CN111291265B - Recommendation information generation method and device - Google Patents
Recommendation information generation method and device Download PDFInfo
- Publication number
- CN111291265B CN111291265B CN202010085171.4A CN202010085171A CN111291265B CN 111291265 B CN111291265 B CN 111291265B CN 202010085171 A CN202010085171 A CN 202010085171A CN 111291265 B CN111291265 B CN 111291265B
- Authority
- CN
- China
- Prior art keywords
- attribute
- attribute node
- server
- node
- recommendation 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012545 processing Methods 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 6
- 230000009471 action Effects 0.000 description 24
- 238000004891 communication Methods 0.000 description 19
- 238000010586 diagram Methods 0.000 description 16
- 241000282461 Canis lupus Species 0.000 description 12
- 238000004590 computer program Methods 0.000 description 7
- 238000006243 chemical reaction Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- 230000005236 sound signal Effects 0.000 description 5
- 241000282421 Canidae Species 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 241000284156 Clerodendrum quadriloculare Species 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000003321 amplification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000006837 decompression Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- User Interface Of Digital Computer (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a recommendation information generation method and a device, which aim at the problems of complex user operation and low search efficiency caused by single recommendation information displayed to a user in the prior art, wherein the method comprises the following steps: based on a first keyword in a keyword set sent by a display device, determining a basic attribute node associated with the first keyword, determining a target associated path set corresponding to the basic attribute node, and generating corresponding recommendation information according to attribute values of the basic attribute node and attribute values of associated attribute nodes contained in each target associated path. According to the method and the device for providing the recommendation information, the target associated path set corresponding to the basic attribute node is determined, so that diversified recommendation information can be provided for the user, the operation complexity of the user is reduced, and the user experience is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for generating recommendation information.
Background
With the rise and development of intelligent televisions, video products, services and various life-related services are introduced by means of television terminals, so that more problems are solved for users, and more value is an important point at present.
In the prior art, when a user uses the search function of the smart television, the initial or the pinyin of the search content is required to be input, and then the smart television displays corresponding recommendation information according to keywords input by the user. For example, when the user inputs "WJ" in the movie search area, the recommendation information displayed by the smart tv may be a movie name or a staff name such as "Wu Jing", "Wu Jing".
Obviously, the recommendation information displayed by the intelligent television is single, and after the user selects the corresponding recommendation information, a large number of search results can be generated, so that the user can not conveniently check the recommendation information. The user may need to repeatedly input different keywords to try to obtain the desired target content, so that the search efficiency is reduced, the operation complexity is increased, and the search experience of the user is affected.
It follows that there is a need to devise a new solution to overcome the above drawbacks.
Disclosure of Invention
The application provides a recommendation information generation method and device, which are used for solving the problems of complex user operation and low search efficiency caused by single recommendation information displayed to a user in the prior art.
In a first aspect, the present application provides a recommendation information generation method, including:
The method comprises the steps that a server determines basic attribute nodes associated with first keywords in a knowledge graph based on the first keywords in a keyword set sent by display equipment, wherein the first keywords are keywords with highest searching weights;
the server determines a target association path set corresponding to the basic attribute node, wherein an item of target association path comprises the basic attribute node and an association attribute node connected with the basic attribute node, and the path length between the association attribute node and the basic attribute node does not exceed a preset path length threshold;
and the server generates and sends corresponding recommendation information to the display equipment according to the attribute values of the basic attribute nodes and the attribute values of the associated attribute nodes contained in each target associated path.
In a second aspect, the present application provides a recommendation information generation method, including:
the method comprises the steps that a display device receives a keyword set input by a user;
the display device sends the keyword set to a server, so that the server feeds back a plurality of recommendation information based on the keyword set, wherein letters or initial letters of at least one arbitrary continuous byte combination of at least one recommendation information at least comprise keywords which do not exist in one keyword set;
The display device receives and presents the plurality of recommended information fed back by the server.
In a third aspect, the present application provides a server comprising:
the determining module is used for determining basic attribute nodes associated with first keywords in the knowledge graph based on the first keywords in the keyword set sent by the display equipment, wherein the first keywords are keywords with highest searching weight;
the processing module is used for determining a target association path set corresponding to the basic attribute node, wherein an item of target association path comprises the basic attribute node and an association attribute node connected with the basic attribute node, and the path length between the association attribute node and the basic attribute node does not exceed a preset path length threshold;
the generation module is used for generating and sending corresponding recommendation information to the display equipment according to the attribute values of the basic attribute nodes and the attribute values of the associated attribute nodes contained in each target associated path.
In a fourth aspect, the present application provides a display apparatus comprising:
the receiving module is used for receiving the keyword set input by the user;
the sending module is used for sending the keyword set to a server, so that the server feeds back a plurality of recommendation information based on the keyword set, wherein letters or initial letters of at least one arbitrary continuous byte combination of at least one recommendation information at least comprise keywords which do not exist in one keyword set;
And the presentation template is used for receiving and presenting the plurality of recommendation information fed back by the server.
In the embodiment of the application, a server determines a basic attribute node associated with a first keyword based on the first keyword in a keyword set sent by a display device, then the server determines a target association path set corresponding to the basic attribute node, and then the server generates and sends corresponding recommendation information to the display device according to the attribute values of the basic attribute node and the attribute values of the association attribute nodes contained in each target association path. The server determines a target association path set corresponding to the basic attribute node according to a first keyword in the keyword set sent by the display device, so that the association attribute node related to the first keyword can be obtained, single recommendation information is not presented any more, and diversification of the recommendation information is realized; secondly, the path length between the associated attribute node and the basic attribute node does not exceed a preset path length threshold, so that the search path length is reduced, and the search efficiency is improved; and then, generating and sending corresponding recommendation information to the display equipment according to the attribute values of the basic attribute nodes and the attribute values of the associated attribute nodes, so that diversified recommendation information can be provided for the user, the operation complexity of the user is reduced, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a knowledge graph in an embodiment of the present application;
fig. 2 is a flow chart of a recommendation information generation method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a knowledge graph in an embodiment of the present application;
FIG. 4 is a flowchart illustrating another method for generating recommendation information according to an embodiment of the present application;
FIG. 5 is a user interface when a user does not input keywords in an embodiment of the present application;
FIG. 6 is a user interface presented after a user has entered keywords in an embodiment of the present application;
FIG. 7 is another user interface presented after a user has entered keywords in an embodiment of the present application;
FIG. 8 is a user interface when a user inputs a keyword and the user's focus moves to a fixed recommendation information in an embodiment of the present application;
Fig. 9 is a schematic structural diagram of a server according to an embodiment of the present application;
fig. 10 is a schematic structural diagram of a display device according to an embodiment of the present application;
FIG. 11 is a schematic diagram of another server according to an embodiment of the present application;
fig. 12 is a schematic structural diagram of another display device according to an embodiment of the present application.
Detailed Description
Aiming at the problems of complex operation and low searching efficiency of a user caused by single recommended information displayed to the user in the prior art, in order to improve the searching efficiency and promote the searching experience of the user, the embodiment of the application provides a solution for generating the recommended information based on a knowledge graph.
The scheme is as follows: determining a basic attribute node associated with a first keyword based on the first keyword in the keyword set sent by the display device, wherein the first keyword is the keyword with the highest searching weight; then, determining a target association path set corresponding to the basic attribute node, wherein an item of target association path comprises the basic attribute node and an association attribute node connected with the basic attribute node, and the path length between the association attribute node and the basic attribute node does not exceed a preset path length threshold; and then, generating and sending corresponding recommendation information to the display equipment according to the attribute values of the basic attribute nodes and the attribute values of the associated attribute nodes contained in each target associated path.
In order to enable a person skilled in the art to better understand the technical solutions of the present application, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that, in practical application, for different scenes, a knowledge graph with attribute nodes of corresponding types as a core is constructed, and in the embodiment of the present application, for convenience of description, only a movie searching scene is taken as an example, and a knowledge graph with attribute nodes of movie and television work types as a core is constructed, as shown in fig. 1, where the movie and television work types include but are not limited to movies, television shows, and various technologies.
Referring to fig. 2, in the embodiment of the present application, a flow of generating recommendation information based on a knowledge graph is as follows.
Step S201: the server determines a basic attribute node associated with a first keyword in the knowledge graph based on the first keyword in the keyword set sent by the display device, wherein the first keyword is the keyword with the highest searching weight.
In some embodiments, the server receives the keyword set sent by the display device, and segments each keyword to obtain the first keyword.
In some embodiments, the first keyword refers to a keyword with highest search weight in a keyword set input by a user, and if a plurality of keywords exist in the keyword set input by the user, the keyword with highest search weight may be, but is not limited to:
A1, a first keyword in a keyword set;
a2, searching the keyword with the highest frequency in the keyword set;
a3, a certain keyword in the keyword set designated by the user.
Further, each attribute node included in the knowledge graph has an attribute value, and the attribute value is attribute content of the attribute node, and the attribute content is associated with each keyword, so that based on a first keyword input by a user, the attribute node with the attribute value associated with the first keyword can be found and used as a basic attribute node.
For example, referring to fig. 1, when the keywords input by the user are "QCX", "DY", the first keyword "QCX" in the keyword set, that is, the keyword having the highest search weight is "QCX", and the basic attribute node "Qu Chuxiao (actor)" associated with "QCX" is determined in the knowledge graph based on the first keyword "QCX".
For another example, referring to fig. 1, when the keywords inputted by the user are "WJ", "DY", "DZ", it is known from the history search that the keyword with the highest search frequency is "WJ", that is, the keyword with the highest search weight is "WJ", and the basic attribute node "Wu Jing (director)", "Wu Jing (actor)", which is associated with "WJ", is determined in the knowledge map based on the first keyword "WJ".
As another example, referring to fig. 1, when the keywords inputted by the user are "WJ", "ZL", the keyword "ZL", that is, the keyword having the highest search weight is "ZJ", and the basic attribute node "warwolf (movie)" associated with "ZL" is determined in the knowledge graph based on the first keyword "ZL".
Step S202: the server determines a target association path set corresponding to the basic attribute node, wherein an item of target association path comprises the basic attribute node and an association attribute node connected with the basic attribute node, and the path length between the association attribute node and the basic attribute node does not exceed a preset path length threshold.
In the embodiment of the application, the preset path length threshold can be preset or determined according to the number of keywords in the keyword set input by the user.
For example, the path length threshold is preset to be 2, or when the keywords input by the user are "QCX", "DY", the path length threshold is set to be 2.
Specifically, in the embodiment of the present application, step S202 may include the following steps:
b1: and the server determines each associated attribute node with the path length not exceeding a preset path length threshold from the base attribute node in the knowledge graph.
For example, referring to fig. 1, when the basic attribute node is "Qu Chuxiao (actor)", and the preset path length threshold is 2, the associated attribute nodes having a path length not exceeding 2 with "Qu Chuxiao (actor)" are "wandering earth (movie)", "Guo Fan (director)", "Wu Jing (actor)", "action (tag)", "chinese (language)", "2019 (time)", "science fiction (tag)", "adventure (tag)", "Li Guangjie (actor)".
B2: and screening out the associated attribute nodes with the search heat meeting the preset conditions from the obtained associated attribute nodes by the server.
Specifically, B2 includes, but is not limited to, the following two implementations:
the first implementation mode: and the server screens out the associated attribute nodes associated with other keywords in the keyword set from the obtained associated attribute nodes.
For example, referring to fig. 1, when the keywords input by the user are "QCX", "DY", the server screens out the association attribute nodes "wandering earth (movie)" associated with "DY" among the obtained association attribute nodes "wandering earth (movie)", "Guo Fan (director)", "Wu Jing (actor)", "action (tag)", "chinese (language)", "2019 (time)", "science fiction (tag)", "adventure (tag)", "Li Guangjie (actor)".
The second implementation mode: and the server screens out the associated attribute nodes with the search frequency reaching a preset search frequency threshold in the appointed historical time from the obtained associated attribute nodes.
For example, referring to fig. 3, when the keywords input by the user are "QCX", "DY", the server screens out the associated attribute nodes "wandering earth (movie)", "action (tag)", "chinese (language)", "2019 (time)", "science fiction (tag)", "adventure (tag)", "Li Guangjie (actor)", and "action (tag)", which have the search frequency reached the preset search frequency threshold 2000 in the last three days, among the obtained associated attribute nodes "wandering earth (movie)", "Guo Fan (director)", "Wu Jing (actor)", "action (tag)", "Wu Jing (actor)".
In the embodiment of the present application, when B2 is executed, the first implementation manner and the second implementation manner may be executed in any one or in combination.
B3: and the server directly or indirectly associates the basic attribute nodes with each screened associated attribute node to generate corresponding target associated paths.
Specifically, the association path of an item may include a base attribute node, an association attribute node connected to the base attribute node, and a relationship between the base attribute node and the association attribute node.
For example, referring to fig. 3, the "Qu Chuxiao (actor)" is directly or indirectly associated with each of the selected association attribute nodes "wandering earth (movie)", "action (tag)", "Wu Jing (actor)", the "Qu Chuxiao (actor)" is directly associated with "wandering earth (movie)", the corresponding target association path 1{ "Qu Chuxiao (actor)", (starburst) ", wandering earth (movie)", the "Qu Chuxiao (actor)", and "Wu Jing (actor)", the target association path 2{ "Qu Chuxiao (actor)" (starburst) "," Wu Jing (actor) ", the" Qu Chuxiao (actor) ", and" action (tag) ", the target association path 3{" Qu Chuxiao (actor) "(starburst)", and the "action (tag)", are generated.
B4: the server obtains a corresponding target association path set based on each obtained target association path.
For example, referring to fig. 3, the server obtains a target associated path set as a target associated path 1, a target associated path 2, and a target associated path 3 based on the obtained target associated path 1, target associated path 2, and target associated path 3.
Step S203: and the server generates and sends corresponding recommendation information to the display equipment according to the attribute values of the basic attribute nodes and the attribute values of the associated attribute nodes contained in each target associated path.
In the embodiment of the application, the attribute names of the associated attribute nodes, the relationships between the basic attribute nodes and the associated attribute nodes and the relationships between the associated attribute nodes can also be used as components of the recommendation information, but not all the relationships can be used as components of the recommendation information, for example, the relationship 'belonging label', 'belonging time', 'belonging language', and the like can not be used as components of the recommendation information.
For example, referring to fig. 1, assuming that the target association path is { "warwolf (movie)" (belonging to tag) "action (tag)" }, determining that the basic attribute node is "warwolf (movie)", and the associated attribute node is "action (tag)", the server may generate recommendation information according to the attribute value "warwolf" of the basic attribute node and the attribute value "action" of the associated attribute node: the warwolf acts.
In the embodiment of the application, the server generates corresponding recommendation information according to the attribute values of the basic attribute nodes and the attribute values of the associated attribute nodes contained in each target associated path, including but not limited to the following two implementation modes:
The first implementation mode: the server determines basic attribute nodes and each associated attribute node contained in each target associated path, and directly generates corresponding recommendation information based on attribute values of the basic attribute nodes and the associated attribute nodes according to the determination sequence of the basic attribute nodes and each associated attribute node.
For example, the server determines that the basic attribute node is "Qu Chuxiao (actor)", the associated attribute node is "wandering earth (movie)", in the target association path 1{ "Qu Chuxiao (actor)" (lead actor) ", the attribute value" wandering earth "of the associated attribute node is" movie ", the relationship" lead actor "is based on the attribute value" Qu Chuxiao "of the basic attribute node, and the recommendation information can be generated according to the determination order of" Qu Chuxiao (actor) "," wandering earth (movie) ", the attribute value" wandering earth "of the associated attribute node, the attribute name" movie "of the associated attribute node: qu Chuxiao the earth.
The second implementation mode: the server generates and presents corresponding recommendation information according to the attribute value of the basic attribute node and the attribute value of the associated attribute node contained in any one target associated path in each target associated path, and specifically comprises the following steps:
The server determines basic attribute nodes and each associated attribute node contained in any target associated path;
the server performs the following operations for the base attribute node and each associated attribute node respectively:
the server calculates the intimacy between the basic attribute node and an associated attribute node according to the duty ratio of the same adjacent attribute node in each adjacent attribute node of the basic attribute node and the associated attribute node;
the server determines the presentation sequence of each associated attribute node according to the intimacy between the basic attribute node and each associated attribute node;
and the server generates recommendation information corresponding to any one target association path according to the presentation sequence based on the attribute values of the basic attribute nodes and each association attribute node.
In the embodiment of the application, the following formula can be adopted to calculate the affinity ID (i, j) between the basic attribute node and each associated attribute node,
wherein i represents a basic attribute node, j represents an associated attribute node, and n i The number of adjacent attribute nodes is equal to the number of adjacent attribute nodes of the base attribute node, r (i) is the number of adjacent attribute nodes of the associated attribute node, and r (i). Andr (j) is the number of adjacent attribute nodes in the adjacent attribute nodes of i and j.
For example, referring to fig. 3, the target association path 2 is { "Qu Chuxiao (actor)" (lead) "wandering earth (movie)" (lead) "Wu Jing (actor)") }, and the basic attribute nodes "Qu Chuxiao (actor)", the association attribute nodes "wandering earth (movie)", "Wu Jing (actor)") are included in the target association path 2;
then, since the number of adjacent nodes of "Qu Chuxiao (actor)" is 1, the number of adjacent nodes of "wandering earth (movie)" is 10, the number of common adjacent nodes of "Qu Chuxiao (actor)" and "wandering earth (movie)" is 0, then the affinity of "Qu Chuxiao (actor)" and "wandering earth (movie)" is 1/9, and at the same time, since the number of adjacent nodes of "Wu Jing (actor)" is 2, the number of common adjacent nodes of "Qu Chuxiao (actor)" and "Wu Jing (actor)" is 1, then the affinity of "Qu Chuxiao (actor)" and "Wu Jing (actor)" is 2;
next, the presentation order of the associated attribute nodes is determined to be "Wu Jing (actor)", "wandering earth (movie)", based on the affinity 1/9 of "Qu Chuxiao (actor)", and "wandering earth (movie)", and the affinity 2 of "Qu Chuxiao (actor)", and "Wu Jing (actor)";
Then, the recommended information corresponding to the target association route 2 is generated based on the attribute value "Qu Chuxiao", the attribute value "wandering earth", the attribute value "Wu Jing" in the presentation order "Wu Jing (actor)", "wandering earth (movie)": qu Chuxiao Wu Jing the earth.
As another example, referring to fig. 3, the target association path 3 is { "Qu Chuxiao (actor)" (director) "(tag)" action (tag) "}, and the basic attribute nodes" Qu Chuxiao (actor) ", the associated attribute nodes" streamer "(movie)", and "action (tag)") are specified to be included in the target association path 3;
then, since the number of adjacent nodes of "Qu Chuxiao (actor)" is 1, the number of adjacent nodes of "wander earth (movie)" is 10, the number of common adjacent nodes of "Qu Chuxiao (actor)" and "wander earth (movie)" is 0, then the affinity of "Qu Chuxiao (actor)" and "wander earth (movie)" is 1/9, and at the same time, since the number of adjacent nodes of "action (tag)" is 2, the number of common adjacent nodes of "Qu Chuxiao (actor)" and "action (tag)" is 1, then the affinity of "Qu Chuxiao (actor)" and "action (tag)" is 2;
Next, the presentation order of the associated attribute nodes is determined to be "action (label)", "wandering earth (movie)", based on the affinity 1/9 of "Qu Chuxiao (actor)", and "wandering earth (movie)", and the affinity 2 of "Qu Chuxiao (actor)", and "action (label)";
then, the recommended information corresponding to the target-related path 2 is generated based on the attribute value "Qu Chuxiao", the attribute value "wandering earth", and the attribute value "action" in the presentation order "action (tag)", "wandering earth (movie)": qu Chuxiao act on the planet earth.
Further, after generating the corresponding recommendation information according to the attribute values of the basic attribute nodes and the attribute values of the associated attribute nodes included in each target associated path, the server may determine the recommendation display order of each recommendation information by using, but not limited to, the following two implementation manners:
the first implementation mode: the server determines the recommendation display sequence of each recommendation information according to the sequence from the small path length to the large path length of each target association path, and sends each recommendation information and the recommendation display sequence to the display device.
For example, the path length of the target association path 1 is 2, the path length of the target association path 2 is 3, the path length of the target association path 3 is 3, and the server determines the recommendation display order of each recommendation information according to the order from the small to the large of the path length of the target association path: qu Chuxiao, qu Chuxiao Wu Jing and Qu Chuxiao act on the wandering earth and send the above-mentioned respective recommended information and the corresponding recommended presentation sequence to the display device.
The second implementation mode: and the server determines the recommendation display sequence of each piece of recommendation information according to the sequence of the user click frequency of each piece of recommendation information from high to low in the appointed historical time length, and sends each piece of recommendation information and the recommendation display sequence to the display device.
For example, the recommended information of the target associated path 1 is Qu Chuxiao wandering earth, the recommended information of the target associated path 2 is Qu Chuxiao Wu Jing wandering earth, the recommended information of the target associated path 3 is Qu Chuxiao moving wandering earth, and the server determines the recommended display sequence of the recommended information according to the sequence from high to low of the user click frequency of the recommended information in the last three days, assuming that the user click frequency of Qu Chuxiao Wu Jing wandering earth is highest and the user click frequency of Qu Chuxiao moving wandering earth is lowest: qu Chuxiao Wu Jing, qu Chuxiao and Qu Chuxiao act on the wandering earth and send the above-mentioned respective recommended information and the corresponding recommended presentation sequence to the display device.
Based on the same inventive concept, referring to fig. 4, an embodiment of the present application provides a recommendation information generating method applied to a display device.
Step S401: the display device receives a set of keywords entered by a user.
Specifically, the display device responds to a first input instruction and enters a first search interface, the first search interface at least comprises a virtual keyboard area and a search result display area, and a certain number of initial search results are displayed in the search result display area based on search frequencies of all search results in a specified history duration.
For example, the display device responds to the first input instruction and enters a first search interface as shown in fig. 5, in the first search interface, the left area is a virtual keyboard area, the right area is a search result display area, and a certain number of initial search results are presented in the search result display area based on the search frequency of each search result in 3 days.
After the display device enters the first search interface, a keyword set input by a user is received in the virtual key area.
For example, after the display device enters the first search interface, the keyword sets "QCX", "DY" entered by the user are received at the virtual keypad.
Step S402: the display device sends the keyword set to the server, so that the server feeds back a plurality of recommendation information based on the keyword set, wherein letters or initial letters of at least one arbitrary continuous byte combination of at least one recommendation information at least contain keywords which are not in one keyword set.
For example, the display device transmits keyword sets "QCX", "DY" to the server, so that the server feeds back a plurality of recommendation information based on the keyword sets: qu Chuxiao, qu Chuxiao Wu Jing, qu Chuxiao, wherein the letters or initials of the combinations of the consecutive bytes of "Qu Chuxiao" comprise the letters or initials of the combinations of the consecutive bytes of "wandering earth" which are not present in the set of keywords, and the letters or initials of the combinations of the consecutive bytes of "Qu Chuxiao Wu Jing" comprise the words "Wu Jing", "wandering earth" which are not present in the set of keywords, and the letters or initials of the combinations of the consecutive bytes of "Qu Chuxiao" which are acting wandering earth "comprise the words" acting "which are not present in the set of keywords.
Step S403: the display device receives and presents a plurality of recommendation information fed back by the server.
Specifically, the display device receives a plurality of pieces of recommended information fed back by the server and a plurality of search results corresponding to the plurality of pieces of recommended information, and presents a second search interface, wherein the second search interface at least comprises a virtual keyboard area, a search result display area and a recommended word display area.
For example, the display device receives a plurality of recommendation information fed back by the server: qu Chuxiao, qu Chuxiao Wu Jing and Qu Chuxiao, and a plurality of search results corresponding to the plurality of recommended information, and presenting a second search interface as shown in fig. 6, wherein in the second search interface, the left area is a virtual keyboard area, the middle area is a recommended word display area, and the right area is a search result display area.
It should be noted that, the search results presented by the search result display area change along with the change of the selected recommended information, and the virtual key area, the recommended word display area and the search result display area are sequentially arranged in the second search interface along the horizontal direction.
Further, the display device presents a plurality of recommendation information in the recommendation word display area and presents a plurality of search results in the search result display area.
In some embodiments, when receiving the plurality of recommendation information fed back by the server, the display device receives a recommendation display order of the plurality of recommendation information, sequentially displays the plurality of recommendation information in a recommendation word display area based on the recommendation display order of the plurality of recommendation information, and displays a plurality of search results in a search result display area.
For example, the recommendation presentation order of the plurality of recommendation information received by the display device is: qu Chuxiao, qu Chuxiao Wu Jing, qu Chuxiao, referring to fig. 6, the display device sequentially displays in the recommended word display area based on the recommended display order of the plurality of recommended information: qu Chuxiao, qu Chuxiao Wu Jing and Qu Chuxiao act on the wandering earth to present the corresponding search results in the search result presentation area.
The above embodiments are further described below using a specific application scenario.
In the embodiment of the application, referring to fig. 5, the smart television responds to a first input instruction and enters a first search interface, in the first search interface, a left area is a virtual keyboard area, a right area is a search result display area, and in the search result display area, a certain number of film and television works are displayed according to the sequence from high to low of the search frequency of all the film and television works within a specified history duration.
Referring to fig. 7, the smart tv receives keywords "WJ", "DY" input by a user, and transmits the keywords "WJ", "DY" to the server, and after the server receives the keyword set, the server may determine a basic attribute node "Wu Jing (director)", "Wu Jing (actor)", which is associated with the keyword "WJ", in a knowledge graph, using a first keyword "WJ" in the keyword set as a first keyword.
Then, taking "Wu Jing (director)" as an example, the server determines that the preset path length threshold is 3 according to the number of keywords 2 in the keyword set input by the user, and the associated attribute nodes with the path length not exceeding the preset path length threshold 2 have "wolf (movie)", "Wu Jing (actor)", "action (tag)", "chinese (language)", "2015 (time)", "war (tag)", "military (tag)", and the like, and in each obtained associated attribute node, screens out the associated attribute nodes "wolf (movie)", which are associated with "DY", and meanwhile, the server screens out the associated attribute nodes "2015 (time)", which have the search frequency reaching the preset search frequency threshold, in the last three days, thereby determining that the target associated path set corresponding to "WJ" contains the target associated path 4{ "Wu Jing (wolf (movie)", the target associated path 5 (director) "(director 2015 (director)", "year (director)", "2015 (director)", "and the like).
Next, for the target association path 4, the server may generate recommendation information directly from the determined order of "Wu Jing (director)" and "warwolf (movie)": wu Jingzhan wolf, for the target association path 5, "Wu Jing (director)" and "warwolf (movie)", "Wu Jing (director)" and "2015 (time)", respectively, and if the calculated affinities of "Wu Jing (director)" and "warwolf (movie)" are higher than those of Wu Jing (director) "and" 2015 (time) ", it is determined that the presentation order is" warwolf (movie) "," 2015 (time) ", and recommendation information can be generated according to the presentation order: wu Jingzhan wolf 2015.
Finally, the server determines the recommendation display sequence of each recommendation information according to the user click frequency of Wu Jingzhan wolves and Wu Jingzhan wolves in 2015 from high to low in the last three days, and sends each recommendation information and the recommendation display sequence to the display device, and if the user click rate of Wu Jingzhan wolves in 2015 is higher than Wu Jingzhan wolves in the last three days, the recommendation display sequence of each recommendation information is as follows in sequence: wu Jingzhan wolf 2015, wu Jingzhan wolf.
Referring to fig. 7, after receiving and presenting a plurality of recommended information fed back by the server, the smart tv presents a second search interface, where the second search interface includes a virtual keyboard area, a search result display area, and a recommended word display area, in the second search interface, a left area is the virtual keyboard area, a middle area is the recommended word display area, a right area is the search result display area, and a plurality of recommended information are sequentially presented: wu Jingzhan wolf 2015 and Wu Jingzhan wolf, if the focus of the user does not move to a certain fixed recommended information, displaying a certain number of film and television works in the search result display area according to the sequence from high to low of the search frequency of the film and television works corresponding to all the recommended information in the appointed historical time.
Referring to fig. 8, when the user focus moves to a certain fixed recommended information, a movie work corresponding to the recommended information is displayed in the search result display area, for example, when the user focus moves to "Wu Jingzhan wolf," a movie work "war wolf" corresponding to "Wu Jingzhan wolf" is displayed in the search result display area.
Compared with the prior art, the letter or initial combination of any word in the recommended word needs to be the same as the keyword combination input by the user. In some embodiments, at least one of the recommended words is associated with the knowledge graph according to the recommended words generated according to the relevance between the knowledge graph entities, wherein letters or initial letters of any continuous byte of the recommended word are different from a keyword set input by the user, and more flexible recommended word options are provided for the user.
In some embodiments, at least one of the recommended words is associated with the knowledge graph according to the recommended words generated according to the relevance between the knowledge graph entities, wherein letters or initial letters of at least one arbitrary continuous byte combination of the recommended words do not include any combination of keywords in the keyword set input by the user, and more flexible recommended word options are provided for the user.
In some embodiments, the user enters keywords by selecting virtual keys in the virtual key region to form a keyword set. The server feeds back the recommended information according to the keyword set and the search result corresponding to the recommended information, and after receiving the recommended information and the search result corresponding to the recommended information, the display device displays the recommended information fed back by the server in the recommended word display area and displays the search result in the search result display area. By default, the search results displayed in the search result display area are results corresponding to the recommendation information at the position where the default focus is located in the recommendation information, and when different recommendation information is selected, the display device controls the search result display area to display different search results, that is, different recommendation information corresponds to different search results, and the search results displayed in the search result display area can be refreshed and adjusted along with the selection of different recommendation words in the recommendation word display area.
In some embodiments, the virtual key area, the recommended word display area and the search result display area are sequentially arranged along the horizontal direction, which is determined by the special scene of the aspect ratio of the display device, and if the display device is a mobile terminal, the scheme that the virtual key area, the recommended word display area and the search result display area are sequentially arranged along the horizontal direction is not used because the longitudinal length of the mobile terminal is far beyond the transverse width of the mobile terminal.
Based on the same inventive concept, fig. 9 illustrates a schematic structural diagram of a server according to an embodiment of the present application, which includes at least a determining module 901, a processing module 902 and a generating module 903, where,
a determining module 901, configured to determine, in a knowledge graph, a basic attribute node associated with a first keyword, where the first keyword is a keyword with a highest search weight, based on a first keyword in a keyword set sent by a display device;
a processing module 902, configured to determine a target association path set corresponding to the base attribute node, where an item of target association path includes the base attribute node and an association attribute node connected to the base attribute node, and a path length between one association attribute node and the base attribute node does not exceed a preset path length threshold;
the generating module 903 is configured to generate and send corresponding recommendation information to the display device according to the attribute values of the basic attribute nodes and the attribute values of the associated attribute nodes included in each target associated path.
Optionally, when determining the target association path set corresponding to the base attribute node, the processing module 902 is specifically configured to:
In the knowledge graph, determining each associated attribute node of which the path length with the basic attribute node does not exceed a preset path length threshold;
screening out the related attribute nodes with the searching heat meeting preset conditions from the obtained related attribute nodes;
directly or indirectly associating the basic attribute nodes with each selected associated attribute node to generate corresponding target associated paths;
based on each obtained target associated path, a corresponding target associated path set is obtained.
Optionally, when screening out the associated attribute nodes with the search heat meeting the preset condition from the obtained associated attribute nodes, the processing module 902 is configured to:
screening out related attribute nodes related to other keywords in the keyword set from the obtained related attribute nodes; or/and the combination of the two,
and screening out the associated attribute nodes with the search frequency reaching a preset search frequency threshold in the appointed historical time from the obtained associated attribute nodes.
Fig. 10 exemplarily shows a schematic structural diagram of a display device according to an embodiment of the present application, which includes at least a receiving module 1001, a transmitting module 1002 and a presenting module 1003, based on the same inventive concept,
A receiving module 1001, configured to receive a keyword set input by a user;
a sending module 1002, configured to send the keyword set to a server, so that the server feeds back a plurality of recommendation information based on the keyword set, where at least one letter or initial of at least one arbitrary continuous byte combination of at least one recommendation information includes at least one keyword that does not exist in the keyword set;
a presentation template 1003, configured to receive and present the plurality of recommendation information fed back by the server.
Optionally, the at least one recommendation information is generated by the server based on each node included in the knowledge graph and the relevance between each node.
Optionally, when receiving the keyword set input by the user, the receiving module 1001 is specifically configured to:
responding to a first input instruction, entering a first search interface, wherein the first search interface at least comprises a virtual keyboard area and a search result display area, and the search result display area displays a certain number of initial search results based on the search frequency of each search result in a specified history duration;
and receiving a keyword set input by a user in the virtual key area.
Based on the same inventive concept, fig. 11 schematically illustrates a structural diagram of a server according to an embodiment of the present application. As shown, the server may include: a processor 1101, memory 1102, a transceiver 1103 and a bus interface 1104;
the processor 1101 is configured to read the computer instructions in the memory 1102, and execute any one of the recommendation information generating methods executed by the server.
The processor 1101 is responsible for managing the bus architecture and general processing, and the memory 1102 may store data used by the processor 1101 in performing the operations. The transceiver 1103 is configured to receive and transmit data under the control of the processor 1101.
The bus architecture may include any number of interconnecting buses and bridges, and in particular one or more processors represented by the processor 1101 and various circuits of the memory, represented by the memory 1102. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., which are well known in the art and, therefore, will not be described further herein. The bus interface provides an interface.
Fig. 12 is a block diagram schematically showing a hardware configuration of a display device according to an embodiment of the present application, based on the same inventive concept. As shown in fig. 12, the display device 1200 includes a controller 1210, a modem 1220, a communication interface 1230, a detector 1240, an input/output interface 1250, a video processor 1260-1, an audio processor 1260-2, a display 1280, an audio output 1270, a memory 1290, a power supply, and an infrared receiver.
A display 1280 for receiving image signals input from the video processor 1260-1 and for displaying video content and images and components of the menu manipulation interface. The display 1280 includes a display screen assembly for presenting pictures, and a drive assembly for driving the display of images. The video content may be displayed from broadcast television content, or may be various broadcast signals receivable via a wired or wireless communication protocol. Alternatively, various image contents received from the network server side transmitted from the network communication protocol may be displayed.
Meanwhile, the display 1280 simultaneously displays a user manipulation UI interface generated in the display apparatus 1200 and used to control the display apparatus 1200.
And, depending on the type of display 1280, a drive assembly for driving the display. Alternatively, if the display 1280 is a projection display, a projection device and a projection screen may be included.
The communication interface 1230 is a component for communicating with an external device or an external server according to various communication protocol types. For example: the communication interface 1230 may be a Wifi chip 1231, a bluetooth communication protocol chip 1232, a wired ethernet communication protocol chip 1233, or other network communication protocol chip or a near field communication protocol chip, and an infrared receiver (not shown in the figure).
The display device 1200 may establish control signal and data signal transmission and reception with an external control device or a content providing device through the communication interface 1230. And an infrared receiver, an interface device for receiving infrared control signals of a control device (such as an infrared remote controller, etc.).
The detector 1240 is a signal used by the display device 1200 to collect the external environment or interact with the outside. The detector 1240 includes a light receiver 1242, a sensor for capturing the intensity of ambient light, a parameter change may be adaptively displayed by capturing ambient light, etc.
And includes an image collector 1241, such as a camera, a video camera, etc., which can be used to collect external environment scenes, collect attributes of a user or interact gestures with the user, adaptively change display parameters, and recognize user gestures to realize interaction with the user.
In other exemplary embodiments, the detector 1240 may also be a temperature sensor or the like, such as by sensing ambient temperature, and the display device 1200 may adaptively adjust the display color temperature of the image. The display device 1200 may be adjusted to display a colder color temperature shade of the image, such as when the temperature is higher, or the display device 1200 may be adjusted to display a warmer color shade of the image when the temperature is lower.
In other exemplary embodiments, the detector 1240 may also be a sound collector or the like, such as a microphone, may be used to receive the user's sound, including a voice signal of a control instruction for the user to control the display device 1200, or collect ambient sound for identifying the type of ambient scene, and the display device 1200 may adapt to ambient noise.
An input/output interface 1250 for data transmission between the display device 1200 and external other devices under the control of the controller 1210. Such as receiving video signals and audio signals of an external device, or command instructions.
Input/output interface 1250 may include, but is not limited to, the following: any one or more of the high definition multimedia interface HDMI interface 1251, analog or data high definition component input interface 1253, composite video input interface 1252, USB input interface 1254, RGB port (not shown in the figures), etc. may be used.
In other exemplary embodiments, input/output interface 1250 may also form a composite input/output interface from the plurality of interfaces described above.
The modem 1220 receives the broadcast television signal by a wired or wireless reception method, and performs modulation and demodulation processing such as amplification, mixing, and resonance, and demodulates the television audio/video signal carried in the television channel frequency selected by the user and the EPG data signal from the plurality of wireless or wired broadcast television signals.
The modem 1220 is responsive to the user selected television signal frequency and television signals carried at that frequency, as selected by the user, and as controlled by the controller 1210.
The tuning demodulator 1220 may receive signals in a variety of ways depending on the broadcasting system of the television signal, such as: terrestrial broadcast, cable broadcast, satellite broadcast, or internet broadcast signals, etc.; and according to different modulation types, the modulation can be digital modulation or analog modulation mode. Depending on the type of television signal received, both analog and digital signals may be used.
In other exemplary embodiments, the modem 1220 may also be in an external device, such as an external set-top box, or the like. Thus, the set-top box outputs television audio and video signals through the modem and into the display device 1200 via the input/output interface 1250.
The video processor 1260-1 is configured to receive an external video signal, perform video processing such as decompression, decoding, scaling, noise reduction, frame rate conversion, resolution conversion, image composition, etc., according to a standard codec protocol of an input signal, and may obtain a signal for display or playback on the directly displayable device 1200.
By way of example, video processor 1260-1 includes a demultiplexing module, a video decoding module, an image compositing module, a frame rate conversion module, a display formatting module, and the like.
The demultiplexing module is used for demultiplexing the input audio/video data stream, such as the input MPEG-2, and demultiplexes the input audio/video data stream into video signals, audio signals and the like.
And the video decoding module is used for processing the demultiplexed video signals, including decoding, scaling and the like.
And an image synthesis module, such as an image synthesizer, for performing superposition mixing processing on the graphic generator and the video image after the scaling processing according to the GUI signal input by the user or generated by the graphic generator, so as to generate an image signal for display.
The frame rate conversion module is configured to convert the input video frame rate, for example, converting the 60Hz frame rate into the 120Hz frame rate or the 240Hz frame rate, and the common format is implemented in an inserting frame manner.
The display format module is used for converting the received frame rate into a video output signal, and changing the video output signal to a signal conforming to the display format, such as outputting an RGB data signal.
An audio processor 1260-2 for receiving an external audio signal, decompressing and decoding according to a standard codec protocol of an input signal, and processing such as noise reduction, digital-to-analog conversion, and amplification processing, to obtain a sound signal that can be played in a speaker.
In other exemplary embodiments, video processor 1260-1 may comprise one or more chips. Audio processor 1260-2 may also include one or more chips.
And, in other exemplary embodiments, the video processor 1260-1 and the audio processor 1260-2 may be separate chips or integrated together in one or more chips with the controller 1210.
An audio output 1270, which receives sound signals output by the audio processor 1260-2 under the control of the controller 1210, such as: the speaker 1272, and an external sound output terminal 1274 which can be output to a generating device of an external device, other than the speaker 1272 carried by the display device 1200 itself, such as: external sound interface or earphone interface, etc.
And a power supply source for providing power supply support for the display device 1200 with power inputted from an external power source under the control of the controller 1210. The power supply may include a built-in power circuit installed inside the display apparatus 1200, or may be an external power source installed in the display apparatus 1200, and a power interface providing an external power source in the display apparatus 1200.
A user input interface for receiving an input signal of a user and then transmitting the received user input signal to the controller 1210. The user input signal may be a remote control signal received through an infrared receiver, and various user control signals may be received through a network communication module.
By way of example, a user inputs a user command through a remote control or a mobile terminal, the user input interface is responsive to the user input through the controller 1210, and the display device 1200 is responsive to the user input.
In some embodiments, a user may input a user command through a Graphical User Interface (GUI) displayed on the display 1280, and the user input interface receives the user input command through the Graphical User Interface (GUI). Alternatively, the user may input the user command by inputting a specific sound or gesture, and the user input interface recognizes the sound or gesture through the sensor to receive the user input command.
The controller 1210 controls the operation of the display apparatus 1200 and responds to the user's operations through various software control programs stored on the memory 1290.
As shown in fig. 12, the controller 1210 includes RAM1213 and ROM1214 as well as a graphics processor 1216, a CPU processor 1212, a communication interface 1230, such as: first interface 1218-1 through nth interfaces 1218-n, and a communication bus. The RAM1213 and the ROM1214, and the graphics processor 1216, the CPU processor 1212, and the communication interface 30 are connected by a bus.
ROM1214 for storing various system startup instructions. When the power-on signal is received, the display device 1200 starts to be powered on, and the CPU processor 1212 runs a system boot instruction in the ROM, copies the operating system stored in the memory 1290 to the RAM1213, so that the running of the boot operating system is started. When the operating system is started, the CPU processor 1212 copies various applications in the memory 1290 to the RAM1213, and then starts running the various applications.
A graphics processor 1216 for generating various graphics objects, such as: icons, operation menus, user input instruction display graphics, and the like. The device comprises an arithmetic unit, wherein the arithmetic unit is used for receiving various interaction instructions input by a user to carry out operation and displaying various objects according to display attributes. And a renderer that generates various objects based on the results of the operator, and the results of rendering are displayed on a display 1280.
CPU processor 1212 is configured to execute operating system and application program instructions stored in memory 1290. And executing various application programs, data and contents according to various interactive instructions received from the outside, so as to finally display and play various audio and video contents.
In some example embodiments, the CPU processor 1212 may include multiple processors. The plurality of processors may include one main processor and a plurality or one sub-processor. A main processor for performing some operations of the display apparatus 1200 in the pre-power-up mode and/or displaying a picture in the normal mode. A plurality of or a sub-processor for one operation in a standby mode or the like.
The controller 1210 may control the overall operation of the display apparatus 1200. For example: in response to receiving a user command to select a UI object to be displayed on the display 1280, the controller 1210 may perform an operation related to the object selected by the user command.
Wherein the object may be any one of selectable objects, such as a hyperlink or an icon. Operations related to the selected object, such as: displaying an operation of connecting to a hyperlink page, a document, an image, or the like, or executing an operation of a program corresponding to the icon. The user command for selecting the UI object may be an input command through various input means (e.g., a mouse, a keyboard, a touch pad, etc.) connected to the display apparatus 1200 or a voice command corresponding to a voice uttered by the user.
Memory 1290, which includes memory stores various software modules for driving display device 1200. Such as: various software modules stored in memory 1290, including: a basic module, a detection module, a communication module, a display control module, a browser module, various service modules and the like.
The base module is a bottom software module for communicating signals between the various hardware in the post-partum care display device 1200 and sending processing and control signals to the upper module. The detection module is used for collecting various information from various sensors or user input interfaces and carrying out digital-to-analog conversion and analysis management.
For example: the voice recognition module comprises a voice analysis module and a voice instruction database module. The display control module is used for controlling the display 1280 to display the image content, and can be used for playing the multimedia image content, the UI interface and other information. And the communication module is used for carrying out control and data communication with external equipment. And the browser module is used for executing data communication between the browsing servers. And the service module is used for providing various services and various application programs.
Meanwhile, the memory 1290 also stores received external data and user data, images of various items in various user interfaces, visual effect maps of focus objects, and the like.
Based on the same inventive concept, an embodiment of the present application provides a storage medium storing computer-executable instructions for causing the computer to execute the recommendation information generation method executed by the server described above.
Based on the same inventive concept, an embodiment of the present application provides a storage medium storing computer-executable instructions for causing the computer to execute the recommended information generation method performed by the display device described above.
In the embodiment of the application, a server determines a basic attribute node associated with a first keyword based on the first keyword in a keyword set sent by a display device, then the server determines a target associated path set corresponding to the basic attribute node, wherein one item of target associated path comprises the basic attribute node and associated attribute nodes connected with the basic attribute node, the path length between one associated attribute node and the basic attribute node does not exceed a preset path length threshold, and then the server generates and sends corresponding recommendation information to the display device according to the attribute values of the basic attribute nodes and the attribute values of the associated attribute nodes contained in each target associated path.
According to a first keyword in a keyword set sent by a display device, a target association path set corresponding to a basic attribute node is determined, so that association attribute nodes related to the first keyword can be obtained, single recommendation information is not presented any more, and diversification of the recommendation information is realized; secondly, the path length between the associated attribute node and the basic attribute node does not exceed a preset path length threshold, so that the search path length is reduced, and the search efficiency is improved; and then, generating and sending corresponding recommendation information to the display equipment according to the attribute values of the basic attribute nodes and the attribute values of the associated attribute nodes, so that diversified recommendation information can be provided for the user, the number of times of repeated input of different keywords by the user is reduced, the operation complexity of the user is reduced, and the user experience is improved.
For system/device embodiments, the description is relatively simple as it is substantially similar to method embodiments, with reference to the description of method embodiments in part.
It should be noted that in this document relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (11)
1. A recommendation information generation method, characterized by comprising:
the method comprises the steps that a server determines basic attribute nodes associated with first keywords in a knowledge graph based on the first keywords in a keyword set sent by display equipment, wherein the first keywords are keywords with highest searching weights;
the server determines a target association path set corresponding to the basic attribute node, wherein an item of target association path comprises the basic attribute node and an association attribute node connected with the basic attribute node, and the path length between the association attribute node and the basic attribute node does not exceed a preset path length threshold;
the server generates and sends corresponding recommendation information to the display equipment according to the attribute values of the basic attribute nodes and the attribute values of the associated attribute nodes contained in each target associated path, wherein the affinity between the basic attribute nodes and each associated attribute node is respectively determined according to the basic attribute nodes and each associated attribute node contained in any one target associated path; determining the presentation sequence of each associated attribute node according to the intimacy between the basic attribute node and each associated attribute node; and generating recommendation information corresponding to any one target association path based on the attribute values of the basic attribute nodes and the association attribute nodes according to the presentation sequence.
2. The method of claim 1, wherein the server determines a set of target associated paths corresponding to the base attribute node, specifically comprising:
the server determines each associated attribute node with the path length not exceeding a preset path length threshold from the knowledge graph;
the server screens out the associated attribute nodes with the searching heat meeting the preset conditions from the obtained associated attribute nodes;
the server directly or indirectly associates the basic attribute nodes with each screened associated attribute node to generate corresponding target associated paths;
the server obtains a corresponding target association path set based on each obtained target association path.
3. The method of claim 2, wherein the server screens out the associated attribute nodes with the search heat meeting the preset condition from the obtained associated attribute nodes, and the method comprises the following steps:
the server screens out the associated attribute nodes associated with other keywords in the keyword set from the obtained associated attribute nodes; or/and the combination of the two,
And the server screens out the associated attribute nodes with the search frequency reaching a preset search frequency threshold in the appointed historical duration from the obtained associated attribute nodes.
4. A method according to claim 1, 2 or 3, wherein the server determines the intimacy between the basic attribute node and each associated attribute node according to the basic attribute node and each associated attribute node included in the arbitrary target associated path, and specifically includes:
the server determines basic attribute nodes and each associated attribute node contained in any one target associated path;
the server performs the following operations for the basic attribute node and each associated attribute node respectively: and calculating the intimacy between the basic attribute node and one associated attribute node according to the duty ratio of the same adjacent attribute node in each adjacent attribute node of the basic attribute node and the associated attribute node.
5. The method of claim 1, wherein the server, after generating each piece of recommended information according to the attribute value of the base attribute node and the attribute value of the associated attribute node included in each target associated path, specifically includes:
The server determines the recommendation display sequence of each piece of recommendation information according to the sequence from small to large of the path length of each target associated path, and sends each piece of recommendation information and the recommendation display sequence to the display equipment; or,
and the server determines the recommendation display sequence of each piece of recommendation information according to the sequence of the user click frequency of each piece of recommendation information from high to low in the appointed historical time duration, and sends each piece of recommendation information and the recommendation display sequence to the display equipment.
6. A recommendation information generation method, characterized by comprising:
the method comprises the steps that a display device receives a keyword set input by a user;
the display device sends the keyword set to a server, so that the server feeds back a plurality of recommendation information based on the keyword set, wherein letters or initial letters of at least one arbitrary continuous byte combination of at least one recommendation information at least comprise keywords which do not exist in one keyword set; any recommendation information is generated by the server according to the intimacy between a basic attribute node contained in a target association path corresponding to the any recommendation information and each associated attribute node contained in the target association path, and based on attribute values of the basic attribute node and each associated attribute node according to the presentation order, the path length between one associated attribute node and the basic attribute node does not exceed a preset path length threshold, the basic attribute node is an attribute node which is determined by the server in a knowledge graph and is associated with a first keyword in the keyword set, and the first keyword is a keyword with highest search weight;
The display device receives and presents the plurality of recommended information fed back by the server.
7. The method of claim 6, wherein the at least one recommendation is generated by the server based on each node included in a knowledge-graph and a correlation between each node.
8. The method according to claim 6 or 7, wherein when the display device receives the keyword set input by the user, the method specifically comprises:
the display equipment responds to a first input instruction and enters a first search interface, wherein the first search interface at least comprises a virtual keyboard area and a search result display area, and a certain number of initial search results are displayed in the search result display area based on the search frequency of each search result in a specified history time length;
the display device receives a keyword set input by a user in the virtual keyboard area.
9. The method according to claim 6 or 7, wherein the display device receives and presents the plurality of recommended information fed back by the server, in particular comprising:
the display equipment receives the plurality of recommendation information fed back by the server and a plurality of search results corresponding to the plurality of recommendation information, and presents a second search interface, wherein the second search interface at least comprises a virtual keyboard area, a search result display area and a recommended word display area;
The display equipment presents the plurality of recommendation information in the recommended word display area, and presents the plurality of search results in the search result display area;
the search results presented by the search result display area change along with the change of the selected recommended information, and the virtual keyboard area, the recommended word display area and the search result display area are sequentially arranged in the second search interface along the horizontal direction.
10. A server, comprising:
the determining module is used for determining basic attribute nodes associated with first keywords in the knowledge graph based on the first keywords in the keyword set sent by the display equipment, wherein the first keywords are keywords with highest searching weight;
the processing module is used for determining a target association path set corresponding to the basic attribute node, wherein an item of target association path comprises the basic attribute node and an association attribute node connected with the basic attribute node, and the path length between the association attribute node and the basic attribute node does not exceed a preset path length threshold;
the generation module is used for generating and sending corresponding recommendation information to the display equipment according to the attribute values of the basic attribute nodes and the attribute values of the associated attribute nodes contained in each target associated path respectively, wherein for any one target associated path in each target associated path, the intimacy between the basic attribute nodes and each associated attribute node is determined according to the basic attribute nodes and each associated attribute node contained in any one target associated path; determining the presentation sequence of each associated attribute node according to the intimacy between the basic attribute node and each associated attribute node; and generating recommendation information corresponding to any one target association path based on the attribute values of the basic attribute nodes and the association attribute nodes according to the presentation sequence.
11. A display device, characterized by comprising:
the receiving module is used for receiving the keyword set input by the user;
the sending module is used for sending the keyword set to a server, so that the server feeds back a plurality of recommendation information based on the keyword set, wherein letters or initial letters of at least one arbitrary continuous byte combination of at least one recommendation information at least comprise keywords which do not exist in one keyword set; any recommendation information is generated by the server according to the intimacy between a basic attribute node contained in a target association path corresponding to the any recommendation information and each associated attribute node contained in the target association path, and based on attribute values of the basic attribute node and each associated attribute node according to the presentation order, the path length between one associated attribute node and the basic attribute node does not exceed a preset path length threshold, the basic attribute node is an attribute node which is determined by the server in a knowledge graph and is associated with a first keyword in the keyword set, and the first keyword is a keyword with highest search weight;
And the presentation template is used for receiving and presenting the plurality of recommendation information fed back by the server.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010085171.4A CN111291265B (en) | 2020-02-10 | 2020-02-10 | Recommendation information generation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010085171.4A CN111291265B (en) | 2020-02-10 | 2020-02-10 | Recommendation information generation method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111291265A CN111291265A (en) | 2020-06-16 |
CN111291265B true CN111291265B (en) | 2023-10-03 |
Family
ID=71024588
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010085171.4A Active CN111291265B (en) | 2020-02-10 | 2020-02-10 | Recommendation information generation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111291265B (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111901656B (en) * | 2020-08-06 | 2022-04-15 | 聚好看科技股份有限公司 | Media data searching method, display equipment and server |
CN112100513A (en) * | 2020-08-27 | 2020-12-18 | 北京明略昭辉科技有限公司 | Knowledge graph-based recommendation method, device, equipment and computer readable medium |
CN112259096B (en) * | 2020-10-23 | 2022-10-18 | 海信视像科技股份有限公司 | Voice data processing method and device |
CN112307294B (en) * | 2020-11-02 | 2024-06-25 | 北京搜狗科技发展有限公司 | Data processing method and device |
CN113038171A (en) * | 2020-12-14 | 2021-06-25 | 海看网络科技(山东)股份有限公司 | IPTV search result display method |
CN112799928B (en) * | 2021-01-29 | 2023-08-18 | 索为技术股份有限公司 | Knowledge graph-based industrial APP association analysis method, device and medium |
CN114302205B (en) * | 2021-05-25 | 2024-05-14 | 海信视像科技股份有限公司 | Information recommendation method and display device |
CN113590774B (en) * | 2021-06-22 | 2023-09-29 | 北京百度网讯科技有限公司 | Event query method, device and storage medium |
CN113704493A (en) * | 2021-08-27 | 2021-11-26 | 北京有竹居网络技术有限公司 | Display information determining method, device, equipment and computer readable storage medium |
CN114064930A (en) * | 2021-11-29 | 2022-02-18 | 北京字节跳动网络技术有限公司 | Data display method and device, computer equipment and storage medium |
CN114141384A (en) * | 2022-01-30 | 2022-03-04 | 北京欧应信息技术有限公司 | Method, apparatus and medium for retrieving medical data |
CN115150673B (en) * | 2022-06-30 | 2023-11-24 | 聚好看科技股份有限公司 | Display equipment and media asset display method |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103744856A (en) * | 2013-12-03 | 2014-04-23 | 北京奇虎科技有限公司 | Method, device and system for linkage extended search |
CN106570144A (en) * | 2016-02-05 | 2017-04-19 | 中科鼎富(北京)科技发展有限公司 | Method and apparatus for recommending information |
CN108073606A (en) * | 2016-11-10 | 2018-05-25 | 北京搜狗科技发展有限公司 | A kind of news recommends method and apparatus, a kind of device recommended for news |
CN108153901A (en) * | 2018-01-16 | 2018-06-12 | 北京百度网讯科技有限公司 | The information-pushing method and device of knowledge based collection of illustrative plates |
CN108228906A (en) * | 2018-02-08 | 2018-06-29 | 北京百度网讯科技有限公司 | For generating the method and apparatus of information |
CN109241341A (en) * | 2018-05-09 | 2019-01-18 | 上海大学 | A kind of video display of knowledge based map preferentially recommender system and method |
CN109299383A (en) * | 2018-11-02 | 2019-02-01 | 北京字节跳动网络技术有限公司 | Generate method, apparatus, electronic equipment and the storage medium for recommending word |
CN109308334A (en) * | 2018-11-13 | 2019-02-05 | 北京搜狗科技发展有限公司 | Information recommendation method and device, search engine system |
CN109508390A (en) * | 2018-12-28 | 2019-03-22 | 北京金山安全软件有限公司 | Input prediction method and device based on knowledge graph and electronic equipment |
CN110334221A (en) * | 2019-07-18 | 2019-10-15 | 桂林电子科技大学 | A kind of interpretation recommended method in knowledge based map path |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10754899B2 (en) * | 2017-08-30 | 2020-08-25 | Pearson Education, Inc. | System and method for sequencing database-based content recommendation |
-
2020
- 2020-02-10 CN CN202010085171.4A patent/CN111291265B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103744856A (en) * | 2013-12-03 | 2014-04-23 | 北京奇虎科技有限公司 | Method, device and system for linkage extended search |
CN106570144A (en) * | 2016-02-05 | 2017-04-19 | 中科鼎富(北京)科技发展有限公司 | Method and apparatus for recommending information |
CN108073606A (en) * | 2016-11-10 | 2018-05-25 | 北京搜狗科技发展有限公司 | A kind of news recommends method and apparatus, a kind of device recommended for news |
CN108153901A (en) * | 2018-01-16 | 2018-06-12 | 北京百度网讯科技有限公司 | The information-pushing method and device of knowledge based collection of illustrative plates |
CN108228906A (en) * | 2018-02-08 | 2018-06-29 | 北京百度网讯科技有限公司 | For generating the method and apparatus of information |
CN109241341A (en) * | 2018-05-09 | 2019-01-18 | 上海大学 | A kind of video display of knowledge based map preferentially recommender system and method |
CN109299383A (en) * | 2018-11-02 | 2019-02-01 | 北京字节跳动网络技术有限公司 | Generate method, apparatus, electronic equipment and the storage medium for recommending word |
CN109308334A (en) * | 2018-11-13 | 2019-02-05 | 北京搜狗科技发展有限公司 | Information recommendation method and device, search engine system |
CN109508390A (en) * | 2018-12-28 | 2019-03-22 | 北京金山安全软件有限公司 | Input prediction method and device based on knowledge graph and electronic equipment |
CN110334221A (en) * | 2019-07-18 | 2019-10-15 | 桂林电子科技大学 | A kind of interpretation recommended method in knowledge based map path |
Non-Patent Citations (1)
Title |
---|
李海林 ; 万校基 ; 林春培 ; .基于关键词重要性和近邻传播聚类的主题分析研究.情报学报.2018,(05),全文. * |
Also Published As
Publication number | Publication date |
---|---|
CN111291265A (en) | 2020-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111291265B (en) | Recommendation information generation method and device | |
CN110737840B (en) | Voice control method and display device | |
US12010373B2 (en) | Display apparatus, server apparatus, display system including them, and method for providing content thereof | |
CN109618206B (en) | Method and display device for presenting user interface | |
EP4072152A1 (en) | Method and device for displaying epg user interface | |
KR20100006846A (en) | A method to provide a widget, and tv using the same | |
WO2021189697A1 (en) | Video display method, terminal, and server | |
CN105379291B (en) | Content providing method and apparatus | |
WO2021109418A1 (en) | Video resource display method, mobile terminal and server | |
KR101708691B1 (en) | Image Display Device and Method for Operating the Same | |
CN112463269B (en) | User interface display method and display equipment | |
CN111770370A (en) | Display device, server and media asset recommendation method | |
US20200301992A1 (en) | Page updating method and display device | |
CN111083538A (en) | Background image display method and device | |
CN111897641B (en) | Micro-service monitoring and scheduling method and display device | |
KR102104438B1 (en) | Image display apparatus, and method for operating the same | |
CN113490032A (en) | Display device and medium resource display method | |
KR101714661B1 (en) | Method for data input and image display device thereof | |
KR101708646B1 (en) | Image Display Device and Method for Operating the Same | |
KR102046642B1 (en) | Image display apparatus, and method for operating the same | |
CN113259733B (en) | Display device | |
KR102110532B1 (en) | Image display apparatus, and method for operating the same | |
KR20130066334A (en) | Image display apparatus, server and method for operating the same | |
CN113573115B (en) | Method for determining search characters and display device | |
CN113825007B (en) | Video playing method and device and display equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |