CN110362737B - Recommended content pushing method and device and server - Google Patents
Recommended content pushing method and device and server Download PDFInfo
- Publication number
- CN110362737B CN110362737B CN201810306097.7A CN201810306097A CN110362737B CN 110362737 B CN110362737 B CN 110362737B CN 201810306097 A CN201810306097 A CN 201810306097A CN 110362737 B CN110362737 B CN 110362737B
- Authority
- CN
- China
- Prior art keywords
- recommended
- information
- option
- edit box
- recommended content
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention provides a method for pushing recommended content, which comprises the following steps: receiving a request for acquiring recommended content information of an edit box sent by a terminal browser; acquiring information of the edit box and historical data of a user of the terminal browser; determining recommended content information according to the information of the edit box and historical data of the user; and pushing the recommended content information to the terminal browser. According to the invention, the recommended content information input in the edit box is recommended to the user, so that the convenience of inputting the content by the user is improved. The invention also provides a pushing device and a server for the recommended content.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method, a device and a server for pushing recommended contents.
Background
With the rapid development of computer technology and internet technology, some mainstream browsers provide a function of saving forms for facilitating a user to input a text, for example, information such as a user name and a password that needs to be filled in when the user logs in a certain website, and when the user logs in the website again next time, corresponding information in an input box is filled in. This function effectively improves the convenience of user input, but its use scenario is single, and it is used only in a form in which the user fills in login verification and the like. But cannot be used when other forms such as forum replies, order evaluation and the like are filled.
In the prior art, the problem of convenience in filling other forms such as reply in forums, order evaluation and the like of users is mainly solved through the function of input method associative input. However, the method has very limited information recommended to the user, and cannot calculate the information required by the user according to the website logged in by the user or the historical data of the user.
Disclosure of Invention
The invention aims to provide a method, a device and a server for pushing recommended content, which improve the convenience of content input by a user by recommending the recommended content information input in an edit box to the user.
In a first aspect, the present invention provides a method for pushing recommended content, including the steps of:
receiving a request for acquiring recommended content information of an edit box sent by a terminal browser;
acquiring information of the edit box and historical data of a user of the terminal browser;
determining recommended content information according to the information of the edit box and historical data of the user;
and pushing the recommended content information to the terminal browser.
With reference to the first aspect, in a first implementation manner of the first aspect, the information of the edit box includes an attribute of the edit box and/or information of an edit box currently input by a user.
With reference to the first implementation manner of the first aspect, in a second implementation manner of the first aspect, the determining recommended content information according to the information of the edit box and the history data of the user includes:
analyzing the information of the edit box to obtain recommended condition information;
screening out a first recommendation option matched with the recommendation condition information from the historical data;
and obtaining recommended content information according to the recommended content in the first recommended option.
With reference to the second implementation manner of the first aspect, in a third implementation manner of the first aspect, the analyzing the information of the edit box to obtain recommendation condition information includes:
performing word segmentation on the information of the current input edit box to obtain first recommendation condition information;
and/or analyzing the website information and attribute category to which the edit box belongs in the edit box attributes to obtain second recommendation condition information.
With reference to the second implementation manner of the first aspect, in a fourth implementation manner of the first aspect, before obtaining the recommended content information according to the recommended content in the first recommendation option, the method further includes:
and communicating with the content recommendation server to acquire a second recommendation option.
With reference to the fourth implementation manner of the first aspect, in a fifth implementation manner of the first aspect, the obtaining, by communicating with the content recommendation server, the second recommendation option includes:
transmitting information of the edit box to the content recommendation server;
and acquiring a second recommendation option determined by the content recommendation server according to the information of the edit box and the third-party data source information.
With reference to the fourth implementation manner of the first aspect, in a sixth implementation manner of the first aspect, the obtaining recommended content information according to the recommended content in the first recommendation option includes:
sequencing the second recommended options at the front and the first recommended options at the back, and combining the recommended content in the second recommended options and the recommended content in the first recommended options to obtain the recommended content information;
or screening out recommended contents matched with each other in the second recommended option and the first recommended option to serve as the recommended content information.
With reference to the sixth implementation manner of the first aspect, in a seventh implementation manner of the first aspect, after the pushing the recommended content information to the terminal browser, the method further includes:
receiving selected content information fed back by the terminal;
and adjusting the sequence of the first recommended option and the second recommended option according to the selected content information to form next recommended content information.
With reference to the seventh implementation manner of the first aspect, in an eighth implementation manner of the first aspect, the adjusting, according to the selected content information, the ordering of the first recommended option and the second recommended option to form next recommended content information includes:
judging whether the selected content information belongs to a first recommended option or not;
if so, ordering the first recommended option in front of the second recommended option, and combining the recommended content in the first recommended option and the recommended content in the second recommended option to form next recommended content information;
if not, the original sequence of the first recommended option and the second recommended option is kept, and next recommended content information is formed.
