CN108205545B - Method and equipment for providing recommendation information for user - Google Patents

Method and equipment for providing recommendation information for user Download PDF

Info

Publication number
CN108205545B
CN108205545B CN201611170648.9A CN201611170648A CN108205545B CN 108205545 B CN108205545 B CN 108205545B CN 201611170648 A CN201611170648 A CN 201611170648A CN 108205545 B CN108205545 B CN 108205545B
Authority
CN
China
Prior art keywords
search
user
recommendation
feed information
information
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
Application number
CN201611170648.9A
Other languages
Chinese (zh)
Other versions
CN108205545A (en
Inventor
黄际洲
林馨怡
王婵娟
季永志
李莹
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Baidu Online Network Technology Beijing Co Ltd
Original Assignee
Baidu Online Network Technology Beijing Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Baidu Online Network Technology Beijing Co Ltd filed Critical Baidu Online Network Technology Beijing Co Ltd
Priority to CN201611170648.9A priority Critical patent/CN108205545B/en
Publication of CN108205545A publication Critical patent/CN108205545A/en
Application granted granted Critical
Publication of CN108205545B publication Critical patent/CN108205545B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search 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 Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention aims to provide a method and equipment for providing recommendation information for a user. The recommendation device acquires one or more feed information pages provided for a user; determining one or more search recommendation sequences corresponding to the feed information page according to the feed information page; and providing the search recommendation sequence to the user. Compared with the prior art, the method and the device have the advantages that the search recommendation sequence is provided for the user according to the feed information page provided for the user, and the user is guided to search, so that the flow guide from the feed information page to the search page is realized, the tedious reading and searching experience of the user is improved, more knowledge points and extension contents which are related to the currently read article and are possibly interested are conveniently provided for the user, the user can obtain better search scene requirements, the information obtaining efficiency of the user is improved, and the user experience is improved.

Description

Method and equipment for providing recommendation information for user
Technical Field
The invention relates to the technical field of internet, in particular to a technology for providing recommended information for a user based on feed information.
Background
Currently, Feed and search are two important ways for users to obtain information.
Feed is a message source, and is a data format. The message sources are, in turn, source feeds, information feeds, manuscripts, abstracts, sources, news subscriptions, web feeds, and the like. The website can transmit the latest information to the user through the feed, and the user can acquire the latest information of the website through subscribing the feed. In other words, the propagation of the feed information is actively initiated by the website, the user passively accepts the feed information, and the propagation of the whole feed information flow is a self-circulation independent closed loop.
The search is to obtain a corresponding search result by actively inputting a search sequence by a user. In other words, the search is actively initiated by the user, the website is passively output, and the information flow propagation of the search is also a self-circulation independent closed loop.
The Feed has the advantages that the user obtains immersive reading experience, however, if the user needs to obtain other information in the Feed reading process, the Feed information stream needs to be jumped out for active search, so that the reading experience is influenced, and the information acquisition efficiency is improved; similarly, the search has the advantage that the user can actively acquire the required information, but the search result may contain a great deal of redundant information, and the user needs to spend a great deal of time and effort to screen out the appropriate reading content, thereby also affecting the efficiency of information acquisition.
Disclosure of Invention
The invention aims to provide a method and equipment for providing recommendation information for a user.
According to an aspect of the present invention, there is provided a method of providing recommendation information to a user, wherein the method includes the steps of:
a, acquiring one or more feed information pages provided for a user;
b, determining one or more search recommendation sequences corresponding to the feed information page according to the feed information page;
c providing the search recommendation sequence to the user.
Optionally, step b comprises at least any one of:
-determining one or more search recommendation sequences corresponding to the feed information page based on one or more keywords contained in the feed information page;
-determining one or more search recommendation sequences corresponding to the feed information page in dependence on one or more association information with which the information content in the feed information page is associated.
Optionally, the association information includes at least any one of:
-an association entity to which the information content in the feed information page is associated;
-associated topics to which the information content in the feed information page is associated;
-an association problem associated with the information content in the feed information page;
-historical search records of other users to which the feed information page corresponds.
Optionally, the step b includes:
-determining one or more search recommendation sequences corresponding to said feed information page in connection with said user's browsing history and/or said user's attribute information, based on said feed information page.
Optionally, the step c includes:
c1 determining the display form corresponding to the search recommendation sequence according to the search recommendation sequence;
-providing the search recommendation sequence to the user in accordance with the presentation form.
Optionally, the step c1 includes:
-extracting multimedia identification information corresponding to said search sequence according to one or more related contents corresponding to said search recommendation sequence;
-determining a presentation form corresponding to the search recommendation sequence based on the multimedia identification information.
Optionally, the method further comprises the steps of:
-obtaining one or more search sequences selected by the user from the search recommendation sequences;
x retrieving the search sequence;
and y, displaying the search result corresponding to the search recommendation sequence to the user.
Optionally, the step x comprises at least any one of:
-retrieving one or more search sequences in a feed information database;
-retrieving, in one or more general search engines, one or more search sequences.
Optionally, the method further comprises:
-determining one or more recommended feed information corresponding to said user from said feed information page and said search sequence;
wherein the step y comprises:
-presenting search results corresponding to the search sequence to the user, wherein the search results comprise the recommended feed information.
According to another aspect of the present invention, there is also provided a recommendation apparatus for providing recommendation information to a user, wherein the apparatus includes:
acquiring means for acquiring one or more feed information pages provided to a user;
determining means for determining one or more search recommendation sequences corresponding to the feed information page according to the feed information page;
providing means for providing the search recommendation sequence to the user.
Optionally, the determining means is for at least any one of:
-determining one or more search recommendation sequences corresponding to the feed information page based on one or more keywords contained in the feed information page;
-determining one or more search recommendation sequences corresponding to the feed information page in dependence on one or more association information with which the information content in the feed information page is associated.
Optionally, the association information includes at least any one of:
-an association entity to which the information content in the feed information page is associated;
-associated topics to which the information content in the feed information page is associated;
-an association problem associated with the information content in the feed information page;
-historical search records of other users to which the feed information page corresponds.
Optionally, the determining means is configured to:
-determining one or more search recommendation sequences corresponding to said feed information page in connection with said user's browsing history and/or said user's attribute information, based on said feed information page.
Optionally, the providing means comprises:
the display determining unit is used for determining a display form corresponding to the search recommendation sequence according to the search recommendation sequence;
and the sequence providing unit is used for providing the search recommendation sequence to the user according to the presentation form.
Optionally, the presentation determining unit is configured to:
-extracting multimedia identification information corresponding to said search sequence according to one or more related contents corresponding to said search recommendation sequence;
-determining a presentation form corresponding to the search recommendation sequence based on the multimedia identification information.
Optionally, the apparatus further comprises:
selecting means for obtaining one or more search sequences selected by the user from the search recommendation sequences;
retrieving means for retrieving the search sequence;
and the result display device is used for displaying the search result corresponding to the search recommendation sequence to the user.
Optionally, the retrieving means is for at least any one of:
-retrieving one or more search sequences in a feed information database;
-retrieving, in one or more general search engines, one or more search sequences.
Optionally, the apparatus further comprises:
a feed recommending device for determining one or more recommended feed information corresponding to the user according to the feed information page and the search sequence;
wherein the result presentation device is configured to:
-presenting search results corresponding to the search sequence to the user, wherein the search results comprise the recommended feed information.
Compared with the prior art, the method and the device have the advantages that the search recommendation sequence is provided for the user according to the feed information page provided for the user, and the user is guided to search, so that the flow guide from the feed information page to the search page is realized, the tedious reading and searching experience of the user is improved, more knowledge points and extension contents which are related to the currently read article and are possibly interested are conveniently provided for the user, the user can obtain better search scene requirements, the information obtaining efficiency of the user is improved, and the user experience is improved.
Moreover, the invention can also determine the search recommendation sequence in various ways, including ways of determining the search recommendation sequence according to one or more keywords contained in the feed information page, one or more associated information associated with the information content in the feed information page, and combining the browsing record of the user and/or the attribute information of the user, thereby improving the accuracy of the determined search recommendation sequence, leading the search recommendation sequence to better meet the requirements of the user and realizing accurate information flow guide.
Moreover, the invention can also search the corresponding search sequence for the user according to the selection of the user on the search recommendation sequence, and show the search result corresponding to the search recommendation sequence to the user; furthermore, one or more pieces of recommended feed information corresponding to the user can be determined according to the feed information page and the search sequence, and the recommended feed information is presented to the user as the search result. Therefore, the invention can also flow from the search to the Feed page on the basis of the flow from the Feed information page to the search page, realizes the combination of recommendation and reading, completes the seamless fusion of two independent closed loops of the search and the Feed in an efficient way, reduces the flow loss after the Feed reaches the search, and effectively controls the Feed information and the search information on the whole.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments made with reference to the following drawings:
FIG. 1 illustrates a schematic diagram of a recommendation device for providing recommendation information to a user in accordance with an aspect of the present invention;
FIG. 2 is a schematic diagram of a recommendation device for providing recommendation information to a user in accordance with a preferred embodiment of the present invention;
FIG. 3 illustrates a flow chart of a method for providing recommendation information to a user in accordance with another aspect of the invention;
FIG. 4 illustrates a flowchart of a method for providing recommendation information to a user in accordance with a preferred embodiment of the present invention;
fig. 5(1) to 5(4) are schematic views respectively showing a method for providing recommendation information to a user according to a preferred embodiment of the present invention;
FIG. 6 is a diagram illustrating a method for providing recommendation information to a user in accordance with a preferred embodiment of the present invention;
fig. 7 is a diagram illustrating a method for providing recommendation information to a user according to a preferred embodiment of the present invention.
The same or similar reference numbers in the drawings identify the same or similar elements.
Detailed Description
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel, concurrently, or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
The "recommendation device" is a "computer device" and is also referred to as a "computer", and refers to an intelligent electronic device that can execute a predetermined process such as numerical calculation and/or logic calculation by running a predetermined program or instruction, and may include a processor and a memory, where the processor executes a pre-stored instruction stored in the memory to execute the predetermined process, or the processor executes a predetermined process by hardware such as ASIC, FPGA, DSP, or a combination thereof.
The computer device comprises user equipment and/or network equipment. Wherein the user equipment includes but is not limited to computers, smart phones, PDAs, etc.; the network device includes, but is not limited to, a single network server, a server group consisting of a plurality of network servers, or a Cloud Computing (Cloud Computing) based Cloud consisting of a large number of computers or network servers, wherein Cloud Computing is one of distributed Computing, a super virtual computer consisting of a collection of loosely coupled computers. Wherein the computer device can be operated alone to implement the invention, or can be accessed to a network and implement the invention through interoperation with other computer devices in the network. The network in which the computer device is located includes, but is not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.
Those skilled in the art should understand that the "recommendation device" described in the present invention may be only a network device, i.e. the network device performs the corresponding operation; or the user equipment and the network equipment or the server are integrated to form the system, namely the user equipment and the network equipment are matched to execute corresponding operations.
It should be noted that the user equipment, the network device, the network, etc. are only examples, and other existing or future computer devices or networks may also be included in the scope of the present invention, and are included by reference.
Here, it should be understood by those skilled in the art that the present invention can be applied to a mobile terminal and a non-mobile terminal, for example, when a user uses a mobile phone or a PC, the method or the apparatus of the present invention can be used to provide recommendation information for the user.
Specific structural and functional details disclosed herein are merely representative and are provided for purposes of describing example embodiments of the present invention. The present invention may, however, be embodied in many alternate forms and should not be construed as limited to only the embodiments set forth herein.
It will be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element may be termed a second element, and, similarly, a second element may be termed a first element, without departing from the scope of example embodiments. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms "a", "an" 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 herein, 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 should also be noted that, in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed substantially concurrently, or the figures may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
The present invention is described in further detail below with reference to the attached drawing figures.
FIG. 1 illustrates a schematic diagram of a recommendation device for providing recommendation information to a user in accordance with an aspect of the present invention; the recommendation device comprises an acquisition device 1, a determination device 2 and a providing device 3. Specifically, the acquiring apparatus 1 acquires one or more feed information pages provided to a user; the determining device 2 determines one or more search recommendation sequences corresponding to the feed information page according to the feed information page; the providing means 3 provides the search recommendation sequence to the user.
The acquisition means 1 acquire one or more feed information pages provided to the user.
The acquiring device 1 acquires one or more feed information pages provided for the user by calling subscription setting, operation information and other modes of the user; or, the obtaining apparatus 1 directly obtains the display interface of the user, and uses the feed information on the display interface as one or more feed information pages provided for the user; alternatively, the acquiring apparatus 1 may acquire one or more feed information pages provided to the user by interacting with a server or other device capable of providing the above information.
The feed information page refers to a specific information flow or a consultation flow which is obtained by a user through subscription, attention and other modes and is pushed by a server; the obtained feed information pages include, but are not limited to, a complete feed information page expanded after clicking, a title or an abstract of an unchecked feed information page, various feed information pages already read or to be read, and the like.
The determining means 2 determines one or more search recommendation sequences corresponding to the feed information page according to the feed information page.
Specifically, the determining device 2 analyzes the content of the feed information page, and determines one or more search recommendation sequences corresponding to the feed information page based on the direct content or the associated content of the feed information page, for example, by extracting one or more keywords included in the feed information page, or determining one or more associated information associated with the information content in the feed information page.
As shown in fig. 5(1), the feed information page is that the "vegetables" topic "of the family vegetables can help your fat meat to go away from you, and the determined search recommendation sequences are" tomato "," balsam pear "and" potato ".
Preferably, the determining device 2 can determine one or more search recommendation sequences corresponding to the feed information page according to one or more keywords contained in the feed information page.
Specifically, the determining means 2 extracts a specific noun and a popular vocabulary contained in the feed information page; or counting the content in the feed information page to determine words with the frequency exceeding a preset threshold value in the feed information page; or analyzing the title, the picture name or description, the video name or description and the like in the feed information page to determine the core words in the feed information page; then, the determining means 2 takes one or more of the above words as one or more keywords contained in the feed information page.
The specific nouns comprise one or more entity nouns such as names of people, articles, commodities, trademarks, works and the like; the popular vocabulary includes but is not limited to various network popular words, network phrases, and the like.
The determination means 2 may directly take the keyword as the search recommendation sequence; the keywords can also be weighted and sorted according to the occurrence frequency, the determining mode and the like of the keywords, so that the keywords with weighted values larger than a certain threshold value or with sorted values before a preset name are used as the search recommendation sequence after weighted sorting; or, according to the sorting sequence after the weighted sorting, providing the keywords as the search recommendation sequence to the user.
For example, if a proper noun such as "AMD", "NVIDIA", "INTEL" appears in the feed information page, the above-mentioned proper noun may be used as the keyword; then, the determination means 2 may take all of the above nouns as the search recommendation sequence; the occurrence frequency of the nouns may be counted, and if the occurrence frequency of "NVIDIA" is the highest, only "NVIDIA" is used as the search recommendation sequence, as shown in fig. 6.
Alternatively, preferably, the determining device 2 may determine one or more search recommendation sequences corresponding to the feed information page according to one or more associated information associated with the information content in the feed information page.
Specifically, the determining device 2 may analyze the information content in the feed information page to obtain one or more associated information associated with the information content; wherein the associated information includes, but is not limited to, associated entities, associated content, associated questions, historical search records of other users, and the like. The associated information may be obtained based on big data statistics (e.g., statistics of consecutive search records of others), classification information within the database, and the like.
Then, the determination means 2 may directly take the associated information as the search recommendation sequence; or performing weighted sorting on the associated information according to the occurrence frequency, the determination mode and the like of the associated information, so that the associated information with a weighted value larger than a certain threshold value or with a sorting value before a predetermined name after weighted sorting is used as the search recommendation sequence; or, according to the sorting order after the weighted sorting, providing the associated information as the search recommendation sequence to the user.
More preferably, the association information includes at least any one of:
-an associated entity to which the information content in the feed information page is associated: the determining device 2 may obtain the associated entity associated with the information content by retrieving a database storing the associated relationship and the like according to the entity, the topic and the like included in the information content in the feed information page. For example, if the feed information page includes an entity "NVIDIA", then "AMD" may be the associated entity; if the feed information page contains the theme of 'weight loss', the balsam pear, the tea and the like can be used as related entities related to the 'weight loss'.
-associated topics to which the information content in the feed information page is associated: the determining device 2 may obtain the related topic associated with the information content by querying the classified information associated with the entity or the topic, querying the browsing record associated with the feed information page, and the like according to the entity, the topic, and the like contained in the feed information page. For example, if the information content of the feed information page is "these family dishes can help your fat go away from you", then "quickly eliminate the lower abdomen proud meat" can be taken as the related topic.
-an association problem associated with the information content in the feed information page: the determining device 2 may obtain the associated question associated with the information content in the feed information page by querying the question associated with the above content according to the existing question, entity, subject, etc. contained in the feed information page. For example, as shown in fig. 7, if the information content of the feed information page is "the smartest dog all over the world, do you want one? "related questions of the golden retriever mentioned in the article, such as" how much money is one for golden retriever? "as a matter of relevance. Here, preferably, the determining means 2 may determine whether to use one or more "association questions" as the association information according to one or more specific character or word triggers, for example, only if "why", "are included in the feed information page? When a specific word is "or the like," the association problem "is used as the association information.
-historical search records of other users to which the feed information page corresponds: if the other users of the feed information page perform a search within a predetermined time threshold by using one or more custom or recommended query sequences after reading the information page, the query sequence or the search result clicked by the user can be used as the related information of the feed information page. The determination device 2 may obtain the query sequence, the queried search result, the query time, and the like of the other user by calling the historical search records of the other user to determine the related information based on the above.
It will be understood by those skilled in the art that the determining means 2 may determine the search recommendation sequence separately according to any one of the above manners and then provide the determined search recommendation sequence to the user; the two modes can be combined, and the search recommendation sequences determined by the two modes can be provided to the user at the same time.
Preferably, the determining device 2 may determine one or more search recommendation sequences corresponding to the feed information page according to the feed information page, in combination with the browsing history of the user and/or the attribute information of the user.
Specifically, the determining device 2 obtains the browsing history of the user and/or the attribute information of the user, and then determines one or more search recommendation sequences corresponding to the feed information page according to the feed information page on the basis of combining the browsing history and/or the attribute information.
Wherein the browsing record comprises at least any one of:
-the total content of the feed information page viewed by the user: for example, if the user browses one or more feed information pages, all the content on the information page is taken as the browsing record;
-a browsing scope of the feed information page browsed by the user: for example, if the user only browses the first half of the content on the feed information page, the part of the content is taken as the browsing record;
-browsing time of the feed information page browsed by the user: for example, if the user spends 3 minutes browsing a certain feed information page, the browsing time is taken as the browsing record; further, the interest point of the user may be determined according to the browsing time, for example, if the browsing time of the user exceeds the average browsing time, the user is considered to be interested in the feed information page, and therefore, more search recommendation sequences may be provided subsequently, and if the browsing time of the user is less than the average browsing time, even less than the fastest browsing threshold, the user is considered to be not interested in the feed information page, and therefore, a small number of search recommendation sequences may be provided subsequently, and even no search sequence is recommended based on the feed information page;
-frequency of browsing of the feed information page browsed by the user: the browsing frequency can be counted according to the browsing times, the browsing interruption times and the like of the user when browsing the feed information page, and the reading habit of the user can be analyzed according to the browsing frequency, so that a recommended search sequence more conforming to the user requirements can be provided. For example, if the user browses a feed information page for a large number of times and browses a small number of interruption times, the user is indicated to be used for immersive reading, and therefore a few and precise recommended search sequence can be provided subsequently; if the user browses the feed information page for a plurality of browsing times and browsing interruption times are large, the user frequently jumps out of the feed information page to obtain other information, and therefore more recommended search sequences can be provided subsequently to guide the user to read;
-association of the user's currently viewed content with historically viewed content: wherein the association includes time association, topic association, entity association, etc., and the determining device 2 may analyze the browsing interest of the user according to the association information, for example, determine the recommended search sequence according to the association information related to the current browsing content and the daily use in the historical browsing.
The attribute information includes, but is not limited to, age, gender, occupation, hobbies, points of interest, and the like.
The determining means 2 may first determine one or more candidate search recommendation sequences corresponding to a feed information page according to the feed information page; screening the candidate recommended search sequences by combining the browsing records of the user and/or the attribute information of the user to determine the search recommended sequences; alternatively, the determining device 2 may determine one or more search recommendation sequences corresponding to the feed information page directly according to the browsing history of the user and/or the attribute information of the user, in combination with the content of the feed information page.
The providing means 3 provides the search recommendation sequence to the user.
Specifically, the providing device 3 may provide the search recommendation sequence to the user within the content of the feed information page or outside the content of the feed information page (e.g., at the end of an article, at a side bar of an article, etc.) based on one or more providing manners. For example, the providing device 3 may determine a presentation format (e.g., a text format, a multimedia format), a presentation position, and the like for the search recommendation sequence based on a predetermined providing manner, a providing manner selected or preferred by the user, a layout of a current feed information page, a category, a semantic, and the like of the search recommendation sequence, so as to provide the search recommendation sequence to the user.
As shown in fig. 5(1), the determined search recommendation sequences "tomato", "bitter gourd" and "potato" are provided to the user in the form of a picture link below the feed article.
Preferably, the providing device 3 comprises a presentation determining unit (not shown) and a sequence providing unit (not shown). Specifically, the presentation determining unit determines a presentation form corresponding to the search recommendation sequence according to the search recommendation sequence; and the sequence providing unit provides the search recommendation sequence to the user according to the presentation form.
The presentation determining unit may determine the presentation form corresponding to the search recommendation sequence according to one or more information of content, length (e.g., a search sequence including 2 characters or a search sequence including 10 characters), type (e.g., text type, multimedia type), determination manner (e.g., determined according to a keyword, determined according to associated information, determined in combination with a browsing history of the user and/or attribute information of the user, etc.), and the like of the search recommendation sequence. The presentation form includes, but is not limited to, whether multimedia is presented, a presentation position, a sorting manner, and the like.
Then, the sequence providing unit provides the search recommendation sequence to the user in the determined presentation form according to the presentation form.
For example, if the determined search recommendation sequence is a noun in the feed article determined according to the keyword in the feed article, the search recommendation sequence may be provided to the user in a manner of highlighting or underlining the feed information page directly, as shown in fig. 6, after the noun "NVIDIA" in the feed article is determined as the search recommendation sequence, the noun "NVIDIA" may be highlighted, and the user may click the word directly to perform a search; if the determined search recommendation sequence is the related information of the feed information page, the search recommendation sequence may be provided below the feed information page, or provided below the related entity of the related information, and so on, as shown in fig. 7, after determining that one or more pieces of related information "read people still," is the search recommendation sequence, the related information is presented below the feed information page to be provided to the user.
Or, for example, if the search recommendation sequence is text information, the search recommendation sequence may be converted into a multimedia format according to the content of the search recommendation sequence for presentation; on the contrary, if the search recommendation sequence is multimedia content, the key information of the search recommendation sequence can be extracted to be converted into text information for displaying and the like.
Alternatively, for example, a suitable presentation position on the current page may be determined according to the length of the search recommendation sequence, and the like.
More preferably, the presentation determining unit may extract multimedia identification information corresponding to the search sequence according to one or more related contents corresponding to the search recommendation sequence; and determining a display form corresponding to the search recommendation sequence according to the multimedia identification information.
Specifically, the presentation determining unit extracts multimedia identification information corresponding to the search sequence according to semantics corresponding to the search recommendation sequence, included multimedia information, corresponding topic information, corresponding description information, and the like; the multimedia identification information can be directly extracted from the multimedia information contained in the search recommendation sequence, and can also be obtained by searching corresponding multimedia information according to the semantics or topics of the search recommendation sequence.
For example, if the search recommendation sequence is "bitter gourd", a picture of "bitter gourd" may be searched from a search engine to serve as the multimedia identification information; and main description information of the balsam pear can be searched out and used as the multimedia identification information.
Here, the multimedia identification information corresponding to each recommended search sequence may be one or more pieces of multimedia identification information, for example, if there are 3 pictures under the content corresponding to a certain recommended search sequence, all of the 3 pictures may be used as the multimedia identification information. In addition, the multimedia identification information includes, but is not limited to, multimedia information such as pictures and videos, and also includes text information such as keyword descriptions.
Then, the presentation determining unit determines, as a part of the presentation form, a presentation position, a presentation arrangement, and the like corresponding to the search recommendation sequence including the multimedia identification information.
FIG. 2 illustrates a schematic diagram of a recommendation device for providing recommendation information to a user in accordance with an aspect of the present invention; the recommendation device comprises an acquisition device 1 ', a determination device 2', a providing device 3 ', a selection device 4', a retrieval device 5 'and a result presentation device 6'. Specifically, the acquiring means 1' acquires one or more feed information sheets provided to the user; the determining device 2' determines one or more search recommendation sequences corresponding to the feed information page according to the feed information page; the providing means 3' provides the search recommendation sequence to the user; the selection means 4' obtains one or more search sequences selected by the user from the search recommendation sequences; said retrieving means 5' retrieves said search sequence; the result presentation means 6' present the search results corresponding to the search recommendation sequence to the user.
The acquiring device 1 ', the determining device 2 ', and the providing device 3 ' are the same as or similar to the devices shown in fig. 1, and therefore are not described herein again and are included herein by reference.
The selection means 4' obtains one or more search sequences selected by the user from the search recommendation sequences.
Specifically, the selection device 4' directly interacts with the user to obtain one or more search sequences selected by the user from the search recommendation sequences by clicking, touching, inputting, and the like; alternatively, the selection means 4' interacts with other devices capable of providing the selected search sequences to obtain one or more search sequences selected by the user from the search recommendation sequences.
For example, as shown in fig. 5(2), the providing device 3' provides "bitter gourd", "tomato" and "potato" as the search recommendation sequence, and the user clicks "bitter gourd" to indicate "bitter gourd" as the search sequence.
The retrieval means 5' retrieves the search sequence.
In particular, the retrieving means 5' performs a search query on the search sequence in a predetermined search engine to determine one or more search results corresponding to the search sequence.
Preferably, the retrieving means 5' may retrieve one or more search sequences in a feed information database. Here, the search means 5' searches the search sequence in a feed information database corresponding to the feed information page or in another feed information database, and takes one or more feed information pages retrieved as the search result corresponding to the search sequence. It will be appreciated by those skilled in the art that the retrieved feed information page may be a title, content, multimedia description, etc. that contains some or all of the information in the search sequence.
Alternatively, the retrieving means 5' may preferably retrieve one or more search sequences in one or more general search engines. Here, the retrieval device 5' retrieves the search sequence in one or more general search engines to obtain a search result corresponding to the search sequence. Those skilled in the art will appreciate that the retrieved search results may be feed pages of information or may be non-feed pages of information such as ordinary web pages.
It will be appreciated by those skilled in the art that the search may be performed in the feed information database alone, in the general search engine alone, or in a combination of the feed information database and the general search engine.
The result presentation device 6' presents the search result corresponding to the search recommendation sequence to the user.
Specifically, the result presentation device 6' presents the search result corresponding to the search recommendation sequence to the user on a page such as a floating page or a newly created result page according to a predetermined presentation manner. Here, the result displaying device 6' may display the search results in a classified manner according to the categories of the search results, for example, a feed information page and a general search result page are displayed separately; or the search results can be sorted according to the weight information corresponding to the search results and displayed in sequence according to the weight.
For example, as shown in fig. 5(2), when the user selects "balsam pear", the retrieving means 5' retrieves the contents such as "balsam pear _ hundred degree encyclopedia" from the general search engine, and retrieves the feed information page such as "ultra-strong slimming belly rapidly eliminates the lower abdomen fat lump" from the feed information database; then, the result displaying device 6' displays the two types of information on the result page in sequence and in a classified manner.
Preferably, the recommendation apparatus further comprises feed recommendation means (not shown); the feed recommending device determines one or more pieces of recommended feed information corresponding to the user according to the feed information page and the search sequence; the result presentation device 6' presents the search result corresponding to the search sequence to the user, where the search result includes the recommended feed information.
Specifically, the feed recommendation device may directly search the search sequence in a feed information database; and then, screening the search results of the search sequence according to the information such as categories, keywords, user reading time and the like corresponding to the feed information page to determine one or more pieces of recommended feed information corresponding to the user. Or, the feed recommending apparatus may directly interact with the retrieving apparatus 5 'to first obtain one or more search results retrieved by the retrieving apparatus 5'; and then, screening the search results of the search sequence according to the information such as categories, keywords, user reading time and the like corresponding to the feed information page to determine one or more pieces of recommended feed information corresponding to the user.
Here, preferably, the recommended feed information may include a feed interface, and the user may subscribe to content corresponding to the feed interface. The feed interface is an aggregated page of feeds about a certain topic, for example, if the search vocabulary is "balsam pear", the feed interface of "balsam pear" is an entry of all feed articles about balsam pear.
Then, the result presentation device 6' presents the search result corresponding to the search sequence to the user, wherein the search result includes the recommended feed information, so that the user is directed to a feed page, and the feed and the search are fused with each other.
For example, as shown in fig. 5(3), the result displaying device 6' may include a recommended feed information page for ultra-strong weight-reducing method to rapidly eliminate belly fat and flesh, and the user may click "focus" on the upper left corner of the page to focus on the topic of the recommended feed information page; after paying attention, the user can view various types of information about the topic, as shown in fig. 5(4), which shows various types of weight-reducing feed information pages pushed after paying attention to the topic of "weight-reducing".
FIG. 3 illustrates a flow diagram of a method for providing recommendation information to a user in accordance with another aspect of the subject invention. Specifically, in step S1, the recommendation device obtains one or more feed information pages provided to the user; in step S2, the recommendation device determines one or more search recommendation sequences corresponding to the feed information page according to the feed information page; in step S3, the recommendation apparatus provides the search recommendation sequence to the user.
In step S1, the recommendation device obtains one or more feed information pages provided to the user.
In step S1, the recommendation device obtains one or more feed information pages provided to the user by invoking subscription settings, operation information, and the like of the user; or, in step S1, the recommendation device directly obtains the display interface of the user, and uses the feed information on the display interface as one or more feed information pages provided to the user; alternatively, in step S1, the recommendation device obtains one or more feed information pages provided to the user by interacting with a server or other device capable of providing the above information.
The feed information page refers to a specific information flow or a consultation flow which is obtained by a user through subscription, attention and other modes and is pushed by a server; the obtained feed information pages include, but are not limited to, a complete feed information page expanded after clicking, a title or an abstract of an unchecked feed information page, various feed information pages already read or to be read, and the like.
In step S2, the recommendation device determines one or more search recommendation sequences corresponding to the feed information page according to the feed information page.
Specifically, in step S2, the recommendation device analyzes the content of the feed information page, and determines one or more search recommendation sequences corresponding to the feed information page based on the direct content or the associated content of the feed information page, for example, by extracting one or more keywords included in the feed information page, or determining one or more associated information associated with the information content in the feed information page.
As shown in fig. 5(1), the feed information page is that the "vegetables" topic "of the family vegetables can help your fat meat to go away from you, and the determined search recommendation sequences are" tomato "," balsam pear "and" potato ".
Preferably, in step S2, the recommendation device may determine one or more search recommendation sequences corresponding to the feed information page according to one or more keywords contained in the feed information page.
Specifically, in step S2, the recommendation apparatus extracts a specific noun, a popular vocabulary, contained in the feed information page; or counting the content in the feed information page to determine words with the frequency exceeding a preset threshold value in the feed information page; or analyzing the title, the picture name or description, the video name or description and the like in the feed information page to determine the core words in the feed information page; then, the recommendation device takes one or more of the above words as one or more keywords contained in the feed information page.
The specific nouns comprise one or more entity nouns such as names of people, articles, commodities, trademarks, works and the like; the popular vocabulary includes but is not limited to various network popular words, network phrases, and the like.
In step S2, the recommendation device may directly take the keyword as the search recommendation sequence; the keywords can also be weighted and sorted according to the occurrence frequency, the determining mode and the like of the keywords, so that the keywords with weighted values larger than a certain threshold value or with sorted values before a preset name are used as the search recommendation sequence after weighted sorting; or, according to the sorting sequence after the weighted sorting, providing the keywords as the search recommendation sequence to the user.
For example, if a proper noun such as "AMD", "NVIDIA", "INTEL" appears in the feed information page, the above-mentioned proper noun may be used as the keyword; then, the recommendation device may take all of the above nouns as the search recommendation sequence; the occurrence frequency of the nouns may also be counted, and if the occurrence frequency of "NVIDIA" is the highest, only "NVIDIA" is used as the search recommendation sequence, as shown in fig. 6.
Alternatively, in step S2, the recommendation device may determine one or more search recommendation sequences corresponding to the feed information page according to one or more association information associated with the information content in the feed information page.
Specifically, in step S2, the recommendation device may analyze the information content in the feed information page to obtain one or more associated information associated with the information content; wherein the associated information includes, but is not limited to, associated entities, associated content, associated questions, historical search records of other users, and the like. The associated information may be obtained based on big data statistics (e.g., statistics of consecutive search records of others), classification information within the database, and the like.
Then, the recommendation device may directly use the associated information as the search recommendation sequence; or performing weighted sorting on the associated information according to the occurrence frequency, the determination mode and the like of the associated information, so that the associated information with a weighted value larger than a certain threshold value or with a sorting value before a predetermined name after weighted sorting is used as the search recommendation sequence; or, according to the sorting order after the weighted sorting, providing the associated information as the search recommendation sequence to the user.
More preferably, the association information includes at least any one of:
-an associated entity to which the information content in the feed information page is associated: the recommendation device may obtain the associated entity associated with the information content by retrieving a database storing the associated relationship and the like according to an entity, a topic and the like included in the information content in the feed information page. For example, if the feed information page includes an entity "NVIDIA", then "AMD" may be the associated entity; if the feed information page contains the theme of 'weight loss', the balsam pear, the tea and the like can be used as related entities related to the 'weight loss'.
-associated topics to which the information content in the feed information page is associated: the recommendation device may obtain the related topic associated with the information content by querying the classified information associated with the entity or the topic, querying the browsing record associated with the feed information page, and the like according to the entity, the topic, and the like included in the feed information page. For example, if the information content of the feed information page is "these family dishes can help your fat go away from you", then "quickly eliminate the lower abdomen proud meat" can be taken as the related topic.
-an association problem associated with the information content in the feed information page: the recommendation device may obtain the associated question associated with the information content in the feed information page by querying the question associated with the content according to the existing question, entity, subject, etc. contained in the feed information page. For example, as shown in fig. 7, if the information content of the feed information page is "the smartest dog all over the world, do you want one? "related questions of the golden retriever mentioned in the article, such as" how much money is one for golden retriever? "as a matter of relevance. Here, preferably, the recommendation device may determine whether to use one or more "association questions" as the association information based on one or more specific character or word triggers, for example, only if "why", "are included in the feed information page? When a specific word is "or the like," the association problem "is used as the association information.
-historical search records of other users to which the feed information page corresponds: if the other users of the feed information page perform a search within a predetermined time threshold by using one or more custom or recommended query sequences after reading the information page, the query sequence or the search result clicked by the user can be used as the related information of the feed information page. The recommendation device may obtain the query sequence, the queried search result, the query time, and the like of the other user by calling the historical search records of the other user, so as to determine the association information based on the above contents.
It will be understood by those skilled in the art that, in step S2, the recommendation device may determine the search recommendation sequence separately according to any one of the above manners, and then provide the determined search recommendation sequence to the user; the two modes can be combined, and the search recommendation sequences determined by the two modes can be provided to the user at the same time.
Preferably, in step S2, the recommending apparatus may determine one or more search recommendation sequences corresponding to the feed information page according to the feed information page, in combination with the browsing history of the user and/or the attribute information of the user.
Specifically, in step S2, the recommendation device obtains the browsing history of the user and/or the attribute information of the user, and then determines one or more search recommendation sequences corresponding to the feed information page according to the feed information page on the basis of combining the browsing history and/or the attribute information.
Wherein the browsing record comprises at least any one of:
-the total content of the feed information page viewed by the user: for example, if the user browses one or more feed information pages, all the content on the information page is taken as the browsing record;
-a browsing scope of the feed information page browsed by the user: for example, if the user only browses the first half of the content on the feed information page, the content is taken as the browsing record;
-the browsing time of the feed information page browsed by the user: for example, if the user spends 3 minutes browsing a certain feed information page, the browsing time is taken as the browsing record; further, the interest point of the user may be determined according to the browsing time, for example, if the browsing time of the user exceeds the average browsing time, the user is considered to be interested in the feed information page, and therefore, more search recommendation sequences may be provided subsequently, and if the browsing time of the user is less than the average browsing time, even less than the fastest browsing threshold, the user is considered to be not interested in the feed information page, and therefore, a small number of search recommendation sequences may be provided subsequently, and even no search sequence is recommended based on the feed information page;
-frequency of browsing of the feed information page browsed by the user: the browsing frequency can be counted according to the browsing times, the browsing interruption times and the like of the user when browsing the feed information page, and the reading habit of the user can be analyzed according to the browsing frequency, so that a recommended search sequence more meeting the user requirements can be provided. For example, if the user browses a feed information page for a large number of times and browses a small number of interruption times, the user is indicated to be used for immersive reading, and therefore a few and precise recommended search sequence can be provided subsequently; if the user browses the feed information page for a plurality of browsing times and browsing interruption times are large, the user frequently jumps out of the feed information page to obtain other information, and therefore more recommended search sequences can be provided subsequently to guide the user to read;
-association of the user's currently viewed content with historically viewed content: wherein the association includes time association, topic association, entity association, etc., and the recommending device may analyze the browsing interest of the user according to the association information, for example, determine the recommended search sequence according to the association information related to the current browsing content and the daily use in the history browsing.
The attribute information includes, but is not limited to, age, gender, occupation, hobbies, points of interest, and the like.
In step S2, the recommendation device may first determine one or more candidate search recommendation sequences corresponding to a feed information page according to the feed information page; screening the candidate recommended search sequence by combining the browsing record of the user and/or the attribute information of the user to determine the search recommended sequence; alternatively, in step S2, the recommendation device may determine one or more search recommendation sequences corresponding to the feed information page directly according to the browsing history of the user and/or the attribute information of the user, in combination with the content of the feed information page.
In step S3, the recommendation apparatus provides the search recommendation sequence to the user.
Specifically, in step S3, the recommendation device may provide the search recommendation sequence to the user within the content of the feed information page or outside the content of the feed information page (e.g., at the end of an article, at an article sidebar, etc.) based on one or more provision manners. For example, in step S3, the recommendation device may determine a presentation format (e.g., a text format, a multimedia format), a presentation position, and the like for the search recommendation sequence based on a predetermined provision manner, a provision manner selected or preferred by the user, a layout of a current feed information page, a category, a semantic, and the like of the search recommendation sequence, so as to provide the search recommendation sequence to the user.
As shown in fig. 5(1), the determined search recommendation sequences "tomato", "bitter gourd" and "potato" are provided to the user in the form of a picture link below the feed article.
Preferably, in step S3, the method includes step S31 (not shown) and step S32 (not shown). Specifically, in step S31, the recommendation device determines, according to the search recommendation sequence, a presentation form corresponding to the search recommendation sequence; in step S32, the recommendation device provides the search recommendation sequence to the user according to the presentation form.
In step S31, the recommendation device may determine the presentation form corresponding to the search recommendation sequence according to one or more information of the content, the length (e.g., a search sequence including 2 characters or a search sequence including 10 characters), the type (e.g., a text type, a multimedia type), the determination manner (e.g., determined according to a keyword, determined according to associated information, determined by combining browsing history of the user and/or attribute information of the user, etc.), and the like of the search recommendation sequence. The presentation form includes, but is not limited to, whether multimedia is presented, a presentation position, a sorting manner, and the like.
Then, in step S32, the recommendation apparatus provides the search recommendation sequence to the user in the determined presentation form according to the presentation form.
For example, if the determined search recommendation sequence is a noun in the feed article determined according to the keyword in the feed article, the search recommendation sequence may be provided to the user in a manner of highlighting or underlining the feed information page directly, as shown in fig. 6, after the noun "NVIDIA" in the feed article is determined as the search recommendation sequence, the noun "NVIDIA" may be highlighted, and the user may click the word directly to perform a search; if the determined search recommendation sequence is the related information of the feed information page, the search recommendation sequence may be provided below the feed information page, or provided below the related entity of the related information, as shown in fig. 7, and after determining that one or more pieces of related information "read already known" are still asked "are the search recommendation sequence, the related information is provided to the user by showing the related information below the feed information page.
Or, for example, if the search recommendation sequence is text information, the search recommendation sequence may be converted into a multimedia format according to the content of the search recommendation sequence for presentation; on the contrary, if the search recommendation sequence is multimedia content, the key information of the search recommendation sequence can be extracted to be converted into text information for displaying and the like.
Alternatively, for example, a suitable presentation position on the current page may be determined according to the length of the search recommendation sequence, and the like.
More preferably, in step S31, the recommendation device may extract multimedia identification information corresponding to the search recommendation sequence according to one or more related contents corresponding to the search recommendation sequence; and determining a display form corresponding to the search recommendation sequence according to the multimedia identification information.
Specifically, in step S31, the recommendation device extracts multimedia identification information corresponding to the search recommendation sequence according to the semantics corresponding to the search recommendation sequence, the included multimedia information, the corresponding topic information, the corresponding description information, and the like; the multimedia identification information can be directly extracted from the multimedia information contained in the search recommendation sequence, and can also be obtained by searching corresponding multimedia information according to the semantics or topics of the search recommendation sequence.
For example, if the search recommendation sequence is "bitter gourd", a picture of "bitter gourd" may be searched from a search engine to serve as the multimedia identification information; and main description information of the balsam pear can be searched out and used as the multimedia identification information.
Here, the multimedia identification information corresponding to each recommended search sequence may be one or more pieces of multimedia identification information, for example, if there are 3 pictures under the content corresponding to a certain recommended search sequence, all of the 3 pictures may be used as the multimedia identification information. In addition, the multimedia identification information includes, but is not limited to, multimedia information such as pictures and videos, and also includes text information such as keyword descriptions.
Then, in step S31, the recommendation device uses the multimedia identification information as a part of the presentation format, and determines the content, such as the presentation position, the presentation arrangement, and the like, corresponding to the search recommendation sequence including the multimedia identification information.
Fig. 4 is a flowchart of a method for providing recommendation information to a user according to a preferred embodiment of the present invention. Specifically, in step S1', the recommendation device obtains one or more feed information pages provided to the user; in step S2', the recommendation device determines one or more search recommendation sequences corresponding to the feed information page according to the feed information page; in step S3', the recommendation device provides the search recommendation sequence to the user; in step S4', the recommendation device acquires one or more search sequences selected by the user from the search recommendation sequences; in step S5', the recommendation device retrieves the search sequence; in step S6', the recommendation device presents the search result corresponding to the search recommendation sequence to the user.
The steps S1 ', S2 ', and S3 ' are the same as or similar to those shown in fig. 3, and are not repeated herein and are included herein by way of reference.
In step S4', the recommendation device acquires one or more search sequences selected by the user from the search recommendation sequences.
Specifically, in step S4', the recommendation device directly interacts with the user to obtain one or more search sequences selected by the user from the search recommendation sequences by clicking, touching, inputting, or the like; alternatively, in step S4', the recommendation device interacts with other devices capable of providing the selected search sequence to obtain one or more search sequences selected by the user from the search recommendation sequences.
For example, as shown in fig. 5(2), the step S3' provides "balsam pear", "tomato" and "potato" as the search recommendation sequence, and the user clicks "balsam pear" to indicate "balsam pear" as the search sequence.
In step S5', the recommendation device retrieves the search sequence.
Specifically, in step S5', the recommendation device performs a search query on the search sequence in a predetermined search engine to determine one or more search results corresponding to the search sequence.
Preferably, in step S5', the recommendation device may retrieve one or more search sequences in the feed information database. Here, in step S5', the recommendation apparatus searches the search sequence in a feed information database corresponding to the feed information page or in another feed information database, and takes one or more feed information pages retrieved as the search results corresponding to the search sequence. It will be appreciated by those skilled in the art that the retrieved feed information page may be a title, content, multimedia description, etc. that contains some or all of the information in the search sequence.
Alternatively, preferably, in step S5', the recommendation device may retrieve one or more search sequences in one or more general search engines. Here, the recommendation device retrieves the search sequence in one or more general search engines to obtain a search result corresponding to the search sequence. Those skilled in the art will appreciate that the retrieved search results may be feed pages of information or may be non-feed pages of information such as ordinary web pages.
It will be appreciated by those skilled in the art that the search may be performed in the feed information database alone, in the general search engine alone, or in a combination of the feed information database and the general search engine.
In step S6', the recommendation device presents the search result corresponding to the search recommendation sequence to the user.
Specifically, in step S6', the recommendation device presents the search result corresponding to the search recommendation sequence to the user in a predetermined presentation manner on a page such as a hover page or a new result page. Here, the recommendation device may display the search results in a classified manner according to the category of the search result, for example, a feed information page and a general search result page are displayed separately; or the search results can be sorted according to the weight information corresponding to the search results and displayed in sequence according to the weight.
For example, as shown in fig. 5(2), when the user selects "balsam pear", the recommendation device retrieves the contents such as "balsam pear _ hundred degree encyclopedia" in the general search engine, and retrieves a feed information page such as "ultra-strong weight-reducing method thin belly quickly eliminates the fat on lower belly" in the feed information database; and then, the recommendation equipment displays the two types of information on a result page in sequence and in a classified manner.
Preferably, the method further comprises step S7' (not shown); in step S7', the recommending apparatus determines one or more recommended feed information corresponding to the user according to the feed information page and the search sequence; in step S6', the recommendation device presents a search result corresponding to the search sequence to the user, where the search result includes the recommended feed information.
Specifically, in step S6', the recommendation device may directly search the search sequence in a feed information database; and then, screening the search results of the search sequence according to the information such as categories, keywords, user reading time and the like corresponding to the feed information page to determine one or more pieces of recommended feed information corresponding to the user. Alternatively, in step S6 ', the recommendation device may directly interact with step S5 ', and first obtain one or more search results retrieved in step S5 '; and then, screening the search results of the search sequence according to the information such as categories, keywords, user reading time and the like corresponding to the feed information page to determine one or more pieces of recommended feed information corresponding to the user.
Here, preferably, the recommended feed information may include a feed interface, and the user may subscribe to content corresponding to the feed interface. The feed interface is an aggregated page of feeds about a certain topic, for example, if the search vocabulary is "balsam pear", the feed interface of "balsam pear" is an entry of all feed articles about balsam pear.
Then, in step S6', the recommendation device presents the search result corresponding to the search sequence to the user, where the search result includes the recommended feed information, so as to guide the user to a feed page, thereby implementing mutual fusion of feed and search.
For example, as shown in fig. 5(3), in step S6', the recommendation device may include a recommendation feed information page for a super-strong weight-reducing method to quickly eliminate the belly fat, and the user may click "focus" on the upper left corner of the page to focus on the topic of the recommendation feed information page; after paying attention, the user can view various types of information about the topic, as shown in fig. 5(4), which shows various types of diet feed information pages pushed after paying attention to the topic of "diet".
It should be noted that the present invention may be implemented in software and/or in a combination of software and hardware, for example, as an Application Specific Integrated Circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present invention may be executed by a processor to implement the steps or functions described above. Also, the software programs (including associated data structures) of the present invention can be stored in a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. Further, some of the steps or functions of the present invention may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.
In addition, some of the present invention can be applied as a computer program product, such as computer program instructions, which when executed by a computer, can invoke or provide the method and/or technical solution according to the present invention through the operation of the computer. Program instructions which invoke the methods of the present invention may be stored on a fixed or removable recording medium and/or transmitted via a data stream on a broadcast or other signal-bearing medium and/or stored within a working memory of a computer device operating in accordance with the program instructions. An embodiment according to the invention herein comprises an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to perform a method and/or solution according to embodiments of the invention as described above.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the apparatus claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Claims (12)

1. A method of providing recommendation information to a user, wherein the method comprises the steps of:
a, acquiring one or more feed information pages on a display interface of a user;
b, determining one or more search recommendation sequences corresponding to the feed information page according to the feed information page;
c, providing the search recommendation sequence to the user on the feed information page;
-obtaining one or more search sequences selected by the user from the search recommendation sequences;
-retrieving the search sequence;
-determining one or more recommended feed information corresponding to said user from said feed information page and said search sequence;
displaying a search result corresponding to the search sequence to the user, wherein the search result comprises the recommended feed information;
the step b comprises at least any one of the following:
-determining one or more search recommendation sequences corresponding to the feed information page based on one or more keywords contained in the feed information page;
-determining one or more search recommendation sequences corresponding to the feed information page in dependence on one or more association information with which the information content in the feed information page is associated.
2. The method of claim 1, wherein the association information comprises at least any one of:
-an association entity to which the information content in the feed information page is associated;
-associated topics to which the information content in the feed information page is associated;
-an association problem associated with the information content in the feed information page;
-historical search records of other users to which the feed information page corresponds.
3. The method according to claim 1 or 2, wherein said step b comprises:
-determining one or more search recommendation sequences corresponding to said feed information page in connection with said user's browsing history and/or said user's attribute information, based on said feed information page.
4. The method according to claim 1 or 2, wherein said step c comprises:
c1 determining the display form corresponding to the search recommendation sequence according to the search recommendation sequence;
-providing the search recommendation sequence to the user in accordance with the presentation form.
5. The method of claim 4, wherein the step c1 includes:
-extracting multimedia identification information corresponding to said search sequence according to one or more related contents corresponding to said search recommendation sequence;
-determining a presentation form corresponding to the search recommendation sequence based on the multimedia identification information.
6. The method of claim 1, wherein the retrieving the search sequence comprises at least any one of:
-retrieving one or more search sequences in a feed information database;
-retrieving, in one or more general search engines, one or more search sequences.
7. A recommendation apparatus for providing recommendation information to a user, wherein the apparatus comprises:
the acquisition device is used for acquiring one or more feed information pages on a display interface of a user;
determining means for determining one or more search recommendation sequences corresponding to the feed information page according to the feed information page;
providing means for providing the search recommendation sequence to the user on the feed information page;
selecting means for obtaining one or more search sequences selected by the user from the search recommendation sequences;
retrieving means for retrieving the search sequence;
a feed recommending device for determining one or more recommended feed information corresponding to the user according to the feed information page and the search sequence;
the result display device is used for displaying the search result corresponding to the search sequence to the user, wherein the search result comprises the recommended feed information;
the determining means is for at least any one of:
-determining one or more search recommendation sequences corresponding to the feed information page based on one or more keywords contained in the feed information page;
-determining one or more search recommendation sequences corresponding to the feed information page in dependence on one or more association information with which the information content in the feed information page is associated.
8. The recommendation device of claim 7, wherein the association information includes at least any one of:
-an association entity to which the information content in the feed information page is associated;
-associated topics to which the information content in the feed information page is associated;
-an association problem associated with the information content in the feed information page;
-historical search records of other users to which the feed information page corresponds.
9. The recommendation device of claim 7 or 8, wherein the determining means is for:
-determining one or more search recommendation sequences corresponding to said feed information page in connection with said user's browsing history and/or said user's attribute information, based on said feed information page.
10. The recommendation apparatus according to claim 7 or 8, wherein the providing means includes:
the display determining unit is used for determining a display form corresponding to the search recommendation sequence according to the search recommendation sequence;
and the sequence providing unit is used for providing the search recommendation sequence to the user according to the presentation form.
11. The recommendation device of claim 10, wherein the presentation determination unit is to:
-extracting multimedia identification information corresponding to said search sequence according to one or more related contents corresponding to said search recommendation sequence;
-determining a presentation form corresponding to the search recommendation sequence based on the multimedia identification information.
12. The recommendation device of claim 7, wherein the retrieving means is for at least any one of:
-retrieving one or more search sequences in a feed information database;
-retrieving, in one or more general search engines, one or more search sequences.
CN201611170648.9A 2016-12-16 2016-12-16 Method and equipment for providing recommendation information for user Active CN108205545B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611170648.9A CN108205545B (en) 2016-12-16 2016-12-16 Method and equipment for providing recommendation information for user

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611170648.9A CN108205545B (en) 2016-12-16 2016-12-16 Method and equipment for providing recommendation information for user

Publications (2)

Publication Number Publication Date
CN108205545A CN108205545A (en) 2018-06-26
CN108205545B true CN108205545B (en) 2022-06-10

Family

ID=62602182

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611170648.9A Active CN108205545B (en) 2016-12-16 2016-12-16 Method and equipment for providing recommendation information for user

Country Status (1)

Country Link
CN (1) CN108205545B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109522473B (en) * 2018-09-30 2021-08-27 南京尚网网络科技有限公司 Method for recommending associated information, terminal and server thereof
CN110502299B (en) * 2019-08-12 2021-05-14 南京大众书网图书文化有限公司 Method and equipment for providing novel information
CN113297468A (en) * 2020-07-30 2021-08-24 阿里巴巴集团控股有限公司 Information display method, information recommendation method, information processing method, information recommendation system and electronic equipment
CN113032680A (en) * 2021-04-19 2021-06-25 南京点橙互联网科技有限公司 Recommendation method based on user subscription hotword mode

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102314508A (en) * 2010-09-01 2012-01-11 微软公司 Network feed content
CN103020057A (en) * 2011-09-21 2013-04-03 幻音科技(深圳)有限公司 Method and device for displaying RSS (really simple syndication) abstract by windowing
CN103389972A (en) * 2013-07-26 2013-11-13 Tcl集团股份有限公司 Method and device for obtaining text based on really simple syndication (RSS)
CN103399891A (en) * 2013-07-22 2013-11-20 百度在线网络技术(北京)有限公司 Method, device and system for automatic recommendation of network content
CN103442001A (en) * 2013-08-22 2013-12-11 百度在线网络技术(北京)有限公司 Information recommendation method, device and server
CN103458047A (en) * 2013-09-13 2013-12-18 北京奇虎科技有限公司 Method for showing interesting information and subscribed information of users and browser
CN103714088A (en) * 2012-10-09 2014-04-09 深圳市世纪光速信息技术有限公司 Method for acquiring search terms, server and method and system for recommending search terms
CN103729359A (en) * 2012-10-12 2014-04-16 阿里巴巴集团控股有限公司 Method and system for recommending search terms
CN104199938A (en) * 2014-09-09 2014-12-10 北京师范大学 RSS-based agricultural land information sending method and system
CN104636334A (en) * 2013-11-06 2015-05-20 阿里巴巴集团控股有限公司 Keyword recommending method and device
CN105069168A (en) * 2015-08-28 2015-11-18 百度在线网络技术(北京)有限公司 Search word recommendation method and apparatus
CN105303394A (en) * 2014-06-12 2016-02-03 紫格网络科技(上海)有限公司 Network advertisement placement method and system based on web search engine
CN105512282A (en) * 2015-12-07 2016-04-20 小米科技有限责任公司 Notification method and device and terminal
CN105589852A (en) * 2014-10-20 2016-05-18 阿里巴巴集团控股有限公司 Information recommendation method and device
CN106055591A (en) * 2016-05-23 2016-10-26 北京金山安全软件有限公司 Weather pushing method and device

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104978368A (en) * 2014-04-14 2015-10-14 百度在线网络技术(北京)有限公司 Method and device used for providing recommendation information
CN103984740B (en) * 2014-05-23 2016-01-06 合一网络技术(北京)有限公司 Based on the method and system that the retrieved page of combination tag shows

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102314508A (en) * 2010-09-01 2012-01-11 微软公司 Network feed content
CN103020057A (en) * 2011-09-21 2013-04-03 幻音科技(深圳)有限公司 Method and device for displaying RSS (really simple syndication) abstract by windowing
CN103714088A (en) * 2012-10-09 2014-04-09 深圳市世纪光速信息技术有限公司 Method for acquiring search terms, server and method and system for recommending search terms
CN103729359A (en) * 2012-10-12 2014-04-16 阿里巴巴集团控股有限公司 Method and system for recommending search terms
CN103399891A (en) * 2013-07-22 2013-11-20 百度在线网络技术(北京)有限公司 Method, device and system for automatic recommendation of network content
CN103389972A (en) * 2013-07-26 2013-11-13 Tcl集团股份有限公司 Method and device for obtaining text based on really simple syndication (RSS)
CN103442001A (en) * 2013-08-22 2013-12-11 百度在线网络技术(北京)有限公司 Information recommendation method, device and server
CN103458047A (en) * 2013-09-13 2013-12-18 北京奇虎科技有限公司 Method for showing interesting information and subscribed information of users and browser
CN104636334A (en) * 2013-11-06 2015-05-20 阿里巴巴集团控股有限公司 Keyword recommending method and device
CN105303394A (en) * 2014-06-12 2016-02-03 紫格网络科技(上海)有限公司 Network advertisement placement method and system based on web search engine
CN104199938A (en) * 2014-09-09 2014-12-10 北京师范大学 RSS-based agricultural land information sending method and system
CN105589852A (en) * 2014-10-20 2016-05-18 阿里巴巴集团控股有限公司 Information recommendation method and device
CN105069168A (en) * 2015-08-28 2015-11-18 百度在线网络技术(北京)有限公司 Search word recommendation method and apparatus
CN105512282A (en) * 2015-12-07 2016-04-20 小米科技有限责任公司 Notification method and device and terminal
CN106055591A (en) * 2016-05-23 2016-10-26 北京金山安全软件有限公司 Weather pushing method and device

Also Published As

Publication number Publication date
CN108205545A (en) 2018-06-26

Similar Documents

Publication Publication Date Title
US9792550B2 (en) Methods and apparatus for providing information of interest to one or more users
KR101637237B1 (en) Systems and methods for providing advanced search result page content
US20170372204A1 (en) Methods and apparatus for providing information of interest to one or more users
US9355185B2 (en) Infinite browse
US8676732B2 (en) Methods and apparatus for providing information of interest to one or more users
KR101361992B1 (en) Systems and methods for providing advanced search result page content
US7860878B2 (en) Prioritizing media assets for publication
JP4637969B1 (en) Properly understand the intent of web pages and user preferences, and recommend the best information in real time
CA2823408C (en) Methods and apparatus for providing information of interest to one or more users
CN108205545B (en) Method and equipment for providing recommendation information for user
US20140143224A1 (en) Method and system for generating search results from a user-selected area
WO2010014082A1 (en) Method and apparatus for relating datasets by using semantic vectors and keyword analyses
US20140379719A1 (en) System and method for tagging and searching documents
EP3529714A1 (en) Animated snippets for search results
CN106682049B (en) Topic display system and topic display method
CN104008180A (en) Association method of structural data with picture, association device thereof
CN108763369B (en) Video searching method and device
WO2021111400A1 (en) System and method for enabling a search platform to users
CN104881447A (en) Searching method and device
US9152698B1 (en) Substitute term identification based on over-represented terms identification
Redondo-García et al. Augmenting TV newscasts via entity expansion
Porselvi et al. Survey on web page visual summarization
CN110147488B (en) Page content processing method, processing device, computing equipment and storage medium
KR101776806B1 (en) Method for context based keyword search and system for the same
LAIC et al. Automatic image annotation

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
GR01 Patent grant
GR01 Patent grant