CN105589852B - A kind of method and apparatus of information recommendation - Google Patents
A kind of method and apparatus of information recommendation Download PDFInfo
- Publication number
- CN105589852B CN105589852B CN201410556988.XA CN201410556988A CN105589852B CN 105589852 B CN105589852 B CN 105589852B CN 201410556988 A CN201410556988 A CN 201410556988A CN 105589852 B CN105589852 B CN 105589852B
- Authority
- CN
- China
- Prior art keywords
- information
- user
- points
- information points
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000010354 integration Effects 0.000 claims description 20
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000009191 jumping Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- BUGYDGFZZOZRHP-UHFFFAOYSA-N memantine Chemical compound C1C(C2)CC3(C)CC1(C)CC2(N)C3 BUGYDGFZZOZRHP-UHFFFAOYSA-N 0.000 description 2
- 229960004640 memantine Drugs 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 235000019633 pungent taste Nutrition 0.000 description 2
- 241000256837 Apidae Species 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 108010050062 mutacin GS-5 Proteins 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of method and apparatus of information recommendation, obtain the resource information recommendation resources bank local as information point deposit from each application server；Related information point is determined for the information point in the recommendation resources bank, to establish distributed content network；According to the distributed content network, the related information point for the information point paid close attention to intelligent terminal recommended user.The present invention can be realized to be recommended to the intersection that user carries out resource information, resource information type i.e. recommended to the user is not limited to the resource information type that user is browsing, user can directly select and browse the resource information of recommendation, without entering back into accordingly after returning to desktop using the resource information for wanting to see is searched by hand, user is facilitated to carry out cross-thread operation in intelligent terminal.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to the technical field of computer application, in particular to an information recommendation method and device.
[ background of the invention ]
With the rapid development of integrated circuit technology and network technology, smart terminals have had powerful processing capabilities, and smart terminals such as tablet computers and smart phones have become important tools for users to work, live and entertain.
Currently, mainstream systems of intelligent terminals, such as android and IOS systems, adopt a top-down tree directory structure and a Dock desktop layout, as shown in fig. 1. The structure is convenient to manage, query and execute from top to bottom. For example, if a user wants to see the "transformers 4", the user can open a video application from a desktop and find the "transformers 4" after entering a movie directory. However, this structure also has this extremely serious drawback: if the user wants to view the information about a main car in the movie while watching transformers 4, the user needs to exit the video application and return to the desktop, and then open a browser or a news application from the desktop to find the information about the car. That is, the user must go through such a complicated process when he wants to perform the cross-thread operation.
[ summary of the invention ]
In view of this, the present invention provides an information recommendation method and apparatus, so as to facilitate a user to perform a cross-thread operation on an intelligent terminal.
The specific technical scheme is as follows:
a method for recommending information, obtain the resource information from every application server as the information point to store in the local recommended resource library;
determining associated information points aiming at the information points in the recommended resource library so as to establish a distributed content network;
and recommending the associated information points of the information points concerned by the user to the intelligent terminal according to the distributed content network.
According to a preferred embodiment of the present invention, determining the associated information point for the information point in the recommended resource pool includes:
establishing a label and a label type of a current information point;
respectively retrieving related information points of each label under the corresponding label type in the recommended resource library;
and determining the relevant information points meeting the preset requirements as the associated information points of the current information points.
According to a preferred embodiment of the present invention, determining a relevant information point meeting a preset requirement as a relevant information point of a current information point includes:
determining a desired presentation score for each relevant information point, the desired presentation score being determined by an information quality score and a user characteristic score;
and determining the relevant information points with the expected display scores meeting the preset requirements as the associated information points of the current information points.
According to a preferred embodiment of the present invention, the establishing of the tag and the tag type of the current information point includes:
selecting a label and a label type determined by a user for a current information point; or,
and acquiring a corresponding search result when the subject word of the current targeted information point is taken as a search keyword, selecting the subject word of the search result as a label, and taking the type of the search result or the attribute of the subject word of the search result as the type of the label.
According to a preferred embodiment of the present invention, the information quality score is determined by at least one of an update time of the related information point, an information browsing amount, and a tag hotness.
According to a preferred embodiment of the present invention, the user feature score is determined by at least one of a degree of matching between the related information point and the user attribute, a degree of matching between the related information point and the user preference resource type, and a degree of matching between the related information point and the user preference label.
According to a preferred embodiment of the present invention, the information points focused by the user include: the information point the user is browsing.
According to a preferred embodiment of the invention, the method further comprises: and displaying the recommended associated information points on the interface which is browsed by the user in a card-form structure module.
According to a preferred embodiment of the invention, the method further comprises: and if one information point is selected from the recommended associated information points, jumping to the application corresponding to the selected information point and displaying the content of the selected information point.
The invention also provides an information recommendation device, which comprises:
the resource integration module is used for acquiring resource information from each application server as information points and storing the information points into a local recommended resource library;
the network establishing module is used for determining associated information points aiming at the information points in the recommended resource library so as to establish a distributed content network;
and the information recommending module is used for recommending the associated information points of the information points concerned by the user to the intelligent terminal according to the distributed content network.
According to a preferred embodiment of the present invention, the network establishing module specifically includes:
the label establishing submodule is used for establishing the label and the label type of the current information point;
the tag retrieval submodule is used for respectively retrieving the related information points of the tags under the corresponding tag types in the recommended resource library;
and the information screening unit is used for determining the relevant information points meeting the preset requirements as the relevant information points of the current information points.
According to a preferred embodiment of the present invention, the information filtering unit specifically includes:
a score determining unit for determining a desired presentation score of each of the related information points, the desired presentation score being determined by the information quality score and the user characteristic score;
and the information screening unit is used for determining the relevant information points with the expected display scores meeting the preset requirements as the relevant information points of the current information points.
According to a preferred embodiment of the present invention, the tag establishing subunit is specifically configured to select a tag and a tag type that are determined by a user for a current information point; or, the method is specifically configured to obtain a corresponding search result when the subject word of the current targeted information point is used as the search keyword, select the subject word of the search result as the tag, and use the type of the search result or the attribute of the subject word of the search result as the tag type.
According to a preferred embodiment of the present invention, the information quality score is determined by at least one of an update time of the related information point, an information browsing amount, and a tag hotness.
According to a preferred embodiment of the present invention, the user feature score is determined by at least one of a degree of matching between the related information point and the user attribute, a degree of matching between the related information point and the user preference resource type, and a degree of matching between the related information point and the user preference label.
According to a preferred embodiment of the present invention, the information points focused by the user include: the information point the user is browsing.
According to a preferred embodiment of the present invention, the related information points recommended by the information recommendation module are displayed on the interface being browsed by the user by a structure module in the form of a card.
According to the technical scheme, the resource information is acquired from each application server as the information point, cross recommendation of the resource information to the user can be achieved, namely the resource information recommended to the user is not limited to the resource information concerned by the user and can also comprise the resource information from other application servers.
[ description of the drawings ]
FIG. 1 is a schematic diagram of a tree directory structure adopted in a Dock desktop layout in the prior art;
FIG. 2 is a schematic diagram of a system upon which embodiments of the present invention are based;
FIG. 3 is a schematic structural representation of a card format according to an embodiment of the present invention;
FIG. 4 is a flowchart of a method for recommending information according to an embodiment of the present invention;
fig. 5 is a flowchart of a method for establishing a distributed content network according to an embodiment of the present invention;
FIG. 6 is a diagram of an example of a distributed content network provided by an embodiment of the present invention;
fig. 7 is a structural diagram of an information recommendation apparatus according to an embodiment of the present invention.
[ detailed description ] embodiments
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
The implementation of the present invention can be based on a system as shown in fig. 2, in which a resource integration server is the core of the present invention, there is an interface between the resource integration server and each application server, and resource information (the resource information may include various resources in the application server, for example, resources used by the application server for recommendation) is obtained from each application server and stored in a local recommended resource library. And the application provider needing to perform the cross resource recommendation opens an interface of the application server to the resource integration server and provides the resource for performing the cross resource recommendation to the resource integration server. By cross-bar resource recommendation is meant implementing resource recommendation between different applications, for example recommending news-like information in video applications. In addition, the recommended resource library can also be used for desktop resource recommendation or screen locking resource recommendation and the like.
The Dock desktop layout has been existing for a long time, people begin to slowly tire on such content structure, and in view of this situation, a structure module in a card form is proposed, that is, each data block is presented in a card-form structure on an interface of an intelligent terminal, for example, as shown in fig. 3. Generally, one type of resource information is displayed on one card-shaped module, and a plurality of card-shaped sub-modules may be included on one card-shaped module to display each resource information. The structure can well integrate and display the resource information, and is convenient for users to browse and operate. If the method is applied to such an application scenario, the resource integration server may be disposed in a card-type resource server, where the card-type resource server is used to push resource information displayed by a structure module in the form of a card to the intelligent terminal. Of course, the method and apparatus provided by the present invention may not be limited to this application scenario.
The core idea of the invention is mainly that resource information associated with the resource information being browsed by the user is recommended to the user through the resource integration server, the recommended resource information is not limited to the type corresponding to the resource information being browsed, the associated resource information is likely to be the associated resource information which the user wants to see, and the user can directly select and browse the recommended resource information. The method and the device for realizing the resource information recommendation are realized at a resource integration server side, and for convenience of description, in the embodiment of the invention, each resource information is called an information point, wherein the information point can be represented by a subject word of the resource information, a summary of the resource information, a keyword extracted from the resource information, or the like. The information point related in the invention is associated with the corresponding application, that is, the user can jump to the application corresponding to the information point by clicking the information point, and further load the content of the information point in the application, that is, jump to the application corresponding to the information point and present the content corresponding to the information point.
Fig. 4 is a flowchart of a method for recommending information according to an embodiment of the present invention, as shown in fig. 4, the method mainly includes two stages: a step of establishing a distributed content network in step 401 and a step of recommending associated information points of information points concerned by a user according to the distributed content network in step 402.
The distributed content network is a network formed by information points with incidence relations, the information points are from a recommended resource library, namely, after the incidence information points of the information points in the recommended resource library are determined, the information points in the recommended resource library form the distributed content network. The distributed content network may be pre-established or may be established in real time as the user browses resource information of an application. The establishment of the distributed content network is described in detail below with reference first to fig. 5.
As shown in fig. 5, the resource integration server performs the following steps for information points in the recommended resource library to determine associated information points of the information points, respectively, where the information point currently targeted is referred to as a current information point:
step 501: and establishing the label and the label type of the current information point.
In this step, the label established for the current information point may be a keyword capable of expressing the subject of the current information point or related to the current information point, and taking "transformers 4 trailer" as an example, the label and the type of the label may include:
[ VIDEO ] transformers 1
[ VIDEO ] transformers 2
[ VIDEO ] transformers 3
[ GUIDE ] Michael & BEI
[ actor ] Mark Walberg
[ actor ] plum ice
'cartoon' Optimus prime
[ caricature ] bumblebee
[ ACOUSTIC STRIP ] Battle Cry
[ AUTOMOBILE ] Chevrolet Corvette
[ AUTOMOBILE ] WAQI GS5
[ AUTOMOBILE ] Faraday 458SPECIALEE
Wherein, the content in [ is the label type, and the content after [ is the label.
The label and the label type can be established in the following two ways:
the first mode is as follows: and manually establishing a label mode, namely manually printing a label and a label type related to the information point aiming at the current information point. This is an easy but labor intensive process.
The second mode is as follows: and acquiring a corresponding search result when the subject term of the current information point is taken as a search keyword, selecting the subject term of the search result as a label, and taking the type of the search result or the attribute of the subject term of the search result as the type of the label. For example, the subject word of "memantine 4 trailer" is "memantine 4", which is used as a search keyword to search, and the first search results in the search results are selected, and the subject words and labels of the search results are extracted, assuming that the first search results in the search results are: when a video webpage of the transformers 1, a cartoon webpage of the Optimus prime, an online singing webpage of the BattleCry of the acoustic tape and the like are watched, the subject words of the transformers 1, the Optimus prime, the BattleCry and the like can be extracted from the videos, the cartoon and the acoustic tape as labels, and the corresponding label types are respectively video, cartoon, acoustic tape and the like.
Of course, either of the above two modes may be adopted, or both of the above two modes may be adopted at the same time.
Step 502: and respectively searching related information points of each label under the corresponding label type in the recommended resource library.
In the retrieval process, information points hit by each tag under the corresponding tag type are determined as related information points, and the hit strategy can adopt a mode of calculating the similarity between the tags and the information points to select the information points of which the similarity meets the preset requirement, for example, the similarity is greater than a preset threshold value, or the similarities are ranked in the first several. In this case, when each tag hits in an information point, it is preferable to keep the tag type of the tag identical to the type of the hit information point. For example, the labels "transformers 1", "michael-shel", "Battle Cry" and "chevrolet Corvette" have the relevant information points shown in table 1:
TABLE 1
Step 503: a desired presentation score is determined for each of the relevant information points, the desired presentation score being determined by the information quality score and the user characteristic score.
The expected showing score of the related information point reflects the possibility that the user expects the related information point to be subjected to associated showing. The information quality score represents the quality status of the relevant information point, and can be determined by at least one of information updating time, information browsing amount, label popularity and the like. Preferably, the information quality score may be obtained by performing weighted calculation on an information update time score, an information browsing amount score, a tag popularity score, and the like. Wherein the information update time score can be determined by the update time of the related information point, the score is higher when the update time is more recent, and the score is lower when the information update time is longer. The information browsing amount score can be determined by the browsing amount of the related information points, wherein the score is higher when the browsing amount is higher, and the score is lower when the browsing amount is lower. The label popularity score can be determined by the search quantity of the label corresponding to the related information point, wherein the higher the search quantity of the corresponding label is, the higher the score is, and conversely, the lower the search quantity of the corresponding label is, the lower the score is.
The user characteristic score represents the matching degree of the related information point and the user, and can be determined by at least one of the matching degree of the related information point and the user attribute, the matching degree of the related information point and the user favorite resource type, the matching degree of the related information point and the user favorite label and the like. Preferably, the user characteristic score may be obtained by performing weighted calculation on the matching degree scores. The matching degree between the related information point and the user attribute may be determined by the browsing frequency or duration of the user of the attribute to the related information point, for example, assuming that the age of a user is 25 years and the gender is female, the browsing frequency or duration of the user attribute to the related information point by a female in the age stage of 20 years to 30 years can determine the matching degree between the related information point and the user attribute, although the user attribute is not limited to the age and the gender, and may also be, for example, region, academic calendar, occupation, and the like. The matching degree of the related information points and the user favorite resource types is determined by the frequency or duration of the resource types of the related information points browsed by the user, and the more the frequency is or the longer the duration is, the higher the matching degree is. The matching degree of the related information points and the favorite labels of the user is determined by the browsing frequency or the browsing time of the labels corresponding to the related information points browsed by the user, and the more the frequency is or the longer the time is, the higher the matching degree is.
Then, after the information quality score and the user characteristic score of the relevant information point are weighted and calculated, the expected showing score of the relevant information point is obtained.
Step 504: and determining the relevant information points with the expected display scores meeting the preset requirements as the associated information points of the current information points.
After step 503, a plurality of relevant information points of the current information point are determined, and in step 504, the relevant information points are further filtered out from the relevant information points. For example, the related information points whose expected display score is greater than or equal to the preset threshold may be determined as the related information points of the current information point, or a preset number of related information points whose expected display score is arranged in front may be determined as the related information points of the current information point.
In the above steps 503 and 504, the relevant information point of the current information point is selected by determining the expected showing score of the relevant information point, which is only one implementation manner given by the present invention, based on the inventive concept of the present invention, the relevant information point of the current information point can also be selected from the relevant information points retrieved in the step 502 by other various manners, for example, all the relevant information points retrieved in the step 502 can be selected as the relevant information point of the current information point, a requirement for the relevant information point can also be set, and the relevant information point is determined by the set requirement, such as setting an upper limit of the number of the relevant information points, or setting a tag type limit, etc., which are not listed here.
After the above steps, the associated information point of the current information point, that is, the information network of an information point, is determined. And each information point in the recommendation resource library has associated information points, so that a network structure, namely a distributed content network, is formed. It should be noted that the phase of establishing the distributed content network may be continuous, and as the resource information in the recommended resource library is updated, the establishment process is executed again, and the distributed content network is updated accordingly.
Thus, the resource information on the intelligent terminal may not be a top-down tree directory structure, but a distributed network structure, for example, as shown in fig. 6, the nodes in fig. 6 represent information points, and the arrow points to represent association relationships, that is, the arrow points to associated information points, it should be noted that fig. 6 only intercepts a segment of the distributed content network. The distributed content network may be through a distributed content network or may be associated with users, for example, the distributed content network may be associated with user preferences, one for each distributed content network.
After the distributed content network is established for the user of the intelligent terminal, when the user is browsing a certain information point, step 402 is executed to recommend the associated information point of the currently browsed information point in the distributed content network on the interface of the currently browsed information point. Step 402 may be actively executed after it is detected that the user browses a certain information point, or may be triggered by the user to execute, for example, the user clicks a relevant function button, or stays on the information point for more than a set time period, and the like.
Since the associated information points of the information points in the distributed content network are not limited to the same type of information points, the cross resource recommendation is realized. For example, the user may recommend the related information points "transformers 4 trailer", "transformers 4 movie ticket", "ice plum ice 4 model", "chevrolet covette" and "trumpet GS 5" on the same interface while browsing the certificate of transformers 4. If the user wants to view the related information of the scholarland, the user can select 'scholarland covette', at this time, the user automatically jumps to an application corresponding to the related information point, such as a browser, and the browser directly shows the content of the related information point selected by the user. The user does not need to return to the desktop, and then re-enter the browser to manually find the related information of the Chevrolet.
In addition, when the recommended resource is displayed, the related information points may also be displayed in a card-form structure module, for example, the same type of related information points are displayed on one card-form structure module, and the same card-form module may further include a plurality of card-form sub-modules to display the related information points. When the user selects the relevant information point for browsing, a selection manner such as clicking, sliding, or long pressing the structure module in the form of the corresponding card may be adopted, which is not limited in this respect.
Through the above flows of fig. 4 and fig. 5, the process of the resource integration server recommending the resource information point associated with the resource information being browsed by the user to the user in the present invention is described in detail. In the present invention, the resource information recommended to the user by the resource integration server is not limited to the resource information associated with the resource information that the user is browsing, and may be resource information associated with the resource information concerned by any user, for example, the resource information concerned by the user may include: the resource information customized by the user and interested in the user, the resource information from the application concerned by the user, and the like can actively recommend the information points concerned by the user and the associated information points to the user based on the user trigger, for example, the recommended content is displayed on a desktop or a lock screen interface or a specific software interface. The detailed recommendation process is substantially identical to the process described above with reference to fig. 4 and 5, and will not be described in detail herein.
The above is a method flow provided by an embodiment of the present invention, and a corresponding apparatus is shown in fig. 7, where the apparatus is disposed at the resource integration server side, and may include: the system comprises a resource integration module 00, a network establishment module 10 and an information recommendation module 20.
The resource integration module 00 is responsible for acquiring recommended resources from each application server as information points and storing the information points into a local recommended resource library. Here, there is an interface between the resource integration server and each application server, and an application provider that needs to perform cross resource recommendation opens an interface of its own application server to the resource integration server, and provides resources for performing cross resource recommendation to the resource integration server.
The network establishment module 10 is responsible for determining associated information points for information points in the recommended resource pool, thereby establishing a distributed content network. The distributed content network is a network formed by information points with incidence relation, the information points are from a recommended resource library, namely, after the incidence information points of the information points in the recommended resource library are determined, the information points in the recommended resource library form the distributed content network.
Specifically, the network establishing module 10 may specifically include a tag establishing sub-module 11, a tag retrieving sub-module 12, and an information filtering sub-module 13.
The label establishing submodule 11 is responsible for establishing the label and the label type of the current information point. The label established here is a keyword which can express the topic of the information point aimed at currently or is related to the information point aimed at currently. The tag creation subunit 11 may specifically adopt, but is not limited to, at least one of the following two ways:
the first mode is as follows: and selecting the label and the label type determined by the user for the current information point.
The second mode is as follows: and acquiring a corresponding search result when the subject word of the current targeted information point is taken as a search keyword, selecting the subject word of the search result as a label, and taking the type of the search result or the attribute of the subject word of the search result as the type of the label.
Then the tag retrieval sub-module 12 retrieves the relevant information points of the tags under the corresponding tag types in the recommendation resource library respectively. In the retrieval process, information points hit by each tag under the corresponding tag type are determined as related information points, and the hit strategy can adopt a mode of calculating the similarity between the tags and the information points to select the information points of which the similarity meets the preset requirement, for example, the similarity is greater than a preset threshold value, or the similarities are ranked in the first several. In this case, when each tag hits in an information point, it is preferable to keep the tag type of the tag identical to the type of the hit information point.
The information screening submodule 13 is responsible for determining the relevant information points meeting the preset requirements as the relevant information points of the information points currently aimed at. Specifically, the information filtering submodule 13 may include: a score determination unit 131 and an information filtering unit 132.
The score determining unit 131 is responsible for determining a desired presentation score for each relevant information point, the desired presentation score being determined by the information quality score and the user characteristic score. The expected showing score of the related information point reflects the possibility that the user expects the related information point to be subjected to associated showing. The information quality score represents the quality status of the relevant information point, and can be determined by at least one of information updating time, information browsing amount, label popularity and the like. Preferably, the information quality score may be obtained by performing weighted calculation on an information update time score, an information browsing amount score, a tag popularity score, and the like. Wherein the information update time score can be determined by the update time of the related information point, the score is higher when the update time is more recent, and the score is lower when the information update time is longer. The information browsing amount score can be determined by the browsing amount of the related information points, wherein the score is higher when the browsing amount is higher, and the score is lower when the browsing amount is lower. The label popularity score can be determined by the search quantity of the label corresponding to the related information point, wherein the higher the search quantity of the corresponding label is, the higher the score is, and conversely, the lower the search quantity of the corresponding label is, the lower the score is.
The user characteristic score represents the matching degree of the related information point and the user, and can be determined by at least one of the matching degree of the related information point and the user attribute, the matching degree of the related information point and the user favorite resource type, the matching degree of the related information point and the user favorite label and the like. Preferably, the user characteristic score may be obtained by performing weighted calculation on the matching degree scores. The matching degree between the related information point and the user attribute may be determined by the browsing frequency or duration of the user of the attribute to the related information point, for example, assuming that the age of a user is 25 years and the gender is female, the browsing frequency or duration of the user attribute to the related information point by a female in the age stage of 20 years to 30 years can determine the matching degree between the related information point and the user attribute, although the user attribute is not limited to the age and the gender, and may also be, for example, region, academic calendar, occupation, and the like. The matching degree of the related information points and the user favorite resource types is determined by the frequency or duration of the resource types of the related information points browsed by the user, and the more the frequency is or the longer the duration is, the higher the matching degree is. The matching degree of the related information points and the favorite labels of the user is determined by the browsing frequency or the browsing time of the labels corresponding to the related information points browsed by the user, and the more the frequency is or the longer the time is, the higher the matching degree is.
Then, after the information quality score and the user characteristic score of the relevant information point are weighted and calculated, the expected showing score of the relevant information point is obtained.
The information screening unit 132 is responsible for determining the relevant information points with the expected display scores meeting the preset requirements as the relevant information points of the currently aimed information points. The information filtering unit 132 actually further filters the relevant information points from the relevant information points. For example, the related information points whose expected display score is greater than or equal to the preset threshold may be determined as the related information points of the current information point, or a preset number of related information points whose expected display score is arranged in front may be determined as the related information points of the current information point.
The network establishment module 10 thus determines the information point associated with the current information point, i.e. the information network of an information point. And each information point in the recommendation resource library has associated information points, so that a network structure, namely a distributed content network, is formed. It should be noted that the phase of establishing the distributed content network by the network establishing module 10 may be continuous, and as the resource information in the recommended resource library is updated, the establishing process is executed again, and the distributed content network is updated accordingly.
Then, the information recommending module 20 may recommend the associated information points of the information points concerned by the user to the intelligent terminal according to the distributed content network. Since the associated information points of the information points in the distributed content network are not limited to the same type of information points, the cross resource recommendation is realized. Preferably, the associated information points recommended by the information recommendation module are displayed on an interface which is browsed by the user in a card-form structure module. When the user selects the relevant information point for browsing, a selection manner such as clicking, sliding, or long pressing the structure module in the form of the corresponding card may be adopted, which is not limited in this respect.
The information display recommended by the invention can be applied to intelligent terminals such as tablet computers, smart phones and smart televisions.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (15)
1. A method of information recommendation, performed by a device for resource integration, the method comprising:
acquiring resource information from each application server as information points and storing the information points into a local recommended resource library;
determining associated information points aiming at the information points in the recommended resource library so as to establish a distributed content network;
recommending associated information points of information points concerned by the user to the intelligent terminal according to the distributed content network;
wherein determining associated information points for information points in the recommended resource pool comprises:
establishing a label and a label type of a current information point;
respectively retrieving related information points of each label under the corresponding label type in the recommended resource library;
and determining the relevant information points meeting the preset requirements as the associated information points of the current information points.
2. The method of claim 1, wherein determining relevant information points meeting preset requirements as associated information points of currently aimed information points comprises:
determining a desired presentation score for each relevant information point, the desired presentation score being determined by an information quality score and a user characteristic score;
and determining the relevant information points with the expected display scores meeting the preset requirements as the associated information points of the current information points.
3. The method of claim 1, wherein the establishing the label and the label type of the current information point comprises:
selecting a label and a label type determined by a user for a current information point; or,
and acquiring a corresponding search result when the subject word of the current targeted information point is taken as a search keyword, selecting the subject word of the search result as a label, and taking the type of the search result or the attribute of the subject word of the search result as the type of the label.
4. The method of claim 2, wherein the information quality score is determined by at least one of an update time of the related information point, an information browsing amount, and a tag hot degree.
5. The method of claim 2, wherein the user characteristic score is determined by at least one of a degree of matching of the associated information point to the user attribute, a degree of matching of the associated information point to the user preference resource type, and a degree of matching of the associated information point to the user preference label.
6. The method according to any one of claims 1 to 5, wherein the information points of interest to the user include: the information point the user is browsing.
7. The method of claim 6, further comprising: and displaying the recommended associated information points on the interface which is browsed by the user in a card-form structure module.
8. The method of any one of claims 1 to 5, further comprising: and if one information point is selected from the recommended associated information points, jumping to the application corresponding to the selected information point and displaying the content of the selected information point.
9. An apparatus for information recommendation, provided in a device for resource integration, the apparatus comprising:
the resource integration module is used for acquiring resource information from each application server as information points and storing the information points into a local recommended resource library;
the network establishing module is used for determining associated information points aiming at the information points in the recommended resource library so as to establish a distributed content network;
the information recommendation module is used for recommending the associated information points of the information points concerned by the user to the intelligent terminal according to the distributed content network;
wherein the network establishing module specifically comprises:
the label establishing submodule is used for establishing the label and the label type of the current information point;
the tag retrieval submodule is used for respectively retrieving the related information points of the tags under the corresponding tag types in the recommended resource library;
and the information screening submodule is used for determining the relevant information points meeting the preset requirements as the relevant information points of the current information points.
10. The apparatus according to claim 9, wherein the information filtering sub-module specifically includes:
a score determining unit for determining a desired presentation score of each of the related information points, the desired presentation score being determined by the information quality score and the user characteristic score;
and the information screening unit is used for determining the relevant information points with the expected display scores meeting the preset requirements as the relevant information points of the current information points.
11. The apparatus according to claim 9, wherein the tag creation sub-module is specifically configured to select a tag and a tag type determined by a user for a current information point; or, the method is specifically configured to obtain a corresponding search result when the subject word of the current targeted information point is used as the search keyword, select the subject word of the search result as the tag, and use the type of the search result or the attribute of the subject word of the search result as the tag type.
12. The apparatus of claim 10, wherein the information quality score is determined by at least one of an update time of the related information point, an information browsing amount, and a tag hot degree.
13. The apparatus of claim 10, wherein the user characteristic score is determined by at least one of a degree of matching of the associated information point to the user attribute, a degree of matching of the associated information point to the user preference resource type, and a degree of matching of the associated information point to the user preference label.
14. The apparatus according to any one of claims 9 to 13, wherein the information points of interest to the user comprise: the information point the user is browsing.
15. The apparatus according to claim 14, wherein the associated information points recommended by the information recommendation module are presented on the interface being browsed by the user in a card-form structure module.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410556988.XA CN105589852B (en) | 2014-10-20 | 2014-10-20 | A kind of method and apparatus of information recommendation |
| HK16112434.1A HK1224394A1 (en) | 2014-10-20 | 2016-10-28 | Method and device for recommending information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410556988.XA CN105589852B (en) | 2014-10-20 | 2014-10-20 | A kind of method and apparatus of information recommendation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105589852A CN105589852A (en) | 2016-05-18 |
| CN105589852B true CN105589852B (en) | 2019-09-03 |
Family
ID=55929442
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410556988.XA Active CN105589852B (en) | 2014-10-20 | 2014-10-20 | A kind of method and apparatus of information recommendation |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105589852B (en) |
| HK (1) | HK1224394A1 (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649675A (en) * | 2016-12-14 | 2017-05-10 | 咪咕文化科技有限公司 | Cross-service electronic resource recommendation method and device |
| CN106611045A (en) * | 2016-12-16 | 2017-05-03 | 北京智能管家科技有限公司 | Intelligent interaction method and device and intelligent terminal |
| CN108205545B (en) * | 2016-12-16 | 2022-06-10 | 百度在线网络技术（北京）有限公司 | Method and equipment for providing recommendation information for user |
| CN106649842A (en) * | 2016-12-30 | 2017-05-10 | 上海博泰悦臻电子设备制造有限公司 | Cross recommendation method based on fusion data, system and vehicle machine |
| CN109117443A (en) * | 2017-06-23 | 2019-01-01 | 北京橙鑫数据科技有限公司 | Recommend the method for electronic card, recommend the device and electronic equipment of electronic card |
| US10776415B2 (en) * | 2018-03-14 | 2020-09-15 | Fuji Xerox Co., Ltd. | System and method for visualizing and recommending media content based on sequential context |
| CN109241425B (en) * | 2018-08-31 | 2022-02-18 | 腾讯科技（深圳）有限公司 | Resource recommendation method, device, equipment and storage medium |
| CN110532295A (en) * | 2019-08-01 | 2019-12-03 | 北京三快在线科技有限公司 | A kind of method and device of computer-implemented information processing, information inquiry |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7185001B1 (en) * | 2000-10-04 | 2007-02-27 | Torch Concepts | Systems and methods for document searching and organizing |
| CN103927324A (en) * | 2014-03-13 | 2014-07-16 | 中国联合网络通信集团有限公司 | Method and device for information pushing |
| CN103942270A (en) * | 2014-03-27 | 2014-07-23 | 上海斐讯数据通信技术有限公司 | Method for intelligently recommending application program and mobile terminal |
| CN103997688A (en) * | 2014-04-28 | 2014-08-20 | 小米科技有限责任公司 | Intelligent interaction system, intelligent interaction device and intelligent interaction method |
| CN104102719A (en) * | 2014-07-18 | 2014-10-15 | 百度在线网络技术（北京）有限公司 | Track information pushing method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9542433B2 (en) * | 2012-12-20 | 2017-01-10 | Bank Of America Corporation | Quality assurance checks of access rights in a computing system |
-
2014
- 2014-10-20 CN CN201410556988.XA patent/CN105589852B/en active Active
-
2016
- 2016-10-28 HK HK16112434.1A patent/HK1224394A1/en not_active IP Right Cessation
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7185001B1 (en) * | 2000-10-04 | 2007-02-27 | Torch Concepts | Systems and methods for document searching and organizing |
| CN103927324A (en) * | 2014-03-13 | 2014-07-16 | 中国联合网络通信集团有限公司 | Method and device for information pushing |
| CN103942270A (en) * | 2014-03-27 | 2014-07-23 | 上海斐讯数据通信技术有限公司 | Method for intelligently recommending application program and mobile terminal |
| CN103997688A (en) * | 2014-04-28 | 2014-08-20 | 小米科技有限责任公司 | Intelligent interaction system, intelligent interaction device and intelligent interaction method |
| CN104102719A (en) * | 2014-07-18 | 2014-10-15 | 百度在线网络技术（北京）有限公司 | Track information pushing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| HK1224394A1 (en) | 2017-08-18 |
| CN105589852A (en) | 2016-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105589852B (en) | A kind of method and apparatus of information recommendation | |
| US11907240B2 (en) | Method and system for presenting a search result in a search result card | |
| JP7356206B2 (en) | Content recommendation and display | |
| US20180152767A1 (en) | Providing related objects during playback of video data | |
| US10410125B1 (en) | Artificial intelligence based identification of negative user sentiment in event data | |
| US20180181569A1 (en) | Visual category representation with diverse ranking | |
| US9615136B1 (en) | Video classification | |
| KR102222729B1 (en) | Tagged search result maintenance | |
| WO2016091044A1 (en) | Method, apparatus, system, device and computer storage medium for recommending hot words | |
| KR102111082B1 (en) | Contextualizing knowledge panels | |
| US10410273B1 (en) | Artificial intelligence based identification of item attributes associated with negative user sentiment | |
| CN113079417A (en) | Method, device and equipment for generating bullet screen and storage medium | |
| WO2023020167A1 (en) | Information display method and apparatus, computer device, and storage medium | |
| US20180060427A1 (en) | Navigating a Taxonomy Using Search Queries | |
| US20170287041A1 (en) | Information processing apparatus, information processing method, and information processing program | |
| JP2023162232A (en) | Intelligent systems and methods for visual search queries | |
| CN111125314B (en) | Display method of book query page, electronic device and computer storage medium | |
| CN110929139A (en) | Search recommendation method and device | |
| CN116542737A (en) | Big data processing method and system of cross-border e-commerce platform | |
| JPH11282875A (en) | Information filtering device | |
| CN114329220A (en) | Search result display method and device, computer equipment and storage medium | |
| CN113297406A (en) | Picture searching method and system and electronic equipment | |
| CN115618075A (en) | Method and device for displaying search results | |
| CN113177170A (en) | Comment display method and device and electronic equipment | |
| KR101801134B1 (en) | Method for providing story, and server and computer-readable recording media using the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1224394 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201112 Address after: Room 603, 6 / F, Roche Plaza, 788 Cheung Sha Wan Road, Kowloon, China Patentee after: Zebra smart travel network (Hong Kong) Limited Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Patentee before: Alibaba Group Holding Ltd. |