In a second aspect, the present invention provides a device for pushing recommended content, including the following modules:
the receiving module is used for receiving a request for acquiring recommended content information of the edit box sent by a terminal browser;
the acquisition module is used for acquiring the information of the edit box and the historical data of the user of the terminal browser;
the determining module is used for determining recommended content information according to the information of the edit box and the historical data of the user;
and the pushing module is used for pushing the recommended content information to the terminal browser.
With reference to the second aspect, in a first implementation manner of the second aspect, the information of the edit box includes an attribute of the edit box and/or information of the edit box currently entered by the user.
With reference to the first implementation manner of the second aspect, in a second implementation manner of the second aspect, the determining module includes:
the analysis unit is used for analyzing the information of the edit box to obtain recommendation condition information;
the screening unit is used for screening out a first recommendation option matched with the recommendation condition information from the historical data;
and the determining unit is used for obtaining recommended content information according to the recommended content in the first recommended option.
With reference to the second embodiment of the second aspect, the present invention provides, in a third embodiment of the second aspect, that the analysis unit is further configured to:
performing word segmentation on the information of the current input edit box to obtain first recommendation condition information;
and/or analyzing the website information and attribute category to which the edit box belongs in the edit box attributes to obtain second recommendation condition information.
With reference to the second implementation manner of the second aspect, in a fourth implementation manner of the second aspect, the present invention further includes a communication unit, configured to communicate with the content recommendation server to obtain the second recommendation option before obtaining the recommended content information according to the recommended content in the first recommendation option.
With reference to the fourth implementation manner of the second aspect, in a fifth implementation manner of the second aspect, the communication unit is further configured to:
transmitting information of the edit box to the content recommendation server;
and acquiring a second recommendation option determined by the content recommendation server according to the information of the edit box and the third-party data source information.
With reference to the fourth implementation manner of the second aspect, in a sixth implementation manner of the second aspect, the determining unit is further configured to:
sequencing the second recommended options at the front and the first recommended options at the back, and combining the recommended content in the second recommended options and the recommended content in the first recommended options to obtain the recommended content information;
or screening out recommended contents matched with each other in the second recommended option and the first recommended option to serve as the recommended content information.
With reference to the sixth embodiment of the second aspect, the present invention, in a seventh embodiment of the second aspect, further includes:
the feedback module is used for receiving the selected content information fed back by the terminal browser after the recommended content information is pushed to the terminal browser;
and the adjusting module is used for adjusting the sequencing of the first recommended option and the second recommended option according to the selected content information to form next recommended content information.
With reference to the seventh implementation manner of the second aspect, in an eighth implementation manner of the second aspect, the adjusting module includes:
the judging unit is used for judging whether the selected content information belongs to a first recommended option or not;
if so, ordering the first recommended option in front of the second recommended option, and combining the recommended content in the first recommended option and the recommended content in the second recommended option to form next recommended content information;
if not, the original sequence of the first recommended option and the second recommended option is kept, and next recommended content information is formed.
In a third aspect, the present invention provides a server, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: the push method of recommended content according to the first aspect is performed.
Compared with the prior art, the push method, the push device and the push server for the recommended content have the following advantages:
(1) according to the method, the device and the server for pushing the recommended content, the recommended content information is determined by the first server according to the obtained information of the edit box and the historical data of the user of the terminal browser, and the recommended content information is pushed to the terminal browser, so that the user can directly select information needing to be input from the recommended content information recommended by the first server, and the convenience of user input is improved. The method specifically comprises the steps of acquiring a webpage currently browsed by a user according to information of an edit box, determining a first recommendation option by combining the currently browsed webpage, information of the edit box input by the user and historical data of the user, and forming recommended content information currently required by the user.
(2) According to the method, the device and the server for pushing the recommended content, the first server is communicated with the content recommendation server to obtain the second recommendation option, the first recommendation option determined by the first server is combined, and the first server integrates the first recommendation option and the second recommendation option to form the recommended content information to be pushed to the terminal server. Specifically, the method adds a process of obtaining a second recommendation option by the communication between the first server and the content recommendation server, and in the content recommendation server, the second recommendation option is determined by combining third-party data source information according to the information of the edit box, so that the finally formed recommendation content information is further enriched, the requirements of the user are determined based on historical data left in the third-party platform by the user, and the accuracy of the finally formed recommendation content information is further improved.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flowchart of a first method of a method for pushing recommended content according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a second method of pushing recommended content according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a third method for pushing recommended content according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a fourth method of pushing recommended content according to an embodiment of the present invention;
FIG. 5 is a block diagram of a first module of a device for pushing recommended content according to a second embodiment of the present invention;
FIG. 6 is a second block diagram of a device for pushing recommended content according to a second embodiment of the present invention;
FIG. 7 is a block diagram of a third module of a content recommendation pushing device according to a second embodiment of the present invention;
fig. 8 is a fourth block diagram of a device for pushing recommended content according to a second embodiment of the present invention;
fig. 9 is a schematic diagram of interaction between a terminal and a server according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As will be understood by those skilled in the art, a "terminal" as used herein includes both devices that include a wireless signal receiver, which are devices having only a wireless signal receiver without transmit capability, and devices that include receive and transmit hardware, which have devices capable of performing two-way communication over a two-way communication link. Such a device may include: a cellular or other communication device having a single line display or a multi-line display or a cellular or other communication device without a multi-line display; PCS (Personal Communications Service), which may combine voice, data processing, facsimile and/or data Communications capabilities; a PDA (Personal Digital Assistant), which may include a radio frequency receiver, a pager, internet/intranet access, a web browser, a notepad, a calendar and/or a GPS (Global Positioning System) receiver; a conventional laptop and/or palmtop computer or other device having and/or including a radio frequency receiver. As used herein, a "terminal" or "terminal device" may be portable, transportable, installed in a vehicle (aeronautical, maritime, and/or land-based), or situated and/or configured to operate locally and/or in a distributed fashion at any other location(s) on earth and/or in space. As used herein, the "terminal Device" may also be a communication terminal, a web terminal, a music/video playing terminal, such as a PDA, an MID (Mobile Internet Device) and/or a Mobile phone with music/video playing function, or a smart tv, a set-top box, etc.
As will be appreciated by those skilled in the art, a remote network device, as used herein, includes, but is not limited to, a computer, a network host, a single network server, a collection of multiple network servers, or a cloud of multiple servers. Here, the Cloud is composed of a large number of computers or network servers based on Cloud Computing (Cloud Computing), which is a kind of distributed Computing, a super virtual computer composed of a group of loosely coupled computer sets. In the embodiment of the present invention, the communication between the remote network device, the terminal device and the WNS server may be implemented by any communication method, including but not limited to, mobile communication based on 3GPP, LTE, and WIMAX, computer network communication based on TCP/IP and UDP protocols, and short-distance wireless transmission based on bluetooth and infrared transmission standards.
The following describes in detail specific embodiments of a method, an apparatus, and a server for pushing recommended content according to the present invention with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention and not to limit the present invention.
Example one
With reference to fig. 1, an embodiment of the present invention provides a method for pushing recommended content, including the steps of:
s01 receiving a request for acquiring edit box recommended content information sent by a terminal browser;
in this embodiment, the implementation subject is a first server directly interacting with the terminal, and when the terminal browser detects that the edit box in the current webpage is in an edit state, a request for acquiring the recommended content information is triggered to be sent to the first server. The editing state of the editing box comprises that a user clicks the editing box, the user inputs information in the editing box and the like.
Further, the interaction between the terminal browser and the first server further comprises an input recommendation device, and the input recommendation device is used for interacting with the first server according to the information of the edit box, namely, the terminal browser and the first server interact through the input recommendation device. Further, the input recommendation device is part of a terminal, and the request is sent by the terminal and received by the first server.
S02, acquiring the information of the edit box and the historical data of the user of the terminal browser;
and the information of the edit box is the information of the current edit box carried when the receiving terminal browser sends the request. Specifically, the information of the edit box includes an edit box attribute and/or information of the edit box currently input by the user. The edit box attribute comprises website information, attribute category and the like to which the edit box belongs, and the information currently input into the edit box by the user is information displayed in the current edit box and comprises text, pictures, expressions, motion pictures and the like.
The historical data of the user of the terminal browser comprises historical information input by the user in a previous webpage, historical records stored by a server, historical data of historical webpages and the like.
When the first server acquires the information of the edit box, the terminal uploads different data according to different conditions. When the user is a new user or in an initial use state, the user needs to input and set personal key information, such as a user name, a mailbox and the like, and the subsequent terminal positions the user according to the personal key information set by the user. When historical data exists, the terminal identifies data matched with the historical data, when the terminal locates a user, the terminal identifies a webpage URL browsed by the user currently, a label ID where an edit box used by the user is located (if the user needs to fill in a title, text content and the like when posting in a webpage, whether the title or the text content is input by the user is identified, the label ID needs to be uploaded to the first server, namely, attribute categories of the edit box are distinguished through the label ID), and/or data such as texts input by the user, selected input options and the like are sorted and uploaded to the first server; when the edit boxes subsequently used by the user are still the same edit box, the terminal only uploads the URL of the currently browsed webpage to the first server, and at the moment, the first server only receives the URL of the currently browsed webpage, and the fact that the data which are the same as the information of the last obtained edit box are adopted can be judged.
S03, determining recommended content information according to the information of the edit box and the historical data of the user;
specifically, with reference to fig. 2, the step S03 determines recommended content information according to the information of the edit box and the history data of the user, and includes the steps of:
s031 analyzing the information of the edit box to obtain recommendation condition information;
after receiving the information of the edit box sent by the terminal browser, the first server analyzes the information of the edit box, specifically, step S031 analyzes the information of the edit box to obtain recommendation condition information, including the steps of:
performing word segmentation on the information of the current input edit box to obtain first recommendation condition information;
the information of the current input edit box is the information of the edit box currently input by the user in the information of the edit box currently acquired by the first server. For example, when the information currently input into the edit box by the user is "everyone happy new year", and the information is divided into "everyone happy new year, everyone happy new year", and the new year happy new year ", the result of the word division will be the first recommendation condition information, that is, the result of the word division will be the condition for subsequently screening the recommendation content information.
And/or analyzing the website information and attribute category to which the edit box belongs in the edit box attributes to obtain second recommendation condition information.
The website information of the edit box in the edit box attribute is a currently browsed webpage URL, and the first server can obtain the title of the webpage according to the website information, further search the content in the webpage and search historical data which is input in the webpage by a user. The attribute category is a search box, a comment box, etc., for example, a user enters "rice" in the search box, and this information will be marked as input text of the search box. At this time, the first server analyzes the website information to which the edit box belongs and the attribute category in the edit box attributes to obtain second recommendation condition information, which is a condition for screening recommendation content information searched by the first server in a webpage currently browsed by the user.
S032 screening out a first recommendation option matched with the recommendation condition information from the historical data;
specifically, the history data is history data in a history webpage used by the user, which is searched by the first server according to the information of the located user uploaded by the terminal. Due to the fact that the amount of historical data in the historical webpages is too large, the historical data in the last several historical webpages are preferably sorted by time, and further, the historical data in the historical webpages are properly selected according to the performance of the terminal equipment used by the user, wherein the historical data comprise titles and contents in the historical webpages.
And screening a first recommendation option by combining the recommendation condition information. Firstly, according to the first recommendation condition information and the second recommendation condition information in the recommendation condition information, the first server searches the title of a webpage in the currently browsed webpage, further searches the content in the webpage, and then searches the historical data input by the user. And obtaining recommendation options of the currently browsed webpage by combining the information searched by the first server in the currently browsed webpage based on the recommendation condition information. And secondly, recommending options of the historical webpage screened from the historical data by the first server. And the recommendation options of the currently browsed webpage and the recommendation options of the historical webpages form a first recommendation option.
And S033 obtaining recommended content information according to the recommended content in the first recommended option.
Specifically, if the first recommendation option includes the civil engineering content "michelin" of the recommendation option of the currently browsed web page and the recommendation content "buy once but do not want to buy the second time true" of the recommendation option of the historical web page, it is preferable to rank the recommendation content of the recommendation option of the currently browsed web page before the recommendation content of the recommendation option of the historical web page, that is, "michelin" is ranked before "buy once but do not want to buy the second time true", and the ranked recommendation content forms recommendation content information.
Furthermore, after the first server finishes visiting a website for the user, the website is analyzed, if the website is a website related to tires, the webpage is analyzed to obtain keywords related to the webpage, such as 10 times of appearance of 'convenient installation', 9 times of appearance of 'cheap', and the like, the keywords appearing for multiple times are stored in the first server, and meanwhile, information such as titles, websites and the like in the webpage are also recorded in the first server. The analysis of the website by the first server facilitates the subsequent formation of recommended content information. For example, if the information of the edit box acquired by the first server includes a text "wheel" of the edit box input by the user, the first server may search the history of the user input according to the history data, if the user has input "tire", the tire is used as one piece of information of the recommended content information, if the user selects "tire" in the recommended content information at this time, all websites with titles related to tires in history visit websites are searched according to the input text "tire" selected by the user, and the text content of the website is captured, for example, a keyword such as "easy to install" that the first server has saved when analyzing the website. At this time, the recommended content information may be formed as "XXX tire installation is convenient".
Preferably, with reference to fig. 3, before obtaining the recommended content information according to the recommended content in the first recommended option in step S033, the method further includes the steps of:
s034, communicating with the content recommendation server to obtain a second recommendation option.
With reference to fig. 9, the content recommendation server is a second server in the present embodiment, which is specifically a remote computing center in communication with the first server. That is, in this embodiment, the system includes a first server (a local computing center for purely local computing and comprehensively recommending the computing results of the remote computing center to the terminal) directly interacting with the terminal, and a second server (a remote computing center for computing the recommended results according to the information of the edit box, sending the request, and sending the result to the first server) communicating with the first server
Specifically, step S034 communicates with the content recommendation server to obtain the second recommendation option, including the steps of:
transmitting information of the edit box to the content recommendation server;
and the first server transmits the information of the edit box uploaded by the terminal acquired by the first server to a content recommendation server through a network, namely the content recommendation server is consistent with the basic data for forming the recommended content information acquired by the first server.
And acquiring a second recommendation option determined by the content recommendation server according to the information of the edit box and the third-party data source information.
The third-party data source information comprises social messages, forum posts, purchased commodities, current news hotspots and the like.
Specifically, the step of determining, by the content recommendation server, a second recommendation option according to the information of the edit box and the third-party data source information includes:
and the content recommendation server performs word segmentation according to the information of the edit box and determines a second recommendation option by combining with the third-party data source information.
Specifically, the participles include the following two:
(1) text-based word segmentation
For example, the information "happy new year", "happy year", "happy family", etc. corresponding to "happy new year" may be the second recommendation.
(2) Word segmentation based on website
The attribute of the edit box in the information of the edit box comprises website information, attribute category and the like of the edit box, and the content recommendation server performs word segmentation on the information of the edit box input by the current user according to the attribute of the edit box and determines a second recommendation option. If the user leaves a message in the electronic product evaluation, and if the current user inputs 'power consumption is high', the content recommendation server determines second recommendation options such as 'express speed is good', 'store-and-restaurant-with-two service attitude is good', 'photographing effect is good' and the like on the basis of the evaluation webpage. Assuming that the current user inputs ' power consumption is high and the content recommendation server evaluates the webpage, second recommendation options such as ' express slow ' and ' store low attitude ' are determined. Specifically, the content recommendation server further determines a different second recommendation option based on whether a conjunction exists in the text input by the user, and if the conjunction is a turning word, determines a reverse recommendation option related to the previously input text; if "and" is a conjunction, then a forward recommendation option associated with the previously entered text is determined.
And the content recommendation server selects at least 1 second recommendation option according to the information of the edit box and the website information to which the edit box belongs and the historical data of the currently browsed webpage, and if the user inputs 'happy new year' in the currently browsed webpage, the 'happy new year' can be used as one of the second recommendation options.
And the content recommendation server determines the second recommendation option by combining the third-party data source information and determines the second recommendation option for selecting other sources. For example, the currently browsed web page can be known according to the information of the edit box, and it is determined that the user needs to reply in the forum according to the analysis of the web page, then the second recommendation option may be given according to a sentence "congratulating friends with dogs and luck" used by the user to reply in other web pages, or the user may determine "physical health" if the user searches and accesses a disease-related website, and may determine "new year wealth" and the like as the second recommendation option if the user accesses the finance website.
In the second recommendation options determined by the content recommendation server, preferably, the second recommendation options (assumed to be 4) for performing word segmentation determination are ranked in the top, then at least 1 recommendation option (assumed to be 1) is selected according to the history data of the currently browsed web page, and finally the second recommendation options (assumed to be 3) determined by combining with the third-party data source information are selected. The formed second recommended options are suitable for the terminal performance and limited by the number, the finally determined second recommended options are optimized according to the sequence, namely when the number is limited, 5 recommended options are assumed, and at the moment, 4 recommended options determined according to the word segmentation result and 1 recommended option determined according to the historical data of the currently browsed webpage are taken as the second recommended options.
Further comprising the steps of: when the user completes the input, the information of which the input is completed is added to the history data.
And if the user finishes inputting in the current webpage, namely the edit box is not in an edit state, saving the currently input finishing information into the historical data. If the user inputs 'western failure', the user name possibly filled in for the user is marked as the user name and stored; if the user enters "very power-consuming," the evaluation information that may have been left on the web page for the user is marked as an evaluation and saved. The history data after joining the content recommendation server will further be used to refine the subsequently determined recommended content information.
Further, step S033 obtains recommended content information according to the recommended content in the first recommended option, including the steps of:
sequencing the second recommended options at the front and the first recommended options at the back, and combining the recommended content in the second recommended options and the recommended content in the first recommended options to obtain the recommended content information;
with reference to step S034, in step S033, preferably, the second recommended option determined by the content recommendation server is ranked in front, and the first recommended option determined by the first server is ranked in the back. As described above, in the first recommendation option, the recommendation contents ranked as "michelin" and "buying the second time true" are determined, and in the second recommendation option, "the store-level two attitude is very poor" is determined as the recommendation contents, at this time, the finally formed recommendation content information is "the store-level two attitude is very poor", "michelin" and "buying the second time true" is not wanted.
Or screening out recommended contents matched with each other in the second recommended option and the first recommended option to serve as the recommended content information.
Specifically, for the recommended content that matches the first recommended item and the second recommended item with each other, the matching is not only similar in text but also includes attributes, such as "poor two-attitude in store" and "buying once without wanting to buy for the second time" both belong to evaluation-type information, and both are referred to as recommended content information.
S04 pushing the recommended content information to the terminal browser.
And after the first server determines the recommended content information, pushing the recommended content information to a terminal browser.
Further, with reference to step S034, when the content recommendation server determines the second recommendation option, the second recommendation option is transmitted to the first server, and the first server integrates the first recommendation option determined by itself and the second recommendation option to form recommended content information, and then pushes the recommended content information to the terminal browser.
Further, with reference to fig. 4, after the step S04 pushes the recommended content information to the terminal browser, the method further includes the steps of:
s05, receiving the selected content information fed back by the terminal browser;
s06, according to the selected content information, adjusting the sequence of the first recommended option and the second recommended option to form next recommended content information.
When the user evaluates the currently browsed webpage, the editing frame is in a long-time editing state, and at the moment, the next recommended content information is further optimized and formed according to the selected content information fed back by the terminal browser.
Specifically, step S06 adjusts the ranks of the first recommended option and the second recommended option according to the selected content information to form next recommended content information, and includes the steps of:
judging whether the selected content information belongs to a first recommended option or not;
if so, ordering the first recommended option in front of the second recommended option, and combining the recommended content in the first recommended option and the recommended content in the second recommended option to form next recommended content information;
if not, the original sequence of the first recommended option and the second recommended option is kept, and next recommended content information is formed.
In step S06, it is mainly determined, according to the selected content information fed back by the terminal browser, which recommended option is determined by which server the selected content information belongs to, or which recommended option is determined by which recommendation condition information of the first server the selected content information belongs to, so as to adjust the ranking of the next recommended content information.
Preferably, the step S06 adjusts the sequence of the first recommended option and the second recommended option according to the selected content information to form next recommended content information, further comprising the steps of:
determining a third recommendation option according to the selected content information;
and the third recommendation option is a recommendation option determined by which server the third recommendation option belongs to is judged according to the selected content information fed back by the current terminal browser, and if the third recommendation option is the first server, the first recommendation option determined by the first server is subdivided according to the selected content. If the selected content information is 'michelin', further, according to the webpage that the 'michelin' belongs to and is titled as the tire, the first recommended option of the related category is further determined. Such as determining "XXX tire installation convenience" as one of the third recommended options, etc.
And determining recommended content information by combining the third recommended option with the first recommended option and the second recommended option.
The step is to sort the recommended contents corresponding to the recommended options or identify whether the recommended contents are matched with each other, preferably sort the third recommended option before the sorted recommended options, and then sort the second recommended option at the end of the sorted recommended options, assuming that the first recommended option is the recommended option.
Example two
In order to further explain the method for pushing recommended content in the foregoing embodiment with reference to fig. 5, modularly explaining the method, a pushing device for providing recommended content includes the following modules:
a receiving module 51, configured to receive a request for obtaining recommended content information of an edit box sent by a terminal browser;
an obtaining module 52, configured to obtain information of the edit box and history data of a user of the terminal browser;
a determining module 53, configured to determine recommended content information according to the information of the edit box and historical data of the user;
a pushing module 54, configured to push the recommended content information to the terminal browser.
And the information of the edit box comprises the attribute of the edit box and/or the information of the edit box currently input by the user.
In conjunction with fig. 6, the determining module 53 includes:
an analyzing unit 531, configured to analyze information of the edit box to obtain recommendation condition information;
a screening unit 532, configured to screen out, from the history data, a first recommendation option matching the recommendation condition information;
the determining unit 533 is configured to obtain recommended content information according to the recommended content in the first recommended option.
The analyzing unit 531 is further configured to:
performing word segmentation on the information of the current input edit box to obtain first recommendation condition information;
and/or analyzing the website information and attribute category to which the edit box belongs in the edit box attributes to obtain second recommendation condition information.
With reference to fig. 7, the apparatus further includes a communication unit 534, configured to communicate with a content recommendation server to obtain a second recommendation option before obtaining the recommended content information according to the recommended content in the first recommendation option.
Further, the communication unit 534 is further configured to:
transmitting information of the edit box to the content recommendation server;
and acquiring a second recommendation option determined by the content recommendation server according to the information of the edit box and the third-party data source information.
Still further, the determining unit 533 is further configured to:
sequencing the second recommended options at the front and the first recommended options at the back, and combining the recommended content in the second recommended options and the recommended content in the first recommended options to obtain the recommended content information;
or screening out recommended contents matched with each other in the second recommended option and the first recommended option to serve as the recommended content information.
With reference to fig. 8, in this embodiment, it is preferable that:
a feedback module 55, configured to receive the selected content information fed back by the terminal browser after the recommended content information is pushed to the terminal browser;
and an adjusting module 56, configured to adjust the ordering of the first recommended option and the second recommended option according to the selected content information, so as to form next recommended content information.
The adjusting module 56 includes:
the judging unit is used for judging whether the selected content information belongs to a first recommended option or not;
if so, ordering the first recommended option in front of the second recommended option, and combining the recommended content in the first recommended option and the recommended content in the second recommended option to form next recommended content information;
if not, the original sequence of the first recommended option and the second recommended option is kept, and next recommended content information is formed.
EXAMPLE III
An embodiment of the present invention provides a server, including:
one or more processors;
a memory;
and one or more computer programs, the one or more computer programs being stored in the memory; the one or more computer programs, when executed by the one or more processors, implement a method for pushing recommended content according to embodiment one.
The server conventionally includes a processor and a computer program product or computer readable medium in the form of a memory. The memory may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory has a memory space for program code for performing any of the method steps of the above-described method. For example, the memory space for the program code may comprise respective program codes for implementing the respective steps in the above method, respectively. The program code can be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. Such a computer program product is typically a portable or fixed storage unit as described. The memory unit may have memory segments or memory spaces or the like in a similar arrangement of memories. The program code may be compressed, for example, in a suitable form. Typically, the memory unit comprises program code for performing the steps of the method according to the invention, i.e. code that can be read by e.g. a processor, which code, when executed by a server, causes the server to perform the steps of the method described above.
In the embodiment of the present invention, the server includes a processor having the following functions:
receiving a request for acquiring recommended content information of an edit box sent by a terminal browser;
acquiring information of the edit box and historical data of a user of the terminal browser;
determining recommended content information according to the information of the edit box and historical data of the user;
and pushing the recommended content information to the terminal browser.
That is, the processor has a function of executing the method for pushing recommended content according to the above-mentioned embodiment, and details are not described herein.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method for pushing recommended content, comprising the steps of:
receiving a request for acquiring recommended content information of an edit box sent by a terminal browser;
acquiring information of the edit box and historical data of a user of the terminal browser, wherein the information of the edit box comprises edit box attributes and/or information of the edit box currently input by the user, and the edit box attributes comprise website information and attribute categories to which the edit box belongs;
determining recommended content information according to the information of the edit box and historical data of the user;
and pushing the recommended content information to the terminal browser.
2. The method for pushing recommended content according to claim 1, wherein the step of determining recommended content information according to the information of the edit box and the history data of the user comprises the steps of:
analyzing the information of the edit box to obtain recommended condition information;
screening out a first recommendation option matched with the recommendation condition information from the historical data;
and obtaining recommended content information according to the recommended content in the first recommended option.
3. The method for pushing recommended content according to claim 2, wherein the step of analyzing the information of the edit box to obtain recommendation condition information comprises the steps of:
performing word segmentation on the information of the current input edit box to obtain first recommendation condition information;
and/or analyzing the website information and attribute category to which the edit box belongs in the edit box attributes to obtain second recommendation condition information.
4. The method for pushing recommended content according to claim 2, wherein before obtaining the recommended content information according to the recommended content in the first recommendation option, the method further comprises:
and communicating with the content recommendation server to acquire a second recommendation option.
5. The method for pushing the recommended content according to claim 4, wherein the step of communicating with the content recommendation server to obtain the second recommendation option comprises the steps of:
transmitting information of the edit box to the content recommendation server;
and acquiring a second recommendation option determined by the content recommendation server according to the information of the edit box and the third-party data source information.
6. The method for pushing recommended content according to claim 4, wherein the obtaining of the recommended content information according to the recommended content in the first recommendation option comprises:
sequencing the second recommended options at the front and the first recommended options at the back, and combining the recommended content in the second recommended options and the recommended content in the first recommended options to obtain the recommended content information;
or screening out recommended contents matched with each other in the second recommended option and the first recommended option to serve as the recommended content information.
7. The method for pushing recommended content according to claim 6, wherein after the pushing of the recommended content information to the terminal browser, the method further comprises the steps of:
receiving selected content information fed back by the terminal browser;
and adjusting the sequence of the first recommended option and the second recommended option according to the selected content information to form next recommended content information.
8. The method for pushing recommended content according to claim 7, wherein the step of adjusting the ordering of the first recommended option and the second recommended option according to the selected content information to form next recommended content information comprises the steps of:
judging whether the selected content information belongs to a first recommended option or not;
if so, ordering the first recommended option in front of the second recommended option, and combining the recommended content in the first recommended option and the recommended content in the second recommended option to form next recommended content information;
if not, the original sequence of the first recommended option and the second recommended option is kept, and next recommended content information is formed.
9. A pushing device for recommending contents is characterized by comprising the following modules:
the receiving module is used for receiving a request for acquiring recommended content information of the edit box sent by a terminal browser;
the acquisition module is used for acquiring the information of the edit box and the historical data of the user of the terminal browser, wherein the information of the edit box comprises the attribute of the edit box and/or the information of the edit box currently input by the user, and the attribute of the edit box comprises the website information and the attribute category of the edit box;
the determining module is used for determining recommended content information according to the information of the edit box and the historical data of the user;
and the pushing module is used for pushing the recommended content information to the terminal browser.
10. A server, characterized in that it comprises:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: the method of pushing recommended content according to any one of claims 1 to 8 is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810306097.7A CN110362737B (en) | 2018-04-08 | 2018-04-08 | Recommended content pushing method and device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810306097.7A CN110362737B (en) | 2018-04-08 | 2018-04-08 | Recommended content pushing method and device and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110362737A CN110362737A (en) | 2019-10-22 |
| CN110362737B true CN110362737B (en) | 2022-02-01 |
Family
ID=68213489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810306097.7A Active CN110362737B (en) | 2018-04-08 | 2018-04-08 | Recommended content pushing method and device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110362737B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110825475A (en) * | 2019-10-31 | 2020-02-21 | 维沃移动通信有限公司 | Input method and electronic equipment |
| CN111026933B (en) * | 2019-11-22 | 2023-03-21 | 泰康保险集团股份有限公司 | Content recommendation method and device, electronic equipment and storage medium |
| CN114357278B (en) * | 2020-09-28 | 2024-03-19 | 腾讯科技（深圳）有限公司 | Topic recommendation method, device and equipment |
| CN112699157B (en) * | 2021-01-12 | 2023-10-20 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, equipment and medium |
| CN112818205B (en) * | 2021-01-27 | 2023-10-31 | 游艺星际(北京)科技有限公司 | Page processing method, device, electronic equipment, storage medium and product |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102955850A (en) * | 2012-10-30 | 2013-03-06 | 北京奇虎科技有限公司 | Method and device for loading sequencing website |
| CN103324742A (en) * | 2013-06-28 | 2013-09-25 | 百度在线网络技术（北京）有限公司 | Method and equipment for recommending keywords |
| CN104462364A (en) * | 2014-12-08 | 2015-03-25 | 百度在线网络技术（北京）有限公司 | Search recommendation method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10025863B2 (en) * | 2014-10-31 | 2018-07-17 | Oath Inc. | Recommending contents using a base profile |
| CN105373608A (en) * | 2015-11-13 | 2016-03-02 | 广州市久邦数码科技有限公司 | Input method based scene-mode content pushing method and system |
-
2018
- 2018-04-08 CN CN201810306097.7A patent/CN110362737B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102955850A (en) * | 2012-10-30 | 2013-03-06 | 北京奇虎科技有限公司 | Method and device for loading sequencing website |
| CN103324742A (en) * | 2013-06-28 | 2013-09-25 | 百度在线网络技术（北京）有限公司 | Method and equipment for recommending keywords |
| CN104462364A (en) * | 2014-12-08 | 2015-03-25 | 百度在线网络技术（北京）有限公司 | Search recommendation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110362737A (en) | 2019-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110362737B (en) | Recommended content pushing method and device and server | |
| CN107679211B (en) | Method and device for pushing information | |
| CN102340514B (en) | Network information push method and system | |
| US7620657B2 (en) | Method and system for registering and retrieving production information | |
| US11151630B2 (en) | On-line product related recommendations | |
| WO2017071251A1 (en) | Information pushing method and device | |
| CN102591995B (en) | Processing method and device based on user information of cloud data center | |
| US20090234876A1 (en) | Systems and methods for content sharing | |
| US10482091B2 (en) | Computerized system and method for high-quality and high-ranking digital content discovery | |
| US8806000B1 (en) | Identifying viral videos | |
| US20070162566A1 (en) | System and method for using a mobile device to create and access searchable user-created content | |
| CN102663064B (en) | A kind of disposal route of favorites data and device | |
| CN103493463A (en) | Privacy protection in recommendation services | |
| EP3292527A1 (en) | Device and method for targeted display of information | |
| CN111125528B (en) | Information recommendation method and device | |
| US20160098416A1 (en) | Auto complete search box based on the user's context to reduce user's input | |
| US20160306887A1 (en) | Methods, apparatuses and systems for linked and personalized extended search | |
| US20100057695A1 (en) | Post-processing search results on a client computer | |
| CN111552884B (en) | Method and apparatus for content recommendation | |
| US20160012130A1 (en) | Aiding composition of themed articles about popular and novel topics and offering users a navigable experience of associated content | |
| US11430049B2 (en) | Communication via simulated user | |
| KR102335780B1 (en) | Online advertising method and online advertising system using influencers using multiple platform servers | |
| US9824149B2 (en) | Opportunistically solving search use cases | |
| CN110929129B (en) | Information detection method, equipment and machine-readable storage medium | |
| CN113886683A (en) | Label cluster construction method and system, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200408 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 100083, Beijing, Haidian District, Cheng Fu Road, No. 28, A building, block 12 Applicant before: UC MOBILE Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |