推送方法及系统 |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8489515B2 (en) * | 2009-05-08 | 2013-07-16 | Comcast Interactive Media, LLC. | Social network based recommendation method and system |
CN101694659B (zh) * | 2009-10-20 | 2012-03-21 | 浙江大学 | 基于多主题追踪的个性化网络新闻推送方法 |
JP2012190417A (ja) * | 2011-03-14 | 2012-10-04 | Nippon Telegr & Teleph Corp <Ntt> | 情報推薦処理装置、方法及びプログラム |
CN103235823A (zh) * | 2013-05-06 | 2013-08-07 | 上海河广信息科技有限公司 | 根据相关网页和当前行为确定用户当前兴趣的方法和系统 |
CN103559265A (zh) * | 2013-11-04 | 2014-02-05 | 北京中搜网络技术股份有限公司 | 一种手机客户端个性化推送方法 |
CN104573054B (zh) * | 2015-01-21 | 2018-06-01 | 杭州朗和科技有限公司 | 一种信息推送方法和设备 |
CN105224699B (zh) * | 2015-11-17 | 2020-01-03 | Tcl集团股份有限公司 | 一种新闻推荐方法及装置 |
-
2016
- 2016-08-22 CN CN201610704731.3A patent/CN106372113B/zh active Active
-
2017
- 2017-06-30 WO PCT/CN2017/091258 patent/WO2018036272A1/zh active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101079824A (zh) * | 2006-06-15 | 2007-11-28 | 腾讯科技(深圳)有限公司 | 一种用户兴趣偏好向量生成系统和方法 |
CN101866341A (zh) * | 2009-04-17 | 2010-10-20 | 华为技术有限公司 | 一种信息推送方法、装置及系统 |
US20120124073A1 (en) * | 2010-11-16 | 2012-05-17 | John Nicholas Gross | System & Method For Recommending Content Sources |
CN103389975A (zh) * | 2012-05-07 | 2013-11-13 | 腾讯科技(深圳)有限公司 | 一种新闻推荐方法及系统 |
CN104199874A (zh) * | 2014-08-20 | 2014-12-10 | 哈尔滨工程大学 | 一种基于用户浏览行为的网页推荐方法 |
CN105512326A (zh) * | 2015-12-23 | 2016-04-20 | 成都品果科技有限公司 | 一种图片推荐的方法及系统 |
CN106372113A (zh) * | 2016-08-22 | 2017-02-01 | 上海亿账通互联网科技有限公司 | 新闻内容的推送方法及系统 |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110955823A (zh) * | 2018-09-26 | 2020-04-03 | 阿里巴巴集团控股有限公司 | 信息推荐方法、装置 |
CN110955823B (zh) * | 2018-09-26 | 2023-04-25 | 阿里巴巴集团控股有限公司 | 信息推荐方法、装置 |
CN111159566A (zh) * | 2019-12-31 | 2020-05-15 | 中国银行股份有限公司 | 金融市场产品的资讯推送方法及装置 |
CN111310048A (zh) * | 2020-02-25 | 2020-06-19 | 西安电子科技大学 | 基于多层感知机的新闻推荐方法 |
CN111708879A (zh) * | 2020-05-11 | 2020-09-25 | 北京明略软件系统有限公司 | 针对事件的文本聚合方法、装置及计算机可读存储介质 |
CN111753197A (zh) * | 2020-06-18 | 2020-10-09 | 达而观信息科技(上海)有限公司 | 新闻要素的提取方法、装置、计算机设备和存储介质 |
CN111753197B (zh) * | 2020-06-18 | 2024-04-05 | 达观数据有限公司 | 新闻要素的提取方法、装置、计算机设备和存储介质 |
CN114065038A (zh) * | 2021-11-17 | 2022-02-18 | 中国银行股份有限公司 | 基于大数据的头条资讯推荐方法及装置 |
CN114817730A (zh) * | 2022-05-06 | 2022-07-29 | 李春良 | 一种大数据情境下的资讯活动信息推荐系统及方法 |
CN114840756A (zh) * | 2022-05-06 | 2022-08-02 | 东南大学 | 一种基于关键热点信息的媒体生成推荐系统 |
CN115277835A (zh) * | 2022-08-01 | 2022-11-01 | 网易(杭州)网络有限公司 | 信息推送方法、装置、存储介质及电子设备 |
CN116226539A (zh) * | 2023-05-04 | 2023-06-06 | 浙江保融科技股份有限公司 | 一种自动化内容推荐方法及系统 |
Also Published As
Publication number | Publication date |
---|---|
CN106372113A (zh) | 2017-02-01 |
CN106372113B (zh) | 2018-03-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2018036272A1 (zh) | 新闻内容的推送方法、电子装置及计算机可读存储介质 | |
JP6487201B2 (ja) | 推奨ページを生成するための方法及び装置 | |
JP5078674B2 (ja) | 分析システム、情報処理装置、アクティビティ分析方法、およびプログラム | |
CN109062950B (zh) | 一种文本标注的方法及装置 | |
CN102819591B (zh) | 一种基于内容的网页分类方法及系统 | |
US10043220B2 (en) | Method, device and storage medium for data processing | |
WO2016150083A1 (zh) | 一种信息输入方法和装置 | |
CN110941738B (zh) | 推荐方法、装置、电子设备及计算机可读存储介质 | |
JP6428795B2 (ja) | モデル生成方法、単語重み付け方法、モデル生成装置、単語重み付け装置、デバイス、コンピュータプログラム及びコンピュータ記憶媒体 | |
WO2016124074A1 (zh) | 一种信息处理方法、客户端及服务器、计算机存储介质 | |
US11055373B2 (en) | Method and apparatus for generating information | |
US10216831B2 (en) | Search results summarized with tokens | |
WO2019153685A1 (zh) | 文本处理方法、装置、计算机设备和存储介质 | |
WO2017121076A1 (zh) | 信息推送方法和装置 | |
CN108292257B (zh) | 用于注解客户端-服务器事务的系统和方法 | |
US20140020079A1 (en) | Method for providing network service and apparatus thereof | |
CN103546446A (zh) | 一种钓鱼网站的检测方法、装置和终端 | |
CN104462096B (zh) | 舆情监测分析方法和装置 | |
WO2021114634A1 (zh) | 文本标注方法、设备及存储介质 | |
CN114629929B (zh) | 一种日志记录方法、装置及系统 | |
WO2019062013A1 (zh) | 电子装置、用户分群的方法、系统及计算机可读存储介质 | |
CN112307318A (zh) | 一种内容发布方法、系统及装置 | |
CN116089732B (zh) | 基于广告点击数据的用户偏好识别方法及系统 | |
CN112947844B (zh) | 一种数据存储方法、装置、电子设备及介质 | |
WO2015068259A1 (ja) | 情報提供方法および装置並びプログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17842696 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 18.07.2019) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 17842696 Country of ref document: EP Kind code of ref document: A1 |